Journal of the Semiconductor & Display Technology (반도체디스플레이기술학회지)

The Korean Society Of Semiconductor & Display Technology (한국반도체디스플레이기술학회)
권호 표지

Scheduling of Wafer Burn-In Test Process Using Simulation and Reinforcement Learning

강화학습과 시뮬레이션을 활용한 Wafer Burn-in Test 공정 스케줄링

  • Soon-Woo Kwon (Department of Industrial and Management Engineering, Myongji University) ;
  • Won-Jun Oh (Department of Industrial and Management Engineering, Myongji University) ;
  • Seong-Hyeok Ahn (Department of Industrial and Management Engineering, Myongji University) ;
  • Hyun-Seo Lee (Department of Industrial and Management Engineering, Myongji University) ;
  • Hoyeoul Lee (Neurocore Co., Ltd ) ;
  • In-Beom Park (Department of Industrial and Management Engineering, Myongji University)
  • 권순우 (명지대학교 산업경영공학과) ;
  • 오원준 (명지대학교 산업경영공학과) ;
  • 안성혁 (명지대학교 산업경영공학과) ;
  • 이현서 (명지대학교 산업경영공학과) ;
  • 이호열 ((주)뉴로코어) ;
  • 박인범 (명지대학교 산업경영공학과)
  • Received : 2024.06.06
  • Accepted : 2024.06.21
  • Published : 2024.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Scheduling of semiconductor test facilities has been crucial since effective scheduling contributes to the profits of semiconductor enterprises and enhances the quality of semiconductor products. This study aims to solve the scheduling problems for the wafer burn-in test facilities of the semiconductor back-end process by utilizing simulation and deep reinforcement learning-based methods. To solve the scheduling problem considered in this study. we propose novel state, action, and reward designs based on the Markov decision process. Furthermore, a neural network is trained by employing the recent RL-based method, named proximal policy optimization. Experimental results showed that the proposed method outperformed traditional heuristic-based scheduling techniques, achieving a higher due date compliance rate of jobs in terms of total job completion time.

Keywords

Acknowledgement

이 논문은 정부(과학기술정보통신부)의 재원으로 한국연구재단(2022R1G1A101175)과 2024년도 부처협업형 반도체전공트랙 사업을 통해 한국산업기술진흥원(G02P18800005502)의 지원을 받아 수행된 연구입니다.

References

  1. In-Beom Park, Jonghun Park. "Scalable scheduling of semiconductor packaging facilities using deep reinforcement learning", IEEE Transactions on Cybernetics, Vol.53, No.6, pp. 3518-3531, 2021.  https://doi.org/10.1109/TCYB.2021.3128075
  2. Beom-suk Chung, Junseok Lim, In-Beom Park, Jonghun Park. "Setup change scheduling for semiconductor packaging facilities using a genetic algorithm with an operator recommender", IEEE Transactions on Semiconductor Manufacturing, Vol.27, No.3, pp. 377-387, 2014.  https://doi.org/10.1109/TSM.2014.2319302
  3. Weigert, Gerald, A. Klemmt, and S. Horn. "Design and validation of heuristic algorithms for simulation-based scheduling of a semiconductor backend facility", International Journal of Production Research, Vol.47, No.8, pp. 2165-2184, 2009.  https://doi.org/10.1080/00207540902744784
  4. Kim, J. K. "Enhancing robustness of deep reinforcement learning based semiconductor packaging lines scheduling with regularized training", Master's degree thesis, 2019. 
  5. Akcalt, Elif, Kazunori Nemoto, and Reha Uzsoy. "Cycle-time improvements for photolithography process in semiconductor manufacturing", IEEE Transactions on Semiconductor Manufacturing Vol.14, No.1, pp. 48-56, 2001.  https://doi.org/10.1109/66.909654
  6. Lim, S., Choi, H., Han, Y., and Lee, C. "Queue Modeling of Semiconductor Test Equipment Using Effective Background Process." International Conference on Modeling and Simulation. Berlin, Heidelberg: Springer Berlin Heidelberg, pp. 15-19, 2012. 
  7. Kress and Muller. "Semiconductor final-test scheduling under setup operator constraints". Computers & Operations Research, Vol.138, 2022. 
  8. Song, Y., Zhang, M. T., Yi, J., Zhang, L., and Zheng, L. "Bottleneck station scheduling in semiconductor assembly and test manufacturing using ant colony optimization." IEEE Transactions on Automation Science and Engineering, Vol.4, No.4, pp. 569-578, 2007.  https://doi.org/10.1109/TASE.2007.906341
  9. Zheng, T., Wan, J., Zhang, J., and Jiang, C. "Deep reinforcement learning-based workload scheduling for edge computing." Journal of Cloud Computing, Vol.11, No.1, pp. 3, 2022. 
  10. Liu, W., Yan, Y., Sun, Y., Mao, H., Cheng, M., Wang, P., and Ding, Z. "Online job scheduling scheme for low-carbon data center operation: An information and energy nexus perspective." Applied Energy, Vol.338, 2023. 
  11. Zhao, L., Fan, J., Zhang, C., Shen, W., and Zhuang, J. "A drl-based reactive scheduling policy for flexible job shops with random job arrivals." IEEE Transactions on Automation Science and Engineering, 2023. 
  12. Wu, X., Yan, X., Guan, D., and Wei, M. "A deep reinforcement learning model for dynamic job-shop scheduling problem with uncertain processing time." Engineering Applications of Artificial Intelligence, Vol.131, 2024. 
  13. Tian, Bei, Gang Xiao, and Yu Shen. "A deep reinforcement learning approach for dynamic task scheduling of flight tests." The Journal of Supercomputing, pp. 1-36, 2024. 
  14. Felder, M., Steiner, D., Busch, P., Trat, M., Sun, C., Bender, J., and Ovtcharova, J. "Energy-flexible job-shop scheduling using deep reinforcement learning." ESSN: 2701-6277, pp. 352-362, 2023.