MUMBAI, India, July 7 -- Intellectual Property India has published a patent application (202641079774 A) filed by Sona College Of Technology on June 29, 2026, for Edge-Intelligent Machine Learning Driven Predictive Risk Index Architecture For Electric Vehicle Batteries.
Inventors include Senthil Kumar M; Pragatheeshvaran N; Purusothaman M J; and Nandhavarman M R.
The application for the patent was published on July 03, 2026, under issue no. 27/2026.
Abstract: ABSTRACT The present invention relates to an Edge-Intelligent Machine Learning Driven Predictive Risk Index Architecture for Electric Vehicle Batteries. The system comprises a multi-parameter sensor layer, edge processing unit, feature engineering module, embedded machine learning engine, Dynamic Battery Risk Index (DBRI) generator, and autonomous protection controller. Battery parameters including voltage, current, temperature, and operational characteristics are continuously monitored and processed to generate advanced electro-thermal behavioral features. A machine learning model executed locally within the edge controller predicts fault probabilities and emerging battery abnormalities. The predicted outputs are converted into a continuously updated Dynamic Battery Risk Index representing battery safety status. Based on the risk index, graded protective actions including warnings, charging control, current limitation, load management, and battery isolation are autonomously initiated. The architecture enables predictive identification of thermal runaway precursors and battery degradation conditions before conventional threshold violations occur, thereby improving safety, reliability, operational performance, and lifecycle management of electric vehicle battery systems.
Disclaimer: Curated by HT Syndication.
