Abstract
Smart manufacturing utilizes digital twins that are virtual forms of their production plants for analyzing and optimizing decisions. Digital twins have been mainly developed as discrete-event models (DEMs) to represent the detailed and stochastic dynamics of productions in the plants. The optimum decision is achieved after simulating the DEM-based digital twins under various what-if decision candidates; thus, simulation acceleration is crucial for rapid optimum determination for given problems. For the acceleration of discrete-event simulations, adaptive abstraction-level conversion approaches have been previously proposed to switch active models of each machine group between a set of DEM components and a corresponding lookup table-based mean-delay model during runtime. The switching is decided by detecting the machine group’s convergence into (or divergence from) a steady state. However, there is a tradeoff between speedup and accuracy loss in the adaptive abstraction convertible simulation (AACS), and inaccurate simulation can degrade the quality of the optimum (i.e., the distance between the calculated optimum and the actual optimum). In this paper, we propose a simulation-based optimization (SBO) that optimizes the problem based on a genetic algorithm (GA) while tuning specific hyperparameters (related to the tradeoff control) to maximize the speedup of AACS under a specified accuracy constraint. For each individual, the proposed method distributes the overall computing budget for multiple simulation runs (considering the digital twin’s probabilistic property) into the hyperparameter optimization (HPO) and fitness evaluation. We propose an efficient HPO method that manages multiple Gaussian process models (as speedup-estimation models) to acquire promising optimal hyperparameter candidates (that maximize the simulation speedups) with few attempts. The method also reduces each individual’s exploration overhead (as the population evolves) by estimating each hyperparameter’s expected speedup using previous exploration results of neighboring individuals without actual simulation executions. The proposed method was applied to optimize raw-material releases of a large-scale manufacturing system to prove the concept and evaluate the performance under various situations.
- Aldeida Aleti and Irene Moser. 2016. A systematic literature review of adaptive parameter control methods for evolutionary algorithms. ACM Computing Surveys (CSUR) 49, 3 (2016), 1–35.Google ScholarDigital Library
- June-Young Bang and Yeong-Dae Kim. 2010. Hierarchical Production Planning for Semiconductor Wafer Fabrication Based on Linear Programming and Discrete-Event Simulation. IEEE Transactions on Automation Science and Engineering 7, 2(2010), 326–336. https://doi.org/10.1109/TASE.2009.2021462Google ScholarCross Ref
- Jennifer Bekki, J.W. Fowler, Gerald Mackulak, and Barry Nelson. 2010. Indirect cycle time quantile estimation using the Cornish–Fisher expansion. IIE Transactions 42(01 2010). https://doi.org/10.1080/07408170903019135Google ScholarCross Ref
- Chun-Hung Chen and Loo Hay Lee. 2011. Stochastic simulation optimization: an optimal computing budget allocation. Vol. 1. World scientific.Google Scholar
- M A Chik, A B Rahim, A Z Md Rejab, K Ibrahim, and U. Hashim. 2014. Discrete event simulation modeling for semiconductor fabrication operation. In 2014 IEEE International Conference on Semiconductor Electronics (ICSE2014). 325–328. https://doi.org/10.1109/SMELEC.2014.6920863Google ScholarCross Ref
- D.P. Connors, G.E. Feigin, and D.D. Yao. 1996. A queueing network model for semiconductor manufacturing. IEEE Transactions on Semiconductor Manufacturing 9, 3(1996), 412–427. https://doi.org/10.1109/66.536112Google ScholarCross Ref
- Carlos Alberto Barrera Diaz, Tehseen Aslam, and Amos H. C. Ng. 2021. Optimizing Reconfigurable Manufacturing Systems for Fluctuating Production Volumes: A Simulation-Based Multi-Objective Approach. IEEE Access 9(2021), 144195–144210. https://doi.org/10.1109/ACCESS.2021.3122239Google ScholarCross Ref
- Ágoston E Eiben, Robert Hinterding, and Zbigniew Michalewicz. 1999. Parameter control in evolutionary algorithms. IEEE Transactions on evolutionary computation 3, 2(1999), 124–141.Google ScholarDigital Library
