Sign in Subscribe
Machine learning

Temperature Estimation of Vehicle Electric Drive System Based On Machine Learning Algorithm

Strategic Insights

— 1 min read

Researchers at the Chongqing University of Technology have developed a new machine learning algorithm to estimate the temperature of key components in a vehicle's electric drive system (EDS). The high temperatures of the EDS can affect the performance and reliability of the system, making accurate temperature estimation crucial. The algorithm, which combines particle swarm optimization (PSO) and back propagation neural network (BPNN), was found to be more accurate than traditional BP estimation methods.

Key Takeaways:

  • The proposed EDS temperature estimation method is based on PSO-BP and can accurately estimate the temperature of key components, including motor winding, rotor, IGBT, and motor shaft gear.
  • The results show that the PSO-BP estimation is more accurate than the BP estimation, with R2 values of 0.994, 0.995, 0.990, and 0.988 for the four key components.
  • The mean absolute error (MAE) values for PSO-BP are 0.731, 0.491, 0.489, and 0.343, while the mean square error (MSE) values are 1.049, 0.479, 0.400, and 0.381.
  • The researchers conclude that the proposed method is more accurate and reliable than traditional methods, making it suitable for practical applications.
  • The study was funded by the Science and Technology Innovation Key R&D Program of Chongqing, the Youth project of science and technology research program of Chongqing Education Commission of China, the Chongqing Graduate Education Teaching Reform Research Project, and the Chongqing University of Technology.

Statistics:

  • R2 values for PSO-BP estimation: 0.994, 0.995, 0.990, and 0.988 for motor winding, rotor, IGBT, and motor shaft gear, respectively.
  • Mean absolute error (MAE) values for PSO-BP: 0.731, 0.491, 0.489, and 0.343 for motor winding, rotor, IGBT, and motor shaft gear, respectively.
  • Mean square error (MSE) values for PSO-BP: 1.049, 0.479, 0.400, and 0.381 for motor winding, rotor, IGBT, and motor shaft gear, respectively.

Sources:

  • NewsRx. New Machine Learning Study Results from Chongqing University of Technology Described (Temperature Estimation of Vehicle Electric Drive System Based On Machine Learning Algorithm). Journal of Engineering. June 23, 2025; p 1615.
  • Temperature Estimation of Vehicle Electric Drive System Based On Machine Learning Algorithm. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, 2025.

Read more