MUMBAI, India, Sept. 28 -- Intellectual Property India has published a patent application (202611093418 A) filed by Dr. Kaustubh Kumar Shukla; Dr. Monica Bhutani; and Mrs. Archana Kumari on July 31, 2026, for Machine Learning-Enabled Digital Twin Framework For Predictive Maintenance And Intelligent Structural Health Monitoring Using Mems-Based Iot Sensors.
Inventors include Dr. Kaustubh Kumar Shukla; Dr. Meenal M Kaliwal; Ms. Vaishali Mogha; Dr. Neelam Baghel; Dr. Omkar Prasad Tripathi; Mr. Sonal Kumar; Dr. Parmanand Prabhat; Dr. Mayuri Baruah; Mr. Shivaraj Teggi; and Dr. Shilpee Patil.
The application for the patent was published on September 25, 2026, under issue no. 39/2026.
Abstract: The present invention relates to a Machine Learning-Enabled Digital Twin Framework for Predictive Maintenance and Intelligent Structural Health Monitoring Using MEMS-Based IoT Sensors for continuous monitoring, analysis, and predictive assessment of critical infrastructure and industrial assets. The proposed system comprises a plurality of MEMS-based sensors configured to acquire real-time structural parameters including vibration, acceleration, inclination, strain, displacement, and temperature. The sensed data are transmitted through an Internet of Things (IoT)-based communication network to an edge-cloud computing platform for pre- processing, storage, and analysis. The framework further incorporates a digital twin module configured to generate and continuously update a virtual representation of the monitored physical asset using real-time sensor data. A machine learning engine analyses historical and live data to identify structural anomalies, classify fault conditions, estimate the remaining useful life (RUL) of components, and generate predictive maintenance recommendations. The system further includes an intelligent decision-support module configured to issue automated alerts, maintenance schedules, and health reports based on predefined safety thresholds and adaptive learning models. The proposed invention improves monitoring accuracy, minimises false alarms, reduces unplanned downtime, optimises maintenance resources, and enhances the operational safety and service life of structures and equipment. The modular architecture enables integration with bridges, buildings, industrial machinery, transportation systems, manufacturing plants, energy infrastructure, and other smart assets. The invention further supports remote monitoring, scalable deployment, and secure data management, making it suitable for Industry 4.0 and smart city applications. The disclosed framework provides a cost-effective, intelligent, and automated solution for predictive maintenance and structural health monitoring by integrating MEMS sensing, IoT communication, machine learning, and digital twin technologies into a unified platform.
Disclaimer: Curated by HT Syndication.
