Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM66111
Volume:
10 |
7 |
Jul 2026
Pages:
1-4
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 computer science engineering
Holycross engineering college

Department of computer science engineering
Holycross engineering college
Department of computer science engineering
Holycross engineering college

Department of computer science engineering
Holycross engineering college
Distribution transformers typically exhibit warning signs prior to failure; however, many still experience explosions or outages only after significant damage has occurred. Common causes include overload current, prolonged overheating, and accidental wire damage. By the time manual inspection is conducted, faults often escalate into outages or, in severe cases, fire hazards. This paper introduces an Artificial Intelligence-based Smart Transformer Monitoring System that aims to detect such issues before they become critical. The system continuously monitors current, voltage, temperature, and wire-continuity data to identify abnormal behavior at an early stage. Upon confirmation of a fault or accident-related condition, such as a snapped wire, a relay automatically disconnects the power supply, and the Electricity Board (EB) cell receives an immediate alert with the precise fault location. For scalable monitoring, the wiring network is visualized on a 3D dashboard, where healthy lines are displayed in green and faulty lines in red, enabling EB staff to quickly identify issues across the grid without waiting for complaint calls.
KEYWORDS
This paper set out to close the gap between a transformer fault occurring and someone actually doing something about it, and the results suggest that combining continuous AI-based monitoring with automatic power isolation is a workable way to do that. Overload, overheating, and wire-cut conditions are caught early, power is cut before the situation turns dangerous, and the EB cell knows exactly where to send a team rather than searching for the problem. The 3D dashboard turned out to be more than a visual add-on — for a team monitoring dozens or hundreds of lines, a quick glance at red versus green is far more usable than scrolling through a log of alerts. Looking ahead, tying this into a city-wide SCADA system and using the accumulated sensor history for predictive maintenance scheduling seem like the natural next steps.
[1] S. V. Kulkarni and S. A. Khaparde, "Transformer Engineering: Design, Technology, and Diagnostics," CRC Press, 2012. [2] IEEE Guide for Loading Mineral-Oil-Immersed Transformers, IEEE Std C57.91-2011. [3] Y. LeCun, Y. Bengio, and G. Hinton, "Deep Learning," Nature, vol. 521, no. 7553, pp. 436-444, 2015. [4] M. A. Taha, A. A. Youssef, and M. Mosaad, "IoT-Based Real-Time Transformer Health Monitoring System," IEEE Access, vol. 9, pp. 43522-43534, 2021. [5] R. Vinayakumar et al., "Deep Learning Approach for Intelligent Fault Detection in Power Systems," IEEE Access, vol. 7, pp. 41525-41550, 2019. [6] A. Shaban, M. F. Zia, and E. Elbouchikhi, "A Review of Machine Learning Approaches for Power Transformer Fault Diagnosis," Energies, vol. 14, no. 20, 2021. [7] S. Hochreiter and J. Schmidhuber, "Long Short-Term Memory," Neural Computation, vol. 9, no. 8, pp. 1735-1780, 1997. [8] M. H. Bhuyan, D. K. Bhattacharyya, and J. K. Kalita, "Anomaly Detection: Methods, Systems and Tools," IEEE Communications Surveys & Tutorials, vol. 16, no. 1, pp. 303-336, 2014. [9] A. J. Bell and S. B. Wicker, "GPS-Enabled Fault Localization for Smart Distribution Grids," IEEE Transactions on Smart Grid, vol. 10, no. 3, pp. 2765-2774, 2019. [10] T. Sousa, T. Soares, and Z. Vale, "Smart Grid Monitoring and Visualization Platforms: A Review," Renewable and Sustainable Energy Reviews, vol. 91, pp. 1136-1147, 2018.
Publication Date
7/16/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
2
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...