Instance Segmentation and Digital Twin Use Case for WIP Tracking in Heavy Industry

Industries such as railways, aerospace, shipbuilding, and construction are known for their heavy manufacturing processes, which involve the production of large and complex products. The railway industry is known for its tight delivery schedules, which make timely production and logistics critical. To address these challenges, manufacturers are increasingly turning to advanced technologies such as artificial intelligence vision (AI-vision) and digital twin (DT) technology. These technologies allow for the automatic creation and consolidation of key production and logistics information, resulting in improved manufacturing productivity. This study focuses on the implementation of a DT in a railway train manufacturing plant. Specifically, this study discusses the use of object detection through instance segmentation to track train body parts, particularly underframes. Using this method, manufacturers can identify status changes in each production process, enabling them to facilitate work-in-process logistics within factory workstations. This approach contributes to gain real-time process visibility and corresponding work efficiency. By embracing these advanced technologies, industrial facilities can build point-of-production systems in a cost-effective way. The use of AI-vision and DT technology is transforming the manufacturing industry, allowing manufacturers to boost productivity, reduce costs, and improve the overall quality of their products.