Abstract
In order to achieve intelligent classification of bearing faults, after comparing a large number of mechanical fault signal features, this paper proposes a bearing intelligent diagnosis algorithm based on vibration potential energy feature extraction and AP clustering. The potential energy features are extracted from the multidimensional eigenmode function (IMF) of the vibration signal after the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), and after self-weighted feature selection, the Affinity Propagation Clustering (AP) algorithm is used to achieve accurate classification of unlabeled faulty bearings. After data validation, the method can be better applied to the fault classification of rolling bearings, and the performance is better than the traditional classification and diagnosis algorithm. The algorithm is used to guide intelligent fault diagnosis of unlabeled data and to improve the applicability of AP clustering algorithm in rotating machinery fault diagnosis.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have