Advances in Electric Vehicle Technology: Remaining Useful Life Interval Prediction

Strategic Insights -

Researchers at North University of China have made a significant breakthrough in predicting the remaining useful life of lithium-ion batteries (LiBs) in electric vehicles. The study focuses on developing a novel method for accurately predicting the lifespan of LiBs using periodic time series and trend filtering segmentation. This innovation has the potential to revolutionize the electric vehicle industry by enabling efficient and cost-effective battery management.

Key Takeaways:

  • The research introduced a construction method for periodic time series to address issues related to insufficient training data and smooth degradation in RUL interval prediction.
  • The new method combines variational mode decomposition (VMD) and gated recurrent unit (GRU) to create a robust RUL interval prediction model.
  • The effectiveness of the proposed method was verified using the CALCE battery dataset and NCA battery dataset.
  • The study aimed to enhance the accuracy of RUL prediction, which is critical for optimizing the performance and prolonging the lifespan of LiBs.
  • Authors Chunsheng Cui, Guangshu Xia, Chenyu Jia, and Jie Wen contributed to the research.
  • The study was supported by the Natural Science Foundation of Shanxi Province.
  • The research was published in the World Electric Vehicle Journal, Volume 16, Issue 7, 2025.

Statistics:

  • The research used a dataset from the CALCE battery and NCA battery to test the effectiveness of the proposed method.
  • The new construction method for periodic time series was applied to the degradation data of LiBs to improve RUL prediction accuracy.
  • The study reported that the method demonstrated improved performance compared to existing RUL interval prediction methods.
  • The research highlighted the importance of accurate RUL prediction in optimizing battery performance and extending the lifespan of LiBs.

Sources:

  • Cui, C., et al. (2025). Remaining Useful Life Interval Prediction for Lithium-Ion Batteries via Periodic Time Series and Trend Filtering Segmentation-Based Fuzzy Information Granulation. World Electric Vehicle Journal, 16(7), 356.
  • North University of China. (2025). Research on Remaining Useful Life Interval Prediction for Lithium-Ion Batteries. Journal of Transportation, 83, 2025.