基于HGWO-MSVM的齿轮箱故障诊断研究  

Research on Gearbox Fault Diagnosis Based on HGWO-MSVM

作　　者：孙明波[1] 马秋丽 雷俊辉 张炎亮[1] SUN Ming-bo;MA Qiu-li;LEI Jun-hui;ZHANG Yan-liang(School of Management Engineering, Zhengzhou University, Zhengzhou 450001 ,China)

机构地区：[1]郑州大学管理工程学院,郑州450001

出　　处：《组合机床与自动化加工技术》2018年第5期95-98,102,共5页Modular Machine Tool & Automatic Manufacturing Technique

基　　金：国家自然科学基金资助项目(71271194);河南省高等学校重点科研项目(16A630035);河南省基础与前沿技术研究项目(162300410073)

摘　　要：针对齿轮箱多类故障信号非线性、不确定性难以进行有效识别的问题,提出了一种混合灰狼优化算法(Hybrid Grey Wolf Optimizer,HGWO)优化多分类支持向量机(Multi-class Support Vector Machine,MSVM)的齿轮箱故障诊断方法。首先利用小波包对齿轮箱故障信号进行降噪处理,并通过信号中各频带的能量,提取能量特征值,再将获取的特征值输入优化后的MSVM模型进行故障模式的识别。实验结果表明,相对于传统的诊断模型,基于HGWO-MSVM的齿轮箱故障诊断模型能够更有效地诊断齿轮箱的实际运行状态,提高识别效率和精度。Aiming at the problem that the nonlinearity of the fault signal of the gear box is difficult to be effectively identified,a diagnosis method based on multi-class support vector machine（MSVM） optimized by hybrid grey wolf optimizer（HGWO） is proposed.Firstly,the wavelet packet is used to denoise the gearbox fault signal,and the energy eigenvalues are extracted by the energy of each band in the signal.Then,the acquired eigenvalues are input into the optimized MSVM model to identify the fault mode.The experimental results show that the fault diagnosis model based on HGWO-MSVM can effectively diagnose the actual running state of the gearbox and improve the efficiency and accuracy of the identification.

关 键 词：小波包 混合灰狼优化算法 多分类支持向量机 齿轮箱 故障诊断 

分 类 号：TH165.3[机械工程—机械制造及自动化] TG659[金属学及工艺—金属切削加工及机床]