Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM68809
Volume:
10 |
11 |
Nov 2026
Pages:
1-12
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.

Department of Electronics and Communication Engineering
Kalpataru Institute of Technology, Tiptur

Department of Electronics and Communication Engineering
Kalpataru Institute of Technology, Tiptur

Department of Electronics and Communication Engineering
Kalpataru Institute of Technology, Tiptur
Department of Electronics and Communication Engineering
Kalpataru Institute of Technology, Tiptur
Electric vehicle batteries require continuous moni-toring to support safe operation, reliable performance, and timely maintenance. This paper presents an Internet of Things (IoT)-based electric vehicle battery monitoring prototype implemented using an ESP32 microcontroller. The system monitors battery voltage, current, temperature, and flame-sensor information. A local TFT touchscreen displays system information, while an embedded HTTP server provides battery information through a local interface. The system also supports cloud data transmission through the ThingSpeak platform. A React-based web dashboard retrieves cloud data and presents selected battery parameters. Battery percentage, health indicators, maintenance status, power consumption, and nominal range are calculated using the implemented firmware logic. The health indicator is based on programmed threshold rules rather than a trained machine-learning model. Similarly, the range value is a nominal estimate derived from battery percentage and is not a measurement of actual vehicle range. To extend the monitoring system towards intelligent bat-tery analysis, a cloud-based AI health prediction framework is proposed for analysing historical battery measurements. The proposed framework can support future battery state-of-health estimation when suitable labelled battery ageing data, model training, and experimental validation are available. This paper describes the system architecture, hardware implementation, software design, monitoring workflow, proposed AI methodology, and functional evaluation of the prototype.
KEYWORDS
This paper presented the design and implementation of an IoT-Based EV Battery Monitoring System with a cloud-connected architecture using an ESP32 microcontroller. The prototype integrates voltage, current, temperature, and flame-sensor inputs to provide information about selected battery operating conditions. The system uses an ESP32 controller to acquire and process sensor measurements. An ILI9341 TFT touchscreen provides local visualization, while an embedded HTTP interface makes selected battery information available over the local network. ThingSpeak supports cloud data transmission, and a React-based web dashboard retrieves the latest uploaded measure-ments for remote monitoring. The firmware calculates battery percentage, a health-related indicator, estimated remaining life, instantaneous power, and nominal range using programmed logic. These calculations provide indicative information for the prototype and are not presented as validated machine-learning predictions or direct measurements of battery degradation. A cloud AI health prediction framework has also been proposed to investigate the use of historical battery measure-ments for future battery health estimation. The framework de-scribes data collection, preprocessing, feature selection, model training, validation, and cloud-based prediction. Actual AI prediction requires suitable labelled battery ageing data and experimental validation. Functional verification was used to examine the operation of the sensor interfaces, display, local communication interface, cloud transmission, and dashboard. The results demonstrate the integration of the principal hardware and software compo-nents under the evaluated conditions. However, further quan-titative testing is required to establish measurement accuracy, communication performance, and the effectiveness of safety-related responses. Overall, the proposed prototype demonstrates a practical approach to combining embedded sensing, local monitoring, and cloud connectivity for electric vehicle battery observation. Its modular architecture provides a foundation for further development towards more accurate battery estimation and cloud-based intelligent monitoring.
This paper presented the design and implementation of an IoT-Based EV Battery Monitoring System with a cloud-connected architecture using an ESP32 microcontroller. The prototype integrates voltage, current, temperature, and flame-sensor inputs to provide information about selected battery operating conditions. The system uses an ESP32 controller to acquire and process sensor measurements. An ILI9341 TFT touchscreen provides local visualization, while an embedded HTTP interface makes selected battery information available over the local network. ThingSpeak supports cloud data transmission, and a React-based web dashboard retrieves the latest uploaded measure-ments for remote monitoring. The firmware calculates battery percentage, a health-related indicator, estimated remaining life, instantaneous power, and nominal range using programmed logic. These calculations provide indicative information for the prototype and are not presented as validated machine-learning predictions or direct measurements of battery degradation. A cloud AI health prediction framework has also been proposed to investigate the use of historical battery measure-ments for future battery health estimation. The framework de-scribes data collection, preprocessing, feature selection, model training, validation, and cloud-based prediction. Actual AI prediction requires suitable labelled battery ageing data and experimental validation. Functional verification was used to examine the operation of the sensor interfaces, display, local communication interface, cloud transmission, and dashboard. The results demonstrate the integration of the principal hardware and software compo-nents under the evaluated conditions. However, further quan-titative testing is required to establish measurement accuracy, communication performance, and the effectiveness of safety-related responses. Overall, the proposed prototype demonstrates a practical approach to combining embedded sensing, local monitoring, and cloud connectivity for electric vehicle battery observation. Its modular architecture provides a foundation for further development towards more accurate battery estimation and cloud-based intelligent monitoring.
Publication Date
11/6/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
6
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...