摘要
针对滚动轴承故障模式识别问题,分析了振动信号的时域特征与经验模态分解剩余信号的能量特征,并将采集的特征一起构成了多域多类别的原始故障特征向量集,同时采用遗传算法对支持向量机径向基核函数参数和惩罚参数进行了寻优,提出了结合经验模态分解剩余信号能量特征的遗传算法优化支持向量机参数的滚动轴承故障模式识别方法。实验表明,给出的故障模式识别方法,对滚动轴承的外圈故障、内圈故障、滚动体故障及正常状态有很好的识别效果,具有较强的实用性,能够为滚动轴承故障的模式识别和智能诊断提供帮助。
Aiming at the fault diagnosis of rolling bearing, the time domain characteristics of the vibration signal and the energy characteristics of the empirical mode decomposition residual signal were analyzed.These features together constituted a multi-domain and multi-category original fault feature vector set. The genetic algorithm was used to optimize the radial basis kernel function parameters and penalty parameters of the support vector machine. The rolling bearing fault diagnosis based on multi-domain feature extraction and genetic algorithm optimized SVM was proposed, which can identify the outer race fault, inner race fault and rolling element fault of rolling bearing. It is practical and can provide help for pattern recognition and intelligent diagnosis of rolling bearing faults.
作者
李俊
刘永葆
余又红
LI Jun;LIU Yong-bao;YU You-hong(College of Power Engineering,Naval University of Engineering,Wuhan 430032,China)
出处
《燃气涡轮试验与研究》
北大核心
2020年第3期28-32,41,共6页
Gas Turbine Experiment and Research
基金
海军工程大学自然科学自主立项项目(425317K004,425317K137)。
关键词
经验模态分解
遗传算法
支持向量机
滚动轴承
特征提取
信号处理
模式识别
empirical mode decomposition(EMD)
genetic algorithm
support vector machine(SVM)
rolling bearing
feature extraction
signal processing
pattern recognition
