Jagger Vicente, “Exploring Data Dependencies in Manufacturing Execution Systems for Advanced Manufacturing”
Mentor: Zhen Zeng, Computer Science, Engineering & Applied Science (College of)
Poster #187
Industry 4.0 is revolutionizing manufacturing through the integration of digital technologies, making the study of data models in Manufacturing Execution Systems (MES) crucial for optimizing production processes. Understanding MES data models within a real testbed enables researchers to assess their efficiency, adaptability, and interoperability in a controlled yet realistic environment. A growing demand for affordable yet quality products alongside a shortage of workers to match demand has led to a strong interest in optimizing manufacturing. With continuous improvements in monitoring systems, data collection, and data storage, great strides have been made in tools like MES and Artificial Intelligence (AI) to refine manufacturing operations using data. Despite the growing use of these tools, their functionality and methods are relatively unknown to users. In this research project, we are looking to better understand data dependencies and data flows between the UWM Connected Systems Institute manufacturing test bed and PLEX MES. We aim to recognize the data used during the manufacturing process and data returned to the MES to track production while analyzing how data travels between the on-site plant and the cloud-oriented MES. This will be accomplished by exploring accessible systems to identify data usage and connect with and interview developers and professionals who better understand the test bed and MES. This research outcome not only enhances decision-making and predictive capabilities but also supports addressing challenges in real-time data synchronization, system scalability, and cyber-physical integration. In this SURF project, we have developed an understanding of the endpoints of the systems by identifying the data used within the test bed and the MES, and we have mapped how the data connects. By exploring MES data models in a testbed, we can bridge the gap between theoretical frameworks and industrial implementation, paving the way for smarter, more autonomous manufacturing systems.