Lifetime of Diesel Locomotive With Respect To Degradation Data

Abstract

The working time of a diesel engine reflects its technical states to a certain extent. Although, even the same kind of engine with the same kind of working hours exhibits different technical states in different kinds of working environments. At the same time, it is quite complicated to derive the complete life data or physical failure mechanism required by traditional life prediction method. In terms of the above cases, a model of diesel engine life prediction based on degradation data and neural networks is developed in the paper. First of all, the degradation parameters are selected and the sample data is to be standardized. After that the principal component analysis method is to be used to simplify different parameters to an extensive parameter. The interpolation method is applied to obtain the parameter’s time series data as the train data of neural network. At last, the life estimation model of the engine based on neural network is established.