首页 期刊 论文 学科刊群 资讯 加盟 关于
EN
image
Article(id=1322594504406839619, tenantId=1146029695717560320, journalId=1225396423026438145, issueId=1322594503278580030, articleNumber=null, orderNo=null, doi=null, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1710172800000, receivedDateStr=2024-03-12, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1793260702468, onlineDateStr=2026-10-29, pubDate=1737734400000, pubDateStr=2025-01-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793260702468, onlineIssueDateStr=2026-10-29, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793260702468, creator=13701087609, updateTime=1793260702468, updator=13701087609, issue=Issue{id=1322594503278580030, tenantId=1146029695717560320, journalId=1225396423026438145, year='2025', volume='45', issue='1', pageStart='1', pageEnd='276', issueExtLink='null', onlineDate='null', pubDate='1737734400000', pubDateStr='2025-01-25', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1793260702199, creator='13701087609', updateTime=1793260702199, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=269, endPage=276, ext={EN=ArticleExt(id=1322594504591388996, articleId=1322594504406839619, tenantId=1146029695717560320, journalId=1225396423026438145, language=EN, title=Research on a Prediction Model of Ash in Flotation Tailings Based on LightGBM Optimized by Genetic Algorithm, columnId=null, journalTitle=Mining Research and Development, columnName=null, runingTitle=null, highlight=null, articleAbstract=

In order to improve the level of on-line detection of ash in coal slime flotation process, the prediction of ash content of tailings in coal slime flotation process was studied, and the prediction model of ash content of flotation tailings based on LightGBM optimized by genetic algorithm was established. Through the collected production data, including slurry flow, concentration, foaming dose, collection dose and dry slime amount, the model training data set was constructed and the model was tested and verified. The experimental results show that the average absolute error of the prediction results of the model is 0.72, which is 11.1% higher than that of the unoptimized LightGBM model. Compared with other models, the average absolute error of the prediction results of the GA-LightGBM model is reduced by 15.8%, which further proves the validity of the model in the prediction accuracy of ash in coal tailings and provides a new technical support for the realization of intelligent flotation.

, authors=Jie HANI, Ranfeng WANGI, Xiang FUI, Jun WANGI, Kai WEII, Qian ZHANGI, authorsList=Jie HAN, Ranfeng WANG, Xiang FU, Jun WANG, Kai WEI, Qian ZHANG, authorCompany=null, correspAuthors=Ranfeng WANG, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1322594507800031570, articleId=1322594504406839619, tenantId=1146029695717560320, journalId=1225396423026438145, language=CN, title=基于遗传算法优化的LightGBM浮选尾煤灰分预测模型研究, columnId=1226462297560892399, journalTitle=矿业研究与开发, columnName=选矿与资源综合利用, runingTitle=null, highlight=null, articleAbstract=

为了提高煤泥浮选过程灰分在线检测的水平，研究了煤泥浮选过程中尾煤灰分的预测，并建立了基于遗传算法优化的LightGBM浮选尾煤灰分预测模型。通过采集的生产过程数据，包括矿浆流量、浓度、起泡剂量、捕收剂量和干煤泥量，构建了模型训练数据集，并对模型进行了测试验证。试验结果显示，该模型预测结果的平均绝对误差为0.72，比未优化的LightGBM模型提升了11.1%的预测精度，相较于其他模型，GA-LightGBM模型预测结果的平均绝对误差降低了15.8%，进一步证明了所建模型在尾煤灰分预测精度上的有效性，为实现智能化浮选提供了新的技术支持。

, authors=韩杰I, 王然风I, 付翔I, 王珺I, 魏凯I, 张茜I, authorsList=韩杰, 王然风, 付翔, 王珺, 魏凯, 张茜, authorCompany=null, correspAuthors=王然风, authorNote=

韩杰（1997—），男，山西晋城人，硕士，主要研究方向为煤泥浮选过程智能控制。E-mail:

, correspAuthorsNote=
王然风（1970—），男，山西长治人，博士，教授，主要研究方向为煤矿智能化开采与分选。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=vwXlXy5C7fSqbjZnjHvoVw==, magXml=C0glDEDAJjqoT+iJtCn97A==, pdfUrl=null, pdf=gUfAi1RwNbzsAl9tFjmW6w==, pdfFileSize=2702156, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=zRtO/jHh13yXKEvWaAYZ4A==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=tcN16HUaVe7aCNxmRSO0fw==, mapNumber=null, fund=null)}, authors=[Author(id=1322594508160741719, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=2412491849@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322594508236239193, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, authorId=1322594508160741719, language=EN, stringName=Jie HAN, firstName=Jie, middleName=null, lastName=HAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322594508320125274, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, authorId=1322594508160741719, language=CN, stringName=韩杰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=太原理工大学 矿业工程学院，山西　太原　030024, bio={"content":"

韩杰（1997—），男，山西晋城人，硕士，主要研究方向为煤泥浮选过程智能控制。E-mail:

