基于GMDH与SVM的信号缺失情景下轴承故障诊断  

Bearing Fault Diagnosis Based on GMDH-SVM in Signal Missing Situation

作　　者：陈琳升 吴永明[1] 李少波[1] CHEN Lin-sheng;WU Yong-ming;LI Shao-bo(Key Laboratory of Advanced Manufacturing Technology, Ministry of Education, Guizhou University, Guiyang 550025, China)

机构地区：[1]贵州大学现代制造技术教育部重点实验室,贵阳550025

出　　处：《组合机床与自动化加工技术》2020年第5期82-85,共4页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：国家自然科学基金资助项目(51505094);贵州省科学技术基金计划项目[(2016)1037];贵州省科技支撑计划项目[(2017)2029];贵州大学引进人才科研项目[贵大人基合字(2014)60号]。

摘　　要：针对在轴承故障数据采集过程中,由于外界干扰导致部分信号缺失的问题,提出一种基于数据分组处理算法(GMDH)与经粒子群优化的支持向量机(PSO-SVM)算法相结合的轴承故障诊断方法。首先,利用GMDH算法搭建时间序列预测模型,预测出并弥补上缺失的数据并与采集信号整合;其次,经过PSO-SVM模型对完整的数据集进行故障类型诊断;最后,实验采用了凯斯西储大学轴承故障振动数据,并与SVM、PSO-SVM等算法进行比较,验证了在信号缺失情景下,GMDH-SVM混合诊断方法的有效性。Aiming at the problem for missing signals in data acquisition of bearing faults caused by external interference,a bearing fault diagnosis method based on the Group Method of Data Handling(GMDH)and support vector machine(PSO-SVM)algorithm is proposed.Firstly,GMDH is used to build a time-series prediction model to predict and compensate for the missing.Secondly,the PSO-SVM model is used to diagnose the fault type through the complete data set.Finally,the experiment uses the vibration data of Case Western Reserve University,and verifies the effectiveness for GMDH-SVM diagnostic method due to absence of signal by comparison with SVM,PSO-SVM.

关 键 词：信号缺失 故障诊断 数据分组处理算法 时间序列预测 支持向量机 

分 类 号：TH165[机械工程—机械制造及自动化] TG506[金属学及工艺—金属切削加工及机床]