摘要
针对电梯运行故障的动态诊断难题,提出一种优化的BF神经网络故障诊断模型,实时分析电梯运行数据,准确快速得出电梯故障信息,提高电梯运行的安全性和可靠性。将粒子群算法引入到神经网络算法中,修改误差目标函数的距离公式,建立电梯故障诊断的改进神经网络模型,并通过实验数据的仿真分析,从而验证了电梯故障诊断具有可行性。
Aiming at the dynamic diagnosis problem of elevator malfunction,an optimized BF neural network fault diagnosis model is proposed,which can make real-time analysis of the elevator running data to accurately and quickly obtain elevator fault information,and improve the safety and reliability of elevator operation.By applying the particle swarm optimization（PSO）algorithm to the neural network algorithm,distance formula of the error objective function has been modified and neural network model for elevator fault diagnosis has been established.Through simulation analysis of the experimental data,Feasibility of the elevator fault diagnosis has been verified.
作者
王赛男
陈敢
WANG Sai-nan;CHEN Gan(Hunan Electrical College of Technology,Xiangtan 411100,China;Hunan Delitong Elevator Co.,LTD.,Zhuzhou 412000,China)
出处
《长江工程职业技术学院学报》
CAS
2018年第2期25-27,共3页
Journal of Changjiang Institute of Technology
基金
湖南省科技厅重点计划项目(编号:2016GK2076)
关键词
故障诊断
神经网络
粒子群算法
电梯故障
fault diagnosis
neural network
particle swarm optimization （PSO）
elevator fault
