基于进化FCM和S2FCM算法的滚动轴承故障诊断研究

Fault Diagnosis of Rolling Bearings Based on Evolution-FCM and S2FCM

在对滚动轴承故障数据进行的分类实验中应用FCM算法,就其不足进行分析。为了克服离群点的影响,提出相对模糊指数概念,并且构建了隶属度归一化修正因子。然后结合S2FCM算法提出一种无监督的FCM融合算法。分别用两个实验平台的数据对该融合算法与传统算法的有效性进行仿真实验。对比不同算法的实验结果说明,FCM融合算法可以有效的提高价值函数的收敛速度,同时聚类结果的准确率也明显优于传统算法。

This paper aims at analysing the disadvantages of the FCM algorithm, which is applied in the data classification experiment of rolling bearing faults. To reduce the effect of outliers, the concept of relative fuzzy index is proposed, and the update value of normalized degree of membership is set. Moreover, the authors propose an unsupervised algorithm that combines the FCM algorithm with the S2 FCM algorithm, and apply it in the data classification experiment of rolling bearing faults. After using the data of both researching platforms to verify its efficiency, the results show that this new algorithm can raise the convergence rate of the merit function efficiently, and it is evidently superior to the traditional algorithm in terms of accuracy rate.