Fault diagnosis of marine main engine based on BP neural network

The fault diagnosis of a marine's main engine is a significant but complicated problem, and artificial intelligence has been considered in this field for decades. This paper describes a fault diagnosis method for main engine based on BP neural network with the system fault classified into hierarchies according to fault tree analysis. Sample data of supercharger's fault is collected and used to train and test the BP network. The simulation results illustrate the effectiveness of the proposed approach.