MUMBAI, India, July 13 -- Intellectual Property India has published a patent application (202641083226 A) filed by Muthayammal Engineering College Autonomous on July 07, 2026, for Intelligent Equipment Degradation Prediction Platform Using Continual Learning And Industrial Digital Twins.
Inventors include Dr. M. Shenbagapriya; Dr. S. Perumal; S. Pavithra; M. Santhiya; M. Meena; G. Santhiya; A. Nishanth; B. Manikanadan; S. D. J. Manohar; and S. Seshathiri.
The application for the patent was published on July 10, 2026, under issue no. 28/2026.
Abstract: The present invention relates to an intelligent equipment degradation prediction platform using continual learning and industrial digital twins for adaptive predictive maintenance of industrial assets. The platform acquires real-time operational data from multiple sensing devices and continuously synchronizes the acquired information with an industrial digital twin representing the physical equipment. A continual learning engine incrementally updates predictive models using newly observed operational conditions, maintenance activities, process variations, and environmental changes while preserving previously acquired knowledge to eliminate catastrophic forgetting. The platform integrates sensor measurements, historical operational information, maintenance records, digital twin simulations, and lifecycle intelligence to estimate equipment health, degradation progression, failure probability, operational risk, and remaining useful life. Based on the predicted degradation trajectory, the system automatically generates optimized maintenance recommendations for improving equipment reliability and reducing unexpected failures. The platform further supports deployment across distributed industrial facilities through edge, cloud, or hybrid computing infrastructures while enabling knowledge transfer among similar industrial assets. The disclosed invention continuously improves degradation prediction accuracy throughout the equipment lifecycle without requiring complete retraining of predictive models, thereby enhancing operational efficiency, maintenance optimization, asset utilization, and industrial system reliability.
Disclaimer: Curated by HT Syndication.
