Demand forecast of equipment spare parts based on EEMD-LSTM

Abstract

Equipment spare parts play an important role in the normal operation of factory equipment. The accuracy of spare parts demand prediction can help improve the factory inventory strategy. Moreover, the demand for spare parts is highly unstable, and the traditional time series model is difficult to obtain good prediction results, Therefore, aiming at the above problems, a combined prediction model based on Ensemble Empirical Mode Decomposition(EEMD) and Long-Short Term Memory(LSTM) neural network is proposed. The Ensemble Empirical Mode Decomposition is used to decompose the spare parts demand data sequence into several relatively stable Intrinsic Mode Functions (IMF), and then the Long-Short Term Memory neural network is used to predict each Intrinsic Mode Functions. Finally, the prediction results of eigenmode components are reconstructed to obtain the final prediction results. Experiments show that compared with ARIMA model, exponential smoothing method and traditional Long-Short Term Memory neural network model, this method can effectively reduce the impact of the instability of spare parts demand on the prediction results and improve the accuracy of the prediction results.