Optimization of Arrangements of Heat-Storage Bricks in a Regenerative Combustion System by Tree Search
Source abstract
Abstract
When there are several different types of heat-storage ceramic bricks (checkers) that can be arranged in a regenerative combustion system, one must find an optimal arrangement (with the highest long-term Waste Heat Recovery Ratio) of these checkers, possibly of different types, in this regenerative combustion system. However, the number of possible arrangements of checkers in a heat regenerator could be huge. For example, when 5 different types of checkers are available for each of 14 positions in a heat regenerator, the total number of possible arrangements of checkers is 6,103,515,625. It is impractical to completely evaluate the efficiency of each of the 6,103,515,625 arrangements of checkers by 3D CFD simulations on Ansys Fluent. Here, we propose an optimization algorithm by tree search to tackle this optimization problem. This tree search method is motivated by the recent applications of Artificial Intelligence, based on combination of Deep Learning with Monte-Carlo Tree Search, to the incredibly complicated board game Go. Empirical evidence shows that this simple tree search algorithm leads to fast convergence of an optimization search and successfully suggests the optimal arrangement of checkers. This simple tree search method/algorithm may effectively enhance the thermal efficiency of a regenerative combustion system.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Control Systems Optimization · Advanced Combustion Engine Technologies · Statistical and Computational Modeling
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Mechanical Engineering, National Pingtung University of Science and Technology, Pingtung 912, Taiwan
Department of Mathematics, National Cheng-Kung University, Tainan City 701, Taiwan
Taiwan Semiconductor Manufacturing Company, Ltd., Tainan City 741, Taiwan
Funding
National Science and Technology Council of Taiwan
References (60)
Show source-provided references
1. Numerical Evaluation of the Energetic Performances of Structured and Random Packed Beds in Regenerative Thermal Oxidizers10.1016/j.applthermaleng.2006.10.016 ↗
2. Reverse Flow Reactors as Sustainable Devices for Performing Exothermic Reactions: Applications and Engineering Aspects10.1016/j.cep.2018.11.019 ↗
3. Coupled CFD and 1-D Dynamic Modeling for the Analysis of Industrial Regenerative Thermal Oxidizers10.1016/j.cep.2020.108117 ↗
4. Simulation of Fixed Bed Regenerative Heat Exchangers for Flue gas Heat Recovery10.1016/j.applthermaleng.2003.08.005 ↗
5. Study on Performance of the Ball Packed-Bed Regenerator: Experiments and Simulation10.1016/S1359-4311(01)00116-8 ↗
6. Karwa, R. (2020). Heat and MassTransfer, Springer Nature Singapore Pte Ltd.
7. Incropera, F.P., DeWitt, D.P., and Bergman, T.L. (2017). Principles of Heat and Mass Transfer, John Wiley & Sons.
8. Yu, Y.-L., Chen, T.-J., Chung, S.-C., Tsai, C.-H., Chen, C.-C., and Hong, Y.-J. (2018, January 19–21). A Study on the Numerical Simulation for the Heat Trans-fer Process of Regenerative Heat Chamber with Heat Storage Brick. Proceedings of the International Stirling Engine Conference, Tainan, Taiwan.
9. Chung, S.-C., Chen, T.-J., Yu, Y.-L., Tsai, C.-H., and Chen, C.-C. (, 2019). A Study on the Mathematical Model for the Heat Transfer Process of Regenerative Heat Chamber with Heat Storage. Proceedings of the 12th Pacific Symposium on Flow Visualization and Image Processing PSVIP12, Taiwan.
10. Syu, W.-J. (2017). Numerical Simulation Analysis of High Temperature Heat Exchange Module. [Master’s Thesis, National Pingtung University of Science and Technology].
