融合KPCA与PSO-RBF的数控机床故障诊断研究  

Research on CNC Machine Fault Diagnosis Based on KPCA-PSO-RBF Neural Network

作　　者：杨东民[1] 陈敏[2] 吴庆朝 

机构地区：[1]包头职业技术学院,内蒙古包头014030 [2]浙江大学信息学部控制科学与工程学院,浙江杭州310000 [3]中国北车大同电力机车有限责任公司,山西大同037038

出　　处：《机械设计与制造》2016年第3期167-170,共4页Machinery Design & Manufacture

基　　金：国家自然科学基金(61134001);内蒙古科技厅高新技术领域科技计划重大项目的部分资助(20130302)

摘　　要：针对数控机床发生故障时多故障源、多变量、强耦合的特点和RBF神经网络结构参数选取依据经验的问题,提出一种融合核主元分析方法(kernel principal component analysis,KPCA)与粒子群算法优化RBF神经网络的数控机床故障诊断方法。首先,对所测信号利用核主元分析方法进行降噪、拨冗余,提取故障特征;其次,利用粒子群算法(Particle swarm optimization,PSO)优化RBF神经网络隐层节点中心和宽度;最后,将经KPCA提取的故障特征作为输入,建立PSO优化RBF的故障诊断模型。通过某数控床伺服系统七种常见故障特征仿真实验,结果表明:与RBF神经网络、PSO优化RBF神经网络相比,融合KPCA和PSO优化RBF神经网络的故障诊断方法不仅提高了网络的训练速度及泛化能力,而且具有更高辨识精度。Having the fault characteristics of multi-sources and multi-variables coupling, fault diagnosis is a great challenge for the computer numerical control （CNC） machine tool. An integrated fault identification method which fuses kernel principal component analysis （KPCA） method, particle swarm optimization （PSO） algorithm and RBF neural network is proposed. In order to improve the efficiency of fault diagnosis, several improvements are given. First of all, the kernel principal component analysis method is employed to extract the fault feature. Then, owning the advantages of good global search ability and fast convergence ability, particle swarm optimization （PSO） algorithm is used to optimize the structure parameters of RBF, such as hidden layer nodes center and width, in order to improve the training speed and generalization ability. Finally, seven kinds of common failures of CNC machine tool servo system are tested with the proposed algorithm. The results show that, compared with RBF and PSO-RBF model, the accuracy of the fault identification is higher and the generalization ability is stronger in case of the proposed method.

关 键 词：核主成分分析 粒子群算法 RBF神经网络数 数控机床 故障诊断 

分 类 号：TH16[机械工程—机械制造及自动化] TP18[自动化与计算机技术—控制理论与控制工程]