Intelligent IoT-Cloud Integrated Wireless RF Framework for Transformer Fault Diagnosis and Predictive Maintenance

Intelligent IoT-Cloud Integrated Wireless RF Framework for Transformer Fault Diagnosis and Predictive Maintenance

  IJETT-book-cover           
  
© 2025 by IJETT Journal
Volume-73 Issue-5
Year of Publication : 2025
Author : Asmita Sharma, R.P. Agarwal, Rajesh Singh
DOI : 10.14445/22315381/IJETT-V73I5P110

How to Cite?
Asmita Sharma, R.P. Agarwal, Rajesh Singh, "Intelligent IoT-Cloud Integrated Wireless RF Framework for Transformer Fault Diagnosis and Predictive Maintenance," International Journal of Engineering Trends and Technology, vol. 73, no. 5, pp.103-115, 2025. Crossref, https://doi.org/10.14445/22315381/IJETT-V73I5P110

Abstract
Transformers play a significant role in the energy management aspect of distribution networks, particularly in the management of energy and voltage regulation. Defeated transformers result in an unsteady power supply, damaged equipment, and economic damage. Old-fashioned monitoring methods depend on excruciatingly slow manual checks that are only done on a reactive basis and are inefficient for advanced fault identification. The amplified need for dependable power highlights the necessity for real-time autonomous transformer efficiency monitoring. The incorporation of the IoT with cloud computing and wireless RF has changed the pace of industrial automation, allowing real-time data capture, monitoring, and maintenance from personnel geographically far away. IoT enables persistent tracking of crucial measurable figures like voltage, current, temperature, and humidity, while LoRa RF is the long-range, low-power radio ideal for electricity transformers situated in isolated regions. Data analytic tools hosted on the cloud easily visualize information, enabling faster maintenance and improved fault diagnosis accuracy. Traditional techniques like DGA, vibration monitoring, and thermal imaging used in fault diagnosis rest upon a feeble premise of slow detection of fault problems, expensive maintenance requirements, and poor flexibility. Our proposal seeks to address the aforementioned issues with an IoT-based Smart Transformer Monitoring System that utilizes machine learning for predictive maintenance, cloud analytics, and an almost limitless range achieved through LoRa RF. While traditional wireless technologies like ZigBee fail to work on transformers due to their range limitation, wired networks suffer from data loss and physical damage, offering no protection against these threats. Myriota will also implement a Transformer Health Monitoring Unit, which will be responsible for collecting real-time sensor data, and an Edge Gateway, which will process and transmit data to the ThingSpeak Cloud for visualization. An embedded Machine Learning model will analyze the data for early fault detection and maximize the reliability, cost, and scalability for optimal transformer monitoring. The goals of this framework are to reduce maintenance costs to improve grid stability and accomplish a higher level of power system management..

Keywords
Transformer Health Monitoring, IoT-Based Fault Diagnosis, LoRa RF Communication, Edge Gateway, ThingSpeak.

References
[1] S.B. Joshi et al., “Transformer Health Monitoring using IoT Based,” International Journal for Research in Applied Science and Engineering Technology, vol. 11, no. 5, pp. 7594-7597, 2023.
[CrossRef] [Publisher Link]
[2] Mzamo Richard Msane, “Internet of Things (IoT) System for Diagnosing Power Transformer Faults using the IEC 60076-1 Standard: Review,” International Journal of Innovative Science and Research Technology, vol. 9, no. 4, pp. 556-565, 2024.
[CrossRef] [Publisher Link]
[3] Ammar K. Al Mhdawi, and Hamed Al-Raweshidy, “A Smart Optimization of Fault Diagnosis in Electrical Grid using Distributed Software-Defined IoT System,” IEEE Systems Journal, vol. 14, no. 2, pp. 2780-2790, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[4] G.B. Murade et al., “IOT Based Transformer Monitoring and Controlling,” International Journal for Research in Applied Science and Engineering Technology, vol. 11, no. 5, pp. 6940-6942, 2023.
[CrossRef] [Publisher Link]
[5] C. Bethalsha et al., “Real-Time Transformer Health Monitoring using IOT,” International Journal for Research in Applied Science and Engineering Technology, vol. 8, no. 9, pp. 521-526, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Pedro H. Feijó de Sousa et al., “Intelligent Incipient Fault Detection in Wind Turbines based on Industrial IoT Environment,” Journal of Artificial Intelligence and Systems, vol. 1, no. 1, pp. 1-19, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Anita Gehlot et al., “Wireless Personal Area Network and PSO-Based Home Security System,” Proceedings of the Second International Conference on Computer and Communication Technologies: Advances in Intelligent Systems and Computing, New Delhi, pp. 251-261, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Anita et al., “Wireless Disaster Monitoring and Management System for Dams,” Procedia Computer Science, vol. 48, pp. 381-386, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Jasjit Singh et al., “Health Monitoring Gadgets,” International Conference on Intelligent Computing and Smart Communication 2019: Algorithms for Intelligent Systems, Singapore, pp. 1547-1552, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Tao Wang et al., “Self-Powered RFID Sensor Tag for Fault Diagnosis and Prognosis of Transformer Winding,” IEEE Sensors Journal, vol. 17, no. 19, pp. 6418-6430, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Aneesh G. Nath et al., “Structural Rotor Fault Diagnosis using Attention-Based Sensor Fusion and Transformers,” IEEE Sensors Journal, vol. 22, no. 1, pp. 707-719, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[12] G. N. S, S. Y. A, and R. M, “IoT based Monitoring and Control of Faults in Power Distribution Transformers,” SSRG International Journal of Electrical and Electronics Engineering, vol. 7, no. 12, pp. 37-41, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Yoganand Selvaraj, and Chithra Selvaraj, “Proactive Maintenance of Small Wind Turbines using IoT and Machine Learning Models,” International Journal of Green Energy, vol. 19, no. 5, pp. 463-475, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Sachin Gee Paul et al., “Transformer Health Monitoring and Protection using IoT,” International Journal for Research in Applied Science and Engineering Technology, vol. 10, no. 10, pp. 524-528, 2022.
[CrossRef] [Publisher Link]
[15] Mayur Ramdham et al., “IoT based Distribution Transformer Health Monitoring System,” International Journal for Research in Applied Science and Engineering Technology, vol. 10, no. 6, pp. 3945-3950, 2022.
[CrossRef] [Publisher Link]
[16] Amol A. Sonune et al., “Condition Monitoring of Distribution Transformer using IOT,” International Journal of Engineering Research & Technology, vol. 9, no. 6, pp. 335-338, 2020.
[Google Scholar] [Publisher Link]
[17] K. Rajashekar et al., “IoT Based Transformer Monitoring System using ESP-32,” International Journal for Research in Applied Science and Engineering Technology, vol. 12, no. 5, pp. 4597-4602, 2024.
[CrossRef] [Publisher Link]