Visualized Feature Extraction Method of Diesel Engine Based on Texture Enhanced Block NMF (TE-BNMF)

Diesel engine is a kind of power machinery equipment and widely used in industrial and agricultural production. Aiming at the difficulty in fault feature extraction of diesel engine, a visualized method based on the texture enhanced block non-negative matrix factorization (TE-BNMF) is proposed. The method firstly performs time-frequency analysis on the collected cylinder head vibration signals; then the local binary pattern (LBP) method is used to re-encode the vibration spectrum based on the gray distribution. After that, we use block non-negative matrix factorization algorithm (BNMF) to directly extract the feature parameters of the generated local binary feature map. By using a classifier to perform pattern recognition on the above-mentioned coding matrix, the automatic diagnosis of diesel engine faults is achieved. This method was applied to the fault diagnosis of 6 typical operating conditions of diesel engines, which can get high and stable fault recognition accuracy. The experiments show that the TE-BNMF diesel engine visualized fault diagnosis method proposed in this paper can discovery rich information contained in the spectrum image of diesel engine vibration deeply and diagnose the valve clearance fault of the diesel engine adaptively.