Automating the static and seismic design of 2-D multistorey reinforced concrete structures by using Monte Carlo Tree Search and Genetic Algorithm

Abstract

This research is based on the idea that certain cognitive-intensive tasks typically carried out by structural engineers—such as choosing how to effectively arrange a building’s structure—can be successfully automated. In this article we investigate two techniques widely used in the field of Artificial Intelligence, namely Monte Carlo Tree Search (MCTS) and Genetic Algorithm (GA). Following a tabula rasa approach, according to which no hints nor external data are used as a reference for navigating the search space, we demonstrate how structural designs of two-dimensional multi-storey reinforced concrete structures can be generated, with no human intervention, by implementing and combining the two techniques from a reinforcement-learning perspective. The design tasks assigned to the developed software agents concern civil structures under static and seismic loads, and the basis for comparison is represented by a combination of construction cost and greenhouse gas emissions associated with the making of the structures. In the article, based on the main concepts of Computational Mechanics, a theoretical framework is introduced, which allows to represent both structures and design tasks in a simple, analytical way. The process of gamification, to which MCTS is often associated, is then described, so that structural design is reduced to the concepts of state, actions and payoff.. Finally, case studies are presented in which different agents—based respectively on GA, MCTS, and a combination of both—are tested. The results suggest that hybrid approaches, where GA operates first followed by MCTS, are the most effective.

Keywords

Monte Carlo Tree Search / Genetic Algorithm / Structural design / Reinforcement learning / Reinforced concrete structures / Artificial Intelligence

References

[1] Aggarwal CC. Neural networks and deep learning, 2018Springer

[2] Amadio C, Fragiacomo M, Lucia P, Luca OD. Optimized design of a steel-glass parabolic vault using evolutionary multi-objective algorithms. International Journal of Space Structures, 2008, 23(1): 21-33

[3] Arciszewski T. Topping BHV. The Inductive System: A New Tool in Civil Engineering. Optimization and Artificial Intelligence in Civil and Structural Engineering, 1992Springer

[4] Arciszewski T, Ziarko W. Inductive learning in civil engineering: A rough sets approach. Microcomputers in Civil Engineering, 1990, 5(1): 19-28

[5] Arneson B, Hayward RB, Henderson P. Monte carlo tree search in hex. IEEE Transactions on Computational Intelligence and AI in Games, 2010, 2(4): 251-258

[6] Auer P, Cesa-Bianchi N, Fischer P. Finite-time analysis of the multiarmed bandit problem. Machine Learning, 2002, 47: 235-256

[7] Various Authors (2022). How to calculate embodied carbon. The Institution of Structural Engineers. Retrieved February 13, 2025 from http://www.istructe.org. Accessed 13 February 2025

[8] Bagrianski, S., & Prevost, J. (2017). An Introduction to Matrix Structural Analysis and Finite Element Method. WSPC.

[9] Baier, H., & Kaisers, M. (2021). Towards explainable MCTS. Proceedings of the AAAI Conference on Artificial Intelligence. https://doi.org/10.48550/arXiv.2506.13223

[10] Baker BM, Ayechew MA. A genetic algorithm for the vehicle routing problem. Computers & Operations Research, 2003, 30(5): 787-800

[11] Bathe KJ. Finite element procedures, 1995First Edition

[12] Bayzidi H, Talatahari S, Saraee M, Lamarche C-P. Social Network Search for Solving Engineering Optimization Problems. Computational Intelligence and Neuroscience, 2021

[13] Bozorgnia Y, Bertero VV. Earthquake Engineering: From Engineering Seismology to Performance-Based Engineering, 2004CRC Press

[14] Browne, C. et al. (2012). A Survey of MCTS Methods. IEEE Transactions on Computational Intelligence and AI in Games.

