有色金属矿山安全生产风险预测系统研究  

Research on Risk Prediction System of Nonferrous Metals Mine Production Safety

作　　者：刘兵 汪令辉[3] 李全明 陈友良[4] LIU Bing;WANG Lin-hui;LI Quan-ming;CHEN You-liang(School of Computer Science and Technology,University of Science and Technology of China,Heifei 230027,China;Tongling Vocational and Technical College,Tongling 244061,China;Tongling Nonferrous Metals Group Co,Tongling 244000,China;China Academy of Safety and Science&Technology,Beijing 100012,China)

机构地区：[1]中国科技大学计算机科学与技术学院,安徽合肥230027 [2]铜陵职业技术学院,安徽铜陵244061 [3]铜陵有色金属集团公司,安徽铜陵244000 [4]中国安全生产科学研究院,北京100012

出　　处：《宜春学院学报》2020年第6期5-10,共6页Journal of Yichun University

基　　金：国家自然科学基金项目(编号:51874260);国家“十三五”重点研发计划项目(项目编号:2017YFC0804600);2018年度安徽高校自然科学研究重点项目(KJ2018A0749,KJ2018A0751)。

摘　　要：有色金属矿山安全生产风险一直受到政府、企业和社会的重要关注。本文根据有色金属矿山的运行参数和具体的监测数据,运用线性回归预测模型、BP神经网络预测模型、回归树预测模型三种预测分析方法并进行比较并选择最优预测模型,从海量的风险监测数据中寻找有色金属矿山运行的规律、预测未来发展趋势。结果表明:该方法用于指导安全生产管理工作,改变传统的安全生产“事后管理”为“事前预防”的方式,创新安全监管监察方法和手段,为监管部门提供宏观决策支持,为企业提供风险预警服务。The risk of safe production in nonferrous metals mines has been an important concern of the government,enterprises and the society.Based on the operation parameters and specific monitoring data of nonferrous metals mines,the paper use three prediction methods,linear regression prediction model,BP neural network prediction model and regression tree prediction model,then compare and select the optimal prediction model,looking for the law of nonferrous metals mine operation and forecasting the future development trend from massive risk monitoring data.The results show that:the method is used to guide the management of safety production,to change the traditional safety production“ex post management”as a“pre prevention”method,to innovate safety supervision and supervision methods and means,to provide macro decision-making support for the supervision department and to provide risk early-warning service for enterprises.

关 键 词：有色金属矿山 安全生产风险 预测方法 线性回归预测模型 BP神经网络预测模型 回归树预测模型 

分 类 号：X922[环境科学与工程—安全科学]