Journal of the Korea Academia-Industrial cooperation Society (한국산학기술학회논문지)

The Korea Academia-Industrial cooperation Society (한국산학기술학회)
권호 표지
DOI QR코드

DOI QR Code

An Adaptive Scheduling Algorithm for Manufacturing Process with Non-stationary Rework Probabilities

비안정적인 Rework 확률이 존재하는 제조공정을 위한 적응형 스케줄링 알고리즘

  • Shin, Hyun-Joon (Dept. of Management Engineering, Sangmyung University) ;
  • Ru, Jae-Pil (Dept. of Management Engineering, Sangmyung University)
  • 신현준 (상명대학교 경영공학과) ;
  • 유재필 (상명대학교 경영공학과)
  • Received : 2010.09.16
  • Accepted : 2010.11.19
  • Published : 2010.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents an adaptive scheduling algorithm for manufacturing processes with non-stationary rework probabilities. The adaptive scheduling scheme named by hybrid Q-learning algorithm is proposed in this paper making use of the non-stationary rework probability and coupling with artificial neural networks. The proposed algorithm is measured by mean tardiness and the extensive computational results show that the presented algorithm gives very efficient schedules superior to the existing dispatching algorithms.

본 논문은 비안정적인 재작업 발생확률이 존재하는 제조공정을 위한 적응형 스케줄링 알고리즘을 제시한다. 본 논문에서 제안하는 하이브리드 Q-학습 알고리즘은 강화학습 기반의 Q-학습과 인공신경망을 결합한 알고리즘으로써 재작업확률이 불안정한 상황의 제조공정에 대해 학습을 통해 적응력을 가질 수 있도록 고안되었다. 제안 알고리즘은 평균지연시간을 척도로 그 성능을 평가하였고, 기존의 작업할당 알고리즘들과 다양한 실험 시나리오를 기반으로 비교함으로써 그 우수성을 보이도록 한다.

Keywords

References

  1. Flapper, S.D.P., J.C. Fransoo, R.A.C.M. Broekmeulen and K. Inderfurth, 2002. Planning and control of rework in the process industries : review, Production Planning & Control, 13(1), 26-34. https://doi.org/10.1080/09537280110061548
  2. Kang, Y.H., Kim, S.S. and Shin H.J. 2010. A dispatching algorithm for parallel machines with rework processes, Journal of the Operational Research Society, 61, 144-155. https://doi.org/10.1057/jors.2008.148
  3. Kuhl, M. E. and Laubisch, G. R. 2004. A simulation study of dispatching rules and rework strategies in semiconductor manufacturing, IEEE/SEMI Advanced Semiconductor Manufacturing Conference. https://doi.org/10.1109/ASMC.2004.1309590
  4. Lee, Y.H. and Pinedo, M. 1997. Scheduling jobs on parallel machines with sequence-dependent setup times, European Journal of Operational Research, 100(3), 464-474. https://doi.org/10.1016/S0377-2217(95)00376-2
  5. Lim, J.M., Bae, S.M. and Suh, J.J., 2006. A Learning based Algorithm for Traveling Salesman Problem, Journal of the Korean Institute of Industrial Engineers, 32(1), 61-73.
  6. Liu, J. J. and Ping, Y., 1996. Optimal lot-sizing in an imperfect production system with homogeneous reworkable jobs, European Journal of Operational Research, 91(3), 517-527. https://doi.org/10.1016/0377-2217(94)00339-4
  7. Sha, D. Y., Hsu, S. Y., Che, Z. H., and Chen, C. H., 2006. A dispatching rule for photolithography scheduling with an online rework strategy, Computers & Industrial Engineering, 50, 233-247. https://doi.org/10.1016/j.cie.2006.04.002
  8. Teunter, R. H. and Flapper, S. D. P., 2003. Lot-sizing for a single-product production system with rework of perishable production defectives, OR Spectrum, 25, 85-96 . https://doi.org/10.1007/s00291-002-0105-3
  9. Zargar, A. M., 1995. Effect Of Rework Strategies On Cycle Time, Computers & Industrial Engineering, 29(1/4), 239-243. https://doi.org/10.1016/0360-8352(95)00078-F