模糊神经网络在提升机制动系统故障诊断中的应用  

Application of Fuzzy Neural Network in Hoist Braking System Fault Diagnosis

作　　者：杨晓邦[1] 刘景艳[1] 李玉东[1] 

机构地区：[1]河南理工大学电气工程与自动化学院,河南焦作454000

出　　处：《煤矿机械》2012年第8期250-252,共3页Coal Mine Machinery

基　　金：河南省教育厅自然科学研究指导性计划项目(2008B510006);中国煤炭工业科技计划项目(MTKJ08-343)

摘　　要：针对BP神经网络在提升机制动系统故障诊断中的局限性,如收敛速度慢和可靠性差等缺点,根据提升机制动系统的故障机理和特点,提出了一种基于遗传算法的模糊神经网络故障诊断方法。结合了神经网络和模糊逻辑的优点,在利用神经网络对提升机制动系统进行故障诊断的基础上,引入模糊逻辑的概念,采用模糊隶属函数来描述这些故障的程度,并利用遗传算法对网络的权值和阈值进行修正,加快了网络收敛的速度,克服了易陷入局部极小的问题。For limitations of BP neural network in braking system fault diagnosis,such as slow convergence rate and poor reliability.According to fault mechanism and characteristics of hoist braking system,a fuzzy neural network fault diagnosis method based on genetic algorithm is proposed,which combines advantages of neural network and fuzzy logic.Fuzzy logic concept is injected on basis that neural network makes fault diagnosis to braking system,and fuzzy membership functions are applied to depict faults level.Genetic algorithm is applied to optimize weights and thresholds of network,so convergence rate is greatly increased and local optimum of BP algorithm is overcame.

关 键 词：提升机 故障诊断 模糊神经网络 遗传算法 

分 类 号：TD534[矿业工程—矿山机电] TP183[自动化与计算机技术—控制理论与控制工程]