MUMBAI, India, June 22 -- Intellectual Property India has published a patent application (202641070696 A) filed by Muthayammal Engineering College Autonomous on June 06, 2026, for Cognitive Iot Framework For Real-Time Anomaly Detection And Intelligent Maintenance Planning.
Inventors include Dr. T. Kowsalya; Dr. C. Selvi; Dr. N. Natarajan; Dr. S. Arun Prakash; Suguneshwar S; Seran K; Yoganadhan M; Sibiraj D; Tamilarasan S; and Poovarasan R.
The application for the patent was published on June 12, 2026, under issue no. 24/2026.
Abstract: The present invention relates to a Cognitive IoT Framework for Real-Time Anomaly Detection and Intelligent Maintenance Planning. The framework comprises interconnected IoT sensing devices, communication networks, edge computing resources, cognitive analytics engines, anomaly detection modules, predictive maintenance engines, knowledge graph repositories, digital twin systems, and intelligent maintenance planning components. Real-time operational data acquired from industrial assets is processed using machine learning, deep learning, contextual reasoning, and predictive analytics techniques to identify anomalies, forecast equipment degradation, estimate remaining useful life, and predict failure probabilities. The framework automatically generates optimized maintenance schedules by considering asset criticality, operational constraints, maintenance priorities, workforce availability, and resource allocation requirements. Continuous feedback learning enables adaptive improvement of anomaly detection accuracy and maintenance planning effectiveness. The invention significantly reduces downtime, improves equipment reliability, minimizes maintenance costs, enhances operational efficiency, and supports autonomous maintenance decision making across industrial environments, manufacturing facilities, utility infrastructures, transportation systems, energy networks, and smart asset management applications. The invention provides a scalable, intelligent, and self-learning maintenance ecosystem capable of transforming traditional maintenance operations into predictive and prescriptive maintenance frameworks.
Disclaimer: Curated by HT Syndication.
