Fault Diagnosis of Aircraft Power Generation System Based on ISSA-SVM

Addressing the challenge of dealing effectively with multiple variables and complex nonlinear relationships in aircraft power generation systems, which are typically difficult to handle using traditional linear methods, this paper presents an enhanced fault diagnosis method. The method combines the squirrel search algorithm and support vector machine (ISSA-SVM) to improve the accuracy of fault classification. The ISSA is enhanced by incorporating the periodic variational perturbation formula, optimizing the performance of the fault classification model. To validate the effectiveness of the proposed method, MATLAB/Simulink simulation experiments are performed using a fault dataset of the power generation system. The experimental results demonstrate that the diagnostic accuracy of the proposed method is significantly high.