Liangyu Fei

Current research focuses primarily on studying the heat dissipation modes of drive devices in various configurations to optimise the energy consumption of cooling systems in new energy vehicles and improve their driving range; however, the overall power consumption is not yet fully grasped or controlled. Grounded in heat transfer theory, this study simulates the losses of the IGBT module under varying phase current, output voltage frequency, gate on–off resistance and heatsink temperature using IPOSIM. It proposes a method to predict losses and temperature rise through the motor’s input current and output speed. Therefore, an experimental platform for the heat dissipation system of a pole‐changing motor driver is set up. In addition, the theoretical relationship between IGBT loss and power consumption of the cooling pump and fan is analysed. An optimal loss model is developed, and the solution with minimal loss is found using the sparrow search algorithm (SSA), polynomial curve fitting (PCF) is used to verify its overall performance. For further verification, the traditional heatsink cooling water inlet temperature of 65°C is used as a comparative example. The results demonstrated that, with the new optimisation method, total loss can be reduced to varying degrees.

This study introduces an Improved Sparrow Search Algorithm (ISSA) to address the challenges of Machine Learning Hyperparameter Optimization (HPO) and efficient modeling of Electric Coolant Pumps (ECP) in electric vehicles. By integrating Lévy flight and Bernoulli mapping, ISSA enhances global search capabilities and ability to escapes from local optima. Experimental validations across 12 benchmark functions demonstrate ISSA outperforming the standard Sparrow Search Algorithm (SSA) and other advanced optimization algorithms in terms of exploratory and exploitative effectiveness. Specifically, ISSA proves exceptionally effective in autonomously handling the HPO for three typical machine learning (ML) algorithms, demonstrating superior performance over SSA and random search methods. A novel ISSA-ML surrogate model for ECP, incorporating structural and operational parameters, showcases significant improvements in predictive accuracy and robustness over traditional polynomial regression and ML models under conventional HPO methods. Furthermore, the application of this surrogate model in multi-objective optimization design for ECPs significantly reduces development time and computational costs, offering a streamlined and cost-effective solution for optimizing ECP performance. This study highlights potential future research directions, including the integration of other ML enhancements and the inclusion of more comprehensive feature parameters, to further improve the model's universality and applicability.