Integrated data-driven and artificial intelligence framework to develop digital twins in distribution system of supply chains: A real industrial case

Abstract

The development of digital twins and the application of industry 4.0, Artificial Intelligence (AI), and recent Machine Learning (ML) approaches have significantly advanced supply chain management and garnered considerable attention. The importance of digital twins in the supply chain became specifically clear following the outbreak of the COVID-19 pandemic, demonstrating substantial benefits in risk and disruption management. We propose an integrated framework for developing digital twins in distribution systems for managing demand risks, and it designs a decision support system for data-driven modeling to respond to two scenarios: (1) proactive design for managing future demand risks and (2) reactive design for managing real-time demand risks. This research aims to provide a more comprehensive study compared to previous investigations by designing this conceptual framework for development of digital twin in distribution systems and creating a support system using technical analysis and demand data via Regression algorithm in machine learning based on a real industrial case problem. The results of the current paper contribute to practical actions and research in demand risk management and the discovery of patterns, trends, and potential changes, enhancing both proactive and reactive decision-making. By integrating the visualization of the distribution system, analyzing historical and online demand data, implementing exogenous variables and connecting it to Enterprise Resource Planning (ERP) systems, this approach ensures the resilience and agility of systems, as well as the continuity of business operations in global companies.