Evaluation of Spare Parts Scheme Based on BP Neural Network

Spare parts are one of the most important material resources to ensure the equipment works normally.. Equipment availability and spare parts satisfaction rate are the evaluation indicators of spare parts scheme. Aiming at the problem of the mean time between failures of parts given by manufacturer is not accurate, an evaluation model of spare parts for naval vessels based on BP neural network model is proposed. Firstly, training and testing data are generated by availability simulation model and spare parts satisfaction rate simulation model; then, the parameters of BP neural network model are trained by training data; finally, the prediction results of BP neural network model are tested by test data. Case results show that: The predicted results of the BP neural network model of the two evaluation indicators are consistent with the actual value trend; when the spare parts fill rate is higher than 0.8, the maximum error between the predicted value and the actual value of the BP neural network model is not more than 0.03. The research can be used as a reference for the decision-making of spare parts allocation evaluation of warships or aircraft.