Authors : P. V. Nimbalkar; Sandip Suresh Shingade; Sneha Santosh Koli; Triveni Vasant Nimbalkar

Volume/Issue : Volume 11 - 2026, Issue 10 - October

Google Scholar : https://tinyurl.com/5f9zm2z8

DOI : https://doi.org/10.38124/ijisrt/26Oct676

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Electrical faults such as arc faults, loose connections, overloads, and overheating can lead to serious fire hazards and equipment damage. This project presents a TinyML-Based Electrical Arc and Loose-Wire Fire Prevention System that combines intelligent fault detection, automatic protection, and IoT-based monitoring. The proposed system uses an ESP32 as the main controller to monitor voltage, current, temperature, and arc-related sound signals from multiple electrical branches. A TinyML-based detection approach is used to identify abnormal conditions such as arc faults, loose wires, and overloads, while relay-based protection isolates the affected branch without interrupting healthy branches. The system also provides real-time fire-risk assessment, OLED status display, SD-card fault logging, IoT dashboard monitoring, and mobile alerts. By integrating machine learning with electrical sensing and automatic fault isolation, the proposed system aims to provide an affordable, compact, and proactive solution for electrical fire prevention and energy monitoring. This survey discusses the existing techniques, sensing methods, machine learning approaches, IoT technologies, and research gaps related to intelligent electrical fault and fire prevention systems. TinyML, Arc Fault Detection, Loose Wire Detection, Electrical Fire Prevention, ESP32, IoT, Machine Learning, Fault Detection, Energy Monitoring.

References :

1. H. D. Vu, E. Calderon, P. Schweitzer, S. Weber, and N. Britsch, “Multi criteria series arc fault detection based on supervised feature selection,” International Journal of Electrical Power Energy Systems, vol. 113, pp. 23–34, 2019.
2. W. Miao, Q. Xu, K. H. Lam, P. W. T. Pong, and H. V. Poor, “DC Arc-Fault Detection Based on Empirical Mode Decomposition of Arc Signatures and Support Vector Machine,” IEEE Journal of Emerging and Selected Topics in Power Electronics, 2021.
3. “Series Arc Fault Detection in Low Voltage Distribution System with Signal Processing and Machine Learning Approach,” in IECON 2021 – 47th Annual Conference of the IEEE Industrial Electronics Society, 2021.
4. “Research on Series Arc Fault Detection and Phase Selection Feature Extraction Method,” IEEE Transactions on Instrumentation and Measurement, vol. 70, Art. no. 2004508, 2021.
5. Y. Fu et al., “Series Arc Fault Detection in a Low-Voltage Power System Based on CEEMDAN Decomposition and Sensitive IMF Selection,” Journal of Sensors, 2022, Art. no. 9453818.
6. K. Xia et al., “Wavelet packet and support vector machine analysis of series DC ARC fault detection in photovoltaic system,” IEEJ Transactions on Electrical and Electronic Engineering, 2019.
7. H. Choi et al., “Series-arc-fault diagnosis using feature fusion-based deep learning model,” ETRI Journal.
8. “Series alternating current arc fault detection method based on relative position matrix and deep convolutional neural network,” Engineering Applications of Artificial Intelligence, 2024, Art. no. 108874.
9. “Anomaly detection based on Artificial Intelligence of Things: A Systematic Literature Mapping,” Internet of Things, vol. 25, Art. no. 101063, 2024.
10. H. Tian, L. Hou, and H. Gao, “Series arc fault detection and line selection method based on STD-RLS feature enhancement,” Electric Power Systems Research, vol. 255, Art. no. 112723, 2026.
11. A. Albaiz and F. Amsaad, “Fully Autonomous Z-Score-Based TinyML Anomaly Detection on Resource-Constrained MCUs Using Power SideChannel Data,” arXiv preprint, 2026.
12. “Applying Machine Learning-Based Approaches Using Experimental Data to Model DC Series Arc Fault in Photovoltaic Systems,” International Transactions on Electrical Energy Systems, 2026, Art. no. 6629476.
13. Z. Yin and C. Xiao, “Integration of wavelet packet transform, residual convolution neural network, and support vector machine for series arc fault detection,” AIP Advances, vol. 14, no. 6, 2024.