Article(id=1147999684720844851, tenantId=1146029695717560320, journalId=1146123346816638986, issueId=1147999683156370319, articleNumber=1000-8063(2025)01-0009-09, orderNo=null, doi=10.13426/j.cnki.yky.2024.10.12, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1730131200000, receivedDateStr=2024-10-29, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1751634053639, onlineDateStr=2025-07-04, pubDate=1739980800000, pubDateStr=2025-02-20, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1751634053639, onlineIssueDateStr=2025-07-04, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1751634053639, creator=13701087609, updateTime=1751634053639, updator=13701087609, issue=Issue{id=1147999683156370319, tenantId=1146029695717560320, journalId=1146123346816638986, year='2025', volume='44', issue='1', pageStart='1', pageEnd='150', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1751634053267, creator=13701087609, updateTime=1759123824852, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1179414062141158321, tenantId=1146029695717560320, journalId=1146123346816638986, issueId=1147999683156370319, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1179414062141158322, tenantId=1146029695717560320, journalId=1146123346816638986, issueId=1147999683156370319, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=9, endPage=17, ext={EN=ArticleExt(id=1147999684989280343, articleId=1147999684720844851, tenantId=1146029695717560320, journalId=1146123346816638986, language=EN, title=Injection Volume Prediction for In-situ Leaching of Uranium Based on Depthwise Separable Convolution Mixer Network Model, columnId=1175805041752556213, journalTitle=Uranium Mining and Metallurgy, columnName=MINING AND HYDROMETALLURGY, runingTitle=null, highlight=null, articleAbstract=

In-situ leaching of uranium, as a green uranium mining technology, generates massive data in production operation, which are available for the big data analysis and trend prediction to improve the reliability of technicians in making production plans. In the current prediction algorithms, the attention mechanism in the temporal prediction model based on the encoder-decoder structure has the problems of computational complexity and high memory consumption. In this paper, we proposed a depthwise separable convolutional model, in which the semantic damage caused by fixed segmentation was reduced by the dynamic sequence segmentation module, and the depthwise separable convolutional mixer module was used to reduce the model running time and capture local features as well as global features. The results show that the Mean Square Error (MSE) and Mean Absolute Error (MAE) of the depthwise separable convolutional hybrid network model are reduced by 1.04% and 4.13% respectively, compared with Patch Time Series Transformer (PatchTST), and the proposed dynamic sequence segmentation module MSE and MAE are reduced by 7.32% and 5.03% respectively, compared to the original model; in the comparative performance analysis, the training speed of this model is 59.91% faster than the Trend Seasonal Decomposition Linear (Decomposition Linear, DLinear) model. The depthwise separable convolutional model can accurately predict the future trend of sulfuric acid injection volume in the production operation of the mining area, improve the existing prediction model for in-situ leaching data by solving the problem of long running time, large running memory, poor data fitting problems, which provide a theoretical and practical reference for the decision-making of in-situ leaching production.

, correspAuthors=null, 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, authorCompany=null, fund=null, authors=null, authorsList=Zhifeng LIU, Junxian TANG, Zhining LIN, Yipeng ZHOU), CN=ArticleExt(id=1147999687824630095, articleId=1147999684720844851, tenantId=1146029695717560320, journalId=1146123346816638986, language=CN, title=基于深度可分离卷积混合网络模型的地浸采铀注液量预测研究, columnId=1175805041991631542, journalTitle=铀矿冶, columnName=开采·选冶, runingTitle=null, highlight=null, articleAbstract=地浸采铀作为铀矿的绿色开采技术,在生产运行中产生海量数据,利用这些海量数据进行大数据分析和趋势预测,能够提升技术人员制定生产计划的可靠性。目前采用的基于编码器-解码器结构的时序预测模型,由于存在注意力机制,导致计算复杂、内存消耗大。本研究提出深度可分离卷积混合模型,通过动态序列分割模块降低固定分割带来的语义破坏,通过深度可分离卷积混合模块降低模型运行时间并捕获局部和全局特征。结果表明,深度可分离卷积混合网络模型的均方误差(Mean Square Error,MSE)与平均绝对误差(Mean Absolute Error,MAE)相较于时间序列分块自注意力模型(Patch Time Series Transformer,PatchTST)分别降低了1.04%和4.13%,提出的动态序列分割模块的MSE与MAE相较于原有模型分别降低了7.32%和5.03%;在性能对比分析上,深度可分离卷积混合模型的训练速度相较于趋势季节分解线性模型(Decomposition Linear,DLinear)提高了59.91%。建立的模型能够准确预测采区生产运行中硫酸注液量的变化趋势,改善了现有预测模型针对地浸铀矿数据集存在的运行时间长、运行内存大、数据拟合差的问题,可为地浸铀矿生产决策提供理论和实践参考。, correspAuthors=null, authorNote=null, correspAuthorsNote=
刘志锋(1979—),男,内蒙古赤峰人,博士,副教授,主要研究方向为大数据分析与可视化。
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=40r3QKNBShCIjGszVK7sBA==, magXml=ye/nXrcr1ubWJXn+1ooWAw==, pdfUrl=null, pdf=jABSUiDNhDqP+80GzL458Q==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=+DDex9A9fhQfrb0hNHMVgQ==, mapNumber=null, authorCompany=null, fund=null, authors=

刘志锋(1979—),男,内蒙古赤峰人,博士,副教授,主要研究方向为大数据分析与可视化。

, authorsList=刘志锋, 唐俊贤, 林芝宁, 周义朋)}, authors=[Author(id=1179340466848940980, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, orderNo=0, 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=1179340466953798584, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, authorId=1179340466848940980, language=EN, stringName=Zhifeng LIU, firstName=Zhifeng, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, 3, address=1 State Key Laboratory of Nuclear Resources and Environment, East China University of Technology, Nanchang 330013, China
2 National Key Laboratory of Uranium Resources Exploration-Minning and Nuclear Remote Sensing, Nanchang 330013, China
3 East China University of Technology, Nanchang 330013, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1179340467037684665, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, authorId=1179340466848940980, language=CN, stringName=刘志锋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, 3, address=1 东华理工大学 核资源与环境国家重点实验室, 江西 南昌 330013
2 铀资源探采与核遥感全国重点实验室, 江西 南昌 330013
3 东华理工大学, 江西 南昌 330013, bio={"content":"