[15] Cascardi A, Micelli F, Aiello M. Analytical model based on artificial neural network for masonry shear walls strengthened with FRM systems. Composites Part b: Engineering, 2016, 95: 252-263

[16] Chakraborty D, Awolusi I, Gutierrez L. An explainable machine learning model to predict and elucidate the compressive behavior of high-performance concrete. Results in Engineering, 2021, 11 100245

[17] Chaslot GMJ-B, Bakkes SCJ, Szita I, Spronck P. Monte-carlo tree search: A new framework for game ai. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 2008

[18] Chaslot GMJ-B, Winands MHM, Van den Herik HJ, Uiterwijk JWHM, Bouzy B. Progressive strategies for MonteCarlo Tree Search. New Math Nat Comput, 2008, 4(3): 343-359

[19] Chen, S.-Y., Situ, J., Mobasher, B., & Rajan, S. D. (1996). Use of genetic algorithms for the automated design of residential steel roof trusses. Advances in Structural Optimization-Proceedings of the First U.S.-Japan Joint Seminar on Structural Optimization, ASCE, New York.

[20] Chen T-Y, Chen C-J. Improvements of simple genetic algorithm in structural design. International Journal for Numerical Methods in Engineering, 1997, 40: 1323-1334

[21] Chikun, C. (2010). Go: A Complete Introduction to the Game. 1st Edition. Kiseido Publishing Co.

[22] Chisari C, Amadio C. TOSCA: A tool for optimisation in structural and civil engineering analyses. International Journal of Advanced Structural Engineering, 2018, 10: 401-419

[23] Chisari C, Bedon C, Amadio C. Dynamic and static identification of base-isolated bridges using genetic algorithms. Engineering Structures, 2015, 102: 80-92

[24] Chopra, A. K. (2016). Dynamics of Structures: Theory and Applications to Earthquake Engineering, Pearson College Division.

[25] Clary P, Morais P, Fern A, Hurst J. Monte-carlo planning for agile legged locomotion. Proceedings of the International Conference on Automated Planning and Scheduling, 2018, 28(1): 446-450

[26] Coello Coello CA, Rudnick M, Christiansen AD. Using genetic algorithms for optimal design of trusses. Proceedings Sixth International Conference on Tools with Artificial Intelligence, TAI, 1994, 94: 88-94

[27] De Vries A. The growing energy footprint of artificial intelligence. Joule, 2023, 7(10): 2191-2194

[28] Dhar P. The carbon impact of artificial intelligence. Nature Machine Intelligence, 2020, 2: 423-425

[29] Dias WPS, Weerasinghe RLD. Artificial neural networks for construction bid decisions. Civil Engineering Systems, 1996, 13(3): 239-253

[30] Dieb TM, Ju S, Shiomi J, et al.. Monte carlo tree search for materials design and discovery. MRS Communications, 2019, 9: 532-536

[31] Doyle JF. Static and Dynamic Analysis of Structures: With an Emphasis on Mechanics and Computer Matrix Methods, 1991Kluwer Academic Publishers

[32] Dung CV, Le Duc A. Autonomous concrete crack detection using deep fully convolutional neural network. Automation in Construction, 2019, 99: 52-58

[33] ECSO (European Construction Sector Observatory) (2017). Fostering the international competitiveness of EU construction enterprises. European Commission. Retrieved February 13, 2025, from https://www.ec.europa.eu

[34] Edelkamp S, Gath M, Greulich C, Humann M, Herzog O, Lawo M. Monte-Carlo Tree Search for Logistics, 2016Springer International Publishing427440

[35] Fadaki M, Asadikia A. Augmenting monte carlo tree search for managing service level agreements. International Journal of Production Economics, 2024, 271 109206

[36] Fahmy AS, El-Madawyb ME, Gobran YA. Using artificial neural networks in the design of orthotropic bridge decks. Alexandria Engineering Journal, 2016, 55: 4

[37] Gaina, R. D., Perez-Liebana, D., Lucas, S. M., Sironi, C. F., & Winands, M. H. M. (2020). Selfadaptive rolling horizon evolutionary algorithms for general video game playing. 2020 IEEE Conference on Games (CoG), pp 367–374. https://doi.org/10.1109/CoG47356.2020.9231587

