Chip packaging test production line performance control method based on Q-learning reinforcement learning

Abstract

The invention relates to the field of semiconductor chip packaging test production line performance control and optimization, and particularly relates to a chip packaging test production line performance control method based on Q-learning reinforcement learning. According to the invention, a more accurate semiconductor packaging test series-parallel production line performance prediction model isestablished; and a Morris screening method and an Arena simulation method are comprehensively used for carrying out global sensitivity quantitative analysis, a plurality of influence factors which have the greatest influence on the production line performance and influence rules thereof are obtained, and the conditions that the Markov state space of equipment is huge and traditional mathematical model analysis is not suitable are avoided. According to the method, the variability factors of the production line are controlled on the basis of performance prediction and sensitivity analysis, and the valuing mode of the parameter [epsilon] is improved, so that the convergence rate of the algorithm is higher, local optimization is avoided, and meanwhile, the performance control method has betterflexibility and real-time performance.

Description

technical field [0001] The invention relates to the field of performance control and optimization of a semiconductor chip packaging and testing production line, specifically for a semiconductor chip packaging and testing production line, and relates to a performance control method combining sensitivity analysis and Q-learning reinforcement learning algorithm. Background technique [0002] The semiconductor manufacturing industry has great strategic value for the development of the national economy. In order to maintain the sound development of my country's semiconductor manufacturing industry, in addition to expanding the production scale, it is also necessary to pay attention to the production efficiency of the manufacturing system and strengthen production management and control technology. Due to the production characteristics of the semiconductor manufacturing system, such as highly reentrant process paths, highly complex production process, long manufacturing cycle, larg...

AI Technical Summary

Problems solved by technology

The method of the present invention aims at the problems of untimely response to the existing variability factors, incomplete consideration of the variability factors, and conflicts in control strategies, etc., combining sensitivity analysis and Q-learning reinforcement learning algorithm to intelligently control the manufacturing performance of the semiconductor chip packaging and testing production line

Images