Research on prediction model of quantitative relationship of pressure attenuation of hydrogen fuel cell air compressor based on artificial neural network

Abstract This thesis considers the field of the pressure attenuation of hydrogen fuel cell air compressors as the main subject of its study. Traditional methods usually model the prediction of pressure attenuation based on a durability test or physical model, which is costly and time-consuming. Based on the method of artificial neural network (ANN), this paper establishes a prediction model of the quantitative relationship of outlet pressure attenuation of hydrogen fuel cell air compressors. A neural network is used to capture the nonlinear relationship of outlet pressure of air compressors, and the prediction results of the model are analyzed and explained to explore the attenuation process of outlet pressure of hydrogen fuel cell air compressors. The comparison between the actual test data and the predicted data through the endurance test of the air compressor shows that the prediction ability of the model is good, and the correlation of the regression analysis results of the prediction model is above 0.99, which can be used to predict the quantitative relationship of outlet pressure attenuation of hydrogen fuel cell air compressor.