Fault Diagnosis Of The Marine Diesel Generator Set Based On Artificial Neural Network

The Marine power station is motive heart of the whole ships system, and which supplies power for the system. Gradually with the high performance and the structure complication complex of the modern ship system, the diesel generator set which constitutes marine power station also increasingly develops toward large and high speed and precision. With the work performance continuously improving, the degree of automating is higher. On the one hand it will rise to the rate of production, rise the electric power quantity of the ships system, lower the maintaining cost and energy consuming; But on the other hand, the problem brought is that once some part or some a link among them go wrong, which usually will make the whole ships system in paralyze, so it directly or indirectly results in huge economy loss, even results in the key equipments damage, and endangers people safety. Therefore, how to quickly judge the reason of the fault and availably eliminate the faults, and guarantee the ships continuing the normal voyage has special important meanings.Under this background, the topic is mainly focus on fault diagnosis of the marine power station. In order to obtain the sample sets which have the typical characteristic, it is separately set up the model of the thermodynamics work process of the diesel engine and set up the generator and the excitation system of the generator. By obtaining the characteristic value of the diesel engine and generators at normal work and fault state , processing the characteristic value , making the value the input sample sets of the nerve network, designing to the output sample, build up the BP and ELMAN Neural Network, using the data training the nerve network, the nerve network has been of the diagnosis function. The diagnosis of the fault or latent fault of the power station is realized, and safe movement of the ships is guaranteed.