MUMBAI, India, Sept. 28 -- Intellectual Property India has published a patent application (202621097513 A) filed by Lakshmi Narain College Of Technology on August 12, 2026, for Ai-Driven Predictive Maintenance And Equipment Failure Prevention System.
Inventors include Dr. Sushil Kumar; Dr. Poonam Choudhari; Prof. Sapna Lonare; Rahul Saini; Prof. Mahesh Malviya; and Satendra Kumar Jain.
The application for the patent was published on September 25, 2026, under issue no. 39/2026.
Abstract: ABSTRACT An AI-driven predictive maintenance and equipment failure prevention system integrates real-time sensor data acquisition, machine learning-based anomaly detection, failure prediction algorithms, and automated maintenance scheduling to prevent equipment failures before they occur. The system comprises a data acquisition module receiving sensor data from industrial equipment, a preprocessing module cleaning and extracting features from the data, a multi-modal anomaly detection module employing parallel detection algorithms with a fusion mechanism generating anomaly scores, a failure mode classification module categorizing detected anomalies, a remaining useful life estimation module predicting time until component failure, a maintenance planning module generating work orders and scheduling interventions based on predictions and operational constraints, an autonomous response module executing corrective actions for high-confidence imminent failure predictions, and a graphical user interface displaying equipment health status and recommendations. The system further incorporates digital twin visualization, generative AI incorporating unstructured service reports, counterfactual model training, image-based failure detection, and continuous model retraining with new operational data. The unified platform provides end-to-end predictive maintenance capabilities addressing data acquisition through action execution, scalable across equipment fleets, integrating with existing enterprise systems, and significantly reducing unplanned downtime, maintenance costs, and operational disruptions. The system applies across manufacturing, transportation, energy, aerospace, marine, hydraulic systems, building management, and critical infrastructure applications.
Disclaimer: Curated by HT Syndication.
