摘要
为提升水电厂现场作业安全,研究基于人因工程的水电厂现场作业安全性分级量化分析模型,降低水电厂现场作业的风险等级。以人因工程中的人、机和环境为切入,分析水电厂现场作业影响因素,并选取人、作业环境及作业现场三部分重要因素,建立水电厂现场作业安全性分级量化分析指标体系,经人因工程指标量化处理后,以此为基础,构建基于BP神经网络的水电厂现场作业安全性分级量化分析模型,以量化处理后水电厂现场作业安全性分级量化分析指标为模型输入,经模型训练、测试后,输出水电厂现场作业安全性分级量化分析等级。实验表明:该模型所得水电厂现场作业安全性分级量化分析结果与实际情况吻合度高,具备风险预警可行性;BP神经网络模型隐含层节点数为15时,模型的风险预警效果最佳;人员劳动负荷和强度越大,水电厂现场作业风险越高,合理设置人员工作强度与负荷,可提升水电厂现场作业安全性。
To improve the safety of on-site operations in hydropower plants,this paper studies a quantitative analysis model based on human factors engineering for the safety classification of on-site operations in hydropower plants to reduce the risk level of on-site operations in hy⁃dropower plants.Taking human factors engineering as the starting point,this paper analyzes the influencing factors of on-site operation in hy⁃dropower plants,and selects three important factors:human factors,operation environment,and operation site to establish a quantitative analysis index system for the safety classification of on-site operation in hydropower plants.After quantifying the human factors engineering indicators,based on this,a BP neural network-based quantitative analysis model for the safety classification of on-site operation in hydro⁃power plants is constructed.The quantified analysis indicators for the safety classification of on-site operations in hydropower plants as the model input is used after model training and testing,the quantitative analysis level for the safety classification of on-site operations in hydro⁃power plants is output.The experiment shows that the quantitative analysis results of on-site operation safety classification of hydropower plants obtained by this model are highly consistent with the actual situation,and have the feasibility of risk warning.When the number of hidden layer nodes in the BP neural network model is 15,the risk warning effect of the model is the best.The greater the labor load and intensity of personnel,the higher the risk of on-site operations in hydropower plants.Reasonable setting of personnel work intensity and load can im⁃prove the safety of on-site operations in hydropower plants.
作者
王乐宁
王军
刘灏
WANG Lei-ning;WANG Jun;LIU Hao(State Energy Dadu Waterfall Gully Power Generation Co.,Ltd,Ya′an 625399,Sichuan Province,China)
出处
《中国农村水利水电》
北大核心
2024年第1期262-267,共6页
China Rural Water and Hydropower
关键词
人因工程
风险预警
指标体系
BP神经网络
水电厂
现场作业
human factors engineering
risk warning
indicator system
BP neural network
hydropower plants
on-site operations