- Matthias Feurer and Frank Hutter. 2019. Hyperparameter optimization. In Automated machine learning. Springer, Cham, 3–33.Google Scholar
- D. Fronckowiak, A. Peikert, and K. Nishinohara. 1996. Using discrete event simulation to analyze the impact of job priorities on cycle time in semiconductor manufacturing. In IEEE/SEMI 1996 Advanced Semiconductor Manufacturing Conference and Workshop. Theme-Innovative Approaches to Growth in the Semiconductor Industry. ASMC 96 Proceedings. 151–155. https://doi.org/10.1109/ASMC.1996.557987Google ScholarCross Ref
- Dean Grosbard, Adar Kalir, Israel Tirkel, and Gad Rabinowitz. 2013. A queuing network model for wafer fabrication using decomposition without aggregation. In 2013 IEEE International Conference on Automation Science and Engineering (CASE). 717–722. https://doi.org/10.1109/CoASE.2013.6653941Google ScholarCross Ref
- Changwu Huang, Yuanxiang Li, and Xin Yao. 2019. A survey of automatic parameter tuning methods for metaheuristics. IEEE transactions on evolutionary computation 24, 2(2019), 201–216.Google Scholar
- James P. Ignizio. 2009. Optimizing Factory Performance: Cost-Effective Ways to Achieve Significant and Sustainable Improvement(1st ed.). McGraw Hill, New York, USA.Google Scholar
- J. Jimenez, B. Kim, J. Fowler, G. Mackulak, and You In Choung. 2002. Operational modeling and simulation of an inter-bay AMHS in semiconductor wafer fabrication. In Proceedings of the Winter Simulation Conference, Vol. 2. 1377–1382 vol.2. https://doi.org/10.1109/WSC.2002.1166405Google ScholarCross Ref
- Rachel T. Johnson, John W. Fowler, and Gerald T. Mackulak. 2005. A Discrete Event Simulation Model Simplification Technique. In Proceedings of the 37th Conference on Winter Simulation (Orlando, Florida) (WSC ’05). Winter Simulation Conference, 2172–2176.Google ScholarCross Ref
- Donald R Jones, Matthias Schonlau, and William J Welch. 1998. Efficient global optimization of expensive black-box functions. Journal of Global optimization 13, 4 (1998), 455–492.Google ScholarDigital Library
- Yeong-Dae Kim, Sang-Oh Shim, Bum Choi, and Hark Hwang. 2003. Simplification methods for accelerating simulation-based real-time scheduling in a semiconductor wafer fabrication facility. IEEE Transactions on Semiconductor Manufacturing 16, 2(2003), 290–298. https://doi.org/10.1109/TSM.2003.811890Google ScholarCross Ref
- Donald E. Knuth. 1997. The Art of Computer Programming, Volume 1 (3rd Ed.): Fundamental Algorithms. Addison Wesley Longman Publishing Co., Inc., USA.Google ScholarDigital Library
- Oliver Kramer. 2010. Evolutionary self-adaptation: a survey of operators and strategy parameters. Evolutionary Intelligence 3, 2 (2010), 51–65.Google ScholarCross Ref
- James T. Lin and Chien-Ming Chen. 2015. Simulation optimization approach for hybrid flow shop scheduling problem in semiconductor back-end manufacturing. Simulation Modelling Practice and Theory 51 (2015), 100–114. https://doi.org/10.1016/j.simpat.2014.10.008Google ScholarCross Ref
- Dong C Liu and Jorge Nocedal. 1989. On the limited memory BFGS method for large scale optimization. Mathematical programming 45, 1 (1989), 503–528.Google Scholar
- Lars Mönch, John W. Fowler, and Scott J. Mason. 2012. Production Planning and Control for Semiconductor Wafer Fabrication Facilities: Modeling, Analysis, and Systems(1st ed.). Springer, New York, USA.Google Scholar
- D. Nazzal and L.F. McGinnis. 2005. Queuing models of vehicle-based automated material handling systems in semiconductor fabs. In Proceedings of the Winter Simulation Conference, 2005.8 pp.–. https://doi.org/10.1109/WSC.2005.1574540Google ScholarCross Ref
- Ashkan Negahban and Jeffrey S. Smith. 2014. Simulation for manufacturing system design and operation: Literature review and analysis. Journal of Manufacturing Systems 33, 2 (2014), 241–261. https://doi.org/10.1016/j.jmsy.2013.12.007Google ScholarCross Ref
- Oliver Rose. 2007. Improved simple simulation models for semiconductor wafer factories. In 2007 Winter Simulation Conference. 1708–1712. https://doi.org/10.1109/WSC.2007.4419793Google ScholarCross Ref
- Moon Gi Seok, Wentong Cai, and Daejin Park. 2021. Hierarchical Aggregation/Disaggregation for Adaptive Abstraction-Level Conversion in Digital Twin-Based Smart Semiconductor Manufacturing. IEEE Access 9(2021), 71145–71158. https://doi.org/10.1109/ACCESS.2021.3073618Google ScholarCross Ref
