Generative Adversarial Networks for Resilient Design of Manufacturing Systems
Research Poster Engineering 2025 Graduate ExhibitionPresentation by Timothy Kuo
Exhibition Number 128
Abstract
Manufacturing systems often face unexpected disruptions such as machine failures or material shortages, which can severely impact the production performance. Traditional methods for addressing these disruptions tend to be time-consuming and resource-intensive, which cannot effectively maintain the resilience of manufacturing systems. Despite recent advances in digital twins (DT) and artificial intelligence (AI), very little has been done to mitigate high computational demands and generate resilient designs of process flows under uncertainty. Therefore, this paper presents a new Generative Adversarial Network (GAN) approach for the on-the-fly design of manufacturing systems in response to production disruptions. First, we propose a novel Generative Adversarial Network for system design (D-GAN) to generate diverse, adaptive system designs that align production performance with target key performance indicators (KPIs). Second, DT models are coupled with statistical metamodeling to optimize the sequential probability of design improvements. Experimental results show the high potential of the proposed D-GAN approaches to generate cost-effective system designs and enhance manufacturing resilience.
Importance
This study offers a new, faster way to help manufacturing systems bounce back when unexpected disruptions occur. In any factory or production line, disruptions such as machine breakdowns or material shortages can slow down production and increase costs. The proposed approach (D-GAN) can quickly generate different system design for how to adjust a manufacturing configurations after a disruption. By integrating with digital twin model, the proposed approach can test many possible system designs and recommend those that best meet production goals while keeping recovery time and expenses low. Overall, this research provides a practical tool that could help manufacturers respond more efficiently to problems, minimize downtime, and maintain consistent production quality.