Fault Diagnosis for Diesel Engines Based on Discrete Hidden Markov Model

Fault diagnosis based on Principal Component Analysis (PCA) and Discrete Hidden Markov Model (DHMM) for engine are studied. First, the vibration signal feature extraction from the diesel engine is realized by PCA; next, the vibration signal feature extraction algorithm is designed; then DHMM is applied for fault diagnosis; furthermore, a fault classifier based on DHMM with diagnostic databases is developed; and, finally, the fault diagnosis strategies of diesal vibration signal is conceived. The practical application results showed that the method proposed in this paper is feasible for diesel engine fault diagnosis that can be achieved with highly accuracy.