평블록 조립 공정에 대한 강화학습 기반 스케줄링 알고리즘 개발

다국어 초록 (Multilingual Abstract)

Rule-based heuristic algorithms and meta-heuristic algorithms have been studied to solve the scheduling problems of production systems. In recent research, reinforcement learning-based adaptive scheduling algorithms have been studied to solve complex problems with high-dimensional and vast state space. A production system in shipyards is a high-variable system where various production factors such as space, workforce, and resources are related. Adaptive scheduling according to the changes in the production system and surrounding environment must be performed in shipyards. In this paper, the main focus was on building a basic reinforcement learning model for scheduling problems of shipyards. A simplified model of the panel block shop in shipyards was assumed and the optimal policy for determining the input sequence of blocks was learned to reduce the flow time. The open source-based DES simulation kernel Simpy was incorporated into the environment of the reinforcement learning model.

목차 (Table of Contents)

• ABSTRACT
• 1. 서론
• 2. 강화학습
• 3. 문제 정의
• 4. 학습 결과
• 5. 결론 및 향후 연구
• References

참고문헌 (Reference)

1 배희철, "유전자 알고리즘을 활용한 조선 소조립 공정 일정계획" 대한산업공학회 20 (20): 33-40, 2007

2 황인혁, "시뮬레이티드 어닐링을 활용한 조선 소조립 라인 소일정계획 최적화" 한국시뮬레이션학회 19 (19): 73-82, 2010

3 곽동훈, "변동성 기반 대기행렬 이론을 이용한 조선 생산계획 및 조달계획 데이터 분석" 대한산업공학회 46 (46): 673-682, 2020

4 Levin, E., "Using Markov Decision Process for Learning Dialogue Strategies" IEEE 1998

5 Lee, Y. G., "Simulationbased Planning System for Shipbuilding" 1-16, 2020

6 Lee, W.J., "Simulation Based Multi-objective Fab Scheduling by Using Reinforcement Learning" IEEE 2019

7 Van Otterlo, M., "Reinforcement Learning and Markov Decision Processes, Reinforcement Learning" 3-42, 2012

8 Zhang, T., "Realtime Job Shop Scheduling Based on Simulation and Markov Decision Processes" IEEE 2017

9 Mnih, V., "Playing Atari with Deep Reinforcement Learning" 2013

10 Waschneck, B., "Optimization of Global Production Scheduling with Deep Reinforcement Learning" 72 (72): 1264-1269, 2018

11 Wang, Y. C., "Learning Policies for Single Machine Job Dispatching" 20 (20): 553-562, 2004

12 Sutton, R.S., "Introduction to Reinforcement Learning" MIT Press 1998

13 Woo, S. B., "Heuristic Algorithms for Resource Leveling in Pre-erection Scheduling and Erection Scheduling of Shipbuilding" 16 (16): 332-343, 2003

14 Kong, L.F., "Dynamic Single Machine Scheduling Using Q-learning Agent" IEEE 2005

15 Pierreval, H., "Dynamic Scheduling Selection of Dispatching Rules for Manufacturing System" 35 (35): 1575-1591, 1997

16 Aydin, M. E., "Dynamic Job-shop Scheduling Using Reinforcement Learning Agents" 33 (33): 169-178, 2000

17 Woo, J. H., "Development of Simulation Framework for Shipbuilding" 31 (31): 210-227, 2018

18 Van Hasselt, H., "Deep Reinforcement Learning with Double qlearning" 2016

19 Liu, Z., "Aggregate Production Planning for Shipbuilding with Variation-inventory Trade-offs" 49 (49): 6249-6272, 2011

20 Gabel, T., "Adaptive Reactive Job-shop Scheduling with Reinforcement Learning Agents" 24 (24): 14-18, 2008

21 Ðurasević, M., "A Survey of Dispatching Rules for the Dynamic Unrelated Machines Environment" 113 : 555-569, 2018

22 Deane, R. H., "A Dispatching Methodology for Balancing Workload Assignments in a Job Shop Production Facility" 4 (4): 277-283, 1972