"}, bioImg=null, bioContent=

韩杰（1997—），男，山西晋城人，硕士，主要研究方向为煤泥浮选过程智能控制。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322594508026523987, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, xref=null, ext=[AuthorCompanyExt(id=1322594508034912596, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China), AuthorCompanyExt(id=1322594508051689813, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学 矿业工程学院，山西　太原　030024)])]), Author(id=1322594508378845532, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wrf197010@126.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322594508475314526, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, authorId=1322594508378845532, language=EN, stringName=Ranfeng WANG, firstName=Ranfeng, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322594508559200607, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, authorId=1322594508378845532, language=CN, stringName=王然风, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=太原理工大学 矿业工程学院，山西　太原　030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322594508026523987, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, xref=null, ext=[AuthorCompanyExt(id=1322594508034912596, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China), AuthorCompanyExt(id=1322594508051689813, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学 矿业工程学院，山西　太原　030024)])]), Author(id=1322594508638892385, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322594508743749987, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, authorId=1322594508638892385, language=EN, stringName=Xiang FU, firstName=Xiang, middleName=null, lastName=FU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322594508823441764, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, authorId=1322594508638892385, language=CN, stringName=付翔, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=太原理工大学 矿业工程学院，山西　太原　030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322594508026523987, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, xref=null, ext=[AuthorCompanyExt(id=1322594508034912596, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China), AuthorCompanyExt(id=1322594508051689813, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学 矿业工程学院，山西　太原　030024)])]), Author(id=1322594508886356326, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322594508957659496, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, authorId=1322594508886356326, language=EN, stringName=Jun WANG, firstName=Jun, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322594509028962665, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, authorId=1322594508886356326, language=CN, stringName=王珺, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=太原理工大学 矿业工程学院，山西　太原　030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322594508026523987, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, xref=null, ext=[AuthorCompanyExt(id=1322594508034912596, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China), AuthorCompanyExt(id=1322594508051689813, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学 矿业工程学院，山西　太原　030024)])]), Author(id=1322594509096071531, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322594509175763309, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, authorId=1322594509096071531, language=EN, stringName=Kai WEI, firstName=Kai, middleName=null, lastName=WEI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322594509234483566, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, authorId=1322594509096071531, language=CN, stringName=魏凯, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=太原理工大学 矿业工程学院，山西　太原　030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322594508026523987, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, xref=null, ext=[AuthorCompanyExt(id=1322594508034912596, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China), AuthorCompanyExt(id=1322594508051689813, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学 矿业工程学院，山西　太原　030024)])]), Author(id=1322594509314175344, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322594509381284210, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, authorId=1322594509314175344, language=EN, stringName=Qian ZHANG, firstName=Qian, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322594509465170291, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, authorId=1322594509314175344, language=CN, stringName=张茜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=太原理工大学 矿业工程学院，山西　太原　030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322594508026523987, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, xref=null, ext=[AuthorCompanyExt(id=1322594508034912596, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China), AuthorCompanyExt(id=1322594508051689813, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学 矿业工程学院，山西　太原　030024)])])], keywords=[Keyword(id=1322594511168057716, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=EN, orderNo=1, keyword=Coal slime flotation), Keyword(id=1322594511251943797, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=EN, orderNo=2, keyword=Ash of coal tailings), Keyword(id=1322594511327441270, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=EN, orderNo=3, keyword=Genetic algorithms), Keyword(id=1322594511407133047, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=EN, orderNo=4, keyword=LightGBM), Keyword(id=1322594511478436216, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=EN, orderNo=5, keyword=Predictive modeling), Keyword(id=1322594511553933689, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=CN, orderNo=1, keyword=煤泥浮选), Keyword(id=1322594511633625466, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=CN, orderNo=2, keyword=尾煤灰分), Keyword(id=1322594511709122939, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=CN, orderNo=3, keyword=遗传算法), Keyword(id=1322594511776231804, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=CN, orderNo=4, keyword=LightGBM), Keyword(id=1322594511839146365, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=CN, orderNo=5, keyword=预测建模)], refs=[Reference(id=1322594513873383829, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2019, volume=45, issue=7, pageStart=28, pageEnd=32, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=王然风, 高建川, 付翔, journalName=工矿自动化, refType=null, unstructuredReference=王然风，高建川，付翔. 智能化选煤厂架构及关键技术[J]. 工矿自动化，2019，45(7): 28-32., articleTitle=智能化选煤厂架构及关键技术, refAbstract=null), Reference(id=1322594513940492694, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2019, volume=45, issue=7, pageStart=28, pageEnd=32, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=WANG Ranfeng, GAO Jianchuan, FU Xiang, journalName=Industry and Mine Automation, refType=null, unstructuredReference=WANG Ranfeng, GAO Jianchuan, FU Xiang. Framework and key technologies of intelligent coal preparation plant[J]. Industry and Mine Automation, 2019, 45(7):28-32., articleTitle=Framework and key technologies of intelligent coal preparation plant, refAbstract=null), Reference(id=1322594515660157335, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2023, volume=51, issue=4, pageStart=26, pageEnd=32, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=白飞燕, 樊民强, 杨宏丽, journalName=选煤技术, refType=null, unstructuredReference=白飞燕，樊民强，杨宏丽，等. 基于 X射线衍射的煤炭灰分快速检测方法研究[J]. 选煤技术，2023, 51(4): 26-32., articleTitle=基于 X射线衍射的煤炭灰分快速检测方法研究, refAbstract=null), Reference(id=1322594515723071896, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2023, volume=51, issue=4, pageStart=26, pageEnd=32, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=BAI Feiyan, FAN Minqiang, YANG Hongli, journalName=Coal Preparation Technology, refType=null, unstructuredReference=BAI Feiyan, FAN Minqiang, YANG Hongli, et al, Study of the X-ray diffraction-based coal ash rapid determination method[J]. Coal Preparation Technology, 2023, 51(4): 26-32., articleTitle=Study of the X-ray diffraction-based coal ash rapid determination method, refAbstract=null), Reference(id=1322594515802763673, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2014, volume=35, issue=10, pageStart=2263, pageEnd=2270, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=程栋, 温和, 滕召胜, journalName=仪器仪表学报, refType=null, unstructuredReference=程栋，温和，滕召胜，等. 基于双能γ射线的煤质灰分软测量技术研究[J]. 仪器仪表学报，2014, 35(10): 2263-2270., articleTitle=基于双能γ射线的煤质灰分软测量技术研究, refAbstract=null), Reference(id=1322594515899232666, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2014, volume=35, issue=10, pageStart=2263, pageEnd=2270, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=CHENG Dong, WEN He, TENG Zhaosheng, journalName=Chinese Journal of Scientific Instrument, refType=null, unstructuredReference=CHENG Dong, WEN He, TENG Zhaosheng, et al. Study on soft-sensing of coal ash content based on dual-energy γ-ray[J]. Chinese Journal of Scientific Instrument, 2014, 35 (10): 2263-2270., articleTitle=Study on soft-sensing of coal ash content based on dual-energy γ-ray, refAbstract=null), Reference(id=1322594515970535835, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2018, volume=169, issue=null, pageStart=77, pageEnd=84, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=ZHU R S, LIU Y Z, ZHANG Q H, journalName=Optik, refType=null, unstructuredReference=ZHU R S, LIU Y Z, ZHANG Q H, et al. Quantitative analysis of Fe and detection of multiple elements in the coal ash by laser-induced breakdown spectroscopy[J].Optik, 2018, 169:77-84., articleTitle=Quantitative analysis of Fe and detection of multiple elements in the coal ash by laser-induced breakdown spectroscopy, refAbstract=null), Reference(id=1322594516134113692, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2013, volume=39, issue=11, pageStart=1879, pageEnd=1888, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=桂卫华, 阳春华, 徐德刚, journalName=自动化学报, refType=null, unstructuredReference=桂卫华，阳春华，徐德刚，等. 基于机器视觉的矿物浮选过程监控技术研究进展[J]. 自动化学报，2013, 39(11): 1879-1888., articleTitle=基于机器视觉的矿物浮选过程监控技术研究进展, refAbstract=null), Reference(id=1322594516205416861, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2013, volume=39, issue=11, pageStart=1879, pageEnd=1888, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=GUI Weihua, YANG Chunhua, XU Degang, journalName=Acta Automatic Sinaca, refType=null, unstructuredReference=GUI Weihua, YANG Chunhua, XU Degang, et al. Machine-vision-based online measuring and controlling technologies for mineral flotation: a review[J]. Acta Automatic Sinaca, 2013, 39(11): 1879-1888., articleTitle=Machine-vision-based online measuring and controlling technologies for mineral flotation: a review, refAbstract=null), Reference(id=1322594516276720030, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2020, volume=39, issue=2, pageStart=144, pageEnd=146, url=null, language=null, rfNumber=[6], rfOrder=9, authorNames=郭西进, 魏凌敖, 杨春宝, journalName=煤炭技术, refType=null, unstructuredReference=郭西进，魏凌敖，杨春宝. 基于深度卷积网络的煤泥浮选尾矿灰分检测方法研究[J]. 煤炭技术，2020，39(2): 144-146., articleTitle=基于深度卷积网络的煤泥浮选尾矿灰分检测方法研究, refAbstract=null), Reference(id=1322594516352217503, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2020, volume=39, issue=2, pageStart=144, pageEnd=146, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=GUO Xijin, WEI Ling'ao, YANG Chunbao, journalName=Coal Technology, refType=null, unstructuredReference=GUO Xijin, WEI Ling'ao, YANG Chunbao. Research on ash detection method of coal slime flotation tailings on convolutional neural network[J]. Coal Technology, 2020, 39 (2):144-146., articleTitle=Research on ash detection method of coal slime flotation tailings on convolutional neural network, refAbstract=null), Reference(id=1322594516440297888, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2023, volume=42, issue=null, pageStart=233, pageEnd=238, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=范富博, 王然风, 付翔, journalName=煤炭技术, refType=null, unstructuredReference=范富博，王然风，付翔. 基于多源异构信息融合的浮选精煤灰分在线检测技术研究与应用[J]. 煤炭技术，2023，42（2）：233-238., articleTitle=基于多源异构信息融合的浮选精煤灰分在线检测技术研究与应用, refAbstract=null), Reference(id=1322594516515795361, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2023, volume=42, issue=2, pageStart=233, pageEnd=238, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=FAN Fubo, WANG Ranfeng, FU Xiang, journalName=Coal Technology, refType=null, unstructuredReference=FAN Fubo, WANG Ranfeng, FU Xiang. Research and application of on-line detection technology of flotation cleaned coal ash based on multi-source heterogeneous information fusion [J]. Coal Technology, 2023, 42 (2): 233-238., articleTitle=Research and application of on-line detection technology of flotation cleaned coal ash based on multi-source heterogeneous information fusion, refAbstract=null), Reference(id=1322594516587098530, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2009, volume=30, issue=6, pageStart=1295, pageEnd=1300, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=周开军, 阳春华, 牟学民, journalName=仪器仪表学报, refType=null, unstructuredReference=周开军，阳春华，牟学民，等. 基于泡沫特征与 LS-SVM的浮选回收率预测[J]. 仪器仪表学报，2009, 30(6): 1295-1300., articleTitle=基于泡沫特征与 LS-SVM的浮选回收率预测, refAbstract=null), Reference(id=1322594516650013091, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2009, volume=30, issue=6, pageStart=1295, pageEnd=1300, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=ZHOU Kaijun, YANG Chunhua, MOU Xuemin, journalName=Chinese Journal of Scientific Instrument, refType=null, unstructuredReference=ZHOU Kaijun, YANG Chunhua, MOU Xuemin, et al. Flotation recovery prediction based on froth features and LS-SVM[J]. Chinese Journal of Scientific Instrument, 2009, 30 (6):1295-1300., articleTitle=Flotation recovery prediction based on froth features and LS-SVM, refAbstract=null), Reference(id=1322594516729704868, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=10, pageStart=1746, pageEnd=1752, url=null, language=null, rfNumber=[9], rfOrder=15, authorNames=唐维, 陶钰欣, 郝启文, journalName=控制工程, refType=null, unstructuredReference=唐维，陶钰欣，郝启文，等. 基于遗传算法优化BP神经网络的曝气量预测[J]. 控制工程，2024(10): 1746-1752., articleTitle=基于遗传算法优化BP神经网络的曝气量预测, refAbstract=null), Reference(id=1322594516809396645, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=10, pageStart=1746, pageEnd=1752, url=null, language=null, rfNumber=[9], rfOrder=16, authorNames=TANG Wei, TAO Yuxin, HAO Qiwen, journalName=Control Engineering of China, refType=null, unstructuredReference=TANG Wei, TAO Yuxin, HAO Qiwen, et al. Prediction of aeration quantity based on bp neural network optimized by genetic algorithm [J]. Control Engineering of China, 2024 (10):1746-1752., articleTitle=Prediction of aeration quantity based on bp neural network optimized by genetic algorithm, refAbstract=null), Reference(id=1322594516943614374, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2024, volume=32, issue=1, pageStart=165, pageEnd=171+178, url=null, language=null, rfNumber=[10], rfOrder=17, authorNames=胡一晨, 耿虎军, journalName=计算机测量与控制, refType=null, unstructuredReference=胡一晨，耿虎军. 基于改进遗传算法优化的 RBF 网络的信道估计[J].