摘要
为了快速准确判别矿井突水水源,降低矿井突水事故给煤矿生产及人类生命财产安全带来的危害,以赵各庄矿为例,提出了主成分分析法(PCA)与极限学习机(ELM)相结合矿井突水水源快速识别方法。结果表明:PCA确定了赵各庄矿中Na+、Ca2+、Mg2+对水样影响较大,为赵各庄矿水样的主控因子,排除了其它指标冗余信息的影响;在MATLAB中导入PCA确定的水样中三种主成分数据,通过ELM模型仿真训练可在10s内得出水样分类结果,分类学习时间迅速;对比ELM模型与BP神经网络对水样的分类结果,ELM仿真训练结果精确度高达100%,而BP神经网络仿真训练结果精确度仅为83.33%,远低于ELM模型精确度。
In order to quickly and accurately identify the source of mine water inrush and reduce the harm of mine water inrush accident to coal mine production and the safety of personnel life and property,a rapid identification method of mine water inrush source combining principal component analysis(PCA)and extreme learning machine(ELM)is proposed,Zhaogezhuang Coal Mine is taken as an example.The results showed that PCA determines that Na+,Ca2+and Mg2+in Zhaogezhuang Mine have great influence on water samples,which is the main control factor of Zhaogezhuang Mine Water Sample and excludes the influence of redundant information of other indicators.Three principal components data determined by PCA are introduced into MATLAB,and the classification results of water samples can be obtained within 10 seconds through ELM simulation training.Classified learning time is fast;compared with the classification results of ELM model and BP neural network,the accuracy of ELM simulation training results is up to 100%,while that of BP neural network simulation training results is only 83.33%,which is much lower.
作者
孙文洁
杨恒
李祥
王子超
杨蕾
SUN Wen-jie;YANG Heng;LI Xiang;WANG Zi-chao;YANG Lei(College of Geoscience and Surveying Engineering,China University of Mining and Technology(Beijing),Beijing 100083,China;State Key Laboratory of Nuclear Resources and Environment(East China University of Technology),Nanchang 330013,China;Open Foundation of State Key Laboratory of Environmental Criteria and Risk Assessment Chinese Research Academy of Environmental Sciences,Beijing 100012,China)
出处
《煤炭工程》
北大核心
2020年第1期111-115,共5页
Coal Engineering
基金
国家重点研发计划(2017YFC0804104)
核资源与环境国家重点实验室(东华理工大学)开放基金(NRE1906)
中国工程院重大咨询项目(2017-ZD-03)
国家自然基金项目(U1710258,41502227)
中国环境科学研究院环境基准与风险评估国家重点实验室开放基金(SKLECRA2016OFP17).
关键词
PCA模型
ELM模型
矿井突水
水源判别
赵各庄矿
PCA model
ELM model
mine water inrush
water source discrimination
Zhaogezhuang mine
