Temperature Accurate Prediction Method of Electric Drive Transmission Considering Spatio-Temporal Correlation Characteristics under High Speed and Heavy Load Working Conditions

Accurate prediction temperature variation of electric drive transmission (EDT) can effectively monitor its abnormal temperature rise that may occur under high speed and heavy load working conditions, so as to ensure the vehicles’ safe operation. In this paper, combined with real temperature and input/output characteristic data collected from EDT test platform under different working conditions, a spatio-temporal relationship dynamic graph convolution neural network based on least square method (OLS-DRGCN) for temperature prediction is proposed. Firstly, OLS is used to estimate the EDT’s internal temperature based on partial sensor information as the input of OLS-DRGCN. Secondly, the spatial dependence relationship of each temperature node is dynamically learned through node embedding and the dynamic thermal network topology of EDT is constructed. Meanwhile, the timing rule of each temperature node is obtained through the gated recurrent unit. The analysis results show that the proposed OLS-DRGCN can effectively predict the temperature changes in the future period based on only a few sensor information when the predicted time is 30s, the mean absolute error of OLS-DRGCN can be controlled within 1.07°C under three different working conditions.