Research on Safety Identification of Key Components of Maglev Train Based on Multi-layer Perceptron

Abstract

AbstractConverter is the key component of maglev train, and aluminum electrolytic capacitor is one of the vulnerable components of converter. The bus aluminum electrolytic capacitor in the converter is taken as the research object. Based on the analysis of the basic characteristics and aging mechanism of aluminum electrolytic capacitor, the research on the parameter identification of aluminum electrolytic capacitor is carried out. Firstly, the basic characteristics, aging mechanism and influencing factors of aluminum electrolytic capacitors are introduced, with emphasis on the effects of ripple current and ambient temperature on the aging of aluminum electrolytic capacitors; Secondly, according to the equivalent model of aluminum electrolytic capacitor, an experimental platform for bus capacitance parameter identification is built, including hardware system and software system; Thirdly, the main parameters are extracted through NI USB-6002 data acquisition card, and the data monitoring system based on Labview is designed; Finally, a capacitance parameter identification system based on five-fold cross multi-layer perceptron is constructed. The ripple current, ripple voltage, ambient temperature and capacitance surface temperature of the capacitance are taken as the input of the neural network, and the capacitance value and equivalent series resistance value of the capacitance are taken as the output of the neural network to realize the parameter identification of the capacitance. Relevant experiments show that the method is feasible, effective, simple and practical. This method also has reference significance and practical application value for the safety identification of other power electronic equipment.KeywordsConverterAluminum electrolytic capacitorAgingParameter identificationMultilayer perceptron