Digital twins and artificial intelligence have shown promise for improving the robustness, responsiveness, and productivity of industrial systems. However, traditional digital twin approaches are often only employed to augment single, static systems to optimise a particular process. This article presents a paradigm for combining digital twins and modular artificial intelligence algorithms to dynamically reconfigure manufacturing systems, including the layout, process parameters, and operation times of numerous assets to allow system decision-making in response to changing customer or market needs. A knowledge graph has been used as the enabler for this system-level decision-making. A simulation environment has been constructed to replicate the manufacturing process, with the example here of an industrial robotic manufacturing cell. The simulation environment is connected to a data pipeline and an application programming interface to assist the integration of multiple artificial intelligence methods. These methods are used to improve system decision-making and optimise the configuration of a manufacturing system to maximise user-selectable key performance indicators. In contrast to previous research, this framework incorporates artificial intelligence for decision-making and production line optimisation to provide a framework that can be used for a wide variety of manufacturing applications. The framework has been applied and validated in a real use case, with the automatic reconfiguration resulting in a process time improvement of approximately 10%.

数字孪生和人工智能已显示出提高工业系统稳健性、响应能力和生产力的希望。然而，传统的数字孪生方法通常仅用于增强单个静态系统以优化特定流程。本文介绍了一种结合数字孪生和模块化人工智能算法以动态重新配置制造系统的范例，包括布局、工艺参数和大量资产的运行时间，以允许系统决策制定以响应不断变化的客户或市场需求。知识图已被用作此系统级决策的推动者。已经构建了一个模拟环境来复制制造过程，这里以工业机器人制造单元为例。仿真环境连接数据管道和应用程序编程接口，辅助多种人工智能方法的集成。这些方法用于改进系统决策和优化制造系统的配置，以最大限度地提高用户可选择的关键性能指标。与之前的研究相比，该框架结合了用于决策和生产线优化的人工智能，以提供可用于各种制造应用的框架。该框架已在实际用例中得到应用和验证，自动重新配置使处理时间缩短了约 10%。