Fault diagnosis for the ship electric propulsion system

According to the actual condition of the ship electric propulsion system, the fault tree was built via analyzing the fault characteristics and reasons of the components of the system. The analytic hierarchy process was used to calculate the weight of the fault reasons and formed a corresponding intelligent fault tree. Some rules which were used to build the knowledge base of fault diagnosis expert system in Access could be extracted from the intelligent tree. The fault diagnosis system made use of the width-first search strategy and forward reasoning control strategy. The BP neural networks algorithm was used to make up the lack of a learning disability. The system could help the workers to diagnose and repair the faults of the marine electric propulsion system more quickly and reduce the cost.