摘要
以故障高发的行星齿轮传动系统为对象,提出基于变分模态分解(variational mode decomposition,VMD)及粒子群算法(particle swarm optimization,PSO)优化支持向量机(support vector machine,SVM)的故障诊断方法。首先,对信号进行VMD分解,采用改进小波降噪的方法处理分解后的本征模态分量(IMF),并对处理后的分量进行重构,凸显信号蕴含的信息;然后,对处理后的振动信号进行特征提取,分别提取信号的样本熵和均方根误差,并组成输入矩阵;最后,引入PSO优化SVM的关键参数,将提取的特征向量输入PSO-SVM进行训练和识别。将该方法应用于行星传动试验平台获取的行星轮裂纹故障、太阳轮轮齿故障及行星轮轴承故障信号,通过多维比较,验证了该方法的有效性。
This paper takes the planetary gear transmission system with high incidence of faults as the object,a fault diagnosis method based on variational mode decomposition(VMD)and particle swarm optimization(PSO)to optimize support vector machine(SVM)is presented.Firstly,the signal is decomposed by VMD,the decomposed components are processed by improved wavelet method,and the processed components are reconstructed to highlight the signal.The weak information of SVM is extracted.Then,the sample entropy and root mean square error of the processed vibration signal are extracted,and the input matrix is formed.Finally,PSO is introduced to optimize the key parameters of SVM,and the extracted eigenvectors are input into PSO-SVM for training and recognition.The method is applied to the planetary gear crack fault,the solar gear tooth fault and the planetary gear bearing fault signal obtained by the planetary transmission test platform.The effectiveness of the method is verified by multi-dimensional comparison.
作者
刘秀丽
王鸽
吴国新
李相杰
Liu Xiuli;Wang Ge;Wu Guoxin;Li Xiangjie(Key Laboratory of Modern Measurement and Control Technology,Ministry of Education,Beijing Information Science and Technology University,Beijing 100192,China;Sinovel Wind Power Technology(Group)Co.Ltd.,Beijing 100000,China)
出处
《电子测量与仪器学报》
CSCD
北大核心
2022年第1期54-61,共8页
Journal of Electronic Measurement and Instrumentation
基金
国家重点研发计划项目(2020YFB1713203)
北京信息科技大学勤信人才项目(QXTCP C202120)资助
关键词
行星齿轮箱
故障特征凸显
PSO优化SVM
适应度函数
样本熵
planetary gearbox
variational mode decomposition
particle swarm optimization introduced support vector machine
fitness function
sample entropy
作者简介
刘秀丽,2016年于北京理工大学获得工学博士学位。现为北京信息科技大学机电测控教育部重点实验室助理研究员,主要研究方向为机电系统测控技术及应用。E-mail:liuxiulilw@163.com
