Research on Reciprocating diesel engines fault diagnosis based on adaptive genetic algorithm optimization

Abstract

The fault diagnosis of marine diesel engine is studied in this paper. The simulation software GT-Suite is used to build the whole engine model, and the diagnosis framework of marine diesel engine based on adaptive genetic algorithm is constructed. Firstly, different faults in the working process of the diesel engine are set by using simulation software, corresponding operation data are derived, and the data are subjected to feature selection to obtain a minimum fault feature set; Then, a diesel engine fault classification model is built based on Elman neural network, and the improved genetic algorithm is used to optimize the weights and thresholds of Elman neural network, so as to realize the efficient and accurate classification of diesel engine faults. Finally, the processed data set is input into the adaptive genetic algorithm optimization. Based on Elman neural network, the fault diagnosis of marine diesel engine is realized. The experiment proves that, The method has high fault accuracy and small error, is not easy to fall into the local minimum, and can effectively diagnose the faults occurring in the working process of the marine diesel engine.