基于灰度纹理特征提取和CS-SNN的双初级永磁同步直线电机退磁故障诊断研究  

Demagnetization Fault Diagnosis Research of DPPMSLM Based on Gray Texture Feature Extraction and CS-SNN

作　　者：刘铄 宋俊材 陆思良[1] 吴先红 丁伟[1] LIU Shuo;SONG Juncai;LU Siliang;WU Xianhong;DING Wei(Anhui University,Hefei 230601,Anhui Province,China)

机构地区：[1]安徽大学,安徽省合肥市230601

出　　处：《中国电机工程学报》2023年第16期6464-6473,共10页Proceedings of the CSEE

基　　金：国家自然科学基金项目(52075002);安徽省自然科学基金项目(2208085QE167);安徽省教育厅高校自然科学研究重点项目(KJ-2021A0018)。

摘　　要：引入一种基于图像形态学纹理特征提取与布谷鸟搜索优化脉冲神经网络(cuckoo search-spiking neural network,CS-SNN)算法相结合的方法,以解决双初级永磁同步直线电机(dual primary permanent magnet synchronous linear motor,DPPMSLM)退磁故障精细定量化诊断识别的问题。首先,根据DPPMSLM拓扑结构约束,通过有限元仿真提取电机气隙空间中三线磁密信号作为有效故障信号;其次,引入图像纹理分析的方法,将一维数据信号映射为二维灰度图像,再采用伽马矫正和边缘提取技术增强图像信息,以提取图像纹理特征组成故障特征向量;然后建立两级CS-SNN分类器实现退磁故障位置类型和严重程度的精确诊断分类;最后,通过退磁样机制作和实验平台验证,提出的新方法能够准确识别DPPMSLM退磁故障位置和严重程度,并具有良好的鲁棒性,是一种有效可行的方法。A method based on the combination of image morphological texture feature extraction and cuckoo search-spiking neural network(CS-SNN)algorithm is introduced to solve the problem of fine quantitative diagnosis and recognition of demagnetization faults in dual primary permanent magnet synchronous linear motor(DPPMSLM).First,according to the constraints of DPPMSLM topology,the three-line magnetic density signal in the air gap space of the motor is extracted by finite element simulation as an effective fault signal.Secondly,the image texture analysis method is introduced to map the one-dimensional data signal to the two-dimensional gray image,and then the gamma correction and edge detection technology are used to enhance the image information,so as to extract the texture features of the image to form the fault feature vector.Then,a two-stage CS-SNN classifier is established to accurately diagnose and classify the location and severity of demagnetization faults.Finally,through the production of demagnetization prototype and experimental platform verification,the new method proposed in this paper can accurately identify the location and severity of demagnetization fault of DPPMSLM,and has good robustness,which is an effective and feasible method.

关 键 词：双初级永磁同步直线电机 退磁故障诊断 图像纹理分析 故障特征向量 布谷鸟搜索优化脉冲神经网络 

分 类 号：TM351[电气工程—电机]