An abnormal temperature rise early warning method for the dynamic process of electric vehicle motors based on Autoregressive Integrated Moving Average Model

To address the lack of consideration for load rate fluctuations in motor temperature rise research, which led to inaccurate early warnings of thermal health states, this paper presents an ARIMA-based anomaly early warning method for the temperature rise in the dynamic process of electric vehicle motors. Taking an 11kw asynchronous motor as an example, the finite element method is adopted to simulate the motor temperature field, and an ARIMA model based on the time series is constructed. For the application scenarios where the load rate of electric vehicle motors changes continuously, the rather extreme change trend of the motor temperature rise is obtained. By integrating the predicted change trend with the equivalent conversion curve, the accurate diagnosis of the motor thermal health state is accomplished, providing theoretical support for thermal health diagnosis and early warning of electric vehicle motors in scenarios with frequent load rate fluctuations.