摘要：Bearing fault is the major fault of the rotating machinery, in order to better identify the fault of bearing, the multi-layer kernel learning methods based on local tangent space alignment (LTSA) and support vector machine (SVM) are proposed. In this method, the supervised learning is embedded into the improved local tangent space alignment algorithm, realize fault feature extraction and new data processing for equipment fault signal, and then correctly classify the faults by non-linear support vector machine. The experiment result for roller bearing fault diagnosis shows that SILTSA-SVM method has better diagnosis effect to related methods.
