Effective heuristic and metaheuristic approaches to optimize component placement in printed circuit board assembly

Considers a scheduling problem that arises for numerically controlled machines in the manufacture of printed circuit boards. In order to maximize the throughput rate of these machines, the time taken for the pick-and-place sequence of components for each board has to be minimized. The determination of good pick-and-place sequences on a single placement machine gives rise to three related problems, namely the assignment of component types to feeder slots, the problem of tool changes and the sequence itself. In this paper, we consider a sophisticated type of placement machinery equipped with multiple placement heads. We introduce a suitable model for this complex scheduling problem and present tailored constructive and local search heuristics to determine good, locally optimal solutions. We embed the local search techniques proposed in the variable neighborhood search metaheuristic framework to find still better locally optimal solutions and effectively search a larger part of the solution space. The heuristics have been implemented and applied to a panel of 12 test circuit boards to analyze their performance.