A data-driven scheduling knowledge management method for smart shop floor

The data-driven method has been widely used to mine knowledge from the smart shop floors' production data to guide dynamic scheduling. However, the mined knowledge may be invalid when the production scene changes. In order to address this problem and ensure the validity of the knowledge, this paper studies a data-driven scheduling knowledge life-cycle management (SKLM) method for the smart shop floor. The proposed method includes four phases: knowledge generation, knowledge application, online knowledge evaluation, and knowledge update. Specifically, the extreme learning machine (ELM) is applied to learn knowledge based on the composite scheduling rules. The quality control theory is used to evaluate the quality of scheduling knowledge. And the online sequential ELM (OS-ELM) is adopted to update the knowledge. Knowledge life-cycle management is implemented through the iterative knowledge update. The proposed method is validated on the MIMAC6, which is a simulation model of the semiconductor production line. Experimental results show that the proposed method could improve the effectiveness of scheduling knowledge and further optimize the performance of the smart shop floor.

Automated summary

This paper presents a data-driven scheduling knowledge life-cycle management method for smart shop floors. The method includes four phases: knowledge generation, knowledge application, online knowledge evaluation, and knowledge update. It uses extreme learning machine and quality control theory to learn, evaluate, and update scheduling knowledge. Experimental results show that the proposed method improves the effectiveness of scheduling knowledge and optimizes the performance of smart shop floors.