计算机测量与控制，2024, 32(1): 165-171+178., articleTitle=基于改进遗传算法优化的 RBF 网络的信道估计, refAbstract=null), Reference(id=1322594517014917543, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2024, volume=32, issue=1, pageStart=165, pageEnd=171+178, url=null, language=null, rfNumber=[10], rfOrder=18, authorNames=HU Yichen, GENG Hujun, journalName=Computer Measurement & Control, refType=null, unstructuredReference=HU Yichen, GENG Hujun. Channel estimation of RBF networks based on improved genetic algorithm optimization [J]. Computer Measurement & Control, 2024, 32(1): 165-171+178., articleTitle=Channel estimation of RBF networks based on improved genetic algorithm optimization, refAbstract=null), Reference(id=1322594517086220712, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2024, volume=41, issue=2, pageStart=233, pageEnd=240, url=null, language=null, rfNumber=[11], rfOrder=19, authorNames=王巍, 丁辉, 夏旭, journalName=中国医学物理学杂志, refType=null, unstructuredReference=王巍，丁辉，夏旭，等. 基于遗传算法优化C-LSTM模型的心律失常分类方法[J]. 中国医学物理学杂志，2024，41（2）：233-240., articleTitle=基于遗传算法优化C-LSTM模型的心律失常分类方法, refAbstract=null), Reference(id=1322594517157523881, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2024, volume=41, issue=2, pageStart=233, pageEnd=240, url=null, language=null, rfNumber=[11], rfOrder=20, authorNames=WANG Wei, DING Hui, XIA Xu, journalName=Chinese Journal of Medical Physics, refType=null, unstructuredReference=WANG Wei, DING Hui, XIA Xu, et al. Arrhythmia classification method based on genetic algorithm optimization of C-LSTM model [J]. Chinese Journal of Medical Physics, 2024, 41(2):233-240., articleTitle=Arrhythmia classification method based on genetic algorithm optimization of C-LSTM model, refAbstract=null), Reference(id=1322594517354656170, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2021, volume=53, issue=增刊1, pageStart=108, pageEnd=111, url=null, language=null, rfNumber=[12], rfOrder=21, authorNames=张月飞, 王伟, 代伟, journalName=煤炭工程, refType=null, unstructuredReference=张月飞，王伟，代伟. 重介分选过程产品指标在线预测方法研究[J]. 煤炭工程，2021，53(增刊1): 108-111., articleTitle=重介分选过程产品指标在线预测方法研究, refAbstract=null), Reference(id=1322594517425959339, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2021, volume=53, issue=Suppl.1, pageStart=108, pageEnd=111, url=null, language=null, rfNumber=[12], rfOrder=22, authorNames=ZHANG Yuefei, WANG Wei, DAI Wei, journalName=Coal Engineering, refType=null, unstructuredReference=ZHANG Yuefei, WANG Wei, DAI Wei. On-line prediction of product indicators in dense medium coal separation[J]. Coal Engineering, 2021, 53(Suppl.1): 108-111., articleTitle=On-line prediction of product indicators in dense medium coal separation, refAbstract=null), Reference(id=1322594517501456812, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2023, volume=68, issue=12, pageStart=309, pageEnd=314, url=null, language=null, rfNumber=[13], rfOrder=23, authorNames=王阳春, 茆梦凡, 龙关旭, journalName=公路, refType=null, unstructuredReference=王阳春，茆梦凡，龙关旭，等. 基于GBDT的锈蚀钢筋混凝土梁抗弯承载力预测研究[J]. 公路，2023, 68(12): 309-314., articleTitle=基于GBDT的锈蚀钢筋混凝土梁抗弯承载力预测研究, refAbstract=null), Reference(id=1322594517581148589, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2023, volume=68, issue=12, pageStart=309, pageEnd=314, url=null, language=null, rfNumber=[13], rfOrder=24, authorNames=WANG Yangchun, MAO Mengfan, LONG Guanxu, journalName=Highway, refType=null, unstructuredReference=WANG Yangchun, MAO Mengfan, LONG Guanxu, et al. Research on prediction of flexural capacity of corroded reinforced concrete beams based on GBDT[J]. Highway, 2023, 68(12):309-314., articleTitle=Research on prediction of flexural capacity of corroded reinforced concrete beams based on GBDT, refAbstract=null), Reference(id=1322594517669228974, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2024, volume=52, issue=1, pageStart=17, pageEnd=24, url=null, language=null, rfNumber=[14], rfOrder=25, authorNames=汪明元, 王振红, 陈松庭, journalName=浙江工业大学学报, refType=null, unstructuredReference=汪明元，王振红，陈松庭. 基于LightGBM算法的海洋土压缩参数预测模型[J]. 浙江工业大学学报，2024, 52(1): 17-24., articleTitle=基于LightGBM算法的海洋土压缩参数预测模型, refAbstract=null), Reference(id=1322594517790863791, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2024, volume=52, issue=1, pageStart=17, pageEnd=24, url=null, language=null, rfNumber=[14], rfOrder=26, authorNames=WANG Mingyuan, WANG Zhenhong, CHEN Songting, journalName=Journal of Zhejiang University of Technology, refType=null, unstructuredReference=WANG Mingyuan, WANG Zhenhong, CHEN Songting. Prediction of marine soil compressibility based on LightGBM algorithm[J]. Journal of Zhejiang University of Technology, 2024, 52(1):17-24., articleTitle=Prediction of marine soil compressibility based on LightGBM algorithm, refAbstract=null), Reference(id=1322594517933470128, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2022, volume=220, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=27, authorNames=HAO X C, ZHANG Z P, XU Q Q, journalName=Chemometrics and Intelligent Laboratory Systems, refType=null, unstructuredReference=HAO X C, ZHANG Z P, XU Q Q, et al. Prediction of f-CaO content in cement clinker: a novel prediction method based on LightGBM and Bayesian optimization[J]. Chemometrics and Intelligent Laboratory Systems, 2022, 220:104461., articleTitle=Prediction of f-CaO content in cement clinker: a novel prediction method based on LightGBM and Bayesian optimization, refAbstract=null), Reference(id=1322594518138991025, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=7, pageStart=679, pageEnd=684, url=null, language=null, rfNumber=[16], rfOrder=28, authorNames=王志彪, 赵丽华, journalName=大地测量与地球动力学, refType=null, unstructuredReference=王志彪，赵丽华. 遗传算法与粒子群优化的Elman神经网络模型预测黄土滑坡变形[J]. 大地测量与地球动力学，2023, 43(7):679-684., articleTitle=遗传算法与粒子群优化的Elman神经网络模型预测黄土滑坡变形, refAbstract=null), Reference(id=1322594518210294194, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=7, pageStart=679, pageEnd=684, url=null, language=null, rfNumber=[16], rfOrder=29, authorNames=WANG Zhibiao, ZHAO Lihua, journalName=Journal of Geodesy and Geodynamics, refType=null, unstructuredReference=WANG Zhibiao, ZHAO Lihua. Prediction of loess landslides deformation using elman neural network model based on genetic algorithm and particle swarm optimization[J]. Journal of Geodesy and Geodynamics, 2023, 43(7):679-684., articleTitle=Prediction of loess landslides deformation using elman neural network model based on genetic algorithm and particle swarm optimization, refAbstract=null), Reference(id=1322594518336123315, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2022, volume=25, issue=6, pageStart=65, pageEnd=69, url=null, language=null, rfNumber=[17], rfOrder=30, authorNames=高明亮, 邵俊捷, 常振臣, journalName=城市轨道交通研究, refType=null, unstructuredReference=高明亮，邵俊捷，常振臣，等. 基于遗传算法–BP神经网络的动车组列车轮对磨耗模型[J]. 城市轨道交通研究，2022, 25(6):65-69., articleTitle=基于遗传算法–BP神经网络的动车组列车轮对磨耗模型, refAbstract=null), Reference(id=1322594518403232180, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2022, volume=25, issue=6, pageStart=65, pageEnd=69, url=null, language=null, rfNumber=[17], rfOrder=31, authorNames=GAO Mingliang, SHAO Junjie, CHANG Zhenchen, journalName=Urban Rail Transit Research, refType=null, unstructuredReference=GAO Mingliang, SHAO Junjie, CHANG Zhenchen, et al. EMU train wheelset wear model based on genetic algorithm-BP neural network[J]. Urban Rail Transit Research, 2022, 25(6):65-69., articleTitle=EMU train wheelset wear model based on genetic algorithm-BP neural network, refAbstract=null), Reference(id=1322594520055787957, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2021, volume=172, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=32, authorNames=ZHANG H, TANG Z H, XIE Y F, journalName=Minerals Engineering, refType=null, unstructuredReference=ZHANG H, TANG Z H, XIE Y F, et al. Grade prediction of zinc tailings using an encoder-decoder model in froth flotation[J]. Minerals Engineering, 2021, 172:107173., articleTitle=Grade prediction of zinc tailings using an encoder-decoder model in froth flotation, refAbstract=null), Reference(id=1322594520156451254, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2002, volume=82, issue=1, pageStart=47, pageEnd=54, url=null, language=null, rfNumber=[19], rfOrder=33, authorNames=TONGCHIM S, CHONGSTITVATANA P, journalName=Information Processing Letters, refType=null, unstructuredReference=TONGCHIM S, CHONGSTITVATANA P. Parallel genetic algorithm with parameter adaptation[J]. Information Processing Letters, 2002, 82(1):47-54., articleTitle=Parallel genetic algorithm with parameter adaptation, refAbstract=null), Reference(id=1322594520231948727, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2022, volume=33, issue=4, pageStart=50, pageEnd=57+63, url=null, language=null, rfNumber=[20], rfOrder=34, authorNames=陈奂良, 李常锁, 高帅, journalName=水资源与水工程学报, refType=null, unstructuredReference=陈奂良，李常锁，高帅，等. 基于遗传算法优化BP神经网络的岩溶泉水位预测研究[J]. 水资源与水工程学报，2022，33(4): 50-57+63., articleTitle=基于遗传算法优化BP神经网络的岩溶泉水位预测研究, refAbstract=null), Reference(id=1322594520320029112, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2022, volume=33, issue=4, pageStart=50, pageEnd=57+63, url=null, language=null, rfNumber=[20], rfOrder=35, authorNames=CHEN Huanliang, LI Changsuo, GAO Shuai, journalName=Journal of Water Resources and Water Engineering, refType=null, unstructuredReference=CHEN Huanliang，LI Changsuo，GAO Shuai，et al. Research on karst spring water level prediction based on genetic algorithm optimization BP neural network [J]. Journal of Water Resources and Water Engineering, 2022, 33(4):50-57+63., articleTitle=Research on karst spring water level prediction based on genetic algorithm optimization BP neural network, refAbstract=null), Reference(id=1322594520391332281, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2023, volume=46, issue=2, pageStart=109, pageEnd=118, url=null, language=null, rfNumber=[21], rfOrder=36, authorNames=邱钱粮, 白向飞, journalName=煤炭转化, refType=null, unstructuredReference=邱钱粮，白向飞. 基于遗传算法优化的BP神经网络气化用煤灰流动温度预测模型[J]. 煤炭转化，2023, 46(2): 109-118., articleTitle=基于遗传算法优化的BP神经网络气化用煤灰流动温度预测模型, refAbstract=null), Reference(id=1322594520458441146, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2023, volume=46, issue=2, pageStart=109, pageEnd=118, url=null, language=null, rfNumber=[21], rfOrder=37, authorNames=QIU Qianliang, BAI Xiangfei, journalName=Coal Conversion, refType=null, unstructuredReference=QIU Qianliang，BAI Xiangfei. Prediction model of fusion temperature of coal ash for gasification based on GA-BP neural network[J]. Coal Conversion, 2023, 46(2): 109-118., articleTitle=Prediction model of fusion temperature of coal ash for gasification based on GA-BP neural network, refAbstract=null), Reference(id=1322594520517161403, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, doi=null, pmid=null, pmcid=null, year=2023, volume=192, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=38, authorNames=TIAN C, TANG Z H, XIE Y F, journalName=Minerals Engineering, refType=null, unstructuredReference=TIAN C, TANG Z H, XIE Y F, et al. Towards tailing grade prediction in zinc flotation via variablewise and temporalwise attention[J]. Minerals Engineering, 2023, 192: 108000., articleTitle=Towards tailing grade prediction in zinc flotation via variablewise and temporalwise attention, refAbstract=null)], funds=[Fund(id=1322594513630114194, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, awardId=52274157, language=CN, fundingSource=国家自然科学基金项目(52274157), fundOrder=null, country=null), Fund(id=1322594513701417363, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, awardId=2022EEDSKJXM010, language=CN, fundingSource=内蒙古自治区重点专项项目(2022EEDSKJXM010), fundOrder=null, country=null), Fund(id=1322594513781109140, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, awardId=202102100401015, language=CN, fundingSource=山西省重点研发计划项目(202102100401015), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1322594508026523987, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, xref=null, ext=[AuthorCompanyExt(id=1322594508034912596, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China), AuthorCompanyExt(id=1322594508051689813, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学 矿业工程学院，山西　太原　030024)])], figs=[ArticleFig(id=1322594511960781182, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=EN, label=Fig.1, caption=LightGBM histogram algorithm, figureFileSmall=TimwhRDk/HGk+G4qMlS5Vw==, figureFileBig=zRtO/jHh13yXKEvWaAYZ4A==, tableContent=null), ArticleFig(id=1322594512040472959, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=CN, label=图1, caption=LightGBM直方图算法, figureFileSmall=TimwhRDk/HGk+G4qMlS5Vw==, figureFileBig=zRtO/jHh13yXKEvWaAYZ4A==, tableContent=null), ArticleFig(id=1322594512208245120, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=EN, label=Fig.2, caption=Growing by layer and by leaf node, figureFileSmall=PGmBeztCC2y22OPYY+F7mw==, figureFileBig=ug50IgLtwn5088C9a/E48g==, tableContent=null), ArticleFig(id=1322594512271159681, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=CN, label=图2, caption=按层生长和按叶子结点生长, figureFileSmall=PGmBeztCC2y22OPYY+F7mw==, figureFileBig=ug50IgLtwn5088C9a/E48g==, tableContent=null), ArticleFig(id=1322594512342462850, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=EN, label=Fig.3, caption=Flow of GA-LightGBM, figureFileSmall=RUwKgoralp7MpmKZdiQKzg==, figureFileBig=/edBThaNX0ph5UDzsl0TMw==, tableContent=null), ArticleFig(id=1322594512409571715, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=CN, label=图3, caption=GA-LightGBM流程, figureFileSmall=RUwKgoralp7MpmKZdiQKzg==, figureFileBig=/edBThaNX0ph5UDzsl0TMw==, tableContent=null), ArticleFig(id=1322594512489263492, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=EN, label=Fig.4, caption=Technological process of flotation, figureFileSmall=TvnndSWbf/jF+ZteJtpTcg==, figureFileBig=hZ5R8KCcBbNIHdPo0R1N0g==, tableContent=null), ArticleFig(id=1322594512564760965, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=CN, label=图4, caption=浮选工艺流程, figureFileSmall=TvnndSWbf/jF+ZteJtpTcg==, figureFileBig=hZ5R8KCcBbNIHdPo0R1N0g==, tableContent=null), ArticleFig(id=1322594512631869830, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=EN, label=Fig.5, caption=Changes in individual fitness during GA training, figureFileSmall=F/lnm//uOBLRmuDyDkAQKg==, figureFileBig=zdI9CeZ5Jc8ILeA7V9v3fw==, tableContent=null), ArticleFig(id=1322594512715755911, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=CN, label=图5, caption=GA训练时个体适应度变化, figureFileSmall=F/lnm//uOBLRmuDyDkAQKg==, figureFileBig=zdI9CeZ5Jc8ILeA7V9v3fw==, tableContent=null), ArticleFig(id=1322594512770281864, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=EN, label=Fig.6, caption=Comparison between the model prodicted values and actual values of ash, figureFileSmall=m0AmMG3BTAWh+nOWRXJopQ==, figureFileBig=oKMc3ka29EITSe9hZDMEKA==, tableContent=null), ArticleFig(id=1322594512841585033, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=CN, label=图6, caption=灰分模型预测值与真实值的对比, figureFileSmall=m0AmMG3BTAWh+nOWRXJopQ==, figureFileBig=oKMc3ka29EITSe9hZDMEKA==, tableContent=null), ArticleFig(id=1322594512900305290, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=EN, label=Table 1, caption=

