MUMBAI, India, Oct. 26 -- Intellectual Property India has published a patent application (202611112544 A) filed by Dimple Saproo; Dr D Prasanth Sai; R. Savitha; Indira S; Dr. Abdul Razak; Dr. Monika Arya; Mrs. R. Madhumitha; Dayananda Sagar Academy Of Technology And Management; Dr. N. Muguntha Manikandan; Sattar Pasha Shaik; Dr. Irissappane Dhanusu Soubache; and Dr. Mohammad Asif Indravadan Gandhi on September 19, 2026, for Ai Agent-Based Real-Time Predictive Maintenance And Intelligent Fault Diagnosis System For Electric Vehicles Using Machine Learning.

Inventors include Dimple Saproo; Dr D Prasanth Sai; R. Savitha; Indira S; Dr. Abdul Razak; Dr. Monika Arya; Mrs. R. Madhumitha; Dr. N. Muguntha Manikandan; Sattar Pasha Shaik; Dr. Irissappane Dhanusu Soubache; and Dr. Mohammad Asif Indravadan Gandhi.

The application for the patent was published on October 23, 2026, under issue no. 43/2026.

Abstract: The present invention provides an AI agent-based real-time predictive maintenance and intelligent fault diagnosis system for electric vehicles (EVs) has been introduced. This system integrates an onboard edge computing device that connects with vehicle sensors via a Controller Area Network (CAN) bus. It features a multi- agent operational layer consisting of a Battery Management System (BMS) Agent, a Powertrain Agent, and a Thermal Agent to continuously monitor subsystem parameters in real time. The outputs from these specialized AI agents are analyzed by a Central Diagnostic Agent employing machine learning models such as Long Short-Term Memory (LSTM) networks, Convolutional Neural Networks (CNN), and Autoencoders to assess State of Charge (SoC), State of Health (SoH), and Remaining Useful Life (RUL). The system addresses challenges like processing delays, noisy time-series data, and black-box interpretability through the incorporation of Explainable AI (XAI) and asynchronous cloud synchronization, which facilitates closed-loop mitigation actions including dynamic power limitation, thermal management, and automated fault notifications. FIG.1

Disclaimer: Curated by HT Syndication.