Prediction of Maintenance Spare Parts Based on BP Neural Network Optimized by Improved Sparrow Search Algorithm

In this paper, for the intermittent sequence prediction of equipment maintenance spare parts demand, the data is first processed by digital modulation technology and time aggregation method, so that it can be used for BP neural network prediction. Tent chaotic sequence and Gaussian mutation strategy are introduced into the initial population distribution and fitness function of sparrows, and a maintenance spare parts prediction method based on improved sparrow search algorithm optimized BP neural network (CGSSA -BP) is proposed. Improve the accuracy and stability of neural network for interval time series forecasting. The method is compared with the SSA-BP neural network model and the traditional BP neural network model. The prediction accuracy of the improved neural network prediction model is better than other prediction models, and the prediction accuracy is in line with expectations, which can provide a basis for the maintenance of spare parts.