11. Nield, D.A., and Bejan, A. (2017). Convection in Porous Media, Springer International Publishing AG.10.1007/978-3-319-49562-0 ↗
12. Shah, R.K., and Sekulic, D.P. (2003). Fundamentals of Heat Exchanger Design, John Wiley & Sons.10.1002/9780470172605 ↗
13. Kilkovský, B. (2020). Review of Design and Modeling of Regenerative Heat Exchangers. Energies, 13.10.3390/en13030759 ↗
14. Monarkin, N., and Monarkina, T. (2022). Experimental Research of a Regenerative Heat Exchanger. Processes, 10.10.3390/pr10010100 ↗
15. Bird, R.B., Stewart, W.E., and Lightfoot, E.N. (2002). Transport Phenomena, John Wiley & Sons.
16. Abramson, B. (1987). The Expected-Outcome Model of Two-Player Games, Department of Computer Science, Columbia University. Technical Report.
17. Brügmann, B. (1993). Monte Carlo Go, Department of Physics, Syracuse University. Technical Report.
18. Coulom, R. (2006). Efficient Selectivity and Backup Operators in Monte-Carlo Tree Search. International Conference on Computers and Games, Springer.10.1007/978-3-540-75538-8_7 ↗
19. Kocsis, L., and Szepesvári, C. (2006, January 18–22). Bandit based Monte Carlo planning. Proceedings of the 17th European Conference on Machine Learning, ECML’06, Berlin, Germany.10.1007/11871842_29 ↗
20. Progressive Strategies for Monte-Carlo Tree Search10.1142/S1793005708001094 ↗
21. Cazenave, T., and Jouandeau, N. (2007). On the Parallelization of UCT. Proceedings of the Computer Games Workshop, HAL CCSD.
22. Cazenave, T., and Jouandeau, N. (2008). A Parallel Monte-Carlo Tree Search Algorithm. Computers and Games: 6th International Conference, CG 2008, Beijing, China, 29 September–1 October 2008, Springer.10.1007/978-3-540-87608-3_1 ↗
23. Gelly, S., and Wang, Y. (, 2006). Exploration Exploitation in Go: UCT for Monte-Carlo Go. Proceedings of the Neural Information 19, Processing Systems Conference on Line Trading of Exploration and Exploitation Workshop, Vancouver, BC, Canada.
24. Monte-Carlo Tree Search and Rapid Action Value Estimation in Computer Go10.1016/j.artint.2011.03.007 ↗
25. The Grand Challenge of Computer Go: Monte-Carlo Tree Search and Extensions10.1145/2093548.2093574 ↗
26. Temporal-Difference Search in Computer Go10.1007/s10994-012-5280-0 ↗
27. Van den Broeck, G., Driessens, K., and Ramon, J. (2009). Monte-Carlo Tree Search in Poker Using Expected Reward Distributions, Springer. Asian Conference on Machine Learning.10.1007/978-3-642-05224-8_28 ↗
28. Robles., D., Rohlfshagen, P., and Lucas, S.M. (September, January 31). Learning Non-Random Moves for Playing Othello: Improving Monte-Carlo Tree Search. Proceedings of the 2011 IEEE Conference on Computational Intelligence and Games (CIG’11), Seoul, Republic of Korea.10.1109/CIG.2011.6032021 ↗
29. Monte-Carlo tree search in Hex10.1109/TCIAIG.2010.2067212 ↗
30. Monte-Carlo Tree Search in Lines of Action10.1109/TCIAIG.2010.2061050 ↗
31. Teytaud, F., and Teytaud, O. (2010). Creating an Upper-Confidence Tree Program for Havannah. Advances in Computer Games, Springer.10.1007/978-3-642-12993-3_7 ↗
32. Mastering the Game of Go with Deep Neural Networks and Tree Search10.1038/nature16961 ↗
33. Science News Staff (2016). From AI to Protein Folding: Our Breakthrough Runners-Up, Science News Staff.
34. Coulom, R. (, 2008). The Monte-Carlo Revolution in Go. Proceedings of the Japanese-French Frontiers of Science Symposium, Available online: https://www.remi-coulom.fr/JFFoS/JFFoS.pdf.
