Prediction of Spare Parts Loss of Railway Dedicated Base Station Based on Grey Markov

To ensure the stability and reliability of railway mobile communication system, and solve the problem of spare parts management and main board supply of railway dedicated base station equipment, it is necessary to propose a suitable loss prediction method for railway base station equipment spare parts. Through investigation and analysis of the loss law of the base station subsystem equipment on typical lines within the jurisdiction of various railway bureaus, a cumulative operation is performed on the original data to reduce its randomness. Then the improved grey Markov prediction model based on grey GM(l,l) model is constructed, that is, the grey GM(l,l) model is used to predict the cumulative loss of the equipment, and the residual difference between the predicted value of grey GM(l,l) and the real value is corrected by Markov chain, so as to realize the loss prediction analysis of the railway dedicated base station equipment. Besides, the corresponding spare parts management configuration principle is proposed and the algorithm is implemented by software. The prediction results show that, taking a fan on a certain line in the railway bureau A as an example, increasing the accumulation times of the original loss data can improve the accuracy of the grey GM(l,l) model. And after residual correction, the average absolute error of fitting of the grey Markov model can be reduced by 0.992, and the prediction accuracy can be increased by 0.492. It shows the improvement of the proposed model to solve the problem of high fluctuation of historical loss data of equipment. In addition, by designing a spare parts prediction software system, the applicability of the algorithm is verified using the base station subsystem equipment on the lines under the jurisdiction of railway bureaus A, B, and C as examples. The research results provide a reference for the loss prediction of spare parts of railway dedicated equipment spare parts, effectively improve the accuracy of spare parts demand prediction, and fully guarantee the continuity and stability of railway communication system.