- Moon Gi Seok, Wentong Cai, Hessam S. Sarjoughian, and Daejin Park. 2020. Adaptive Abstraction-Level Conversion Framework for Accelerated Discrete-Event Simulation in Smart Semiconductor Manufacturing. IEEE Access 8(2020), 165247–165262. https://doi.org/10.1109/ACCESS.2020.3022276Google ScholarCross Ref
- Moon GI Seok, Chew Wye Chan, Wentong Cai, Hessam S. Sarjoughian, and Daejin Park. 2020. Runtime Abstraction-Level Conversion of Discrete-Event Wafer-Fabrication Models for Simulation Acceleration. In Proceedings of the 2020 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation (Miami, FL) (SIGSIM-PADS ’20). Association for Computing Machinery, New York, NY, USA, 83–92. https://doi.org/10.1145/3384441.3395982Google ScholarDigital Library
- Moon Gi Seok, Wen Jun Tan, Wentong Cai, and Daejin Park. 2022. Digital-Twin Consistency Checking Based on Observed Timed Events With Unobservable Transitions in Smart Manufacturing. IEEE Transactions on Industrial Informatics(2022), 1–12. https://doi.org/10.1109/TII.2022.3200598Google ScholarCross Ref
- Moon Gi Seok, Wen Jun Tan, Boyi Su, and Wentong Cai. 2022. Hyperparameter Tunning in Simulation-Based Optimization for Adaptive Digital-Twin Abstraction Control of Smart Manufacturing System. In Proceedings of the 2022 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation(Atlanta, GA, USA) (SIGSIM-PADS ’22). Association for Computing Machinery, New York, NY, USA, 61–68. https://doi.org/10.1145/3518997.3531024Google ScholarDigital Library
- ES Skakov and VN Malysh. 2018. Parameter meta-optimization of metaheuristics of solving specific NP-hard facility location problem. In Journal of Physics: Conference Series, Vol. 973. IOP Publishing, 012063.Google Scholar
- C. P. L. Veeger, L. F. P. Etman, E. Lefeber, I. J. B. F. Adan, J. van Herk, and J. E. Rooda. 2011. Predicting Cycle Time Distributions for Integrated Processing Workstations: An Aggregate Modeling Approach. IEEE Transactions on Semiconductor Manufacturing 24, 2(2011), 223–236. https://doi.org/10.1109/TSM.2010.2094630Google ScholarCross Ref
- Jia Wu, Xiu-Yun Chen, Hao Zhang, Li-Dong Xiong, Hang Lei, and Si-Hao Deng. 2019. Hyperparameter optimization for machine learning models based on Bayesian optimization. Journal of Electronic Science and Technology 17, 1(2019), 26–40.Google Scholar
- Li Yang and Abdallah Shami. 2020. On hyperparameter optimization of machine learning algorithms: Theory and practice. Neurocomputing 415(2020), 295–316.Google ScholarCross Ref
- Enrique Ruiz Zúñiga, Matias Urenda Moris, Anna Syberfeldt, Masood Fathi, and Juan Carlos Rubio-Romero. 2020. A Simulation-Based Optimization Methodology for Facility Layout Design in Manufacturing. IEEE Access 8(2020), 163818–163828. https://doi.org/10.1109/ACCESS.2020.3021753Google ScholarCross Ref
Index Terms
- Hyperparameter Tuning with Gaussian Processes for Optimal Abstraction Control in Simulation-based Optimization of Smart Semiconductor Manufacturing Systems
Recommendations
Hyperparameter Tunning in Simulation-based Optimization for Adaptive Digital-Twin Abstraction Control of Smart Manufacturing System
SIGSIM-PADS '22: Proceedings of the 2022 ACM SIGSIM Conference on Principles of Advanced Discrete SimulationSmart manufacturing utilizes digital twins (DTs) that are virtual forms of their production plants for optimizing decisions. Discrete-event models (DEMs) are frequently used to model the production dynamics of the plants. To accelerate the performance ...
Simulation of manufacturing systems
WSC '85: Proceedings of the 17th conference on Winter simulationSimulation is the most widely used technique for designing and analyzing manufacturing systems. However, there is an unfortunate impression that simulation is just a complicated exercise in computer programming. Consequently, many “studies” have been ...
Performance optimization of a flexible manufacturing system using simulation: the Taguchi method versus OptQuest
The Taguchi method is widely used in the field of manufacturing systems performance simulation and improvement. On the other hand, Arena/OptQuest is one of the most efficient contemporary simulation/optimization software tools. The objective of this paper ...
Comments