Automatic selection method of dynamic scheduling strategy of semiconductor production line

Abstract

The invention relates to an automatic selection method of a dynamic scheduling strategy of a semiconductor production line. The automatic selection method comprises the following steps of: obtaining a production attribute set, a scheduling strategy set and a performance index set of the production line according to the actual semiconductor production line; obtaining various performance index values of the production line under different scheduling strategies through simulation, and establishing a sample set; training the training sample set, obtaining an optimized production attribute set and SVM (Support Vector Machine) training parameters, and forming a dynamic scheduling rule classifier A* based on SVM; inputting the A* to a test sample set, judging whether the prediction accuracy of the scheduling strategy based on a character subset is superior to that of a universal set, and if yes, training the training sample set S1 according to the obtained character subset and the SVM training parameters, and obtaining a final dynamic scheduling rule classifying model A; and inputting real-time state information of the production line to the A, and dynamically obtaining an optimized scheduling strategy. Compared with the prior art, the automatic selection method of the dynamic scheduling strategy of the semiconductor production line has the advantages that the scheduling instantaneity is good, the production efficiency is improved, and the like.

Description

technical field [0001] The invention relates to the field of automatic production scheduling, in particular to an automatic selection method for a dynamic scheduling strategy of a semiconductor production line. Background technique [0002] For the semiconductor production line, the production scheduling problem is the core issue, and reasonable and efficient production scheduling is an effective way to improve enterprise efficiency and market competitiveness. For the production process scheduling problem, the essence of its optimization is: to select the optimal scheduling strategy under the constraints related to the process and resources in the production process scheduling problem, so that one or more scheduling performance indicators can be optimized or better. [0003] Traditional optimization methods for production process scheduling problems mainly include the following four categories: operations research methods, heuristic methods, artificial intelligence methods ...

AI Technical Summary

Problems solved by technology

[0004] For semiconductor scheduling problems, the above-mentioned traditional optimal scheduling methods are often difficult to balance in terms of real-time and production performance. Using heuristic rules, the real-time scheduling is good, but the performance indicators cannot be optimized; while using artificial intelligence, although the performance indicators can be achieved. Optimization, but the calculation time is long, it is difficult to meet the real-time requirements of production

Images