Study on Diesel Engine Fault Diagnosis Based on Integration of Bayesian and Genetic Neural Network Method
The characteristic vector of cylinder vibration signal is extracted by wavelet packet decomposition. The factor of selection is proposed to take adaptive integration on basis of improved super parent one dependence estimator Bayesian method and back propagation genetic algorithm neural network method. Experimental results on WD615 diesel engine showed that the method has high accuracy rate of detection.
X. Wang et al., "Study on Diesel Engine Fault Diagnosis Based on Integration of Bayesian and Genetic Neural Network Method", Advanced Materials Research, Vols. 311-313, pp. 2277-2281, 2011