刘志锋(1979—),男,内蒙古赤峰人,博士,副教授,主要研究方向为大数据分析与可视化。

"}, bioImg=null, bioContent=

刘志锋(1979—),男,内蒙古赤峰人,博士,副教授,主要研究方向为大数据分析与可视化。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1179340466601477034, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, xref=1, ext=[AuthorCompanyExt(id=1179340466618254251, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466601477034, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 State Key Laboratory of Nuclear Resources and Environment, East China University of Technology, Nanchang 330013, China), AuthorCompanyExt(id=1179340466626642860, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466601477034, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 东华理工大学 核资源与环境国家重点实验室, 江西 南昌 330013)]), AuthorCompany(id=1179340466689557421, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, xref=2, ext=[AuthorCompanyExt(id=1179340466697946030, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466689557421, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 National Key Laboratory of Uranium Resources Exploration-Minning and Nuclear Remote Sensing, Nanchang 330013, China), AuthorCompanyExt(id=1179340466702140335, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466689557421, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 铀资源探采与核遥感全国重点实验室, 江西 南昌 330013)]), AuthorCompany(id=1179340466756666288, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, xref=3, ext=[AuthorCompanyExt(id=1179340466765054897, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466756666288, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 East China University of Technology, Nanchang 330013, China), AuthorCompanyExt(id=1179340466773443506, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466756666288, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 东华理工大学, 江西 南昌 330013)])]), Author(id=1179340467113182139, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, orderNo=1, 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=1179340467188679614, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, authorId=1179340467113182139, language=EN, stringName=Junxian TANG, firstName=Junxian, middleName=null, lastName=TANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 3, address=1 State Key Laboratory of Nuclear Resources and Environment, East China University of Technology, Nanchang 330013, China
3 East China University of Technology, Nanchang 330013, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1179340467247399871, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, authorId=1179340467113182139, language=CN, stringName=唐俊贤, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 3, address=1 东华理工大学 核资源与环境国家重点实验室, 江西 南昌 330013
3 东华理工大学, 江西 南昌 330013, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1179340466601477034, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, xref=1, ext=[AuthorCompanyExt(id=1179340466618254251, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466601477034, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 State Key Laboratory of Nuclear Resources and Environment, East China University of Technology, Nanchang 330013, China), AuthorCompanyExt(id=1179340466626642860, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466601477034, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 东华理工大学 核资源与环境国家重点实验室, 江西 南昌 330013)]), AuthorCompany(id=1179340466756666288, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, xref=3, ext=[AuthorCompanyExt(id=1179340466765054897, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466756666288, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 East China University of Technology, Nanchang 330013, China), AuthorCompanyExt(id=1179340466773443506, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466756666288, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 东华理工大学, 江西 南昌 330013)])]), Author(id=1179340467314508737, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, 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=1179340467385811908, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, authorId=1179340467314508737, language=EN, stringName=Zhining LIN, firstName=Zhining, middleName=null, lastName=LIN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 3, address=1 State Key Laboratory of Nuclear Resources and Environment, East China University of Technology, Nanchang 330013, China
3 East China University of Technology, Nanchang 330013, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1179340467461309381, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, authorId=1179340467314508737, language=CN, stringName=林芝宁, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 3, address=1 东华理工大学 核资源与环境国家重点实验室, 江西 南昌 330013
3 东华理工大学, 江西 南昌 330013, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1179340466601477034, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, xref=1, ext=[AuthorCompanyExt(id=1179340466618254251, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466601477034, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 State Key Laboratory of Nuclear Resources and Environment, East China University of Technology, Nanchang 330013, China), AuthorCompanyExt(id=1179340466626642860, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466601477034, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 东华理工大学 核资源与环境国家重点实验室, 江西 南昌 330013)]), AuthorCompany(id=1179340466756666288, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, xref=3, ext=[AuthorCompanyExt(id=1179340466765054897, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466756666288, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 East China University of Technology, Nanchang 330013, China), AuthorCompanyExt(id=1179340466773443506, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466756666288, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 东华理工大学, 江西 南昌 330013)])]), Author(id=1179340467536806855, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, 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=1179340467633275851, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, authorId=1179340467536806855, language=EN, stringName=Yipeng ZHOU, firstName=Yipeng, middleName=null, lastName=ZHOU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, 3, address=1 State Key Laboratory of Nuclear Resources and Environment, East China University of Technology, Nanchang 330013, China
2 National Key Laboratory of Uranium Resources Exploration-Minning and Nuclear Remote Sensing, Nanchang 330013, China
3 East China University of Technology, Nanchang 330013, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1179340467717161932, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, authorId=1179340467536806855, language=CN, stringName=周义朋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, 3, address=1 东华理工大学 核资源与环境国家重点实验室, 江西 南昌 330013
2 铀资源探采与核遥感全国重点实验室, 江西 南昌 330013
3 东华理工大学, 江西 南昌 330013, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1179340466601477034, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, xref=1, ext=[AuthorCompanyExt(id=1179340466618254251, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466601477034, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 State Key Laboratory of Nuclear Resources and Environment, East China University of Technology, Nanchang 330013, China), AuthorCompanyExt(id=1179340466626642860, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466601477034, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 东华理工大学 核资源与环境国家重点实验室, 江西 南昌 330013)]), AuthorCompany(id=1179340466689557421, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, xref=2, ext=[AuthorCompanyExt(id=1179340466697946030, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466689557421, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 National Key Laboratory of Uranium Resources Exploration-Minning and Nuclear Remote Sensing, Nanchang 330013, China), AuthorCompanyExt(id=1179340466702140335, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466689557421, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 铀资源探采与核遥感全国重点实验室, 江西 南昌 330013)]), AuthorCompany(id=1179340466756666288, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, xref=3, ext=[AuthorCompanyExt(id=1179340466765054897, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466756666288, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 East China University of Technology, Nanchang 330013, China), AuthorCompanyExt(id=1179340466773443506, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466756666288, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 东华理工大学, 江西 南昌 330013)])])], keywords=[Keyword(id=1179340467847185357, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, language=EN, orderNo=1, keyword=in-situ leaching of uranium), Keyword(id=1179340467905905614, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, language=EN, orderNo=2, keyword=injection volume prediction), Keyword(id=1179340467973014479, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, language=EN, orderNo=3, keyword=depthwise separable convolution), Keyword(id=1179340468035929040, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, language=EN, orderNo=4, keyword=prediction model), Keyword(id=1179340468103037905, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, language=CN, orderNo=1, keyword=地浸采铀), Keyword(id=1179340468161758162, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, language=CN, orderNo=2, keyword=注液量预测), Keyword(id=1179340468212089811, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, language=CN, orderNo=3, keyword=深度可分离卷积), Keyword(id=1179340468295975892, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, language=CN, orderNo=4, keyword=预测模型)], refs=[Reference(id=1179340470057583592, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=2022, volume=31, issue=12, pageStart=64, pageEnd=69, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=阳奕汉, 苏学斌, 陈梅芳, journalName=中国矿业, refType=null, unstructuredReference=阳奕汉, 苏学斌, 陈梅芳, 等. “数字建井”在砂岩型铀矿地浸开发中的探索与应用[J]. 中国矿业, 2022, 31(12):64-69., articleTitle=“数字建井”在砂岩型铀矿地浸开发中的探索与应用, refAbstract=null), Reference(id=1179340470124692457, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=2022, volume=31, issue=12, pageStart=64, pageEnd=69, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=YANG Yihan, SU Xuebin, CHEN Meifang, journalName=China Mining Magazine, refType=null, unstructuredReference=YANG Yihan, SU Xuebin, CHEN Meifang, et al. Exploration and application of "digital well construction" in in-situ leaching of sandstone uranium deposit[J]. China Mining Magazine, 2022, 31(12):64-69 (in Chinese)., articleTitle=Exploration and application of "digital well construction" in in-situ leaching of sandstone uranium deposit, refAbstract=null), Reference(id=1179340470191801322, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=2021, volume=38, issue=3, pageStart=287, pageEnd=294, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=张明林, 刘洋, 吴建勇, journalName=世界核地质科学, refType=null, unstructuredReference=张明林, 刘洋, 吴建勇, 等. 中国铀矿地质勘查信息化建设现状及“十四五”发展思路[J]. 世界核地质科学, 2021, 38(3):287-294., articleTitle=中国铀矿地质勘查信息化建设现状及“十四五”发展思路, refAbstract=null), Reference(id=1179340470263104491, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=2021, volume=38, issue=3, pageStart=287, pageEnd=294, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=ZHANG Minglin, LIU Yang, WU Jianyong, journalName=World Nuclear Geoscience, refType=null, unstructuredReference=ZHANG Minglin, LIU Yang, WU Jianyong, et al. Construction situation of uranium exploration informatization and development idea for the 14th Five-Year Plan in China[J]. World Nuclear Geoscience, 2021, 38(3):287-294 (in Chinese)., articleTitle=Construction situation of uranium exploration informatization and development idea for the 14th Five-Year Plan in China, refAbstract=null), Reference(id=1179340470401516524, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=2024, volume=694, issue=6, pageStart=82, pageEnd=84, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=毛鑫磊, journalName=化工管理, refType=null, unstructuredReference=毛鑫磊. 信息化技术在内蒙古某地浸采铀矿山中的应用[J]. 化工管理, 2024, 694(6):82-84., articleTitle=信息化技术在内蒙古某地浸采铀矿山中的应用, refAbstract=null), Reference(id=1179340470464431085, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=2024, volume=694, issue=6, pageStart=82, pageEnd=84, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=MAO Xinlei, journalName=Chemical Enginering Management, refType=null, unstructuredReference=MAO Xinlei. Application of information technology in a in-situ leaching of uranium mine in Inner Mongolia[J]. Chemical Enginering Management, 2024, 694(6):82-84 (in Chinese)., articleTitle=Application of information technology in a in-situ leaching of uranium mine in Inner Mongolia, refAbstract=null), Reference(id=1179340470531539950, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=11, pageStart=85, pageEnd=95, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=袁志华, 孙占学, 周义朋, journalName=有色金属(冶炼部分), refType=null, unstructuredReference=袁志华, 孙占学, 周义朋, 等. 绿色铀矿山研究进展[J]. 有色金属(冶炼部分), 2021(11):85-95., articleTitle=绿色铀矿山研究进展, refAbstract=null), Reference(id=1179340470590260207, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=11, pageStart=85, pageEnd=95, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=YUAN Zhihua, SUN Zhanxue, ZHOU Yipeng, journalName=Nonferrous Metals(Extractive Metallurgy), refType=null, unstructuredReference=YUAN Zhihua, SUN Zhanxue, ZHOU Yipeng, et al. Research progress of green uranium mines[J]. Nonferrous Metals(Extractive Metallurgy), 2021(11):85-95 (in Chinese)., articleTitle=Research progress of green uranium mines, refAbstract=null), Reference(id=1179340470657369072, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=王亮, 王海峰, 霍建党, journalName=中国核学会.中国核科学技术进展报告(第三卷)——中国核学会2013年学术年会论文集, refType=null, unstructuredReference=王亮, 王海峰, 霍建党, 等. 纳岭沟矿床地浸采铀现场试验浸出液铀浓度变化研究[C]// 中国核学会.中国核科学技术进展报告(第三卷)——中国核学会2013年学术年会论文集:第2册. 北京: 核工业北京化工冶金研究院,2013:7., articleTitle=纳岭沟矿床地浸采铀现场试验浸出液铀浓度变化研究, refAbstract=null), Reference(id=1179340470720283633, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=2023, volume=13, issue=19, pageStart=10958, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=9, authorNames=KUCHIN Y, MUKHAMEDIEV R, YUNICHEVA N, journalName=Applied Sciences, refType=null, unstructuredReference=KUCHIN Y, MUKHAMEDIEV R, YUNICHEVA N, et al. Application of machine learning methods to assess filtration properties of host rocks of uranium deposits in Kazakhstan[J]. Applied Sciences, 2023, 13(19):10958., articleTitle=Application of machine learning methods to assess filtration properties of host rocks of uranium deposits in Kazakhstan, refAbstract=null), Reference(id=1179340470783198194, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=2023, volume=42, issue=3, pageStart=10, pageEnd=16, url=null, language=null, rfNumber=[7], rfOrder=10, authorNames=贾皓, 廖文胜, 杜志明, journalName=铀矿冶, refType=null, unstructuredReference=贾皓, 廖文胜, 杜志明, 等. 基于人工智能算法的地浸采区产量预测[J]. 