35. Mastering the Game of Go without Human Knowledge10.1038/nature24270 ↗
36. A General Reinforcement Learning Algorithm That Masters Chess, Shogi, and Go through Self-Play10.1126/science.aar6404 ↗
37. Learning the Game of Go by Scalable Network without Prior Knowledge of Komi10.1109/TG.2020.2992858 ↗
38. Gaina, R.D., Perez-Liebana, D., Lucas, S.M., Sironi, C.F., and Winands, M.H. (2020, January 24–27). Self-Adaptive Rolling Horizon Evolutionary Algorithms for General Video Game Playing. Proceedings of the 2020 IEEE Conference on Games, Osaka, Japan.10.1109/CoG47356.2020.9231587 ↗
39. Rolling Horizon Evolutionary Algorithms for General Video Game Playing10.1109/TG.2021.3060282 ↗
40. Planning Chemical Syntheses with Deep Neural Networks and Symbolic AI10.1038/nature25978 ↗
41. Addressing adjacency Constraints in Rectangular Floor Plans using Monte-Carlo Tree Search10.1016/j.autcon.2020.103187 ↗
42. DrugSynthMC: An Atom-Based Generation of Drug-like Molecules with Monte Carlo Search10.1021/acs.jcim.4c01451 ↗
43. Two-Step Monte Carlo Tree Search for Optimal Design of High-Frequency Toroidal Inductors in Power Electronics Circuits10.1109/TMAG.2024.3493941 ↗
44. Monte Carlo Tree Search: A Review of Recent Modifications and Applications10.1007/s10462-022-10228-y ↗
45. Plaat, A. (2022). Deep Reinforcement Learning, Springer Nature Singapore Pte Ltd.10.1007/978-981-19-0638-1 ↗
46. The Monte Carlo Method10.1080/01621459.1949.10483310 ↗
47. Terrell, G. (1999). Mathematical Statistics: A Unified Introduction, Springer, NewYork, Inc.
48. DeGroot, M., and Schervish, M. (2012). Probability and Statistics, Pearson Education, Inc.
49. Roe, B. (2020). Probability and Statistics in the Physical Sciences, Springer Nature, Switzerland AG.
50. Ito, K., and McKean, H.P. (1965). Diffusion Processes and Their Sample Paths, Springer.
51. Transformation of Markov Processes by Multiplicative Functionals
52. The Pricing of Options and Corporate Liabilities10.1086/260062 ↗
53. Storn, R., and Price, K.V. (2005). Differential Evolution: A Practical Approach to Global Optimization, Springer.
54. Differential Evolution with Composite Trial Vector Generation Strategies and Control Parameters10.1109/TEVC.2010.2087271 ↗
55. Arafa, M., Sallam, E.A., and Fahmy, M.M. (2014, January 6–8). An Enhanced Differential Evolution Optimization Algorithm. Proceedings of the 2014 Fourth International Conference on Digital Information and Communication Technology and its Applications (DICTAP), Bangkok, Thailand.10.1109/DICTAP.2014.6821685 ↗
56. Chen, T.-J., Hong, Y.-J., Lin, C.-H., and Wang, J.-Y. (2023). Optimization on Linkage System for Vehicle Wipers by the Method of Differential Evolution. Appl. Sci., 13.10.3390/app13010332 ↗
57. Mauri, R. (2023). Transport Phenomena in Multiphase Flows, Springer Nature Switzerland AG.10.1007/978-3-031-28920-0 ↗
58. Chaichian, M., Merches, I., and Tureanu, A. (2012). Mechanics, Springer.10.1007/978-3-642-17234-2 ↗
59. An Experimental Verification of Pressure Drop for Integrated Regenerative Equipment
60. Optimizing Building Thermal Insulation: The Impact of Brick Geometry and Thermal Coefficient on Energy Efficiency and Comfort10.3390/ceramics6030089 ↗