Process variables statistics

, figureFileSmall=null, figureFileBig=null, tableContent=
过程变量均值标准差最小值中位数最大值
矿浆流量反馈725.5139.03516.68724.38892.39
浓度计反馈97.353.5581.6897.46122.62
捕收剂汇总输入12.872.714.7613.4720.00
起泡剂汇总输入8.470.816.028.5210.89
干煤泥量70.675.2645.1970.0892.06
AI矿浆灰分仪反馈71.593.0953.2572.0083.50
), ArticleFig(id=1322594512988385675, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=CN, label=表1, caption=

过程变量统计

, figureFileSmall=null, figureFileBig=null, tableContent=
过程变量均值标准差最小值中位数最大值
矿浆流量反馈725.5139.03516.68724.38892.39
浓度计反馈97.353.5581.6897.46122.62
捕收剂汇总输入12.872.714.7613.4720.00
起泡剂汇总输入8.470.816.028.5210.89
干煤泥量70.675.2645.1970.0892.06
AI矿浆灰分仪反馈71.593.0953.2572.0083.50
), ArticleFig(id=1322594513101631884, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=EN, label=Table 2, caption=

Parameters of genetic algorithm

, figureFileSmall=null, figureFileBig=null, tableContent=
参数名称参数值
种群数量Npop10
均匀交叉概率0.5
均匀整数突变概率0.3
迭代次数Ngen10
锦标赛选择次数k15
单次锦标赛选手数量p2
), ArticleFig(id=1322594513172935053, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=CN, label=表2, caption=

遗传算法参数

, figureFileSmall=null, figureFileBig=null, tableContent=
参数名称参数值
种群数量Npop10
均匀交叉概率0.5
均匀整数突变概率0.3
迭代次数Ngen10
锦标赛选择次数k15
单次锦标赛选手数量p2
), ArticleFig(id=1322594513256821134, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=EN, label=Table 3, caption=

Parameters of the LightGBM model

, figureFileSmall=null, figureFileBig=null, tableContent=
参数类型变量名作用值
共享参数objective模型目标类型，回归/分类regression
loss训练过程中的损失函数MSE
boosting集成算法的类别GBDT
data_sample_strategy数据采样方式GOSS
metric评价指标R2
待优化参数num_leaves单棵树的叶子数量{31,63,127,255,512}
max_depth单棵树的最大深度{5,6,7,8,9}
min_data_in_leaf单个叶子上的最少数据{20,40,60,80,100}
GA训练时参数num_iterations迭代数量5 000
early_stop_iterations指标停止更新多少迭代后早停50
learning_rate学习率0.1
评估时参数num_iterations迭代数量30 000
early_stop_iterations指标停止更新多少迭代后早停200
learning_rate学习率0.05
), ArticleFig(id=1322594513340707215, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=CN, label=表3, caption=