铀矿冶, 2023, 42(3):10-16., articleTitle=基于人工智能算法的地浸采区产量预测, refAbstract=null), Reference(id=1179340470841918451, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=2023, volume=42, issue=3, pageStart=10, pageEnd=16, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=JIA Hao, LIAO Wensheng, DU Zhiming, journalName=Uranium Mining and Metallurgy, refType=null, unstructuredReference=JIA Hao, LIAO Wensheng, DU Zhiming, et al. Production prediction of in-situ leaching mining area based on artificial intelligence algorithm[J]. Uranium Mining and Metallurgy, 2023, 42(3):10-16 (in Chinese)., articleTitle=Production prediction of in-situ leaching mining area based on artificial intelligence algorithm, refAbstract=null), Reference(id=1179340470904833012, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=2, pageStart=92, pageEnd=98, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=余东原, 罗跃, 梁大业, journalName=有色金属(冶炼部分), refType=null, unstructuredReference=余东原, 罗跃, 梁大业, 等. 基于机器学习方法预测地浸过程中铀浸出金属量的变化[J]. 有色金属(冶炼部分), 2024(2):92-98., articleTitle=基于机器学习方法预测地浸过程中铀浸出金属量的变化, refAbstract=null), Reference(id=1179340470984524789, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=2, pageEnd=98, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=YU Dongyuan, LUO Yue, LIANG Daye, journalName=Nonferrous Metals (Extractive Metallurgy), refType=null, unstructuredReference=YU Dongyuan, LUO Yue, LIANG Daye, et al. Pred-icting the variation of uranium leaching metal content in ground-leaching process based on machine learning methods[J]. Nonferrous Metals (Extractive Metallurgy), 2024(2):92-98 (in Chinese)., articleTitle=Pred-icting the variation of uranium leaching metal content in ground-leaching process based on machine learning methods, refAbstract=null), Reference(id=1179340471064216566, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=2024, volume=40, issue=3, pageStart=578, pageEnd=586, url=null, language=null, rfNumber=[9], rfOrder=14, authorNames=贾明滔, 谭笑, 苏学斌, journalName=铀矿地质, refType=null, unstructuredReference=贾明滔, 谭笑, 苏学斌, 等. 基于卷积和长短期记忆网络的地浸开采铀浓度预测研究[J]. 铀矿地质, 2024, 40(3):578-586., articleTitle=基于卷积和长短期记忆网络的地浸开采铀浓度预测研究, refAbstract=null), Reference(id=1179340471139714039, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=2024, volume=40, issue=3, pageStart=578, pageEnd=586, url=null, language=null, rfNumber=[9], rfOrder=15, authorNames=JIA Mingtao, TAN Xiao, SU Xuebin, journalName=Uranium Geology, refType=null, unstructuredReference=JIA Mingtao, TAN Xiao, SU Xuebin, et al. Uranium concentration prediction for in-situ leaching based on convolution and long short-term memory networks[J]. Uranium Geology, 2024, 40(3):578-586 (in Chinese)., articleTitle=Uranium concentration prediction for in-situ leaching based on convolution and long short-term memory networks, refAbstract=null), Reference(id=1179340471223600120, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=1, pageEnd=7, url=https://doi.org/10.13426/j.cnki.yky.2024.06.05, language=null, rfNumber=[10], rfOrder=16, authorNames=张宇, 马亮, 李召坤, journalName=铀矿冶, refType=null, unstructuredReference=张宇, 马亮, 李召坤, 等. 基于多目标优化算法的“水平井-直井”系统流量决策方法[J/OL]. 铀矿冶, 2024:1-7[2024-11-03]. https://doi.org/10.13426/j.cnki.yky.2024.06.05., articleTitle=基于多目标优化算法的“水平井-直井”系统流量决策方法, refAbstract=null), Reference(id=1179340471324263417, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=1, pageEnd=7, url=null, language=null, rfNumber=[10], rfOrder=17, authorNames=ZHANG Yu, MA Liang, LI Zhaokun, journalName=Uranium Mining and Metallurgy, refType=null, unstructuredReference=ZHANG Yu, MA Liang, LI Zhaokun, et al. Flow decision-making method for the "horizontal well-vertical well" system based on multi-objective optimization algorithm[J/OL]. Uranium Mining and Metallurgy, 2024:1-7[2024-11-03], articleTitle=Flow decision-making method for the "horizontal well-vertical well" system based on multi-objective optimization algorithm, refAbstract=null), Reference(id=1179340471399760890, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=2024, volume=40, issue=2, pageStart=336, pageEnd=345, url=null, language=null, rfNumber=[11], rfOrder=18, authorNames=周渊凯, 刘祜, journalName=铀矿地质, refType=null, unstructuredReference=周渊凯, 刘祜. 基于深度学习方法的测井岩性识别研究[J]. 铀矿地质, 2024, 40(2):336-345., articleTitle=基于深度学习方法的测井岩性识别研究, refAbstract=null), Reference(id=1179340471529784315, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=2024, volume=40, issue=2, pageStart=336, pageEnd=345, url=null, language=null, rfNumber=[11], rfOrder=19, authorNames=ZHOU Yuankai, LIU Hu, journalName=Uranium Geology, refType=null, unstructuredReference=ZHOU Yuankai, LIU Hu. Deep learning based lithology recognition of well logging data[J]. Uranium Geology, 2024, 40(2):336-345 (in Chinese)., articleTitle=Deep learning based lithology recognition of well logging data, refAbstract=null), Reference(id=1179340471580115964, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://doi.org/10.48550/arXiv.1607.08022, language=null, rfNumber=[12], rfOrder=20, authorNames=ULYANOV D, VEDALDI A, LEMPITSKY V, journalName=null, refType=null, unstructuredReference=ULYANOV D, VEDALDI A, LEMPITSKY V. Instance normalization:The missing ingredient for fast stylization[EB/OL]. (2016-07-27). https://doi.org/10.48550/arXiv.1607.08022., articleTitle=Instance normalization:The missing ingredient for fast stylization, refAbstract=null), Reference(id=1179340471655613437, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=21, authorNames=KIM T, KIM J, TAE Y, journalName=Kigali, refType=null, unstructuredReference=KIM T, KIM J, TAE Y, et al. Reversible instance normalization for accurate time-series forecasting against distribution shift[C]. Kigali: International Conference on Learning Representations (ICLR), 2022., articleTitle=Reversible instance normalization for accurate time-series forecasting against distribution shift, refAbstract=null), Reference(id=1179340471726916606, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=22, authorNames=NIE Y Q, NGUYEN N H, SINTHONG P, journalName=Kigali, refType=null, unstructuredReference=NIE Y Q, NGUYEN N H, SINTHONG P, et al. A time series is worth 64 words:Long-term forecasting with transformers[C]. Kigali: International Conference on Learning Representations (ICLR), 2023., articleTitle=A time series is worth 64 words:Long-term forecasting with transformers, refAbstract=null), Reference(id=1179340471798219775, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=764, pageEnd=773, url=null, language=null, rfNumber=[15], rfOrder=23, authorNames=DAI J F, QI H Z, XIONG Y W, journalName=Venice, refType=null, unstructuredReference=DAI J F, QI H Z, XIONG Y W, et al. Deformable convolutional networks[C]. Venice: 2017 Institute of Electrical and Electronics Engineers (IEEE) International Conferenceon Computer Vision,2017:764-773., articleTitle=Deformable convolutional networks, refAbstract=null), Reference(id=1179340471869522944, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=2899, pageEnd=2907, url=null, language=null, rfNumber=[16], rfOrder=24, authorNames=CHEN Z Y, ZHU Y S, ZHAO C Y, journalName=Beijing, refType=null, unstructuredReference=CHEN Z Y, ZHU Y S, ZHAO C Y, et al. DPT:Deformable patch-based transformer for visual recognition[C]. Beijing: Association for Computing Machinery,2021:2899-2907., articleTitle=DPT:Deformable patch-based transformer for visual recognition, refAbstract=null), Reference(id=1179340471945019392, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=2024, volume=46, issue=5, pageStart=3123, pageEnd=3136, url=null, language=null, rfNumber=[17], rfOrder=25, authorNames=WANG W X, CHEN W, QIU Q B, journalName=Institute of Electrical and Electronics Engineers (IEEE) Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=WANG W X, CHEN W, QIU Q B, et al. Crossformer++:A versatile vision transformer hinging on cross-scale attention[J]. Institute of Electrical and Electronics Engineers (IEEE) Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(5):3123-3136., articleTitle=Crossformer++:A versatile vision transformer hinging on cross-scale attention, refAbstract=null), Reference(id=1179340472087625729, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=2021, volume=35, issue=12, pageStart=11106, pageEnd=11115, url=null, language=null, rfNumber=[18], rfOrder=26, authorNames=ZHOU H Y, ZHANG S H, PENG J Q, journalName=Association for the Advancement of Artificial Intelligence (AAAI)-21 Technical Tracks, refType=null, unstructuredReference=ZHOU H Y, ZHANG S H, PENG J Q, et al. Informer: Beyond efficient transformer for long sequence time-series forecasting[J]. Association for the Advancement of Artificial Intelligence (AAAI)-21 Technical Tracks, 2021, 35(12): 11106-11115., articleTitle=Informer: Beyond efficient transformer for long sequence time-series forecasting, refAbstract=null), Reference(id=1179340472200871938, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=27, authorNames=DAS A, KONG W, LEACH A, journalName=arXiv preprint arXiv, refType=null, unstructuredReference=DAS A, KONG W, LEACH A, et al. Long-term forecasting with TiDE: Time-series dense encoder[EB/OL]. arXiv preprint arXiv:2304.08424,2023., articleTitle=Long-term forecasting with TiDE: Time-series dense encoder, refAbstract=null), Reference(id=1179340472385421315, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, doi=null, pmid=null, pmcid=null, year=2023, volume=37, issue=9, pageStart=11121, pageEnd=11128, url=null, language=null, rfNumber=[20], rfOrder=28, authorNames=ZENG A L, CHEN M X, ZHANG L, journalName=Proceedings of the 37-th Association for the Advancement of Artificial Intelligence(AAAI) Conference on Artificial Intelligence, refType=null, unstructuredReference=ZENG A L, CHEN M X, ZHANG L, et al. Are Transformers effective for time series forecasting[J]. Proceedings of the 37-th Association for the Advancement of Artificial Intelligence(AAAI) Conference on Artificial Intelligence, 2023, 37(9): 11121-11128., articleTitle=Are Transformers effective for time series forecasting, refAbstract=null)], funds=[Fund(id=1179340469730427877, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, awardId=2022NRE-LH-14, language=CN, fundingSource=中国铀业有限公司-东华理工大学核资源与环境国家重点实验室联合创新基金(2022NRE-LH-14), fundOrder=null, country=null), Fund(id=1179340469810119654, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, awardId=null, language=CN, fundingSource=国家国防科技工业局核能开发项目“铀裂变瞬发n-γ融合测井及航空监测关键技术研究”, fundOrder=null, country=null), Fund(id=1179340469898200039, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, awardId=20242BAB25084, language=CN, fundingSource=江西省自然科学基金(20242BAB25084), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1179340466601477034, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, xref=1, ext=[AuthorCompanyExt(id=1179340466618254251, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466601477034, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 State Key Laboratory of Nuclear Resources and Environment, East China University of Technology, Nanchang 330013, China), AuthorCompanyExt(id=1179340466626642860, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466601477034, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 东华理工大学 核资源与环境国家重点实验室, 江西 南昌 330013)]), AuthorCompany(id=1179340466689557421, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, xref=2, ext=[AuthorCompanyExt(id=1179340466697946030, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466689557421, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 National Key Laboratory of Uranium Resources Exploration-Minning and Nuclear Remote Sensing, Nanchang 330013, China), AuthorCompanyExt(id=1179340466702140335, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466689557421, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 铀资源探采与核遥感全国重点实验室, 江西 南昌 330013)]), AuthorCompany(id=1179340466756666288, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, xref=3, ext=[AuthorCompanyExt(id=1179340466765054897, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466756666288, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 East China University of Technology, Nanchang 330013, China), AuthorCompanyExt(id=1179340466773443506, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, companyId=1179340466756666288, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 东华理工大学, 江西 南昌 330013)])], figs=[ArticleFig(id=1179340468467942357, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, language=EN, label=Fig. 1, caption=Architecture of depthwise separable convolutional mixer net model, figureFileSmall=b9+x0dFGIDdQ/t7/MVwkEw==, figureFileBig=PT+tgBfpLdnZwtP4hi/ynQ==, tableContent=null), ArticleFig(id=1179340468539245526, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, language=CN, label=图1, caption=深度可分离卷积混合网络模型架构, figureFileSmall=b9+x0dFGIDdQ/t7/MVwkEw==, figureFileBig=PT+tgBfpLdnZwtP4hi/ynQ==, tableContent=null), ArticleFig(id=1179340468597965783, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, language=EN, label=Fig. 2, caption=DSSM modular framework, figureFileSmall=pCRwUvh6u5PU5ILLrgikgQ==, figureFileBig=wPliOQu4dwHjYI5zfV+fuw==, tableContent=null), ArticleFig(id=1179340468652491736, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, language=CN, label=图2, caption=DSSM模块框架, figureFileSmall=pCRwUvh6u5PU5ILLrgikgQ==, figureFileBig=wPliOQu4dwHjYI5zfV+fuw==, tableContent=null), ArticleFig(id=1179340468715406297, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, language=EN, label=Fig. 3, caption=Schematic diagram of depthwise separable convolution, figureFileSmall=J9CTgxoUU2W/k0D1ge+yLg==, figureFileBig=Y3ULWsH3iC+XKm0getslhg==, tableContent=null), ArticleFig(id=1179340468778320858, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, language=CN, label=图3, caption=深度可分离卷积示意图, figureFileSmall=J9CTgxoUU2W/k0D1ge+yLg==, figureFileBig=Y3ULWsH3iC+XKm0getslhg==, tableContent=null), ArticleFig(id=1179340468837041115, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, language=EN, label=Fig. 4, caption=Conv-Mixer-Net modular framework, figureFileSmall=Ln5JdH1qxVaZhA4kvI8qSw==, figureFileBig=ZNP1CsjPD6GpuMSJzk+TQA==, tableContent=null), ArticleFig(id=1179340468912538588, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, language=CN, label=图4, caption=Conv-Mixer-Net模块框架, figureFileSmall=Ln5JdH1qxVaZhA4kvI8qSw==, figureFileBig=ZNP1CsjPD6GpuMSJzk+TQA==, tableContent=null), ArticleFig(id=1179340468971258845, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, language=EN, label=Fig. 5, caption=Test set performance of different models with seq_len=96 and pre_len=60, figureFileSmall=5TvzUmG5P/lDC8DRyLSuGQ==, figureFileBig=hRuCMF8lEkcBvcyVF69lFw==, tableContent=null), ArticleFig(id=1179340469029979102, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, language=CN, label=图5, caption=不同模型在seq_len=96与pre_len=60下的测试集表现, figureFileSmall=5TvzUmG5P/lDC8DRyLSuGQ==, figureFileBig=hRuCMF8lEkcBvcyVF69lFw==, tableContent=null), ArticleFig(id=1179340469139031007, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, language=EN, label=Table 1, caption=

