A Shop Floor Production Scheduling Case based on RFID-supported Smart Factory
2026-08-17 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors studied how using RFID technology on a factory floor can help manage uncertainties in production processes. They analyzed real-time data collected by RFID to understand how operations change and used this information to improve scheduling of work tasks. By applying a deep reinforcement learning method, the authors showed through simulations that their new scheduling approach works better than common methods like FIFO, LIFO, and basic deep Q learning in reducing the total operation time. This research highlights the benefit of combining RFID data with advanced learning techniques for smarter factory scheduling.
RFIDshop floor schedulingdynamic schedulingproduction planninguncertainty quantificationdeep reinforcement learningproduction sequence miningmakespanfirst in first out (FIFO)deep Q network (DQN)
Authors
Zhihui Chen, Yize Sun, Yuhao Dong, Zeyu Xiao, Ray Y. Zhong
Abstract
Radio frequency identification (RFID) technology has been widely implemented for real-time data collection in manufacturing shop floors, which, in turn, can be used to support dynamic shop floor production planning and scheduling. Within such an environment, uncertainty in operation and production processes collectively contribute to the dynamicity in manufacturing, thereby hampering the scheduling system from achieving maximal utility. To highlight the importance of handling such uncertainty, this paper addresses the problem of dynamic shop floor scheduling for a real-life case smart factory equipped with RFID technology. Feasible production sequence mining and real-time processing rate estimation are conducted on RFID-collected production data to quantify the operation and production uncertainties. A deep reinforcement learning approach based on the RFID data analysis is then presented for shop floor production scheduling. Simulation studies based on real-life case data have demonstrated the feasibility and practicality of the proposed dynamic production scheduling framework. Specifically, it is observed that the proposed framework outperforms existing dispatch methods in terms of minimizing operation makespan, including first in first out (FIFO), last in first out (LIFO) and deep Q network (DQN).