(372al) Pinn-Based Modular Digital Twin Development for Sustainable Electroplating Manufacturing

In the quest for sustainable manufacturing, the electroplating industry faces significant challenges, including adapting to rapid technology advancement, ensuring cost effectiveness, complying with stringent environmental regulations, and maintaining process safety and health standard. This study pioneers the use of Modular Digital Twins (MDTs) informed by Physics-Informed Neural Networks (PINNs) to revolutionize adaptability, efficiency, and sustainability of electroplating systems. Our approach leverages the latest advancements in PINNs to integrate real-time and historical data, facilitating a dynamic, self-evolving system that accurately mirrors, predicts, and improve the physical system.

We introduce a novel methodology for developing plant-wide MDTs, offering unprecedented flexibility in process management and scalability—essential for tailoring to various operational scenarios within the electroplating systems. By embedding physical laws directly into the neural network learning process, our PINN-based MDTs provide a more accurate and comprehensive analysis of plant design and operations. This innovation not only improves the real-time monitoring and control of electroplating processes but also facilitates a deeper understanding of the complex interactions within these systems. As a result, our MDT system can dynamically assess sustainability performance, identifying opportunities for resource optimization, waste reduction, and energy savings with high precision; thereby significantly improving decision-making for sustainability performance enhancement. The case studies illustrate the superiority of dynamic sustainability assessments conducted with our MDT system over traditional static methods, highlighting significant improvements in resource efficiency, waste reduction, and economic viability. This research not only contributes a groundbreaking tool for the electroplating industry but also sets a new standard for the application of DT technology and AI in manufacturing for sustainability.