An improved SVM classifier based on multi-verse optimizer for fault diagnosis of autopilot

With regard to the lack of the sample of faults in the test of autopilot, a model of fault diagnosis based on support vector machine (SVM) optimized by multi-verse optimizer (MVO) is put forward. SVM does well in solving the few samples and nonlinear problem, which is suitable for the fault diagnosis of autopilot. To solve the overfitting and underfitting resulted from the improper parameters of SVM, multi-verse optimizer was applied to optimizing the parameters of SVM. By this way, a model of fault diagnosis with better performance was built. The simulation experiment results show that the accuracy of SVM based on MVO can achieve 98.3673% using 50 training samples. However, the accuracy of genetic algorithm (GA)-SVM achieves 91.0204% and the accuracy of SVM based on gravitational search algorithm (GSA) achieves 91.6327%. The simulation experiment results shows that SVM based on MVO has much better performance than others.