基于优化神经网络的电梯故障诊断系统研究  

Research on elevator fault diagnosis system based on Optimized Neural Network

作　　者：刘影 赵迎龙[1] 魏斌[1] 马同飞[1] 陈作超[1] LIU Ying;ZHAO Yinglong;WEI Bin;MA Tongfei;CHEN Zuochao(Branch of Wuxi,Special Equipment Safety Supervision Inspection Institute of Jiangsu Province,Wuxi,Jiangsu 214000,China)

机构地区：[1]江苏省特种设备安全监督检验研究院无锡分院,江苏无锡214000

出　　处：《自动化与仪器仪表》2022年第5期88-92,共5页Automation & Instrumentation

摘　　要：针对电梯系统数学模型难以获取,运行故障动态诊断难的问题,引入遗传算法,提出一种优化的神经网络电梯故障诊断系统。首先介绍了BP神经网络在电梯故障诊断中的基本原理,随后建立电梯故障诊断神经网络模型,并在Matlab环境下,对故障诊断系统进行仿真实现。实验结果表明,遗传算法优化后的神经网络减少了运算量,提高了网络稳定性,具有更高的故障诊断精度。Aiming at the problem that the mathematical model of elevator system is difficult to obtain and the dynamic fault diagnosis is difficult,an optimized neural network elevator fault diagnosis system is proposed by introducing genetic algorithm.Firstly,the basic principle of BP neural network in elevator fault diagnosis is introduced,then the neural network model of elevator fault diagnosis is established,and the fault diagnosis system is simulated in Matlab environment.The experimental results show that the neural network optimized by genetic algorithm reduces the amount of computation,improves the stability of the network,and has higher fault diagnosis accuracy.

关 键 词：电梯 故障诊断 神经网络 遗传算法 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置] TU857[自动化与计算机技术—控制科学与工程]