DESIGNING OF DIGITAL SUPPLY CHAIN TWINS TO IMPROVE SUPPLY CHAIN RESILIENCE USING MACHINE LEARNING AND SIMULATION MODELS

Abstract

Due to global diversification and risk, supply chain resiliency has become crucial. Supply chain risks must be identified, assessed, and mitigated to preserve continuity and gain a competitive edge. Although supply chain disruptions have been a problem for a long time, researchers need to pay more attention to using modern technology to develop resilient supply systems. Digital twin technology offers significant benefits to supply chain management through real-time monitoring, simulation, and optimization. This research looks into leveraging advanced technology by integrating a digital twin environment into supply chains, which could be used to mitigate disruptions. Moreover, this research aims to study how the digital supply chain twin' improves and manages the supply chain's resilience using machine learning and simulation models. Thus, this research seeks to address two gaps: knowledge and methodology. This study's contributions include designing a phase to integrate a digital twin into the supply chain, developing a conceptual resilient digital supply chain twin framework, modeling a digital supply chain twin using machine learning and simulation to improve supply chain resilience, and validating the model by case study.