| Issue |
E3S Web Conf.
Volume 692, 2026
3rd International Conference on Intelligent and Sustainable Power and Energy Systems (ISPES 2025)
|
|
|---|---|---|
| Article Number | 03009 | |
| Number of page(s) | 12 | |
| Section | Artificial Intelligence and Human-Computer Interaction | |
| DOI | https://doi.org/10.1051/e3sconf/202669203009 | |
| Published online | 04 February 2026 | |
Cloud IoT Framework for Transformer Health Monitoring System and Predictive Failure Detection
Department of Electrical and Electronics Engineering, Erode Sengunthar Engineering College, Perundurai – 638057, Tamil Nadu, India
* Corresponding author: This email address is being protected from spambots. You need JavaScript enabled to view it.
Abstract
Power transformers must be reliable otherwise the modern power system will break down due to lack of supply. Most monitoring techniques do not monitor data in real time or analyze and predict potential equipment failures in advance. This work proposes a cloud-based framework for monitoring transformer health and predicting failure. This system uses sensors enabled by IoT to continuously capture other parameters like oil temperature, winding temperature, load current, voltage and dissolved gases. Information is sent to the cloud through gateways and the software embedded within does analysis and machine learning on it to predict faults.
Key words: IoT Sensors / Cloud Computing / Condition Monitoring / Predictive Analysis / Transformer Health Assessment
© The Authors, published by EDP Sciences, 2026
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.