Article(id=1242140722829271444, tenantId=1146029695717560320, journalId=1146031591421210625, issueId=1242140702436570024, articleNumber=null, orderNo=14, doi=10.3981/j.issn.1000-7857.2023.20.012, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1661097600000, receivedDateStr=2022-08-22, revisedDate=1676390400000, revisedDateStr=2023-02-15, acceptedDate=null, acceptedDateStr=null, onlineDate=1699249897020, onlineDateStr=2023-11-06, pubDate=1698422400000, pubDateStr=2023-10-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1699249897020, onlineIssueDateStr=2023-11-06, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1774079026178, creator=sys-migrate, updateTime=1774079026178, updator=sys-migrate, issue=Issue{id=1242140702436570024, tenantId=1146029695717560320, journalId=1146031591421210625, year='2023', volume='41', issue='20', pageStart='1', pageEnd='112', issueExtLink='null', onlineDate='null', pubDate='1698422400000', pubDateStr='2023-10-28', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=3, issueType=-1, specialIssue=null, createTime=1774079021316, creator='sys-migrate', updateTime=1774079021316, updator='sys-migrate', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=106, endPage=112, ext={EN=ArticleExt(id=1242140727782748193, articleId=1242140722829271444, tenantId=1146029695717560320, journalId=1146031591421210625, language=EN, title=A prediction model for coal calorific value based on L-M gradient iterative algorithm, columnId=1150494644690366681, journalTitle=Science & Technology Review, columnName=Papers, runingTitle=null, highlight=null, articleAbstract=The coal quality test data of about 150 thermal power enterprises are selected, and the coal calorific value prediction model based on L-M algorithm is built by analyzing the ubiquitous coal quality test data information. The experimental results show that: (1) the linear relationships between calorific value and carbon, ash are significant respectively, and the correlation coefficients are 0.8768 and 0.6880; (2) principal component analysis(PCA) method excavates the information of the principal component eigenvalue, characteristic matrix and score, which could realize the dimension reduction effect from six-dimensional matrix to four-dimensional matrix, and enhance the convergence stability of neural network in the training process; (3) based on the L-M algorithm, the training coefficient , verification coefficient and test coefficient of the Levenberg-Marquardt back propagation neural network prediction method(LMBP) model are 0.9957, 0.9942 and 0.9963 respectively, and the overall coefficient is 0.9931. Through the further verification of 20 groups of data to be tested, the LMBP prediction model is more reliable, the prediction accuracy is higher, and better to meet the actual forecast demand., authors=HUANG Kui1 , WANG Chongshi2 , WANG Linli1 , DOU Youquan1 , ZHANG Donglian1 , ZENG Wenhui2 , WANG Jiayin2 , ZENG Yong2 , authorsList=HUANG Kui, WANG Chongshi, WANG Linli, DOU Youquan, ZHANG Donglian, ZENG Wenhui, WANG Jiayin, ZENG Yong, authorCompany=1. Guoneng Nanjing Coal Quality Supervision and Inspection Corporation Ltd., Nanjing 210031, Chinad ）、灰分（Aad ）与发热量（Qgr,ad ）的线性关系较为显著，相关系数 R2 为0.8768和0.6880；（2）主成分分析法挖掘出影响煤质发热量的主成分特征值、特征矩阵及得分，实现了由六维矩阵降至四维矩阵的降维效果，增强了神经网络在训练过程中收敛的稳定性；（3）基于L-M算法下，改进的BP神经网络预测模型（LMBP）的训练集系数Rt 、验证集系数Ra 和测试集系数Rm 分别为0.9957、0.9942和0.9963，总体系数为0.9931，同时通过待测20组数据进一步验证了LMBP预测模型可靠，预测精度较高，更符合实际预测需求。, authors=黄奎1 ，王充实2 ，王林立1 ，窦有权1 ，张冬练1 ，曾文慧2 ，王嘉垠2 ，曾勇2 , authorsList=黄奎，王充实，王林立，窦有权，张冬练，曾文慧，王嘉垠，曾勇, authorCompany=1. 国能南京煤炭质量监督检验有限公司，南京 210031
