基于GMR和VAR的复杂工况下齿轮箱早期异常检测  

The anomaly detection of gearboxes under complex operating conditions based on GMR and VAR algorithms

作　　者：李鑫 沈希[1] 左洪福 李伟男[1] 马新宇 Li Xin;Shen Xi;Zuo Hongfu;Li Weinan;Ma Xinyu(School of Automobile and Rail Transit,Nanjing Institute of Technology,Jiangsu Nanjing,211167,China;College of Civil Aviation,Nanjing University of Aeronautics and Astronautics,Jiangsu Nanjing,211106,China)

机构地区：[1]南京工程学院汽车与轨道交通学院,江苏南京211167 [2]南京航空航天大学民航学院,江苏南京211106

出　　处：《机械设计与制造工程》2023年第8期87-92,共6页Machine Design and Manufacturing Engineering

基　　金：江苏省自然科学基金(BK20220687);南京工程学院高层次引进人才科研启动基金(YKJ201843);国家自然科学基金重点基金(U1933202)。

摘　　要：针对复杂工况下齿轮箱的全寿命周期振动信号进行早期异常检测分析。首先,使用时域同步平均算法对原始数据进行预处理;其次,为了减小工况变化对信号的干扰,基于齿轮运行残差(GMR)信号去除基础啮合频率及其谐波信号,运用EVIEWS软件建立向量自回归(VAR)模型并计算残差;最后,通过计算残差的峭度、标准差和均方根等判断齿轮异常发生的时间点,并与基于时域同步平均的方法进行对比。结果表明,所提方法能够在第109号文件检测出齿轮箱发生早期故障,比现有方法提前20个文件发现异常,为齿轮箱的早期故障诊断和维修决策奠定了基础。Early fault detection is carried out for the whole life cycle vibration signals of the gearbox under complex working conditions.It uses the time synchronous averaging algorithm to preprocess the original data.Then in order to reduce the signal interference caused by the change of working conditions,it applies the gear motion residual(GMR)to remove the basic meshing frequency and its harmonic signals,and the vector autoregressive(VAR)model is established based on EVIEWS software and the residual is calculated.Finally,by calculating the statistical indexes such as the kurtosis,standard deviation and root mean square value of the residual error,the occurrence of gear abnormality is determined and compared with the traditional method based on TSA.The results show that the algorithm proposed in this paper can diagnose the early faults of the gearbox in the document 109,and find the abnormal points of the gearbox in 20 files earlier than the traditional method,which lays a foundation for the early fault diagnosis and maintenance decision of the gearbox.

关 键 词：齿轮箱 时域同步平均 齿轮运行残差 向量自回归模型 故障检测 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]