LightGBM 模型参数

, figureFileSmall=null, figureFileBig=null, tableContent=
参数类型变量名作用值
共享参数objective模型目标类型，回归/分类regression
loss训练过程中的损失函数MSE
boosting集成算法的类别GBDT
data_sample_strategy数据采样方式GOSS
metric评价指标R2
待优化参数num_leaves单棵树的叶子数量{31,63,127,255,512}
max_depth单棵树的最大深度{5,6,7,8,9}
min_data_in_leaf单个叶子上的最少数据{20,40,60,80,100}
GA训练时参数num_iterations迭代数量5 000
early_stop_iterations指标停止更新多少迭代后早停50
learning_rate学习率0.1
评估时参数num_iterations迭代数量30 000
early_stop_iterations指标停止更新多少迭代后早停200
learning_rate学习率0.05
), ArticleFig(id=1322594513441370512, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=EN, label=Table 4, caption=

Comparison of evaluation results of the models

, figureFileSmall=null, figureFileBig=null, tableContent=
模型MAEMSEMAPER2
AdaBoost2.377±0.078 02.939±0.076 50.033±0.001 00.099±0.052 1
BP1.975±0.115 82.603±0.109 90.028±0.001 70.293±0.057 4
DT0.856±0.003 61.415±0.015 40.012±0.000 10.791±0.003 0
ElasticNet2.057±0.007 02.730±0.015 80.029±0.000 10.223±0.003 0
GBDT1.045±0.006 41.486±0.007 50.015±0.000 10.770±0.003 2
GA-LightGBM0.720±0.002 21.035±0.008 40.010±0.000 00.888±0.001 0
LightGBM0.810±0.002 31.187±0.005 60.012±0.000 00.839±0.001 1
SVR2.086±0.005 82.760±0.013 90.029±0.000 10.206±0.002 7
XGBoost0.910±0.002 31.298±0.002 80.013±0.000 00.824±0.001 2
), ArticleFig(id=1322594513508479377, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, language=CN, label=表4, caption=

模型评价结果对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型MAEMSEMAPER2
AdaBoost2.377±0.078 02.939±0.076 50.033±0.001 00.099±0.052 1
BP1.975±0.115 82.603±0.109 90.028±0.001 70.293±0.057 4
DT0.856±0.003 61.415±0.015 40.012±0.000 10.791±0.003 0
ElasticNet2.057±0.007 02.730±0.015 80.029±0.000 10.223±0.003 0
GBDT1.045±0.006 41.486±0.007 50.015±0.000 10.770±0.003 2
GA-LightGBM0.720±0.002 21.035±0.008 40.010±0.000 00.888±0.001 0
LightGBM0.810±0.002 31.187±0.005 60.012±0.000 00.839±0.001 1
SVR2.086±0.005 82.760±0.013 90.029±0.000 10.206±0.002 7
XGBoost0.910±0.002 31.298±0.002 80.013±0.000 00.824±0.001 2
)], attaches=null, journal=Journal(id=1225396331729022976, delFlag=0, nameCn=矿业研究与开发, nameEn=Mining Research and Development, nameHistory1=null, nameHistory2=null, issn=1005-2763, eissn=null, cn=43-1215/TD, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=BLic9JllTIKtYRYod5zIVQ==, journalPrice=null, startedYear=null, abbrevIsoEn=Mining Research and Development, journalRemark=null, publicationField=null, createdTime=1770086852251, updatedTime=1784018193958, createdBy=18614031015, updatedBy=13041195026, firstLetterCn=K, firstLetterEn=K, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=BLic9JllTIKtYRYod5zIVQ==, picEn=Bqi6ei4JhI5hinJcqiOo2A==, jcr=null, cjcr=null, exts=[JournalExt(id=1283828614093321209, language=CN, name=矿业研究与开发, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1784018193982, updatedTime=1784018193982, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.chinamine.org.cn/kyyjykf/author/login, submissionEditorUrl=http://www.chinamine.org.cn/kyyjykf/editor/login, submissionReviewUrl=http://www.chinamine.org.cn/kyyjykf/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1283828614143652858, language=EN, name=Mining Research and Development, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1784018193994, updatedTime=1784018193994, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.chinamine.org.cn/kyyjykfen/author/login, submissionEditorUrl=http://www.chinamine.org.cn/kyyjykfen/editor/login, submissionReviewUrl=http://www.chinamine.org.cn/kyyjykfen/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1225396423026438145, websiteList=[Website(id=1225409554104627231, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1225396423026438145, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kyyjykf/CN, language=CN, createTime=1770090004708, createBy=18614031015, updateTime=1770090031995, updateBy=18614031015, name=矿业研究与开发-中文, tplId=1146099689490845704, title=矿业研究与开发, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1228001470277153440, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=articleTextType, value=kx, createTime=1770707965678, updateTime=1770707965678, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470256181917, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=banner, value=null, createTime=1770707965673, updateTime=1770707965673, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470293930659, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=grayFlag, value=0, createTime=1770707965682, updateTime=1770707965682, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470251987612, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=logo, value=https://castjournals.cast.org.cn/joweb/kyyjykf/CN/file/pic?fileId=++etCLRiS7F8czudkkUdPA==, createTime=1770707965672, updateTime=1770707965672, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470302319269, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=minRunFlag, value=0, createTime=1770707965684, updateTime=1770707965684, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470268764831, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kyyjykf/CN/file/pic, createTime=1770707965676, updateTime=1770707965676, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470298124964, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=silenceFlag, value=0, createTime=1770707965683, updateTime=1770707965683, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470264570526, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1770707965675, updateTime=1770707965675, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470281347745, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=themeColor, value=null, createTime=1770707965679, updateTime=1770707965679, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001470285542050, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554104627231, code=themeStyle, value=null, createTime=1770707965680, updateTime=1770707965680, creator=18614031015, updator=18614031015)]), Website(id=1225409554180124705, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1225396423026438145, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kyyjykf/EN, language=EN, createTime=1770090004726, createBy=18614031015, updateTime=1770090069284, updateBy=18614031015, name=矿业研究与开发英文, tplId=1146101810881728533, title=Mining Research and Development, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1225410562574696778, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=articleTextType, value=kx, createTime=1770090245145, updateTime=1770090245145, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562553725255, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=banner, value=null, createTime=1770090245140, updateTime=1770090245140, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562612445517, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=grayFlag, value=0, createTime=1770090245154, updateTime=1770090245154, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562536948038, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=logo, value=https://castjournals.cast.org.cn/joweb/kyyjykf/EN/file/pic?fileId=++etCLRiS7F8czudkkUdPA==, createTime=1770090245136, updateTime=1770090245136, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562629222735, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=minRunFlag, value=0, createTime=1770090245158, updateTime=1770090245158, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562566308169, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kyyjykf/EN/file/pic, createTime=1770090245143, updateTime=1770090245143, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562620834126, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=silenceFlag, value=0, createTime=1770090245156, updateTime=1770090245156, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562562113864, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1770090245142, updateTime=1770090245142, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562583085387, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=themeColor, value=null, createTime=1770090245147, updateTime=1770090245147, creator=18614031015, updator=18614031015), WebsiteProps(id=1225410562604056908, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225409554180124705, code=themeStyle, value=null, createTime=1770090245152, updateTime=1770090245152, creator=18614031015, updator=18614031015)])], journalTitle=矿业研究与开发, weixinUrl=null, journalUrl=null, iacademicId=null, status=1, seqNo=null, journalTitleEn=Mining Research and Development, journalPhotoCn=BLic9JllTIKtYRYod5zIVQ==, journalPhotoEn=Bqi6ei4JhI5hinJcqiOo2A==, journalFirstLetter=K, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/kyyjykf/CN/Y2025/V45/I1/269, detailUrlEn=https://castjournals.cast.org.cn/joweb/kyyjykf/EN/Y2025/V45/I1/269, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kyyjykf/CN/PDF/Y2025/V45/I1/269, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kyyjykf/EN/PDF/Y2025/V45/I1/269, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1737734400000, fullTextJson=null, articleText=null, reference=null)
收藏切换
基于遗传算法优化的LightGBM浮选尾煤灰分预测模型研究
收藏切换
PDF下载
韩杰 I , 王然风 I , 付翔 I , 王珺 I , 魏凯 I , 张茜 I
矿业研究与开发 | 选矿与资源综合利用 2025,45(1): 269-276
收起
收藏切换
矿业研究与开发 |选矿与资源综合利用 2025 , 45 (1) : 269 -276
基于遗传算法优化的LightGBM浮选尾煤灰分预测模型研究
全屏
[Author(id=1322594508160741719, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=2412491849@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322594508236239193, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, authorId=1322594508160741719, language=EN, stringName=Jie HAN, firstName=Jie, middleName=null, lastName=HAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322594508320125274, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, authorId=1322594508160741719, language=CN, stringName=韩杰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=太原理工大学 矿业工程学院，山西　太原　030024, bio={"content":"

韩杰（1997—），男，山西晋城人，硕士，主要研究方向为煤泥浮选过程智能控制。E-mail:

