Combined Fuzzy Time Series Prediction Method for Fault Prediction of EML Pulse Capacitors

Abstract

Metallized film capacitors are an important part of the electromagnetic rail launch system. It is of great significance to predict its failure. In engineering, the failure law of capacitor is obtained by cyclic pulse accelerated life test of capacitor module with a small number of samples, and is used to predict the actual failure of capacitor in electromagnetic launch (EML) system. This method has the following problems: first, there are few samples of capacitor in life test at affordable cost, which cannot include all capacitor characteristics; second, the time interval of actual EML missions and the voltage of the capacitors are both changing and inconsistent with the conditions used in the life test; third, the statistical law is affected by the measurement and other errors. For these reasons, the prediction accuracy of the existing methods is limited. In this article, a new combined time series prediction method is proposed by using the high-order fuzzy time series prediction theory. Based on the capacitor used in the prototype of an electromagnetic railgun, the life test data of 20 pulse capacitors are used as the prior knowledge input, and the prediction model is obtained. Five groups of capacitor life test data simulating real launch conditions are used as test data to verify that the prediction accuracy of the proposed method is better than that of the traditional method, and the prediction accuracy of capacitor capacitance, which made by different processes, is much higher than that of the traditional method.