[38] Gamerman D. Markov chain monte carlo: Stochastic simulation for Bayesian inference, 1997CRC Press

[39] Gaymann A, Montomoli F. Deep neural network and Monte Carlo tree search applied to fluid-structure topology optimization. Scientific Reports, 2019

[40] Ghaheri A, Shoar S, Naderan M, Hoseini SS. The applications of genetic algorithms in medicine. Oman Medical Journal, 2015, 30(6): 406-416

[41] Hayek SI. Mechanical Vibration and Damping, 2003WILEY-VCH Verlag GmbH & Co KGaA

[42] Holland, J. (1992). Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology. Control, and Artificial Intelligence. Bradford Books. https://it.wikipedia.org/wiki/Speciale:RicercaISBN/0262581116

[43] Houssein EH, Hossam Abdel Gafar M, Fawzy N, et al.. Recent metaheuristic algorithms for solving some civil engineering optimization problems. Scientific Reports, 2025, 15 7929

[44] Hudson MG, Parmee IC. Sharpe J. The application of genetic algorithms to conceptual design. AI System Support for Conceptual Design, 1995Springer-Verlag17-36

[45] Hughes TJR. The Finite Element Method: Linear Static and Dynamic Finite Element Analysis, 20001Dover Publications

[46] Inazumi S, Intui S, Jotisankasa S, Chaiprakaikeow S, Kojima K. Artificial intelligence system for supporting soil classification. Results in Engineering, 2020, 8 100188

[47] Islam MS, Rokonuzzaman M. Optimized design of foundations: An application of genetic algorithms. Australian Journal of Civil Engineering, 2018, 16: 2018-2021

[48] Kanyilmaz A, Navarro Tichell PR, Loiacono D. A genetic algorithm tool for conceptual structural design with cost and embodied carbon optimization. Engineering Applications of Artificial Intelligence, 2022, 112: 10471

[49] Kartal B, Nunes E, Godoy J, Gini M. Monte Carlo Tree Search for Multi-Robot Task Allocation. Proceedings of the AAAI Conference on Artificial Intelligence, 2016

[50] Kelly DW. A dual formulation for generating information about constrained optima in automated design. Computer Methods in Applied Mechanics and Engineering, 1975, 5(3): 339-352

[51] Kita E, Tamaki T, Tanie H. Burczyński T, Osyczka A. Structural Design Using Genetic Algorithm. IUTAM Symposium on Evolutionary Methods in Mechanics, 2004Springer

[52] Kocsis, L., & Szepesvári, C. (2006). Bandit Based Monte-Carlo Planning. Lecture Notes in Computer Science, pp 282–293.

[53] Kővári B, Pelenczei B, Knáb IG, Bécsi T. Beyond trial and error: Lane keeping with Monte Carlo tree search-driven optimization of reinforcement learning. Electronics, 2024, 13(112058

[54] Koza JR. Genetic Programming: On the Programming of Computers by Means of Natural Selection, 1992MIT Press

[55] Krish S. A practical generative design method. Computer-Aided Design, 2011, 43(188-100

[56] Labbé, Y., Zagoruyko, S., Kalevatykh, I., Laptev, I., Carpentier, J., Aubry, M., & Sivic, J. (2020). Monte-Carlo Tree Search for Efficient Visually Guided Rearrangement Planning. IEEE Robotics and Automation Letters. https://arxiv.org/abs/1904.10348

[57] Laschet, C., Buijs, J. O. D., Winands, M. H. M., & Pauws, S. (2020). Service Selection using Predictive Models and Monte-Carlo Tree Search. Retrieved February 13, 2025 from https://arxiv.org/abs/2002.04852

[58] Li H, Love P. Using improved genetic algorithms to facilitate time-cost optimization. Journal of Construction Engineering and Management, 1997, 123(3): 233-237

