摘要
针对带式输送机轴承故障难以精确诊断的问题,提出一种基于参数优化变分模态分解(VMD)和引力搜索算法优化支持向量机(GSA-SVM)的轴承故障诊断方法。首先以样本熵为适应度值,遗传算法优化VMD参数,得到最优模态参数K和惩罚因子α的组合;然后利用优化后的VMD分解振动信号,得到K个模态分量,并将模态分量的散布熵作为特征向量;最后将特征向量带入GSA-SVM中进行故障模式识别,得到故障诊断结果。实例验证可知,该方法能够实现轴承准确故障诊断,且优于对比方法。
Aiming at the problem that it is difficult to accurately diagnose the bearing faults of belt conveyors, a bearing fault diagnosis method based on parameter optimized variational modal decomposition(VMD) and gravity search algorithm optimized support vector machine(GSA-SVM) was proposed. Firstly, with the sample entropy as the fitness value, the VMD parameters were optimized by genetic algorithm to obtain the combination of the optimal modal parameter K and the penalty factor α.Then, the optimized VMD was used to decompose the vibration signal to obtain K modal components,and the dispersion entropy of the modal components was used as the feature vector. Finally, the feature vector was introduced into GSA-SVM for fault pattern recognition, and the fault diagnosis results were obtained. Case verification shows that this method can realize the accurate bearing fault diagnosis, and is superior to the comparison method.
作者
孙英倩
王鸿烨
靳震震
Sun Yingqian;Wang Hongye;Jin Zhenzhen(Guangxi Transport Vocational and Technical College,Nanning 530227,China;Guangxi University,Nanning 530007,China)
出处
《煤矿机械》
2021年第8期194-196,共3页
Coal Mine Machinery
基金
2020年度校级科学研究重点项目(JZY2020KAZ16)
广西职业教育教学改革研究项目(GXGZJG2017B0720)
2019年度校级科学研究重点项目(JZY2019KAZ07)。
