MUMBAI, India, May 29 -- Intellectual Property India has published a patent application (202641048904 A) filed by Agni College Of Technology, Chennai, Tamil Nadu, on April 17, for 'ai- based transformer health monitoring system.'
Inventor(s) include Mehjabeen U; Reshma A; Sathish Kumar B; Swathi P S; and Tejashwini A.
The application for the patent was published on May 29, under issue no. 22/2026.
According to the abstract released by the Intellectual Property India: "Power transformer is an essential component of the power transmission and distribution network. Any structural defects, i.e., cracks on the transformer's body, may lead to insulation deterioration, leakage of the transformer's oil, etc., which may result in the transformer's failure if not rectified at an early stage. The conventional method of transformer inspection involves manual inspection. AI&ML, in addition, has provided an opportunity to implement smart monitoring systems. In this paper, an AI-based smart transformer health-monitoring system is implemented using embedded computer vision for crack detection. In this system, an ESP32-CAM module is used for acquiring images of the transformer's surface during the monitoring process. These acquired images are used to create a dataset, which is then categorised into two types: Crack and No Crack. Using the Edge Impulse tool, an ML-based model is created and optimised for implementation on an embedded platform. The proposed model is implemented directly."
Disclaimer: Curated by HT Syndication.
