Color Coated Coil Scheduling in Cold Rolling Plant Using Artificial Neural Network

Abstract

This paper investigates the problem of generating satisfactory production sequence of steel coils for color coating process in cold rolling plant. The characteristic of scheduling involves two parts of work. One is to optimally choose steel coils from available ones, the other is to generate a satisfactory processing plan so as to minimize production cost. To solve the problem, this paper transfers all the production requirements into the distance between any pair of coils, reduces the scheduling problem to prize-collecting traveling salesman problem (PCTSP) and develops pertinent Hopfield network algorithm, taking full advantage of the enlarged solving space of PCTSP. The performance of the proposed approach is verified by randomly generated problem instances. Computational results show that the proposed approach outperforms the existing heuristics with respect to solution quality