Data-driven Discovery of Manufacturing Processes and Performance from Worker Localisation

Digital sensing technologies are essential for realizing Industry 4.0, as they enhance productivity, assist with real-time decision-making, and provide flexibility and agility in manufacturing factories. However, implementing these technologies can be a significant challenge due to the need to consider various factors in manufacturing factories, such as heterogeneous equipment, fragmented knowledge, customization requirements, multiple alternative technologies, and the substantial costs involved in the trial-and-error process. A Knowledge Graph (KG) approach is proposed to streamline the implementation of the factory movement tracking system. The KG approach utilizes a knowledge representation reference model that integrates manufacturing objective, activity, resource, environment, factory movement, data, infrastructure, and decision support system. This reference model aids in classifying key phrases extracted from research abstracts and establishing knowledge relationships among them. A synthesized KG, created by analyzing thirty research abstracts, has correctly answered search queries about implementing the factory movement tracking system. This approach establishes a pathway for developing a software system to support movement tracking implementation through automatic interpretation, reasoning, and suggestions.