Dual-Optimized Support Vector Machine for Fault Diagnosis of Rotating Equipment Based on CM-GA

Since the rotary machinery equipment is the fundamental and crucial part of mechanical equipment, the fault diagnosis of rotary machinery has become a particularly important issue in mechanical engineering. This paper adopted a genetic algorithm (GA) based on the cloud model (CM) to optimize traditional SVM for fault diagnosis of rotating machinery with dual optimization levels. The first optimization level is to use the CM to optimize crossover operators in GA (CM-GA), so as to obtain a faster search process and achieve more effective optimization results. The second optimization level is using CM-GA to optimize SVM. In addition, we have proposed an optimized framework of SVM model based on CM-GA for fault diagnosis of rotating machinery. In the end we used two kinds of rolling bearing fault database for experiments and the diagnosis results have proved the validity and feasibility of the proposed method.