MUMBAI, India, Oct. 12 -- Intellectual Property India has published a patent application (202641119339 A) filed by Dr. S P Venkatesan; Prof. Jareena Shaikh; Jammana Lalu Prasad; Dr. Y. V. Raghava Rao; Shinde Harshda Rajendra; K. Tamilvanan; Shantarani S Birajdar; Mr. Jitendra Gupta; and Roshan Nayak on October 06, 2026, for Agentic Ai-Driven System For Real-Time Predictive Maintenance And Intelligent Fault Diagnosis In Electric Vehicles.
Inventors include Dr. S P Venkatesan; Prof. Jareena Shaikh; Jammana Lalu Prasad; Dr. Y. V. Raghava Rao; Shinde Harshda Rajendra; K. Tamilvanan; Shantarani S Birajdar; Mr. Jitendra Gupta; and Roshan Nayak.
The application for the patent was published on October 09, 2026, under issue no. 41/2026.
Abstract: The present invention provides a vehicle fault diagnosis system comprises three interconnected diagnostic layers: signal-based, model-based, and knowledge-based, all functioning within a cohesive computational framework. The signal-based layer utilizes units from the time domain, frequency domain, and time-frequency domain to derive multi-domain feature metrics from telemetry signals. The model-based layer assesses the deterioration of physical components through techniques such as system identification parameter estimation, observer/filter-based estimation, and parity relation modules. Meanwhile, the knowledge-based layer integrates a qualitative symbolic AI component with a quantitative machine learning segment applying supervised, unsupervised, and reinforcement learning algorithms to analyze the extracted features and residual outputs. This system enables real-time fault detection and estimates remaining useful life for electric vehicle architectures that include battery management systems, electric powertrains, and inverter modules. FIG.1
Disclaimer: Curated by HT Syndication.
