Flexible Job Shop Scheduling Rules Mining Based on Random Forest

Abstract

With the development of the global economy and customization, the manufacturing scheduling problem is increasingly complicated. Flexible job shops (FJSs) have to be more flexible and dynamic to handle these complex and various manufacturing environments. Aiming at the dynamic scheduling problem of FJS, a method of mining scheduling rules from scheduling related historical data with industrial big data characteristics is proposed. In the mining of scheduling rules, an improved random forest algorithm is proposed, which is suitable for mining scheduling rules from historical data related to large-scale, high-dimensional, and noisy scheduling. Experimental results show that the scheduling rules obtained by the mining method have good performance in terms of scheduling performance and computational efficiency.