[59] Li K, Deng Q, Zhang L, Fan Q, Gong G, Ding S. An effective MCTS-based algorithm for minimizing makespan in dynamic flexible job shop scheduling problem. Computers & Industrial Engineering, 2021, 155 107211

[60] Lorterapong, P., & Rattanadamrongagsorn, T. (2001). Viewing Construction Scheduling as a Constraint Satisfaction Problem. In Topping BHV, Kumar B (Editors) Proceedings of the Sixth International Conference on the Application of Artificial Intelligence to Civil and Structural Engineering, Civil-Comp Press, Stirlingshire, UK. https://doi.org/10.4203/ccp.74.8

[61] Lubosch M, Kunath M, Winkler H. Industrial scheduling with Monte Carlo tree search and machine learning. Procedia CIRP, 2018

[62] Luo R, Wang Y, Xiao W, Zhao X. AlphaTruss: Monte carlo tree search for optimal truss layout design. Buildings, 2022, 12: 641

[63] Mankowitz DJ, Michi A, Zhernov A, et al.. Faster sorting algorithms discovered using deep reinforcement learning. Nature, 2023, 618: 257-263

[64] Matsuzaki K. Empirical Analysis of PUCT Algorithm with Evaluation Functions of Different Quality. Conference on Technologies and Applications of Artificial Intelligence (TAAI), 2018

[65] Mazzoni, S., Frank, M., Michael, H. S., & Gregory, L. F. (2006). OpenSees Command Language Manual. Pacific Earthquake Engineering Research (PEER) Center, vol 264.

[66] Mehat J, Cazenave T. A parallel general game player. KI Journal, 2011, 25(1): 43-47

[67] Miles JC, Sisk GM, Moore CJ. The conceptual design of commercial buildings using a genetic algorithm. Computers and StructurEs, 2001, 79(17): 1583-1592

[68] Minaee, S., Mikolov, T., Nikzad, N., Chenaghlu, M., Socher, R., Amatriain, X., & Gao, J. (2024). Large Language Models: A Survey. Retrieved February 13, 2025, from https://doi.org/10.48550/arXiv.2402.06196

[69] MIT – Ministero delle Infrastrutture e dei Trasporti (2019). Decreto Ministeriale del 14 gennaio 2008 - Aggiornamento delle «Norme tecniche per le costruzioni». GU Serie Generale. Ordinario n. 8 (in Italian).

[70] Mitchell, M. (1996). An Introduction to Genetic Algorithms. pp. 205, Bradford Books.

[71] National Earthquake Information Center (2023). M 7.8 - 26 km ENE of Nurdağı, Turkey. United States Geological Survey. Retrieved February 13, 2025 from https://earthquake.usgs.gov

[72] Nguyen THD, Lee WS, Leong TY. Bootstrapping Monte Carlo Tree Search with an Imperfect Heuristic. Lecture Notes in Computer Science, 2012

[73] Omara FA, Arafa MM. Genetic algorithms for task scheduling problem. Journal of Parallel and Distributed Computing, 2010, 70(1): 13-22

[74] Parducci, A. (2007). Progetto delle costruzioni in zona sismica. Liguori Editore, pp 512 (in Italian)

[75] Paz, M. (2009). Matrix Structural Analysis and Dynamics: Theory and Computation. Computers and Structures Inc.

[76] Pepels T, Winands MHM, Lanctot M. Real-time Monte Carlo tree search in Ms Pac-Man. IEEE Transactions on Computational Intelligence and AI in Games, 2014, 6(3): 245-257

[77] Pérez J, Rico M, Rabuñal J, Abella F. Applying Genetic Programming to Civil Engineering in the Improvement of Models, Codes and Norms. Advances in Artificial Intelligence IBERAMIA, 2008

[78] Rafiq, Y., Sui, C., Zhou, G. C., Easterbrook, D., & Bugmann, G. (2005). Using Artificial Intelligence Techniques to Predict the Behaviour of Masonry Panels. In B.H.V. Topping, (Editor), Proceedings of the Eighth International Conference on the Application of Artificial Intelligence to Civil, Structural and Environmental Engineering. Civil-Comp Press: Stirlingshire, UK

