MUMBAI, India, July 24 -- Intellectual Property India has published a patent application (202641085260 A) filed by S Singaravelan; Dr. S. Jenifa Sabeena; G. Jeya; K. Vinodh Kumar; S. Anitha; A. Jenifer Nirosha; Hemasilviavinothini S; M. Sowjanya; Dr. C. Rajeshkumar; S. Janaki Ramudu; T. Nancy Lydia; and Dr. Aravind B on July 12, 2026, for Ai-Enabled Autonomous Dark Factory Management System With Intelligent Production Optimization.
Inventors include S Singaravelan; Dr. S. Jenifa Sabeena; G. Jeya Gopal; K. Vinodh Kumar; S. Anitha; A. Jenifer Nirosha; Hemasilviavinothini S; M. Sowjanya; Dr. C. Rajeshkumar; S. Janaki Ramudu; T. Nancy Lydia; and Dr. Aravind B.
The application for the patent was published on July 17, 2026, under issue no. 29/2026.
Abstract: The present invention relates to an Artificial Intelligence (AI)-enabled autonomous dark factory management system for intelligent production optimization in advanced manufacturing environments. The invention integrates Industrial Internet of Things (IIoT) devices, edge computing, cloud computing, digital twin technology, autonomous robotic systems, machine learning, deep learning, reinforcement learning, and intelligent analytics into a unified manufacturing management platform. The system continuously acquires real-time data from production equipment, environmental sensors, robotic workstations, automated guided vehicles, programmable logic controllers, and quality inspection units. The acquired data are processed using an AI-based decision engine that autonomously performs production scheduling, machine resource allocation, predictive maintenance, energy optimization, inventory management, quality inspection, and workflow coordination without continuous human intervention. A digital twin continuously replicates the physical production environment to simulate operational scenarios, predict equipment behavior, optimize manufacturing parameters, and validate production strategies before deployment. Computer vision models automatically detect manufacturing defects and initiate corrective actions, while reinforcement learning algorithms dynamically optimize production sequences based on machine availability, production demand, material flow, and energy consumption. The invention further includes a closed-loop feedback mechanism that continuously retrains AI models using operational data, thereby improving production efficiency and decision accuracy over time. The proposed autonomous management system significantly improves Overall Equipment Effectiveness (OEE), reduces manufacturing downtime, minimizes operational costs, enhances production flexibility, improves product quality, reduces energy consumption, and supports sustainable Industry 4.0 and Industry 5.0 manufacturing environments. The invention is applicable to automotive, aerospace, electronics, semiconductor, pharmaceutical, food processing, textile, and other highly automated industrial sectors.
Disclaimer: Curated by HT Syndication.