"}, bioImg=null, bioContent=

韩杰（1997—），男，山西晋城人，硕士，主要研究方向为煤泥浮选过程智能控制。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322594508026523987, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, xref=null, ext=[AuthorCompanyExt(id=1322594508034912596, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China), AuthorCompanyExt(id=1322594508051689813, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学 矿业工程学院，山西　太原　030024)])]), Author(id=1322594508378845532, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wrf197010@126.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1322594508475314526, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, authorId=1322594508378845532, language=EN, stringName=Ranfeng WANG, firstName=Ranfeng, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322594508559200607, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, authorId=1322594508378845532, language=CN, stringName=王然风, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=太原理工大学 矿业工程学院，山西　太原　030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322594508026523987, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, xref=null, ext=[AuthorCompanyExt(id=1322594508034912596, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China), AuthorCompanyExt(id=1322594508051689813, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学 矿业工程学院，山西　太原　030024)])]), Author(id=1322594508638892385, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322594508743749987, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, authorId=1322594508638892385, language=EN, stringName=Xiang FU, firstName=Xiang, middleName=null, lastName=FU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322594508823441764, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, authorId=1322594508638892385, language=CN, stringName=付翔, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=太原理工大学 矿业工程学院，山西　太原　030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322594508026523987, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, xref=null, ext=[AuthorCompanyExt(id=1322594508034912596, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China), AuthorCompanyExt(id=1322594508051689813, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学 矿业工程学院，山西　太原　030024)])]), Author(id=1322594508886356326, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322594508957659496, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, authorId=1322594508886356326, language=EN, stringName=Jun WANG, firstName=Jun, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322594509028962665, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, authorId=1322594508886356326, language=CN, stringName=王珺, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=太原理工大学 矿业工程学院，山西　太原　030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322594508026523987, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, xref=null, ext=[AuthorCompanyExt(id=1322594508034912596, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China), AuthorCompanyExt(id=1322594508051689813, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学 矿业工程学院，山西　太原　030024)])]), Author(id=1322594509096071531, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322594509175763309, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, authorId=1322594509096071531, language=EN, stringName=Kai WEI, firstName=Kai, middleName=null, lastName=WEI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322594509234483566, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, authorId=1322594509096071531, language=CN, stringName=魏凯, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=太原理工大学 矿业工程学院，山西　太原　030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322594508026523987, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, xref=null, ext=[AuthorCompanyExt(id=1322594508034912596, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China), AuthorCompanyExt(id=1322594508051689813, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学 矿业工程学院，山西　太原　030024)])]), Author(id=1322594509314175344, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322594509381284210, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, authorId=1322594509314175344, language=EN, stringName=Qian ZHANG, firstName=Qian, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322594509465170291, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, authorId=1322594509314175344, language=CN, stringName=张茜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=I, address=太原理工大学 矿业工程学院，山西　太原　030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322594508026523987, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, xref=null, ext=[AuthorCompanyExt(id=1322594508034912596, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China), AuthorCompanyExt(id=1322594508051689813, tenantId=1146029695717560320, journalId=1225396423026438145, articleId=1322594504406839619, companyId=1322594508026523987, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学 矿业工程学院，山西　太原　030024)])])]
韩杰I , 王然风I , 付翔I, 王珺I, 魏凯I, 张茜I
作者信息
  • 太原理工大学 矿业工程学院，山西　太原　030024
通讯作者:
王然风（1970—），男，山西长治人，博士，教授，主要研究方向为煤矿智能化开采与分选。E-mail:
作者简介:

韩杰（1997—），男，山西晋城人，硕士，主要研究方向为煤泥浮选过程智能控制。E-mail:

Research on a Prediction Model of Ash in Flotation Tailings Based on LightGBM Optimized by Genetic Algorithm
Jie HANI , Ranfeng WANGI , Xiang FUI, Jun WANGI, Kai WEII, Qian ZHANGI
Affiliations
  • School of Mining Engineering, Taiyuan University of Technology, Taiyuan, Shanxi 030024, China
出版时间: 2025-01-25
文章导航
收藏切换
摘要
收起

为了提高煤泥浮选过程灰分在线检测的水平，研究了煤泥浮选过程中尾煤灰分的预测，并建立了基于遗传算法优化的LightGBM浮选尾煤灰分预测模型。通过采集的生产过程数据，包括矿浆流量、浓度、起泡剂量、捕收剂量和干煤泥量，构建了模型训练数据集，并对模型进行了测试验证。试验结果显示，该模型预测结果的平均绝对误差为0.72，比未优化的LightGBM模型提升了11.1%的预测精度，相较于其他模型，GA-LightGBM模型预测结果的平均绝对误差降低了15.8%，进一步证明了所建模型在尾煤灰分预测精度上的有效性，为实现智能化浮选提供了新的技术支持。

煤泥浮选  /  尾煤灰分  /  遗传算法  /  LightGBM  /  预测建模

In order to improve the level of on-line detection of ash in coal slime flotation process, the prediction of ash content of tailings in coal slime flotation process was studied, and the prediction model of ash content of flotation tailings based on LightGBM optimized by genetic algorithm was established. Through the collected production data, including slurry flow, concentration, foaming dose, collection dose and dry slime amount, the model training data set was constructed and the model was tested and verified. The experimental results show that the average absolute error of the prediction results of the model is 0.72, which is 11.1% higher than that of the unoptimized LightGBM model. Compared with other models, the average absolute error of the prediction results of the GA-LightGBM model is reduced by 15.8%, which further proves the validity of the model in the prediction accuracy of ash in coal tailings and provides a new technical support for the realization of intelligent flotation.

