LEARNING-BASED SCHEDULING IN A FLEXIBLE MANUFACTURING FLOW LINE

We develop a bilevel framework for scheduling a circuit board (PCB) assembly plant which uses surface mount technology for inserting electronic components. Machine learning techniques are utilized for developing a system that adaptively utilizes the most appropriate heuristics given the current state of the system. We consider heuristics for both part-release and dispatching at machines. The results demonstrate the effectiveness of our approach compared to some other existing heuristic scheduling approaches.