Mining logistics trajectory knowledge from RFID-enabled production big data

Radio frequency identification (RFID) has been widely used in supporting the logistics management within manufacturing shopfloors. Various materials attached with RFID facilitates are converted into smart manufacturing objects (SMOs) which are moving frequently within the RFID-enabled ubiquitous production environment, where SMOs are able to sense, interact and reason each other. Enormous data have been collected and could be used for supporting further knowledge discovery and decision-makings except information visibility and traceability. Thus, big data for mining trajectory knowledge from such data could be enabled. This paper proposes an entire big data approach to excavate the frequent trajectory from massive RFID-enabled shopfloor logistics data for supporting production decision-making. This approach comprises several key steps: warehousing for raw RFID data, cleansing mechanism for RFID big data, mining frequent patterns, as well as pattern interpretation and visualization. The utility and feasibility of the proposed big data approach is evaluated and examined from a rich set of experimental demonstration. Key findings and observations are converted into managerial implications, which are useful in practical applications.