Comparison of experimental results by different models

, figureFileSmall=null, figureFileBig=null, tableContent=
预测
步长
DS-Conv-Mixer-Net PatchTST TiDE DLinear Crossformer Informer
MSE MAE MSE MAE MSE MAE MSE MAE MSE MAE MSE MAE
24 0.016 2 0.053 0 0.016 5 0.055 9 0.019 5 0.067 5 0.020 5 0.088 7 0.038 3 0.148 2 0.160 6 0.286 4
36 0.018 3 0.058 7 0.018 3 0.060 7 0.020 4 0.070 3 0.029 1 0.113 5 0.055 5 0.182 4 0.153 2 0.263 0
48 0.020 4 0.063 9 0.020 5 0.066 3 0.022 2 0.074 6 0.034 8 0.132 8 0.064 5 0.181 4 0.183 6 0.336 1
60 0.020 9 0.065 9 0.021 3 0.069 1 0.022 9 0.077 6 0.038 7 0.146 7 0.066 0 0.195 2 0.260 8 0.374 5
Avg 0.019 0 0.060 4 0.019 2 0.063 0 0.021 3 0.072 5 0.030 8 0.120 4 0.056 1 0.176 8 0.189 6 0.315 0
性能/% 0 0 -1.04 -4.13 -10.80 -16.69 -38.31 -49.83 -66.13 -65.84 -89.98 -80.83
), ArticleFig(id=1179340469231305696, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, language=CN, label=表1, caption=

