Fault Diagnosis of Vacuum Leakage in Intake System of Automobile Engine Based on K-Means++ and RBF

To enhance the efficiency of fault diagnosis for automobile engines, this study employs an improved K-means algorithm to determine the number of hidden layer neurons, center values, and other related parameters of the RBF neural network classification model. Engine exhaust data from different states under hot idle conditions were used as the diagnostic basis. The model was applied to diagnose vacuum leaks in the intake system of automobile engines and compared with traditional RBF neural networks. The results show that the intelligent diagnostic method designed in this paper achieves an accuracy of 96.67% on the test set, which is superior to the traditional RBF neural network classification method.