Coal slime flotation  /  Ash of coal tailings  /  Genetic algorithms  /  LightGBM  /  Predictive modeling
韩杰, 王然风, 付翔, 王珺, 魏凯, 张茜. 基于遗传算法优化的LightGBM浮选尾煤灰分预测模型研究. 矿业研究与开发, 2025 , 45 (1) : 269 -276 .
Jie HAN, Ranfeng WANG, Xiang FU, Jun WANG, Kai WEI, Qian ZHANG. Research on a Prediction Model of Ash in Flotation Tailings Based on LightGBM Optimized by Genetic Algorithm[J]. Mining Research and Development, 2025 , 45 (1) : 269 -276 .
正文
收起
0　引言
收起
近年来，智能化选煤[1]技术得到了大力发展，政府对其应用给予了极大的支持和重视。在选煤智能化体系建设中，煤泥浮选技术发挥着重要作用。而在这一体系中，尾煤灰分预测技术则显得至关重要，它是实现智能化浮选的关键环节之一。准确预测尾煤灰分能够帮助及时调整浮选系统的入料和药剂添加情况，从而确保产品质量的稳定，并实现降本增效的目标。
目前，尾煤灰分预测方法主要采用两种。一种是基于高精度设备的在线快速检测，例如，白飞燕等[2]提出了一种基于X射线衍射的煤炭灰分快速检测方法，大大提高了检测速度。程栋等[3]提出了基于双能γ射线的煤质灰分测量方法，利用γ射线源和探测器采集到的γ计数对煤质灰分进行预测。此外，ZHU等[4]则通过激光诱导击穿光谱法对煤灰进行元素分析，为煤灰检测提供了新的思路。然而，由于浮选工况环境的复杂性，这些检测设备的应用需要高水平的专业知识和技术支持。因此，目前现场灰分检测仍主要采用人工灼烧称重的方式。
另一种方法是基于机器学习的灰分软测量方法，学者们在这方面做了大量工作。例如，桂卫华等[5]通过浮选过程泡沫图像特征提取等手段，提出了基于机器视觉的灰分软测量方法。郭西进等[6]则通过多层神经网络对尾煤灰分图像进行特征提取，提出了基于深度卷积网络的煤泥浮选尾矿灰分预测方法。范富博等[7]结合浮选过程变量，利用改进的灰狼算法优化反向传播(Back Propagation, BP)的神经网络模型，并用于对浮选精煤灰分的预测。此外，周开军等[8]采用最小二乘支持向量机构建浮选灰分预测模型，用图像特征和灰分数据对模型进行训练。然而，这些预测模型的建立依赖于人工经验对超参数和神经网络结构的设定，使得参数调整工作尤为繁琐。有时候，这可能导致落入局部最优的调参范围，从而影响模型的预测精度。
目前，国内已有多位学者将遗传算法（Genetic Algorithm, GA)优化特性应用于提升各类机器学习的性能。例如，唐维等[9]结合遗传算法优化BP神经网络的权值和阈值，发现经GA优化的BP神经网络具有更快的速度和更高的精确度。胡一晨等[10]提出了一种基于遗传算法(GA)优化的径向基函数(RBF)神经网络模型方法，该方法能提高信道估计器的性能。王巍等[11]结合遗传算法的全局寻优特性，提出了一种GC-LSTM模型，并进行测试，测试结果表明，该方法在避免大量试验调参的同时具有较高的精度和准确率。
轻量梯度提升机[12]（Light Gradient Boosting Machine, LightGBM)是一款Boosting(增强学习）算法框架。作为梯度提升决策树（Gradient Boosting Decision Tree, GBDT[13]）的改进方法，LightGBM在工程实现上更快速、更高效。然而，由于其包含较多超参数，导致调参效率偏低且过于依赖人工经验。利用遗传算法的优势可以有效解决效率低、收敛慢以及陷入局部最优的问题，从而提高预测准确率。本研究提出了一种基于遗传算法优化的LightGBM灰分预测模型，命名为GA-LightGBM。该模型将LightGBM参数组的优化问题视为遗传算法的搜索目标，利用遗传算法对LightGBM进行调参优化，得到全局最优参数组合，从而提升浮选灰分预测模型的准确性。
1　基于GA优化的LightGBM模型
收起
1.1　LightGBM算法原理
LightGBM[14] 作为GBDT的一种工程实现，其基本训练过程与传统的GBDT相似。二者都是基于决策树的模型，通过组合多个决策树来进行预测。在给定训练集D={(x1,y1),(x2,y2),…,(xN,yN)}的情况下，GBDT 算法的一般流程可归纳为以下步骤。
（1）建立初始化提升树模型。
（2）对样本i(i=1,2,…,N)计算负梯度拟合残差，将所得到的残差作为样本新的真实值，并将数据(xi,rmi)(m=1,2,…,M)作为下一棵树的训练数据，得到一棵新的回归树fm(x)，其对应的叶子结点区域为Rmj(j=1,2,…,J)，其中J为回归树T的叶子结点的个数。再对叶子区域计算最优拟合值，并更新提升树模型，得到最终的梯度提升树。
1.2　LightGBM优化的特点
LightGBM分别基于直方图算法、单边梯度抽样、互斥特征捆绑算法以及按叶子节点(Leaf-Wise) 生长策略 4 个方法来对 GBDT 算法框架进行提升优化。
（1）直方图算法。为了减少特征分裂点数量和更加高效地寻找最优特征分裂点，LightGBM采用直方图算法[9]寻找最优特征分裂点。其主要思路是将连续的浮点特征值离散化为k个整数并构造一个宽度为k的直方图。对某个特征数据进行遍历的时候，将离散化的值用于索引作为直方图的累积统计量。遍历完一次后，直方图便可累积对应的统计量，然后根据该直方图寻找最优分裂点。直方图算法过程如图1所示。
（2）单边梯度抽样。单边梯度抽样(Gradient-Based One-Side Sampling, GOSS)算法是从减少样本的角度进行优化而设计的算法，是LightGBM的核心原理之一。单边梯度抽样算法的主要思路是从减少样本的角度出发，将训练过程中大部分权重较小的样本剔除，仅对剩余样本数据计算信息增益。
（3）互斥特征捆绑算法。互斥特征捆绑算法是针对特征的优化。互斥特征捆绑（Exclusive Feature Bundling, EFB)算法通过将两个互斥的特征捆绑为一个特征。在不丢失特征信息的前提下，减少特征数，从而加速模型训练。
（4）Leaf-Wise生长策略。LightGBM还提出了区别于按层生长的叶子结点生长方法，即带有深度限制的按叶子结点生长[15]的决策树生长方法。按层生长和按叶子结点生长的方法如图2 所示。
1.3　GA-LightGBM模型的构建
遗传算法[16]（Genetic Algorithm, GA）是一种启发式的基于生物进化原理的算法，该算法近似模拟生物界的自然选择和遗传，并通过目标函数来指定生物的生存环境。由于种群遗传过程中具有的随机性和目标函数的全局性等，使得其内部的每个个体之间存在竞争关系，并且由于环境适应性和计算方法等使得每个个体会朝着目标函数的方向去进行自身优化。同时，个体之间的基因交换行为和基因突变等方式，能避免种群陷入局部最优解。最后，每个个体之间的相互独立性，使得其开始的时候搜索范围大，收敛前搜索范围变小，这样的过程可以高效地确定全局最优解，从而获得最优的目标函数值。遗传算法的出现，使其迅速在各领域如目标优化、调度方案、模式识别、机器学习等得到广泛的应用，成为了一种鲁棒性强、效率高的优化方法。
基于遗传算法融合的LightGBM改进方案，实现步骤如下，流程如图3右侧所示。
步骤1：根据选定的编码方式，生成个体数量为Npop的初始种群[17]。
步骤2：计算种群中所有个体的适应度。
步骤3：利用锦标赛规则分k次选择出选手数量为p的个体择优，作为培育下一代的临时种群，即临时种群数量为k个个体(k>Npop)。
步骤4：在临时种群中相邻个体之间进行均匀交叉操作。
步骤5：在临时种群中每个个体内进行均匀整数突变。
步骤6：计算临时种群中所有个体的适应度。
步骤7：在保持个体数量Npop不变的情况下，保留适应度最好的个体作为下一次迭代的输入。
步骤8：若迭代次数小于Ngen，则返回步骤3；否则迭代结束，输出最优参数。
锦标赛规则就是模拟锦标赛的方式，首先在族群中随机抽取p个个体（一般取2），然后从中选取具有最佳适应度的个体，将此过程重复k次，获得育种族群。p越大，选择强度越高，选择之后留下的育种族群的平均适应度也就越高。均匀交叉是指设定一个交叉概率，两父代中的基因都以该概率交叉；均匀整数变异是指对序列中的每一位按概率变异，变异后的值为编码区间内按均匀分布随机选取的一个整数。
本文采用GA对LightGBM模型的参数进行优化，优化的流程主要分为LightGBM模型训练和GA迭代优化，最终将GA优化后的LightGBM模型与其他机器学习模型进行评价效果对比。模型优化流程图见图3。
2　试验与结果
收起
2.1　数据来源
本文以四川某选煤厂采集的生产数据作为研究对象，浮选工艺流程如图4所示。选取浮选过程中对灰分影响较明显的5个因素（见表1)作为预测模型的输入。通过矿浆流量、浓度、起泡剂量、捕收剂量、干煤泥量5个特征量来预测灰分，并对获取数据的均值、标准差、最大值、最小值、中位数等进行了统计计算。
2.2　数据预处理
（1）异常值处理。本文先后采用箱型图和3σ原则的方法对异常数据进行剔除。由于实时数据存在非生产过程和数据异常的情况，导致数据尺度变化较大，箱型图最大的优点就是不受尺度变化的影响，通过其判定异常值的标准可以实现非生产过程数据的去除。再结合3σ原则将异常极值去掉，得到最终使用的数据。
（2）数据分区。将数据划按4:1分成训练集和测试集。训练集用于训练灰分预测模型和进行交叉验证选择模型参数，测试集用于验证模型预测性能。
(3) 数据归一化。由于各个特征的尺度相差较大，为了消除数据尺度对于特征重要性的影响，采用最大最小值归一化方法[18]将所有特征缩放到(0,1)区间。
2.3　模型准确率评价指标
为了度量预测模型的误差，本研究采用平均绝对误差（MAE）、均方根误差（RMSE）、平均绝对百分比误差（MAPE）和决定系数（R2）作为评价指标[13]。
2.4　试验结果
遗传算法运行时选择的参数主要有种群数量、迭代次数、均匀交叉概率等[19]，具体参数见表2，种群规模一般为10~100，较大的种群规模并不能优化遗传算法的结果，反而会使模型运算时间成倍数规模增加，但如果种群规模过小又不能获取足够的采样点，根据模型运行情况，本文选取种群规模数量为10。交叉概率主要用于控制交叉操作[20]，通常取0.4~0.8。概率太大会使交叉操作过于频繁，种群更新速度变快，适应度高的个体会被破坏；概率太小则会使交叉操作频次过少，种群偏向于稳定，使得搜寻耗时很长，因此本模型中交叉概率取0.5。突变概率是丰富种群多样性的必要手段，取值通常为0.01~0.3。本研究为获取更多新的个体，经模型的实际验证，变异概率取0.3为优。迭代次数的设定是用来帮助终止遗传算法的，迭代次数较小时算法不易收敛，迭代过多会增加运算时间且后期无用的迭代会造成浪费[21]。本模型优化迭代次数为10，从图5可以看出，在迭代次数达6时最优个体适应度已不再变化。
表3为GA优化过程中LightGBM模型所用参数，其中共享参数是模型运行的基本参数，待优化参数为GA优化的目标参数。为了提高GA训练时LightGBM模型的收敛速度，本文对迭代次数和学习率进行了设定。LightGBM模型最终评估时，选取较高的迭代次数和较低的学习率来提高模型的收敛效果。
最终优化后得到的LightGBM模型参数num_leaves、max_depth和min_data_in_leaf分别为127、9和20。
3　模型对比结果分析
收起
为进一步研究所建立的GA-LightGBM灰分预测模型的预测能力，同样采用上述输入参数建立AdaBoost、BP神经网络、DT、ElasticNet、GBDT、LightGBM、SVR、XGBoost模型并进行训练，与GA优化后的LightGBM模型进行对比[22]。评价结果的对比见表4。
由表4中各项评价指标值可以看出，所提出的GA-LightGBM模型优于其他模型。通过对比GA-LightGBM和LightGBM模型，发现GA-LightGBM相较于未优化的LightGBM,MAE值平均降低了11.1%，这说明GA优化后的参数使得模型精确度更高。通过对比GA-LightGBM和GBDT系列模型，MAE值分别平均降低了15.8%（DT模型）、31.1%（GBDT模型）、20.8%（XGBoost模型），这说明遗传算法优化后的LightGBM模型比GBDT系列模型具有较大的性能优势。再对比GA-LightGBM与AdaBoost、BP神经网络、ElasticNet、SVR模型，MAE值分别平均降低了69.7%、63.5%、65.0%、65.5%，GA优化后的LightGBM展现出了更大的性能优势。
将GA优化后的LightGBM模型预测的灰分结果与真实灰分结果进行对比，如图6所示。
从图6可以看出，模型预测值的变化趋势基本与真实值保持一致，同时在与表4中其他模型中性能最好的LightGBM模型进行对比时，可以看出GA优化后的LightGBM模型在预测结果的稳定性和准确率上都略优于LightGBM模型，进一步证明了所建模型的准确性。
4　结论
收起
（1）本文基于LightGBM模型和遗传算法的优势，提出并设计了一种GA-LightGBM尾煤灰分预测模型，并详细介绍了模型的优势和建模流程，用实际生产中的过程数据完成了对模型的训练和验证。
（2）试验结果表明，GA-LightGBM模型预测结果的平均绝对误差为0.72。相比于未经GA优化的LightGBM模型，平均绝对误差降低了11.1%；GA优化后的LightGBM模型具有更高的精确度和稳定性。相较于其他模型，GA-LightGBM在多项模型评价指标上均展现出了一定优势。
（3）GA-LightGBM模型预测的灰分值与真实灰分值在变化趋势上基本保持一致，进一步证明了本模型的有效性，间接解决了传统检测方法无法在线精准检测的问题。
基金
收起
  • 国家自然科学基金项目(52274157)
  • 内蒙古自治区重点专项项目(2022EEDSKJXM010)
  • 山西省重点研发计划项目(202102100401015)
文献
收起
参考文献 引证文献
排序方式：
[1]
