Intelligent Diesel Engine Fault Diagnosis Method Based on Time-Frequency-Nonconvex Robust Principal Component Analysis

Intelligent fault diagnosis is an effective method to ensure the continuous and efficient operation of machinery. In practical industrial applications, noise is unavoidable, which leads to serious degradation of the performance of intelligent fault diagnosis methods. Given this, an intelligent diesel engine fault diagnosis method based on Time-Frequency Distribution (TFD) and Non-Convex Robust Principal Component Analysis (NCRPCA) method is studied in this paper, aiming to provide a way to accurately diagnose faults in a noisy environment. Firstly, the original vibration signals were analyzed to obtain the time-frequency training matrix, and then the NCRPCA method was used to automatically extract the fault features. And the Support Vector Machine (SVM) method is used to identify the fault. The method is trained directly on the original dataset and has strong adaptability to noise. The method is applied to the diesel engine fault diagnosis experiment, and the results show that the method is effective for the performance evaluation of diesel valve clearance fault, and has high fault diagnosis accuracy.