基于神经网络的高线中轧电机故障诊断的研究  

Research on Fault Diagnosis of the Intermediate Mill for High Speed Wire Rod Mill Based on Neural Network

作　　者：但斌斌[1] 何义文[1] 马乾[1] 

机构地区：[1]武汉科技大学机械自动化学院,湖北武汉430081

出　　处：《机电工程技术》2009年第7期51-52,145,共3页Mechanical & Electrical Engineering Technology

基　　金：国家自然科学基金(编号:50705069)

摘　　要：在对中轧电机故障诊断的特点和要求基础上,提出了一种基于神经网络的故障诊断方法。对所采集的高线中轧电机的各参数进行数据预处理与特征提取、归一化后,把这些特征参数作为神经网络的输入,经过学习训练,以判断系统状态,识别系统的故障。工程实践表明该故障诊断方法可行、有效。Based on the research of the characteristics and demands of fault diagnosis for intermediate mill,a fault diagnosis method based on neural network information fusion was proposed.This method used characteristic information of intermediate mill,finished data preprocessing,feature extraction,and normalization.Then it used these characteristic parameters as the inputs of the neural network,studies and trains,judged the state of system,and recognized the fault of system.The simulating experiment results of the system based on the method showed that its fault diagnosis was feasible and effective.

关 键 词：BP算法 神经网络 中轧电机 故障诊断 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TP206.3[自动化与计算机技术—控制科学与工程]