MUMBAI, India, July 13 -- Intellectual Property India has published a patent application (202641081617 A) filed by Cmr Institute Of Technology on July 02, 2026, for Maximizing Section Throughput Using Aipowered Precise Train Traffic Control.
Inventors include Eppakayala Sandeep; Gaddala Navya Sri; Velicheti Rahul; Vilasagar Sidhartha; Jaishri Pandhari Wankhede; and S. Alagumuthukrishnan.
The application for the patent was published on July 10, 2026, under issue no. 28/2026.
Abstract: An artificial intelligence-powered system and method for maximizing section throughput and minimizing train delays in railway networks is disclosed. The invention provides a distributed software architecture deployed across station control nodes, comprising a Python-based AI decision engine that employs A* search, Dijkstra's algorithm, graph neural networks, and reinforcement learning to compute optimal train routing, precedence, and crossing decisions in real time. The system integrates with existing Route Relay Interlocking infrastructure through a secure FastAPI gateway to automate signal state changes and route configurations upon approval of AI recommendations by authorized traffic controllers. An inter-station communication module based on asynchronous WebSocket protocols enables low-latency, structured exchange of route allocation requests and acknowledgements between adjacent stations, replacing error-prone voicebased coordination. A Digital Twin simulation subsystem constructs a live virtual model of the railway network as a directed weighted graph and validates every routing decision in simulation before deployment to live infrastructure, preventing conflicts and deadlocks. The system employs a three-tier database architecture encompassing SQLite, PostgreSQL, and Redis, along with a TensorFlow and PyTorch-based machine learning training pipeline that continuously learns from historical operational data. A React and Material-UI graphical dashboard presents animated network visualizations and ranked, explainable AI recommendations to control personnel. The invention substantially reduces train delays, improves safety by minimizing human error, increases section throughput, and optimizes platform and track resource utilization across large-scale mixedtraffic railway networks.
Disclaimer: Curated by HT Syndication.
