Forecasting the need for spare parts of machine hydraulic systems using a neural network

The paper considers the possibility of using artificial neural networks to predict the need for spare parts for machine hydraulic systems. The analysis of the distribution of faults is carried out in relation to ground transport and technological means, and the results of the analysis of existing traditional methods of reservation are presented. An approach to training an artificial neural network based on the multilayer perceptron model is proposed. The implementation of a variant of retraining an artificial neural network of the multilayer perceptron type for predicting the need for spare parts for machine hydraulic systems based on small volumes of input data for the past years using modern Data Mining technology on the 1C: Enterprise platform is presented. The results of the study can be useful for optimizing spare parts stocks and increasing the efficiency of machine hydraulic systems.