Sign in Subscribe
Batteries

Accurate Prediction of Heat Generation Rate in Lithium-Ion Batteries Using Machine Learning

Strategic Insights

— 1 min read

Research conducted by the Indian Institute for Technology has made a significant breakthrough in predicting the heat generation rate (HGR) in lithium-ion batteries, a critical factor in ensuring thermal safety and performance in electric vehicles (EVs). A team of researchers developed a machine learning (ML)-based approach to estimate HGR using experimentally measured data from an isothermal battery calorimeter. The study presents a reliable correlation for HGR prediction under diverse operating conditions, providing a significant step towards real-time thermal management of EVs.

Key Takeaways:

  • The researchers developed three ML models: Feedforward Neural Network (FNN), Long Short-Term Memory (LSTM), and Support Vector Machine (SVM) for predicting HGR in lithium-ion batteries.
  • The SVM model demonstrated the highest accuracy, achieving a mean absolute error (MAE) of 0.0063, root mean square error (RMSE) of 0.0112, and R2 of 0.9994.
  • The researchers used symbolic regression to enhance interpretability and reduce complexity, resulting in a compact and accurate correlation for HGR prediction.
  • The final correlation is expressed as a function of C-rate, current, Depth of Discharge (DOD), and temperature.
  • The study provides a reliable estimation of HGR across 10°C-60°C and 0.5C-6C operating conditions.
  • Jishnu Bhattacharya, the lead researcher, emphasized the importance of accurate HGR prediction for ensuring thermal safety and performance in EVs.
  • The study received financial support from the Ministry of Human Resource Development (MHRD), Government of India.

Statistics:

  • Mean absolute error (MAE) of 0.0063
  • Root mean square error (RMSE) of 0.0112
  • R2 correlation coefficient of 0.9994
  • Experimentally measured data points from 0.5C to 6C and ambient temperatures from 10°C to 60°C
  • The study used a battery calorimeter to measure HGR in lithium-ion batteries.

Sources:

  • NewsRx. Research Conducted at Indian Institute for Technology Has Provided New Information about Machine Learning (Developing an Accurate Correlation for Estimating Heat Generation Rate By an 18650 Lithium Iron Phosphate Cell Through a Machine Learning ...). Journal of Engineering.
  • Developing an Accurate Correlation for Estimating Heat Generation Rate By an 18650 Lithium Iron Phosphate Cell Through a Machine Learning Model Trained On Experimental Measurements. Energy, 2025; 334.

Read more