Publication Type : Conference Proceedings
Publisher : IEEE
Source : 2025 International Conference on Machine Learning and Autonomous Systems (ICMLAS)
Url : https://doi.org/10.1109/icmlas64557.2025.10967909
Campus : Chennai
School : School of Engineering
Year : 2025
Abstract : In this paper, the battery life using Machine Learning Algorithms was predicted using MATLAB Software. Early and accurate predictions are important for electric vehicles, electronics, and energy storage. Traditional methods need a lot of real-time data, leading to inefficiencies. This article uses machine learning to predict battery performance early, based on factors like temperature, voltage, and current during initial charge-discharge cycles. Mechanisms such as Gradient Boosting, Random Forest, SVM, as well as Neural Networks, are tested with historical battery data to find patterns of degradation. The study also explores how well these models work for different types of batteries.
Cite this Research Publication : Dasari Naga Vinod, N Kapileswar, Judy Simon, Aarthi Elaveini M, Phani Kumar Polasi, Enhancing Battery Durability: Early Life Cycle Prediction Through Machine Learning, 2025 International Conference on Machine Learning and Autonomous Systems (ICMLAS), IEEE, 2025, https://doi.org/10.1109/icmlas64557.2025.10967909