The Research of the Intelligent Fault Diagnosis Optimized by ACA for Marine Diesel Engine

The marine diesel engine has the important function to guarantee the marine security and reliability. It is a strong coupling relationship’s system with multi-fault attributes. In this paper an advanced method of intelligent fault diagnosis based on fuzzy neural network (FNN) optimized and trained by ant colony algorithm (ACA) is proposed. The model, structure and parameters learning of intelligent fault diagnosis based on FNN were described concretely. The weight and the threshold value of this FNN are optimized and trained by the ant colony optimization algorithm. By simulation that has been carried out to evaluate the performance of proposed method and to compare with conventional FNN fault diagnosis method for this marine diesel engine’s combustion system, the results show good quick convergence performance. The knowledge expression and the precision of fault diagnosis also can be improved effectively. Therefore, this method has the good application prospects in other similar system.