不同模型对比实验

, figureFileSmall=null, figureFileBig=null, tableContent=
预测
步长
DS-Conv-Mixer-Net PatchTST TiDE DLinear Crossformer Informer
MSE MAE MSE MAE MSE MAE MSE MAE MSE MAE MSE MAE
24 0.016 2 0.053 0 0.016 5 0.055 9 0.019 5 0.067 5 0.020 5 0.088 7 0.038 3 0.148 2 0.160 6 0.286 4
36 0.018 3 0.058 7 0.018 3 0.060 7 0.020 4 0.070 3 0.029 1 0.113 5 0.055 5 0.182 4 0.153 2 0.263 0
48 0.020 4 0.063 9 0.020 5 0.066 3 0.022 2 0.074 6 0.034 8 0.132 8 0.064 5 0.181 4 0.183 6 0.336 1
60 0.020 9 0.065 9 0.021 3 0.069 1 0.022 9 0.077 6 0.038 7 0.146 7 0.066 0 0.195 2 0.260 8 0.374 5
Avg 0.019 0 0.060 4 0.019 2 0.063 0 0.021 3 0.072 5 0.030 8 0.120 4 0.056 1 0.176 8 0.189 6 0.315 0
性能/% 0 0 -1.04 -4.13 -10.80 -16.69 -38.31 -49.83 -66.13 -65.84 -89.98 -80.83
), ArticleFig(id=1179340469310997473, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, language=EN, label=Table 2, caption=

Performance analysis of different models with seq_len=96 and pre_len=60

, figureFileSmall=null, figureFileBig=null, tableContent=
项目 DS-Conv-Mixer-Net PatchTST TiDE DLinear Crossformer Informer
time/s MSE time/s MSE time/s MSE time/s MSE time/s MSE time/s MSE
预测步
长60
27.762 2 0.020 9 131.179 0 0.021 3 182.766 7 0.022 9 44.395 0 0.038 7 79.725 8 0.066 0 93.331 0 0.260 8
性能/% 0 0 372.51 -1.88 558.33 -8.73 59.91 -45.99 187.17 -68.33 236.18 -91.99
), ArticleFig(id=1179340469378106338, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, language=CN, label=表2, caption=

不同模型在seq_len=96与pre_len=60下的性能分析

, figureFileSmall=null, figureFileBig=null, tableContent=
项目 DS-Conv-Mixer-Net PatchTST TiDE DLinear Crossformer Informer
time/s MSE time/s MSE time/s MSE time/s MSE time/s MSE time/s MSE
预测步
长60
27.762 2 0.020 9 131.179 0 0.021 3 182.766 7 0.022 9 44.395 0 0.038 7 79.725 8 0.066 0 93.331 0 0.260 8
性能/% 0 0 372.51 -1.88 558.33 -8.73 59.91 -45.99 187.17 -68.33 236.18 -91.99
), ArticleFig(id=1179340469466186723, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, language=EN, label=Table 3, caption=

Results of ablation experiments

, figureFileSmall=null, figureFileBig=null, tableContent=
预测步长 DS-Conv-Mixer-Net w/o DSSM
MSE MAE MSE MAE
24 0.016 2 0.053 0 0.016 8 0.056 8
36 0.018 3 0.058 7 0.018 5 0.061 2
48 0.020 4 0.063 9 0.023 0 0.067 3
60 0.020 9 0.065 9 0.023 7 0.069 2
Avg 0.019 0 0.060 4 0.020 5 0.063 6
Avg/% 0 0 -7.32 -5.03
), ArticleFig(id=1179340469545878500, tenantId=1146029695717560320, journalId=1146123346816638986, articleId=1147999684720844851, language=CN, label=表3, caption=

消融实验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
预测步长 DS-Conv-Mixer-Net w/o DSSM
MSE MAE MSE MAE
24 0.016 2 0.053 0 0.016 8 0.056 8
36 0.018 3 0.058 7 0.018 5 0.061 2
48 0.020 4 0.063 9 0.023 0 0.067 3
60 0.020 9 0.065 9 0.023 7 0.069 2
Avg 0.019 0 0.060 4 0.020 5 0.063 6
Avg/% 0 0 -7.32 -5.03
)], attaches=null, journal=Journal(id=1146119359820312588, delFlag=0, nameCn=铀矿冶, nameEn=Uranium Mining and Metallurgy, nameHistory1=null, nameHistory2=null, issn=1000-8063, eissn=, cn=11-1969/TL, coden=null, periodic=2, language=CN, oaType=0, 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=KmudR/G+rYvTqd4XcYqogQ==, journalPrice=null, startedYear=null, abbrevIsoEn=Uran Min Metal, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1755587156394, createdBy=null, updatedBy=15831073675, firstLetterCn=U, firstLetterEn=U, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=KmudR/G+rYvTqd4XcYqogQ==, picEn=9rbWk3ds8oZefNFxqqUVow==, jcr=null, cjcr=null, exts=[JournalExt(id=1164580199531238247, language=CN, name=铀矿冶, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=https://ykyi.cbpt.cnki.net/portal, createdTime=1755587156422, updatedTime=1755587156422, createdBy=15831073675, updatedBy=15831073675, submissionGuidelinesUrl=http://ykye.juqk.net/buy/, submissionAuthorUrl=https://ykyi.cbpt.cnki.net/EditorE3N/index.aspx?t=1, submissionEditorUrl=https://ykyi.cbpt.cnki.net/EditorE3N/index.aspx?t=3, submissionReviewUrl=https://ykyi.cbpt.cnki.net/EditorE3N/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1164580199573181288, language=EN, name=Uranium Mining and Metallurgy, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=https://ykyie.cbpt.cnki.net/portal, createdTime=1755587156432, updatedTime=1755587156432, createdBy=15831073675, updatedBy=15831073675, submissionGuidelinesUrl=http://ykye.juqk.net/buy/, submissionAuthorUrl=https://ykyi.cbpt.cnki.net/EditorE3N/index.aspx?t=1, submissionEditorUrl=https://ykyi.cbpt.cnki.net/EditorE3N/index.aspx?t=3, submissionReviewUrl=https://ykyi.cbpt.cnki.net/EditorE3N/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123346816638986, websiteList=[Website(id=1148007952688087041, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123346816638986, 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/yky/EN, language=EN, createTime=1751636024889, createBy=18614031015, updateTime=1753523175948, updateBy=18614031015, name=《铀矿冶》-英文站点, tplId=1146101810881728533, title=Uranium Mining and Metallurgy, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155923533696983256, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148007952688087041, code=articleTextType, value=kx, createTime=1753523246454, updateTime=1753523246454, creator=18614031015, updator=18614031015), WebsiteProps(id=1155923533676011733, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148007952688087041, code=banner, value=null, createTime=1753523246449, updateTime=1753523246449, creator=18614031015, updator=18614031015), WebsiteProps(id=1155923533667623124, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148007952688087041, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=MbrBQF5iwbqJZg/6eQNpYQ==, createTime=1753523246447, updateTime=1753523246447, creator=18614031015, updator=18614031015), WebsiteProps(id=1155923533688594647, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148007952688087041, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753523246452, updateTime=1753523246452, creator=18614031015, updator=18614031015), WebsiteProps(id=1155923533680206038, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148007952688087041, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753523246450, updateTime=1753523246450, creator=18614031015, updator=18614031015)]), Website(id=1148243567316820393, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123346816638986, 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/yky/CN, language=CN, createTime=1751692199786, createBy=18614031015, updateTime=1753523196222, updateBy=18614031015, name=《铀矿冶》-中文站点, tplId=1146099689490845704, title=铀矿冶, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148623394028941377, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243567316820393, code=articleTextType, value=kx, createTime=1751782757527, updateTime=1751782757527, creator=18614031015, updator=18614031015), WebsiteProps(id=1148623394003775550, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243567316820393, code=banner, value=null, createTime=1751782757521, updateTime=1751782757521, creator=18614031015, updator=18614031015), WebsiteProps(id=1148623393991192637, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243567316820393, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=MbrBQF5iwbqJZg/6eQNpYQ==, createTime=1751782757518, updateTime=1751782757518, creator=18614031015, updator=18614031015), WebsiteProps(id=1148623394020552768, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243567316820393, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782757525, updateTime=1751782757525, creator=18614031015, updator=18614031015), WebsiteProps(id=1148623394012164159, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243567316820393, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782757523, updateTime=1751782757523, creator=18614031015, updator=18614031015)])], journalTitle=铀矿冶, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Uranium Mining and Metallurgy, journalPhotoCn=KmudR/G+rYvTqd4XcYqogQ==, journalPhotoEn=9rbWk3ds8oZefNFxqqUVow==, journalFirstLetter=U, 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), detailUrlCn=https://castjournals.cast.org.cn/joweb/yky/CN/10.13426/j.cnki.yky.2024.10.12, detailUrlEn=https://castjournals.cast.org.cn/joweb/yky/EN/10.13426/j.cnki.yky.2024.10.12, pdfUrlCn=https://castjournals.cast.org.cn/joweb/yky/CN/PDF/10.13426/j.cnki.yky.2024.10.12, pdfUrlEn=https://castjournals.cast.org.cn/joweb/yky/EN/PDF/10.13426/j.cnki.yky.2024.10.12, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于深度可分离卷积混合网络模型的地浸采铀注液量预测研究
收藏切换
PDF下载
刘志锋 1, 2, 3 , 唐俊贤 1, 3 , 林芝宁 1, 3 , 周义朋 1, 2, 3
铀矿冶 | 开采·选冶 2025,44(1): 9-17
收起
收藏切换
铀矿冶 | 开采·选冶 2025, 44(1): 9-17
基于深度可分离卷积混合网络模型的地浸采铀注液量预测研究
全屏
刘志锋1, 2, 3, 唐俊贤1, 3, 林芝宁1, 3, 周义朋1, 2, 3
作者信息
  • 1 东华理工大学 核资源与环境国家重点实验室, 江西 南昌 330013
  • 2 铀资源探采与核遥感全国重点实验室, 江西 南昌 330013
  • 3 东华理工大学, 江西 南昌 330013
  • 刘志锋(1979—),男,内蒙古赤峰人,博士,副教授,主要研究方向为大数据分析与可视化。