王然风，高建川，付翔. 智能化选煤厂架构及关键技术[J]. 工矿自动化，2019，45(7): 28-32.
WANG Ranfeng, GAO Jianchuan, FU Xiang. Framework and key technologies of intelligent coal preparation plant[J]. Industry and Mine Automation, 2019, 45(7):28-32.
[2]
白飞燕，樊民强，杨宏丽，等. 基于 X射线衍射的煤炭灰分快速检测方法研究[J]. 选煤技术，2023, 51(4): 26-32.
BAI Feiyan, FAN Minqiang, YANG Hongli, et al, Study of the X-ray diffraction-based coal ash rapid determination method[J]. Coal Preparation Technology, 2023, 51(4): 26-32.
[3]
程栋，温和，滕召胜，等. 基于双能γ射线的煤质灰分软测量技术研究[J]. 仪器仪表学报，2014, 35(10): 2263-2270.
CHENG Dong, WEN He, TENG Zhaosheng, et al. Study on soft-sensing of coal ash content based on dual-energy γ-ray[J]. Chinese Journal of Scientific Instrument, 2014, 35 (10): 2263-2270.
[4]
ZHU R S, LIU Y Z, ZHANG Q H, et al. Quantitative analysis of Fe and detection of multiple elements in the coal ash by laser-induced breakdown spectroscopy[J].Optik, 2018, 169:77-84.
[5]
桂卫华，阳春华，徐德刚，等. 基于机器视觉的矿物浮选过程监控技术研究进展[J]. 自动化学报，2013, 39(11): 1879-1888.
GUI Weihua, YANG Chunhua, XU Degang, et al. Machine-vision-based online measuring and controlling technologies for mineral flotation: a review[J]. Acta Automatic Sinaca, 2013, 39(11): 1879-1888.
[6]
郭西进，魏凌敖，杨春宝. 基于深度卷积网络的煤泥浮选尾矿灰分检测方法研究[J]. 煤炭技术，2020，39(2): 144-146.
GUO Xijin, WEI Ling'ao, YANG Chunbao. Research on ash detection method of coal slime flotation tailings on convolutional neural network[J]. Coal Technology, 2020, 39 (2):144-146.
[7]
范富博，王然风，付翔. 基于多源异构信息融合的浮选精煤灰分在线检测技术研究与应用[J]. 煤炭技术，2023，42（2）：233-238.
FAN Fubo, WANG Ranfeng, FU Xiang. Research and application of on-line detection technology of flotation cleaned coal ash based on multi-source heterogeneous information fusion [J]. Coal Technology, 2023, 42 (2): 233-238.
[8]
周开军，阳春华，牟学民，等. 基于泡沫特征与 LS-SVM的浮选回收率预测[J]. 仪器仪表学报，2009, 30(6): 1295-1300.
ZHOU Kaijun, YANG Chunhua, MOU Xuemin, et al. Flotation recovery prediction based on froth features and LS-SVM[J]. Chinese Journal of Scientific Instrument, 2009, 30 (6):1295-1300.
[9]
唐维，陶钰欣，郝启文，等. 基于遗传算法优化BP神经网络的曝气量预测[J]. 控制工程，2024(10): 1746-1752.
TANG Wei, TAO Yuxin, HAO Qiwen, et al. Prediction of aeration quantity based on bp neural network optimized by genetic algorithm [J]. Control Engineering of China, 2024 (10):1746-1752.
[10]
胡一晨，耿虎军. 基于改进遗传算法优化的 RBF 网络的信道估计[J].计算机测量与控制，2024, 32(1): 165-171+178.
HU Yichen, GENG Hujun. Channel estimation of RBF networks based on improved genetic algorithm optimization [J]. Computer Measurement & Control, 2024, 32(1): 165-171+178.
[11]
王巍，丁辉，夏旭，等. 基于遗传算法优化C-LSTM模型的心律失常分类方法[J]. 中国医学物理学杂志，2024，41（2）：233-240.
WANG Wei, DING Hui, XIA Xu, et al. Arrhythmia classification method based on genetic algorithm optimization of C-LSTM model [J]. Chinese Journal of Medical Physics, 2024, 41(2):233-240.
[12]
张月飞，王伟，代伟. 重介分选过程产品指标在线预测方法研究[J]. 煤炭工程，2021，53(增刊1): 108-111.
ZHANG Yuefei, WANG Wei, DAI Wei. On-line prediction of product indicators in dense medium coal separation[J]. Coal Engineering, 2021, 53(Suppl.1): 108-111.
[13]
王阳春，茆梦凡，龙关旭，等. 基于GBDT的锈蚀钢筋混凝土梁抗弯承载力预测研究[J]. 公路，2023, 68(12): 309-314.
WANG Yangchun, MAO Mengfan, LONG Guanxu, et al. Research on prediction of flexural capacity of corroded reinforced concrete beams based on GBDT[J]. Highway, 2023, 68(12):309-314.
[14]
汪明元，王振红，陈松庭. 基于LightGBM算法的海洋土压缩参数预测模型[J]. 浙江工业大学学报，2024, 52(1): 17-24.
WANG Mingyuan, WANG Zhenhong, CHEN Songting. Prediction of marine soil compressibility based on LightGBM algorithm[J]. Journal of Zhejiang University of Technology, 2024, 52(1):17-24.
[15]
HAO X C, ZHANG Z P, XU Q Q, et al. Prediction of f-CaO content in cement clinker: a novel prediction method based on LightGBM and Bayesian optimization[J]. Chemometrics and Intelligent Laboratory Systems, 2022, 220:104461.
[16]
王志彪，赵丽华. 遗传算法与粒子群优化的Elman神经网络模型预测黄土滑坡变形[J]. 大地测量与地球动力学，2023, 43(7):679-684.
WANG Zhibiao, ZHAO Lihua. Prediction of loess landslides deformation using elman neural network model based on genetic algorithm and particle swarm optimization[J]. Journal of Geodesy and Geodynamics, 2023, 43(7):679-684.
[17]
高明亮，邵俊捷，常振臣，等. 基于遗传算法–BP神经网络的动车组列车轮对磨耗模型[J]. 城市轨道交通研究，2022, 25(6):65-69.
GAO Mingliang, SHAO Junjie, CHANG Zhenchen, et al. EMU train wheelset wear model based on genetic algorithm-BP neural network[J]. Urban Rail Transit Research, 2022, 25(6):65-69.
[18]
ZHANG H, TANG Z H, XIE Y F, et al. Grade prediction of zinc tailings using an encoder-decoder model in froth flotation[J]. Minerals Engineering, 2021, 172:107173.
[19]
TONGCHIM S, CHONGSTITVATANA P. Parallel genetic algorithm with parameter adaptation[J]. Information Processing Letters, 2002, 82(1):47-54.
[20]
陈奂良，李常锁，高帅，等. 基于遗传算法优化BP神经网络的岩溶泉水位预测研究[J]. 水资源与水工程学报，2022，33(4): 50-57+63.
CHEN Huanliang，LI Changsuo，GAO Shuai，et al. Research on karst spring water level prediction based on genetic algorithm optimization BP neural network [J]. Journal of Water Resources and Water Engineering, 2022, 33(4):50-57+63.
[21]
邱钱粮，白向飞. 基于遗传算法优化的BP神经网络气化用煤灰流动温度预测模型[J]. 煤炭转化，2023, 46(2): 109-118.
QIU Qianliang，BAI Xiangfei. Prediction model of fusion temperature of coal ash for gasification based on GA-BP neural network[J]. Coal Conversion, 2023, 46(2): 109-118.
[22]
TIAN C, TANG Z H, XIE Y F, et al. Towards tailing grade prediction in zinc flotation via variablewise and temporalwise attention[J]. Minerals Engineering, 2023, 192: 108000.
2025年第45卷第1期
PDF下载
30
16
引用本文
BibTeX
文章信息
  • 接收时间：2024-03-12
  • 首发时间：2026-10-29
  • 出版时间：2025-01-25
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期：2024-03-12
基金
国家自然科学基金项目(52274157)
内蒙古自治区重点专项项目(2022EEDSKJXM010)
山西省重点研发计划项目(202102100401015)
作者信息
    太原理工大学 矿业工程学院，山西　太原　030024

通讯作者:

王然风（1970—），男，山西长治人，博士，教授，主要研究方向为煤矿智能化开采与分选。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kyyjykf/CN/1322594504406839619
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数
科
Family		 属数
Number of
genus		 种数
Number of
species		 占总种数比例
Percentage of
total species (%)		 属
Genus		 种数
Number of
species		 占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
相关链接
论文
最新文章
热读文章
热点专题
内参
蓝皮书
产业发展报告
传播力报告
期刊分级目录
资讯
学术新闻
行业新闻
学术会议
行业会议
关于
关于我们
联系我们
北京市海淀区学院南路86号
100081
010-62662699（运营及技术支持）
qkjq@cast.org.cn

中国科学技术协会版权所有 京ICP 备10216604号-4 海淀分局备案 1101084647
科技导报社主办 中国科协信息中心技术支持