Intelligent digital twin (iDT) for supply chain stress-testing, resilience, and viability

Abstract

A large variety of models have been developed in the last two decades aiming at supply chain (SC) stress-testing and resilience. New digital and artificial intelligence (AI) technologies allow to develop novel approaches and tools in this area for the transition from standalone models to intelligent decision-support systems (DSSs). However, the literature lacks concepts and guidelines for the design of such systems. In this paper, we offer a generalized decision-making framework for using digital twins in SC stress-testing and resilience analysis as well as delineate how digital twins can contribute to theory development in SC resilience and viability. We position our proposed approach as an intelligent digital twin (iDT) – a human–AI system which visualizes physical SCs in digital form, collects and processes data for modelling using analytics methods, mimics human decision-making rules, and creates new knowledge and decision-making algorithms through human–AI collaboration. We conclude that the iDT supports monitoring, disruption prediction (early signals), event-driven responses, learning, and proactive thinking, integrating proactive and reactive approaches to SC resilience. The iDT helps to make the unknown known and so contributes to the development of a proactive, adaptation-based view on SC resilience and viability. This research can be used to solve existing problems in the industry, and it develops new methods and infrastructures for solutions to future problems.