Hybrid Intelligent Fault Diagnosis Based on Granular Computing

To solve the problem of lacking hybrid modes and common algorithms in hybrid intelligent diagnosis, this paper presents a new approach to hybrid intelligent fault diagnosis of the mechanical equipment based on granular computing. The hybrid intelligent diagnosis model based on neighborhood rough set is constructed in different granular levels, and the results of support vector machines (SVMS) and artificial neural network (ANN) in granular levels are combined by criterion matrix algorithm as output of hybrid intelligent diagnosis. Finally, the proposed model is applied to fault diagnosis in roller bearings of high-speed locomotive. The applied results show that the classification accuracy of hybrid model reaches to 97.96%, which is 8.49% and 39.12% higher than the classification accuracy of SVMS and ANN respectively. It shows that the proposed model as a new common algorithm can reliably recognize different fault categories and effectively enhance robustness of the hybrid intelligent diagnosis model.