通讯作者:

刘志锋(1979—),男,内蒙古赤峰人,博士,副教授,主要研究方向为大数据分析与可视化。
Injection Volume Prediction for In-situ Leaching of Uranium Based on Depthwise Separable Convolution Mixer Network Model
Zhifeng LIU1, 2, 3, Junxian TANG1, 3, Zhining LIN1, 3, Yipeng ZHOU1, 2, 3
Affiliations
  • 1 State Key Laboratory of Nuclear Resources and Environment, East China University of Technology, Nanchang 330013, China
  • 2 National Key Laboratory of Uranium Resources Exploration-Minning and Nuclear Remote Sensing, Nanchang 330013, China
  • 3 East China University of Technology, Nanchang 330013, China
出版时间: 2025-02-20 doi: 10.13426/j.cnki.yky.2024.10.12
文章导航
收藏切换
地浸采铀作为铀矿的绿色开采技术,在生产运行中产生海量数据,利用这些海量数据进行大数据分析和趋势预测,能够提升技术人员制定生产计划的可靠性。目前采用的基于编码器-解码器结构的时序预测模型,由于存在注意力机制,导致计算复杂、内存消耗大。本研究提出深度可分离卷积混合模型,通过动态序列分割模块降低固定分割带来的语义破坏,通过深度可分离卷积混合模块降低模型运行时间并捕获局部和全局特征。结果表明,深度可分离卷积混合网络模型的均方误差(Mean Square Error,MSE)与平均绝对误差(Mean Absolute Error,MAE)相较于时间序列分块自注意力模型(Patch Time Series Transformer,PatchTST)分别降低了1.04%和4.13%,提出的动态序列分割模块的MSE与MAE相较于原有模型分别降低了7.32%和5.03%;在性能对比分析上,深度可分离卷积混合模型的训练速度相较于趋势季节分解线性模型(Decomposition Linear,DLinear)提高了59.91%。建立的模型能够准确预测采区生产运行中硫酸注液量的变化趋势,改善了现有预测模型针对地浸铀矿数据集存在的运行时间长、运行内存大、数据拟合差的问题,可为地浸铀矿生产决策提供理论和实践参考。
地浸采铀  /  注液量预测  /  深度可分离卷积  /  预测模型

In-situ leaching of uranium, as a green uranium mining technology, generates massive data in production operation, which are available for the big data analysis and trend prediction to improve the reliability of technicians in making production plans. In the current prediction algorithms, the attention mechanism in the temporal prediction model based on the encoder-decoder structure has the problems of computational complexity and high memory consumption. In this paper, we proposed a depthwise separable convolutional model, in which the semantic damage caused by fixed segmentation was reduced by the dynamic sequence segmentation module, and the depthwise separable convolutional mixer module was used to reduce the model running time and capture local features as well as global features. The results show that the Mean Square Error (MSE) and Mean Absolute Error (MAE) of the depthwise separable convolutional hybrid network model are reduced by 1.04% and 4.13% respectively, compared with Patch Time Series Transformer (PatchTST), and the proposed dynamic sequence segmentation module MSE and MAE are reduced by 7.32% and 5.03% respectively, compared to the original model; in the comparative performance analysis, the training speed of this model is 59.91% faster than the Trend Seasonal Decomposition Linear (Decomposition Linear, DLinear) model. The depthwise separable convolutional model can accurately predict the future trend of sulfuric acid injection volume in the production operation of the mining area, improve the existing prediction model for in-situ leaching data by solving the problem of long running time, large running memory, poor data fitting problems, which provide a theoretical and practical reference for the decision-making of in-situ leaching production.

