Real-time data-driven monitoring in job-shop floor based on radio frequency identification

Abstract

Real-time manufacturing data plays more and more important roles in today’s competitive manufacturing industry; however, many enterprises are still troubled by the lack of this timely, accurate, and consistent manufacturing data as there are no effective data collecting and process methods. The hysteretic and unmatched information flows lead to great opacity and uncertainty for production management. This paper thereby proposes a comprehensive real-time data-driven monitoring method in job-shop floor based on radio frequency identification (RFID) technology to address these issues. Firstly, a RFID configuration strategy is put forward including both RFID tag and device configuration schemas. The essence of RFID applications in job-shop floor is revealed too. Next, different levels of data collecting and monitoring models are established one by one, from single RFID reader level to process and process flow levels, wherein different types of state blocks are deployed to a decomposed process/process flow, generating a series of continuous event-driven data collecting units (EDCUs), which not only specify how to collect real-time on-site data but also point out what data should be collected. Then, three data processing methods are presented for different situations such as data preprocessing, fusion, and exception handling. Finally, a use case of a typical part is studied based on a prototype system which demonstrates how to use the proposed models and methods to monitor the production process of the part in job-shop floor and shows their feasibility simultaneously.