科技导报
| 论文 2023, 41(20): 106-112
基于L-M梯度迭代算法的煤质发热量预测模型
全屏
黄奎，王充实，王林立，窦有权，张冬练，曾文慧，王嘉垠，曾勇
作者信息
A prediction model for coal calorific value based on L-M gradient iterative algorithm
HUANG Kui, WANG Chongshi, WANG Linli, DOU Youquan, ZHANG Donglian, ZENG Wenhui, WANG Jiayin, ZENG Yong
Affiliations
出版时间: 2023-10-28
doi: 10.3981/j.issn.1000-7857.2023.20.012
文章导航
选取150家火电企业的煤质检测数据，通过分析泛在煤质化验数据信息，构建L-M算法下的煤质发热量的预测模型。实验结果表明：（1）煤质化验数据中仅碳（Cd ）、灰分（Aad ）与发热量（Qgr,ad ）的线性关系较为显著，相关系数 R2 为0.8768和0.6880；（2）主成分分析法挖掘出影响煤质发热量的主成分特征值、特征矩阵及得分，实现了由六维矩阵降至四维矩阵的降维效果，增强了神经网络在训练过程中收敛的稳定性；（3）基于L-M算法下，改进的BP神经网络预测模型（LMBP）的训练集系数Rt 、验证集系数Ra 和测试集系数Rm 分别为0.9957、0.9942和0.9963，总体系数为0.9931，同时通过待测20组数据进一步验证了LMBP预测模型可靠，预测精度较高，更符合实际预测需求。
煤质化验数据
/
主成分分析法
/
L-M算法
/
训练集系数
The coal quality test data of about 150 thermal power enterprises are selected, and the coal calorific value prediction model based on L-M algorithm is built by analyzing the ubiquitous coal quality test data information. The experimental results show that: (1) the linear relationships between calorific value and carbon, ash are significant respectively, and the correlation coefficients are 0.8768 and 0.6880; (2) principal component analysis(PCA) method excavates the information of the principal component eigenvalue, characteristic matrix and score, which could realize the dimension reduction effect from six-dimensional matrix to four-dimensional matrix, and enhance the convergence stability of neural network in the training process; (3) based on the L-M algorithm, the training coefficient , verification coefficient and test coefficient of the Levenberg-Marquardt back propagation neural network prediction method(LMBP) model are 0.9957, 0.9942 and 0.9963 respectively, and the overall coefficient is 0.9931. Through the further verification of 20 groups of data to be tested, the LMBP prediction model is more reliable, the prediction accuracy is higher, and better to meet the actual forecast demand.
coal quality test data
/
Principal component analysis
/
L-M algorithm
/
training set coefficient
黄奎，王充实，王林立，窦有权，张冬练，曾文慧，王嘉垠，曾勇.
基于L-M梯度迭代算法的煤质发热量预测模型.
科技导报,
2023
, 41
(20)
: 106
-112
.
DOI: 10.3981/j.issn.1000-7857.2023.20.012
HUANG Kui, WANG Chongshi, WANG Linli, DOU Youquan, ZHANG Donglian, ZENG Wenhui, WANG Jiayin, ZENG Yong.
A prediction model for coal calorific value based on L-M gradient iterative algorithm[J].
Science & Technology Review ,
2023
, 41
(20)
: 106
-112
.
DOI: 10.3981/j.issn.1000-7857.2023.20.012
2023年第41卷第20期
PDF下载
230
28
引用本文
BibTeX
文章信息
doi: 10.3981/j.issn.1000-7857.2023.20.012
接收时间：2022-08-22
首发时间：2023-11-06
出版时间：2023-10-28
收稿日期：2022-08-22
修回日期：2023-02-15
https://castjournals.cast.org.cn/joweb/kjdb/CN/10.3981/j.issn.1000-7857.2023.20.012
引用本文
BibTeX
2种不同金属材料的力学参数
科 属数 种数 占总种数比例 属 种数 占总种数比例 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
BibTeX
EndNote
RefWorks
TxT
PDF下载
全屏
230
28
关闭全屏
北京市海淀区学院南路86号
010-62199257
qkjq@cast.org.cn