in-situ leaching of uranium  /  injection volume prediction  /  depthwise separable convolution  /  prediction model
刘志锋, 唐俊贤, 林芝宁, 周义朋. 基于深度可分离卷积混合网络模型的地浸采铀注液量预测研究. 铀矿冶, 2025 , 44 (1) : 9 -17 . DOI: 10.13426/j.cnki.yky.2024.10.12
Zhifeng LIU, Junxian TANG, Zhining LIN, Yipeng ZHOU. Injection Volume Prediction for In-situ Leaching of Uranium Based on Depthwise Separable Convolution Mixer Network Model[J]. Uranium Mining and Metallurgy, 2025 , 44 (1) : 9 -17 . DOI: 10.13426/j.cnki.yky.2024.10.12
随着地浸采铀技术的快速发展,铀矿地质勘查信息化建设逐步完善,对地浸过程中产生的生产、化验分析等数据与数字化、信息化、人工智能算法进行的融合,大幅提高了矿业技术人员工作效率[1-3]。目前,随着数字化矿山建设的深入以及信息化技术的发展,生产数据得到有效收集;但对收集数据的分析利用不足,往往只对部分数据进行了人工分析[4]。面对收集的海量数据,由于缺乏有效的数据建模手段,技术人员难以挖掘数据之间的内在规律,也无法充分利用现有数据来制定未来的生产计划。
在地浸采铀中,注液量受多种因素影响,包括矿石的矿物组成、矿石的粒度、浸出剂的性质,以及含矿含水层厚度等。注液量与地浸铀矿山生产效率关系密切,注液量过多可能导致资源浪费和环境污染,而注液量不足则会影响铀的浸出率[5]。为提高铀浸出率,需要准确预测注液量的未来变化趋势,进而合理安排铀矿资源的开采,降低矿业公司开采成本。
近年来,人工智能模型主要用于处理复杂非线性关系,在铀矿领域已有诸多成果。Kuchin Y等人利用地浸铀矿山勘探阶段的水文地质研究数据与测井数据,并使用基于支持向量算法、梯度提升树等的回归模型,对其母岩的过滤特性进行了预测[6]。贾皓等人使用人工神经网络对某矿床采区日金属量进行了预测[7]。余东原等人利用地浸铀矿生产数据,采用机器学习方法,筛选出多层感知机(Multilayer Perceptron,MLP)和随机森林(Random Forest,RF)模型来预测铀浸出金属量[8]。张宇等人使用多目标优化算法为“水平井-直井”抽注系统提供经济高效的抽注液量决策方案选择[9]。近年来,已有部分学者采用深度学习方法对铀矿领域进行相关分析,如贾明滔等人基于碱法地浸单元数据,提出了集成多种深度学习方法来有效预测浸采单元铀浓度[10];周渊凯等人采用深度学习方法,对纳岭沟地区测井解析岩性获得90%以上的分类精度[11]。然而,目前的研究主要是通过机器学习、数理统计等方法来对相关酸法地浸铀矿数据进行预测处理,探寻特征间的关系;但无法对未来趋势做出准确判断,没有把时间作为协变量进行相关时序序列的预测分析。
为了解决上述问题,针对地浸铀矿生产数据集的自身特点,以深度可分离卷积神经网络(Depthwise Separable Convolution,DS-Conv)为基础时序预测模型,提出一种深度可分离卷积混合网络模型(Depthwise Separable Convolution Mixer Net,DS-Conv-Mixer-Net),并用其进行研究。
本地浸铀矿数据集A1来源于某矿业公司采区的生产运行数据。采区生产运行数据参数包括日期、浸出液、浸出剂、液固比、浸出率;自2017年7月至2023年8月,记录时长为6年,采样时间间隔为1天。
为了提高模型预测能力以及训练速度,减少冗余信息的干扰,结合专家知识筛选出合适的地浸铀矿数据集,并构成相应时序序列,即d={dcjs,dzjs,${d}_{\mathrm{z}{\mathrm{H}}_{2}\mathrm{S}{\mathrm{O}}_{4}}$,ddqu,dzyl},其中dcjsdzjs${d}_{\mathrm{z}{\mathrm{H}}_{2}\mathrm{S}{\mathrm{O}}_{4}}$ddqudzyl分别表示t时刻历史抽液金属量、浸出剂金属量、注液硫酸浓度、当前矿山剩余金属量、注液量。以注液量为输出预测数据,记为xi;同时,根据滑动窗口形式生成每个时间序列实例,记为i(i代表第i个实例)。由于本研究将时间作为地浸铀矿数据集中的协变量;而这些时间序列数据在实际应用中存在不稳定性,测试数据还可能面临分布漂移问题,这会影响模型的预测性能和准确性[12-13]。为提高预测准确性通过用零均值和单位标准差在序列分割之前对每个xi进行归一化,并且在结果输出后将平均值和偏差添加到输出上,然后经过全连接预测层将结果输出。模型流程见图1
动态序列分割模块(Dynamic Sequence Segmentation Module,DSSM)的主要目标是辨别不同时间步长的数据点之间的相关性。在大多数现有时序预测研究中,保留原始逐点时间序列数据作为输入几乎是默认做法。然而,单个时间步骤所带来的语义不能像句子中的单词那么多,因此提高每个输入单元的信息密度对于提高最终结果的准确性至关重要。近年来,基于迁移(Transformer)结构的时序预测方法将相邻时间点聚合成子序列[14]2,然后将每个子序列分组到局部区域中,进而耦合它们的依赖性。但是固定大小的序列分割有可能破坏序列之间的语义性,导致性能下降。因此,本研究根据Dai、Chen等人的思想[15-16],建立动态序列分割模块(图2)。
对于DSSM模块来说,时序序列的输入为XRC×T,其中CT分别表示变量(通道)的数量和序列长度。首先,在进行DSSM模块之前,序列数据固定分割大小为N=(T-P)/S+2,其中每个子序列(子序列简称patch)的形状用XRP×C表示,N代表patch的数量,P为每个相应patch的大小,T表示输出通道数量,S表示每个patch窗口滑动大小。同时,为了保证均匀分割序列,在patch分割之前将最后一个XRP×C使用S个重复数填充到原始序列末尾。其次,每个patch设定3个关键控制变量,即中心位置xc、中心偏移δc和尺度变化δpxc由patch分割决定其大小,δcδp通过式(1)~式(2)计算得到。
δc=Gelu $\left[{W}_{\mathrm{off}}·f\left({x}_{\mathrm{i}\mathrm{n}}\right)\right]$,
δp=Relu $\left[{W}_{\mathrm{dss}}·f\left({x}_{\mathrm{i}\mathrm{n}}\right)\right]$,
式中:f(xin)为轻量预测线性函数;Gelu、Relu为激活函数;WoffWdss为权重矩阵,分别用于学习中心偏移和尺度变化。基于以上中心位置x、中心偏移δc和尺度变化δp结果,可以计算出新的patch序列的中心位置${x}_{\mathrm{c}}^{i+1}$和长度pi+1,以及左边界位置L和右边界位置R
${x}_{\mathrm{c}}^{i+1}$=xc+δc,pi+1=P+λ·δp;
L= ${x}_{\mathrm{c}}^{i}$- $\frac{{p}^{i}}{2}$,R= ${x}_{\mathrm{c}}^{i+1}$+ $\frac{{p}^{i+1}}{2}$;
式中:λ为缩放因子;P为初始化patch的大小;${x}_{\mathrm{c}}^{i}$为当前patch的中心位置;pi为当前patch的长度大小;${x}_{\mathrm{c}}^{i+1}$为下一个patch的中心位置;pi+1为下一个patch的长度大小;L为左边界位置;R为右边界位置。根据这些控制变量,DSSM模块能够自适应调整每个patch的位置和尺度,减少固定大小的序列分割可能引起的语义信息丢失。最后,通过轻量级线性预测函数将新的patch变换到嵌入空间中,从而使得模型能够更加灵活地捕捉时间序列数据中的局部模式和长期依赖关系。
为了更有效地处理DSSM生成的自适应patch,采用深度可分离卷积混合模块(Conv-Mixer-Net)对多个分支的时间序列数据进行建模。该网络首先使用分组卷积,即分组卷积中分组数等于DSSM模块中patch长度。同时,对于深度卷积层(Depthwise Convolution)来说,N个patch同时采用相同的卷积核大小(均为patch的长度P),分组数量等于patch的数量N;而对于逐点卷积层(Pointwise Convolution)来说,N个patch同时采用相同的卷积核大小(均为1),分组数量等于1。这种设计通过将输入数据划为多个“patch”,并进行混合捕捉全局上下文和局部特征,使得每个patch在深度卷积和逐点卷积上通过一个专用的卷积核进行处理,从而增强模型对不同时间序列特征的捕捉能力。
同时,为了扩展模型的感受野并捕捉时间序列数据中的长期依赖关系,本研究参考了时间序列分块自注意力模型(Patch Time Series Transformer,PatchTST)研究中的策略,将卷积操作的步长设置为S,针对步长S设置卷积核大小为8。在这一步骤中,输入特征图中的每个patch都独立地与一个卷积核进行卷积操作。这种操作生成了N个特征图,每个特征图代表了对应patch的卷积结果。随后,这些特征图按照生成的顺序进行连接,形成一个具有N个通道的输出特征图。深度卷积网络通过使用组卷积核,对共享相同空间位置的块应用相同的卷积操作,这有助于模型捕捉时间序列中patch间的潜在周期性模式。
深度卷积混合模块使用卷积核为k=P的分组卷积操作,通过对输入的通道(input channels)进行卷积处理。这种操作将生成与输入通道数量相同的特征图(feature maps),每个特征图都对应一个特定的输入通道;逐点卷积使用1×1的卷积核将深度卷积得到的特征图进行组合,生成已经定义的N个特征图,具体卷积操作见图3。上述模块同时结合激活函数Gelu以及残差网络来弥补梯度消失、简化网络结构,Conv-Mixer-Net实现跨patch通道混合信息,生成最终输出特征图,然后通过全连接层将预测结果输出。Conv-Mixer-Net模块具体流程见图4
网络训练优化均以Tesla V100服务器为硬件平台,运行内存为16 GB,采用PyTorch深度学习框架构建DS-Conv-Mixer-Net模型。模型训练采用损失函数和Adam优化器,数据集划分比例为7∶2∶1,分别对应训练集、测试集和验证集。模型输入时间序列长度设置为seq_len=96,用于预测未来24、36、48、60天的生产数据,分别对应不同的预测步长pre_len={24,36,48,60}。迭代次数设定为30次,学习率设定为0.000 1。在模型的DSSM模块中,patch长度默认为16,步长默认为8。Conv-Mixer-Net的层数默认设置为N=1。
模型性能评价指标以平均绝对误差(Mean Absolute Error,MAE)和均方误差(Mean Square Error,MSE)为准,误差指标计算公式如下:
MAE= $\frac{1}{n}\stackrel{n}{\sum _{i=1}}\left|{y}_{i}-\stackrel{︿}{{y}_{i}}\right|$,
MSE= $\frac{1}{n}\stackrel{n}{\sum _{i=1}}({y}_{i}{-\stackrel{︿}{{y}_{i}})}^{2}$
式中:yi为第i个观测值的实际输出;$\stackrel{︿}{{y}_{i}}$为模型预测的输出;n为观测值的总数。
对当前时间序列预测领域的多个先进模型进行了比较分析。这些模型包括基于Transformer架构的最新研究成果,例如PatchTST[14]9、Crossformer[17]以及Informer[18],以及基于线性网络结构的TiDE[19]和DLinear[20]模型。为了确保实验的一致性,所有参与比较的模型在实验中均采用统一的时间步长设置,其中序列长度为seq_len=96,预测步长pre_len则分别设定为24、36、48和60。
不同模型在相同实验环境下,通过MSE与MAE来评价模型预测性能,结果见表1。从归一化后的数值来看,与表现最好的基于Transformer结构的PatchTST模型相比,本模型(DS-Conv-Mixer-Net)在MSE与MAE上分别降低了1.04%与4.13%。与模型简单且表现较好的基于多层感知机结构的TiDE与DLinear模型相比,本模型在MSE上分别降低10.80%和38.31%,在MAE上分别降低16.69%和49.83%。
2022年6月26日至2023年6月26日时间跨度内测试集的拟合效果见图5。可以看出,在seq_len=96与pre_len=60的情况下。DS-Conv-Mixer-Net与PatchTST模型与真实值拟合较好;但根据集合表1结果,通过计算得出,本模型的MSE与MAE较PatchTST模型分别下降了1.88%与4.63%,优于Patch模型。同样,TiDE与DLinear模型的MSE与MAE低于本模型且测试集拟合较差。Crossformer和Informer模型由于自身注意力机制比较依赖于大型数据集等特点,其MSE和MAE值较大,导致与真实值拟合偏差较大。综上,本模型在seq_len=96与pre_len=60的测试集情况下拟合能力优于其他5种模型。
为了更好地突出DS-Conv-Mixer-Net模型的特点,对不同模型在相同实验环境下,设定seq_len=96、pre_len=60进行性能分析,结果见表2。实验表明,在评价指标为MSE的情况下,DS-Conv-Mixer-Net模型训练的总时长最小且对应实验评价指标MSE最小,分别为27.762 2 s和0.020 9;DLinear模型的结果次之,训练的总时长和MSE分别为44.395 s和0.038 7;DS-Conv-Mixer-Net模型比次优模型(DLinear)的训练速度提高59.91%。
为了证明DSSM模块的有效性,进行了相关消融实验,结果见表3。可以看出,在相同实验环境下,在研究的预测步长范围内,未使用DSSM的模型的平均MSE和MAE性能下降7.32%和5.03%。实验证明,相较于常规固定式分割patch来说,DSSM可根据数据特性动态分割成“非固定式”patch,而动态变化的patch可增强模型对局部和全局上下文的理解,减少由于固定分割造成的语义信息丢失。
