The research and application of a dynamic dispatching strategy selection approach based on BPSO-SVM for semiconductor production line

Reasonable choice of scheduling strategies to optimize the production is an effective way to improve the economic benefit and market competitiveness of manufacturing enterprises. In this paper, a dynamic dispatching strategy selection approach for semiconductor production line is studied. The proposed approach is based on historical data, uses support vector machine (SVM) as a data mining tool and binary particle swarm optimization algorithm (BPSO) to optimize production attributes (i.e. features) subset, and finally creates a SVM-based dynamic scheduling strategy classification model for production line. Under any given production status, an approximate optimal scheduling strategy can be real-time acquired through the model. Finally, the proposed dynamic scheduling approach in this paper is tested in an actual semiconductor production line for its effectiveness and feasibility.