Optimizing Lithium-Ion Battery Discharge Capacity Prediction Using Light GBM and Explainable AI (XAI) Framework

Maithili Shailesh Andhare; Sarange Shreepad Marotrao; Senthil Kumar A; Dileep Reddy Bolla; Suptasish Sarkar; R. Senthamil Selvan

doi:10.63278/10.63278/mme.v31.1

Authors

Maithili Shailesh Andhare Department of Electronics and telecommunication and engineering, PCCOE&R, India
Sarange Shreepad Marotrao Department of Mechanical Engineering, Ajeenkya D Y Patil School of Engineering, India
Senthil Kumar A Department of Computer Science and engineering, School of engineering, Dayananda Sagar University, India
Dileep Reddy Bolla Department of Computer Science and engineering, Nitte Meenakshi Institute of Technology, India
Suptasish Sarkar Department of Electrical Engineering, Brainware University, India
R. Senthamil Selvan Department of Electronics and Communication Engineering, Annamacharya Institute of Technology and Sciences(Autonomous), India

DOI:

https://doi.org/10.63278/10.63278/mme.v31.1

Keywords:

Lithium-Ion Batteries (LiBs), Machine Learning, Explainable Artificial Intelligence (XAI), Battery Management System (BMS), State of Health (SoH) Estimation.

Abstract

Improving the lifetime and cost-effectiveness of energy storage systems depends on exact control of lithium-ion battery (LiB) capacity. To estimate LiB discharge capacity, this work uses AdaBoost, gradient boost, XGBoost, LightGBM, Catboost, as well as ensemble learning among other machine learning models. Mean absolute error (the MAE), mean squared error (the MSE), along with R-squared values all were used to assess model performance. LightGBM had the best results among the models via the lowest MAE (0.104) along with MSE (0.018), in addition to the greatest R-squared value (0.888), therefore proving better prediction accuracy. Closely in performance were gradient boosting and XGBoost. The success of the combined model implies that including many models could improve general forecast accuracy. Furthermore, the impact of important parameters, like temperature, cycle index, voltage, as well as current, on model predictions was investigated using explainable artificial intelligence (XAI, which) techniques more especially, SHAP values. Results show that discharge capacity is very much influenced by temperature. This paper emphasizes the possibilities of machine learning as well XAI in LiB management optimization, therefore supporting more sustainable and effective energy storage systems.

References

Oyucu, Saadin, et al. "Optimizing Lithium-ion battery performance: Integrating machine learning and explainable AI for enhanced energy management." Sustainability 16.11 (2024): 4755.

Manimegalai, R., et al. "Optimizing Battery Charge Prediction Accuracy Utilizing Machine Learning Methods." Metallurgical and Materials Engineering 31.1 (2025): 238-248.

Faraji Niri, Mona, et al. "A review of the applications of explainable machine learning for lithium–ion batteries: From production to state and performance estimation." Energies 16.17 (2023): 6360.

Shah, Jalpa, and Sneha Tiwari. "Enhanced State of Charge Estimation for Lithium Ion Batteries with Explainable AI." 2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT). IEEE, 2024.

Jafari, Sadiqa, and Yung Cheol Byun. "Accurate remaining useful life estimation of lithium-ion batteries in electric vehicles based on a measurable feature-based approach with explainable AI." The Journal of Supercomputing 80.4 (2024): 4707-4732.

Mohanty, Prasant Kumar, et al. "Leveraging Generative & Explainable AI for Electric Vehicle Energy towards Sustainable, Consumer-Centric Transportation." IEEE Access (2024).

Mewada, Shivlal, et al. "Smart diagnostic expert system for defect in forging process by using machine learning process." Journal of Nanomaterials 2022.1 (2022): 2567194.

Patro, Pramoda, et al. "A hybrid approach estimates the real-time health state of a bearing by accelerated degradation tests, Machine learning." 2021 Second International Conference on Smart Technologies in Computing, Electrical and Electronics (ICSTCEE). IEEE, 2021.

Sassi, Mounira, and Hanen Idoudi. "A PSO-Optimized Neural Network and ABC Feature Selection Approach with eXplainable Artificial Intelligence (XAI) for Natural Disaster Prediction." Recent Advances in Computer Science and Communications (2024).

Korkmaz, Mehmet. "SoC estimation of lithium-ion batteries based on machine learning techniques: A filtered approach." Journal of Energy Storage 72 (2023): 108268.

Saarela, Mirka, and Vili Podgorelec. "Recent applications of Explainable AI (XAI): A systematic literature review." Applied Sciences 14.19 (2024): 8884.

Wong, Andrew Jun Yao, et al. "Battery materials discovery and smart grid management using machine learning." Batteries & Supercaps 5.11 (2022): e202200309.

BramahHazela, et al. "Machine Learning: Supervised Algorithms to Determine the Defect in High‐Precision Foundry Operation." Journal of Nanomaterials 2022.1 (2022): 1732441.

Çetinus, Büşra, et al. "The Role of Machine Learning in Enhancing Battery Management for Drone Operations: A Focus on SoH Prediction Using Ensemble Learning Techniques." Batteries 10.10 (2024): 371.

Zhang, Xinfang, et al. "A review of machine learning approaches for electric vehicle energy consumption modelling in urban transportation." Renewable Energy 234 (2024): 121243.

Chadaga, Krishnaraj, et al. "An explainable decision support framework for differential diagnosis between mild COVID-19 and other similar influenzas." IEEE Access (2024).

Cummins, Logan, et al. "Explainable predictive maintenance: A survey of current methods, challenges and opportunities." IEEE access (2024).

Nguyen, Duc An, Khanh TP Nguyen, and Kamal Medjaher. "Enhancing Trustworthiness in AI-Based Prognostics: A Comprehensive Review of Explainable AI for PHM." Artificial Intelligence for Safety and Reliability Engineering: Methods, Applications, and Challenges (2024): 101-136.

Rane, Nitin Liladhar, Saurabh P. Choudhary, and Jayesh Rane. "Artificial Intelligence and machine learning in renewable and sustainable energy strategies: A critical review and future perspectives." Partners Universal International Innovation Journal 2.3 (2024): 80-102.

Senarathne, Lakmini Rangana, Gaurav Nanda, and Raji Sundararajan. "Identifying salient features of cooling energy usage of commercial buildings using explainable artificial intelligence." Advances in Building Energy Research 17.5 (2023): 489-506.

Mariappan, Ramasamy. "Extensive Review of Literature on Explainable AI (XAI) in Healthcare Applications." Recent Advances in Computer Science and Communications 18.1 (2025): E200324228159.

Arun, Vanya, et al. "AI Based Prediction Algorithms for Enhancing the Waste Management System: A Comparative Analysis." E3S Web of Conferences. Vol. 552. EDP Sciences, 2024.

Elshaarawy, Mohamed Kamel, and Abdelrahman Kamal Hamed. "Machine learning and interactive GUI for estimating roller length of hydraulic jumps." Neural Computing and Applications (2024): 1-30.

Eagon, Matthew J., et al. "Neural network-based electric vehicle range prediction for smart charging optimization." Journal of Dynamic Systems, Measurement, and Control 144.1 (2022): 011110.

Zeng, Fanlong, Jintao Wang, and Chaoyan Zeng. "An optimized machine learning framework for predicting and interpreting corporate ESG greenwashing behavior." PloS one 20.3 (2025): e0316287.