收集某矿业公司采区生产运行数据,将时间作为协变量,同时结合多个影响地浸采铀注液量的特征参数,形成地浸采铀数据集,以深度卷积神经网络为架构,改进常用的序列分割模块,构建了一种深度可分离卷积混合网络模型(DS-Conv-Mixer-Net),并用于预测注液量。该模型能够有效降低运行时间,提高数据的拟合能力。选取约6年生产运行数据,制作地浸采铀数据集,用于注液量实验验证。
1)针对地浸铀矿的生产运行数据,将时间作为重要因素纳入模型,并结合多个注液量影响因素,使用深度卷积与点卷积来处理局部特征与全局特征,提高了数据处理速度。同时,改进常规固定patch分割处理,提高了对采区注液量的预测精度和效率。
2)对比实验显示,DS-Conv-Mixer-Net模型在数据拟合和运行时间上优于其他5种现有预测模型,具备明显的预测精度和计算效率优势。消融实验显示,本研究提出的DSSM模块在一定程度上能够动态处理地浸采铀数据集,提高预测精度。
3)尽管模型拟合程度良好,但现地浸矿山数据难以获取且数据集尚不完整,未来有望通过完整的数据集进行更有效地建模。在地浸采铀过程中,对控制流量等设备的调整可能导致数据异常,影响模型预测能力。因此,未来研究将考虑引入突变因素作为协变量,进一步提升模型的鲁棒性和适应能力。
  • 中国铀业有限公司-东华理工大学核资源与环境国家重点实验室联合创新基金(2022NRE-LH-14)
  • 国家国防科技工业局核能开发项目“铀裂变瞬发n-γ融合测井及航空监测关键技术研究”
  • 江西省自然科学基金(20242BAB25084)
参考文献 引证文献
排序方式:
[1]
阳奕汉, 苏学斌, 陈梅芳, 等. “数字建井”在砂岩型铀矿地浸开发中的探索与应用[J]. 中国矿业, 2022, 31(12):64-69.
YANG Yihan, SU Xuebin, CHEN Meifang, et al. Exploration and application of "digital well construction" in in-situ leaching of sandstone uranium deposit[J]. China Mining Magazine, 2022, 31(12):64-69 (in Chinese).
[2]
张明林, 刘洋, 吴建勇, 等. 中国铀矿地质勘查信息化建设现状及“十四五”发展思路[J]. 世界核地质科学, 2021, 38(3):287-294.
ZHANG Minglin, LIU Yang, WU Jianyong, et al. Construction situation of uranium exploration informatization and development idea for the 14th Five-Year Plan in China[J]. World Nuclear Geoscience, 2021, 38(3):287-294 (in Chinese).
[3]
毛鑫磊. 信息化技术在内蒙古某地浸采铀矿山中的应用[J]. 化工管理, 2024, 694(6):82-84.
MAO Xinlei. Application of information technology in a in-situ leaching of uranium mine in Inner Mongolia[J]. Chemical Enginering Management, 2024, 694(6):82-84 (in Chinese).
[4]
袁志华, 孙占学, 周义朋, 等. 绿色铀矿山研究进展[J]. 有色金属(冶炼部分), 2021(11):85-95.
YUAN Zhihua, SUN Zhanxue, ZHOU Yipeng, et al. Research progress of green uranium mines[J]. Nonferrous Metals(Extractive Metallurgy), 2021(11):85-95 (in Chinese).
[5]
王亮, 王海峰, 霍建党, 等. 纳岭沟矿床地浸采铀现场试验浸出液铀浓度变化研究[C]// 中国核学会.中国核科学技术进展报告(第三卷)——中国核学会2013年学术年会论文集:第2册. 北京: 核工业北京化工冶金研究院,2013:7.
[6]
KUCHIN Y, MUKHAMEDIEV R, YUNICHEVA N, et al. Application of machine learning methods to assess filtration properties of host rocks of uranium deposits in Kazakhstan[J]. Applied Sciences, 2023, 13(19):10958.
[7]
贾皓, 廖文胜, 杜志明, 等. 基于人工智能算法的地浸采区产量预测[J]. 铀矿冶, 2023, 42(3):10-16.
JIA Hao, LIAO Wensheng, DU Zhiming, et al. Production prediction of in-situ leaching mining area based on artificial intelligence algorithm[J]. Uranium Mining and Metallurgy, 2023, 42(3):10-16 (in Chinese).
[8]
余东原, 罗跃, 梁大业, 等. 基于机器学习方法预测地浸过程中铀浸出金属量的变化[J]. 有色金属(冶炼部分), 2024(2):92-98.
YU Dongyuan, LUO Yue, LIANG Daye, et al. Pred-icting the variation of uranium leaching metal content in ground-leaching process based on machine learning methods[J]. Nonferrous Metals (Extractive Metallurgy), 2024(2):92-98 (in Chinese).
[9]
贾明滔, 谭笑, 苏学斌, 等. 基于卷积和长短期记忆网络的地浸开采铀浓度预测研究[J]. 铀矿地质, 2024, 40(3):578-586.
JIA Mingtao, TAN Xiao, SU Xuebin, et al. Uranium concentration prediction for in-situ leaching based on convolution and long short-term memory networks[J]. Uranium Geology, 2024, 40(3):578-586 (in Chinese).
[10]
张宇, 马亮, 李召坤, 等. 基于多目标优化算法的“水平井-直井”系统流量决策方法[J/OL]. 铀矿冶, 2024:1-7[2024-11-03]. https://doi.org/10.13426/j.cnki.yky.2024.06.05. https://doi.org/10.13426/j.cnki.yky.2024.06.05
ZHANG Yu, MA Liang, LI Zhaokun, et al. Flow decision-making method for the "horizontal well-vertical well" system based on multi-objective optimization algorithm[J/OL]. Uranium Mining and Metallurgy, 2024:1-7[2024-11-03]
[11]
周渊凯, 刘祜. 基于深度学习方法的测井岩性识别研究[J]. 铀矿地质, 2024, 40(2):336-345.
ZHOU Yuankai, LIU Hu. Deep learning based lithology recognition of well logging data[J]. Uranium Geology, 2024, 40(2):336-345 (in Chinese).
[12]
ULYANOV D, VEDALDI A, LEMPITSKY V. Instance normalization:The missing ingredient for fast stylization[EB/OL]. (2016-07-27). https://doi.org/10.48550/arXiv.1607.08022. https://doi.org/10.48550/arXiv.1607.08022
[13]
KIM T, KIM J, TAE Y, et al. Reversible instance normalization for accurate time-series forecasting against distribution shift[C]. Kigali: International Conference on Learning Representations (ICLR), 2022.
[14]
NIE Y Q, NGUYEN N H, SINTHONG P, et al. A time series is worth 64 words:Long-term forecasting with transformers[C]. Kigali: International Conference on Learning Representations (ICLR), 2023.
[15]
DAI J F, QI H Z, XIONG Y W, et al. Deformable convolutional networks[C]. Venice: 2017 Institute of Electrical and Electronics Engineers (IEEE) International Conferenceon Computer Vision,2017:764-773.
[16]
CHEN Z Y, ZHU Y S, ZHAO C Y, et al. DPT:Deformable patch-based transformer for visual recognition[C]. Beijing: Association for Computing Machinery,2021:2899-2907.
[17]
WANG W X, CHEN W, QIU Q B, et al. Crossformer++:A versatile vision transformer hinging on cross-scale attention[J]. Institute of Electrical and Electronics Engineers (IEEE) Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(5):3123-3136.
[18]
ZHOU H Y, ZHANG S H, PENG J Q, et al. Informer: Beyond efficient transformer for long sequence time-series forecasting[J]. Association for the Advancement of Artificial Intelligence (AAAI)-21 Technical Tracks, 2021, 35(12): 11106-11115.
[19]
DAS A, KONG W, LEACH A, et al. Long-term forecasting with TiDE: Time-series dense encoder[EB/OL]. arXiv preprint arXiv:2304.08424,2023.
[20]
ZENG A L, CHEN M X, ZHANG L, et al. Are Transformers effective for time series forecasting[J]. Proceedings of the 37-th Association for the Advancement of Artificial Intelligence(AAAI) Conference on Artificial Intelligence, 2023, 37(9): 11121-11128.
2025年第44卷第1期
PDF下载
341
138
引用本文
BibTeX
文章信息
doi: 10.13426/j.cnki.yky.2024.10.12
  • 接收时间:2024-10-29
  • 首发时间:2025-07-04
  • 出版时间:2025-02-20
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-10-29
基金
中国铀业有限公司-东华理工大学核资源与环境国家重点实验室联合创新基金(2022NRE-LH-14)
国家国防科技工业局核能开发项目“铀裂变瞬发n-γ融合测井及航空监测关键技术研究”
江西省自然科学基金(20242BAB25084)
作者信息
    1 东华理工大学 核资源与环境国家重点实验室, 江西 南昌 330013
    2 铀资源探采与核遥感全国重点实验室, 江西 南昌 330013
    3 东华理工大学, 江西 南昌 330013

通讯作者:

刘志锋(1979—),男,内蒙古赤峰人,博士,副教授,主要研究方向为大数据分析与可视化。
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/yky/CN/10.13426/j.cnki.yky.2024.10.12
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

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

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