Volume 2 - Issue 3, May - June 2026

The rapid evolution of modern industrial systems has highlighted the need for dynamic, real-time cyberphysical synchronisation. Traditional digital twins often lack the predictive capabilities required to autonomously adapt to complex, ever-changing environments. This paper presents an artificial intelligence-driven digital twin framework designed to enhance predictive maintenance and overall operational efficiency. By integrating machine learning algorithms with real-time sensor data, the proposed model transitions the digital twin from a passive monitoring tool into an active, forecasting system. We detail the architecture of this intelligent twin, which continuously learns from both historical and streaming data to anticipate potential system anomalies and optimise performance parameters. Experimental simulations indicate that the application of artificial intelligence significantly improves the accuracy of failure detection and reduces unexpected downtime compared to conventional monitoring methods. Ultimately, this research provides a robust, scalable foundation for deploying intelligent digital twins, offering a practical pathway toward fully autonomous and resilient operations.

Mr. Jayesh Dhuri, Blessy Varshith, Shubham Panigrahi,"AI Driven Digital Twin" International Journal of Advanced Multidisciplinary Research and Educational Development, V2(3): Page(292-297) May-June 2026. ISSN: 3107-6513. www.ijamred.com. Published by Scientific and Academic Research Publishing.