An AI-Enabled IoT Framework for Real-Time Battery Health Monitoring and Remaining Useful Life Prediction of Lithium-Ion Batteries in Electric Vehicles: A Comprehensive Review

Sanjay B. Warkad; Dhanashri R. Pohokar; Sanika S. Takale; Surabhi S. Bhudukale; Anushka A. PaturkarPaturkar; Adhirath S. Taware; Radhika S. Katole; Vedant R. Khorgade

doi:10.36948/ijfmr.2026.v08i05.88493

An AI-Enabled IoT Framework for Real-Time Battery Health Monitoring and Remaining Useful Life Prediction of Lithium-Ion Batteries in Electric Vehicles: A Comprehensive Review

Author(s)	Dr. Sanjay B. Warkad, Ms. Dhanashri R. Pohokar, Ms. Sanika S. Takale, Ms. Surabhi S. Bhudukale, Ms. Anushka A. PaturkarPaturkar, Mr. Adhirath S. Taware, Ms. Radhika S. Katole, Mr. Vedant R. Khorgade
Country	India
Abstract	The increasing number of electric vehicles (EVs) being adopted has made it necessary for battery management systems to go beyond simple protection and state-of-charge estimation and instead focus on continuous state-of-health (SOH) assessment, degradation forecasting, and prediction of remaining useful life (RUL). The ageing of lithium-ion batteries is caused by a combination of electrochemical, thermal, mechanical, and operational processes, which makes it hard to accurately predict their condition when they are being driven and charged under changing conditions. This review brings together the most recent developments in battery sensing, health indicators, data preprocessing, machine learning, deep learning, physics-informed learning, transfer learning, uncertainty-aware prognosis, Internet of Things (IoT) connectivity, edge-cloud computing, and digital twins. The existing literature is divided into five clear sections and is then used to develop an integrated AI-enabled IoT framework in which safety-critical decisions remain at the edge of the vehicle while at the same time fleet-wide model training, long-term RUL forecasting, and lifecycle analysis are carried out in the cloud. The review also looks at public battery datasets, evaluation methods, cybersecurity, explainability, and cross-chemistry generalisation. The synthesis reveals that for practical deployment of EVs it is necessary not only to have a low prediction error but also to ensure physical consistency, to provide calibrated uncertainty, to achieve computational efficiency, to have secure connectivity, and to be robust against shifts in battery chemistry, temperature, and usage domain. The framework thus offers a succinct reference architecture for real-time battery health monitoring and for predictive maintenance in connected electric vehicles.
Keywords	lithium-ion battery, electric vehicle, battery management system, artificial intelligence, Internet of Things, state of health, remaining useful life, predictive maintenance, edge computing, physics-informed learning
Field	Engineering
Published In	Volume 8, Issue 5, September-October 2026
Published On	2026-09-30
DOI	https://doi.org/10.36948/ijfmr.2026.v08i05.88493

View / Download PDF File

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

An AI-Enabled IoT Framework for Real-Time Battery Health Monitoring and Remaining Useful Life Prediction of Lithium-Ion Batteries in Electric Vehicles: A Comprehensive Review

Share this