A Framework for Manufacturing System Reconfiguration Based on Artificial Intelligence and Digital Twin

Abstract

Abstract The application of digital twins and artificial intelligence to manufacturing has shown potential in improving system resilience, responsiveness, and productivity. Traditional digital twin approaches are generally applied to single, static systems to enhance a specific process. This paper proposes a framework that applies digital twins and artificial intelligence to manufacturing system reconfiguration, i.e., the layout, process parameters, and operation time of multiple assets, to enable system decision making based on varying demands from the customer or market. A digital twin environment has been developed to simulate the manufacturing process with multiple industrial robots performing various tasks. A data pipeline is built in the digital twin with an API (application programming interface) to enable the integration of artificial intelligence. Artificial intelligence methods are used to optimise the digital twin environment and improve system decision-making. Finally, a multi-agent program approach shows the communication and negotiation status between different agents to determine the optimal configuration for a manufacturing system to solve varying problems. Compared with previous research, this framework combines distributed intelligence, artificial intelligence for decision making, and production line optimisation that can be widely applied in modern reactive manufacturing applications.