MUMBAI, India, Aug. 31 -- Intellectual Property India has published a patent application (202641099827 A) filed by Dr. Harika B; Dr. T. Nadana Ravishankar; Dr. N. Prasath; Ms. Manimala S; Mrs. Joan Adline Moses; Pradnya A. Jadhav; L. Priya; Ms. R. Sowmiya; S. Nandhini Devi; Dr. Keerthika T; Dr. L. Arulmozhiselvan; and G. Neelima on August 18, 2026, for Edge Ai-Enabled Real-Time Digital Twin Platform For Continuous Data-Driven Simulation.
Inventors include Dr. Harika B; Dr. T. Nadana Ravishankar; Dr. N. Prasath; Ms. Manimala S; Mrs. Joan Adline Moses; Pradnya A. Jadhav; L. Priya; Ms. R. Sowmiya; S. Nandhini Devi; Dr. Keerthika T; Dr. L. Arulmozhiselvan; and G. Neelima.
The application for the patent was published on August 28, 2026, under issue no. 35/2026.
Abstract: The present invention discloses an Edge AI-Enabled Real-Time Digital Twin Platform for Continuous Data-Driven Simulation configured to provide intelligent monitoring, dynamic simulation, predictive analysis, and adaptive control of physical assets and cyber-physical systems. The platform comprises a multimodal sensing layer, Edge Artificial Intelligence (Edge AI) processing module, real-time communication module, cloud/server infrastructure, digital twin engine, continuous simulation engine, visualization module, and intelligent decision and control mechanism. Heterogeneous sensors continuously acquire operational and environmental data from a physical asset and transmit the acquired information to edge computing nodes. The Edge AI module performs preprocessing, feature extraction, sensor-data fusion, anomaly detection, state estimation, event recognition, and AI-based inference near the physical data source, thereby reducing communication latency, bandwidth consumption, and dependence on centralized processing. Processed information is communicated to the digital twin engine for continuously synchronizing a virtual representation with the current state of the corresponding physical asset. The continuous data-driven simulation engine dynamically updates simulation parameters using real-time measurements, historical information, Edge AI outputs, and digital twin states to perform what-if analysis, performance evaluation, failure assessment, and future-state prediction. Predictive and simulation results are utilized by the decision and control module to generate maintenance recommendations, operational adjustments, optimization decisions, and automated control instructions. A closed- loop feedback mechanism communicates selected decisions to the physical system and incorporates subsequent physical responses into further processing and simulation cycles. The proposed platform thereby enables continuous physical-virtual synchronization, low-latency intelligence, predictive operation, adaptive simulation, and efficient real-time control across diverse cyber-physical applications.
Disclaimer: Curated by HT Syndication.
