基于小波包和AGA-LSSVM模型的滚动轴承故障诊断

为了解决滚动轴承故障特征提取和故障类型识别问题,提高诊断准确率,提出了一种基于小波包与自适应遗传算法优化最小二乘支持向量机(AGA-LSSVM)相结合的故障诊断模型.首先由小波包分解与重构获取振动信号中能反映不同故障状态的能量特征向量,其次,由经过自适应遗传算法优化的LSSVM模型对滚动轴承常见故障进行诊断.Matlab运行结果表明,相较于传统LSSVM方法,所采用的方法可靠度较高,可以较好地实现对轴承故障的诊断.

Fault Diagnosis for Rolling Bearing Based on Model of Wavelet Packet and Adaptive Genetic Algorithm Least Squares Support Vector Machine

To solve the problems of fault feature extraction and fault type recognition about rolling bearing and improve the diagnostic accuracy,a fault diagnosis model based on wavelet packet and AGA-LSSVM is proposed.Firstly,the energy eigenvector of vibration signals which can reflect different fault types is extracted by using wavelet packet transform.Then,LSSVM model optimized by the adaptive genetic algorithm is used to diagnose the faults of the rolling bearing.The result of Matlab shows that the new model has a higher reliability than traditional LSSVM model and can effectively realize the goal of fault diagnosis.