摘要
深部矿井热害严重威胁矿工们身心健康,阻碍井下正常开采活动。对深部矿井热害风险进行评价,能够帮助煤矿企业制定有效措施降低矿井内热害,减少其对矿工及开采活动的影响。本文构建了深部煤矿热害风险评价指标体系,并利用熵权改进的BP神经网络模型对深部矿井热害风险进行评价。研究结果表明:相比较于BP神经网络模型,熵权-BP神经网络模型对深部矿井的热害评估更加准确,预测精度高达96.68%。最后以A煤矿为例对模型进行验证,模型预测结果与实际相符,说明该模型可以实际应用于深部矿井热害风险评价。
Thermal injury in deep mines seriously threatens the physical and mental health of miners and hinders normal underground mining activities.The evaluation of heat damage risk in the deep mine can help coal mining enterprises develop effective measures to reduce heat damage in mines and its influence on miners and mining activities.In this paper,the evaluation index system of deep coal mine heat damage risk is constructed,and the BP neural network model improved by entropy weight is used to evaluate the deep coal mine heat damage risk.The results show that compared with the BP neural network model,the entropy-BP neural network model is more accurate in evaluating the thermal damage of deep mines,and the prediction accuracy is up to 96.68%.Finally,this paper takes a coal mine as an example to verify the model.The predicted results of the model conforms to with the reality,indicating that the model can be applied to the thermal damage risk assessment of deep mines.
作者
秦致远
杨力
QIN Zhiyuan;YANG Li(School of Economics and Management,Anhui University of Science and Technology,Huainan 232000,China)
出处
《安徽工程大学学报》
CAS
2023年第3期58-64,94,共8页
Journal of Anhui Polytechnic University
基金
国家自然科学基金资助项目(71971003)。
关键词
深部矿井
热害
熵权法
BP神经网络
风险评价
deep mine
heat damage
entropy weight method
BP neural network
risk evaluation
