基于AFSA-SVM的滚动轴承故障诊断研究

Bearing Fault Diagnosis Based on Artificial Fish Swarm Optimization Support Vector Machine Algorithm

针对滚动轴承运行过程中引发的滚动体故障、内圈故障以及外圈故障,文章第一次将人工鱼群优化支持向量机的算法用于滚动轴承故障类型的诊断识别。同时,将该算法诊断识别的结果与PSO-SVM、GA-SVM的结果进行比较。通过对比分析可知,该算法故障诊断识别的准确率为95%,PSO-SVM的准确率为85%,GA-SVM的准确率为87.5%。这表明了,该算法在滚动轴承故障类型的诊断识别方面,具有良好的故障诊断识别效果。

For the rolling element fault,inner ring fault and outer ring fault caused by rolling bearing operation,the artificial fish swarm optimization support vector machine algorithm is used for fault diagnosis and identification of rolling bearing for the first time.At the same time,the algorithm is compared with the fault diagnosis results of PSO-SVM and GA-SVM.Through comparison and analysis,the accuracy of the algorithm for fault diagnosis and recognition is 95%,the accuracy of PSO-SVM is 82.5%,and the accuracy of GA-SVM is 87.5%.This indicates that the algorithm has a good fault diagnosis and recognition effect in the diagnosis and identification of rolling bearing fault types.