摘要
文章提出一种综合考虑轴承各种不同状态,以最小包络熵和为适应度函数的蚱蜢算法优化的变分模态分解(GOA-VMD),以多特征参数作为滚动轴承故障特征向量,并采用集成支持向量机(ISVM)作为故障诊断模型的滚动轴承故障诊断方法。首先,采用GOA-VMD获得最优分解参数;其次,采用VMD将轴承振动信号分解为K个IMF分量,计算IMF分量的奇异值特征、能量熵特征、样本熵特征和排列熵特征,计算原信号的时频域特征,将该多特征参数组合在一起作为特征向量;然后采用主成分分析法对特征向量进行降维处理;最后,将降维后的特征向量输入ISVM中识别故障类型。实验研究结果表明,此方法可获得理想的滚动轴承故障诊断准确率。
A rolling bearing fault diagnosis method is proposed in this paper,which combines the Grasshopper Optimization Algorithm based on Variational Mode Decomposition(GOA-VMD)with multiple feature parameters as the fault feature vector of rolling bearings,and adopts the Integrated Support Vector Machine(ISVM)as the fault diagnosis model.Firstly,the optimal decomposition parameters are obtained using GOA-VMD.Then,the vibration signals of the bearing are decomposed into K Intrinsic Mode Functions(IMFs)using VMD,and the singular value features,energy entropy features,sample entropy features,and permutation entropy features of the IMF components are calculated,as well as the time-frequency domain features of the original signal.These multiple feature parameters are combined as the feature vector.Next,Principal Component Analysis(PCA)is used to reduce the dimension of the feature vector.Finally,the reduced feature vector is input into the ISVM for fault type recognition.Experimental results show that the proposed method achieves satisfactory accuracy in rolling bearing fault diagnosis.
作者
郭绍强
Guo Shaoqiang(Jingmen Branch of China Petroleum&Chemical Corporation,Jingmen,Hubei 448001,China)
出处
《化工设备与管道》
CAS
北大核心
2023年第6期72-79,共8页
Process Equipment & Piping
关键词
滚动轴承
故障诊断
蚱蜢优化算法
变分模态分解
多特征参数
集成支持向量机
rolling bearing
fault diagnosis
grasshopper optimization algorithm
variational mode decomposition
multi-feature parameters
integrated support vector machine
作者简介
郭绍强(1975-),男,本科,高级工程师。设备工程管理。