[79] Renner G, Ekárt A. Genetic algorithms in computer aided design. Computer-Aided Design, 2003, 35(8): 709-726

[80] Rossi L, Winands MHM, Butenweg C. Monte Carlo Tree Search as an intelligent search tool in structural design problems. Engineering with Computers, 2022, 38: 3219-3236

[81] Rubinstein MF. Matrix Computer Analysis of Structures, 19661Prentice-Hall

[82] Russel SJ, Norvig P. Artificial Intelligence: A Modern Approach, 20214Pearson

[83] Sacks R, Eastman C, Lee G. BIM Handbook: A Guide to Building Information Modeling for Owners, Designers, Engineers, Contractors, and Facility Managers, 2018John Wiley Sons Inc

[84] Schultz, J., Adamek, J., Jusup, M., Lanctot, M., Kaisers, M., Perrin, S., Hennes, D., Shar, J., Lewis, C., Ruoss, A., Zahavy, T., Veličković, P., Prince, L., Singh, S., Malmi, E., & Tomašev, N. (2024). Mastering Board Games by External and Internal Planning with Language Models. Retrieved February 13, 2025 from https://doi.org/10.48550/arXiv.2412.12119

[85] Segler MHS, Preuss M, Waller MP. Learning to plan chemical syntheses. Nature, 2018, 555: 604-610

[86] Senington R, Schmidt B, Syberfeldt A. Monte carlo tree search for online decision making in smart industrial production. Computers in Industry, 2021, 128 103433

[87] Sironi, C. F. (2019). Monte-Carlo Tree Search for Artificial General Intelligence in Games. Proefschriftmaken.nl || Uitgeverij BOXPress. https://doi.org/10.26481/dis.20191113cs

[88] Silver D, et al.. Mastering the game of go with deep neural networks and tree search. Nature, 2016, 529: 484-489

[89] Silver D, Hubert T, Schrittwieser J, Antonoglou I, et al.. A general reinforcement learning algorithm that masters chess, shogi, and go through self-play. Science, 2018, 362(6419): 1140-1144

[90] Srinivas M, Patnaik LM. Genetic algorithms: A survey. Computer, 1994, 27(6): 17-26

[91] Sutton, R. S., & Barto, A. G. (2018). Reinforcement Learning. Second edition: An Introduction, 2nd edition, Bradford Books.

[92] Świechowski M, Godlewski K, Sawicki B, et al.. Monte carlo tree search: A review of recent modifications and applications. Artificial Intelligence Review, 2023, 56: 2497-2562

[93] The MathWorks Inc. (2022). MATLAB version: 9.13.0 (R2022b). Retrieved February 13, 2025 from https://www.mathworks.com

[94] Tong Z. A genetic algorithm approach to optimizing the distribution of buildings in urban green space. Automation in Construction, 2016, 72: 46-51

[95] Torky AA, Aburawwash AA. A Deep Learning Approach to Automated Structural Engineering of Prestressed Members. International Journal of Structural Civil Engineering Research, 2018, 7: 4

[96] Building Transparency (2020). Embodied Carbon in Construction Calculator (EC3) tool. Retrieved February 13, 2025, from https://www.buildingtransparency.org/

[97] Trunda O, Barták R. Using Monte Carlo Tree Search to Solve Planning Problems in Transportation Domains. Advances in Soft Computing and Its Applications, 2013Springer435-449

[98] Tu J, Yang SX. Genetic algorithm based path planning for a mobile robot. IEEE International Conference on Robotics and Automation, Taipei, Taiwan, 2003

[99] Regione Umbria (2023). Elenco regionale dei prezzi. (In Italian.) Retrieved February 13, 2025 from https://www.regione.umbria.it

[100] United Nations Environment Programme (2021). Global Status Report for Buildings and Construction: Towards a Zero-emission, Efficient and Resilient Buildings and Construction Sector. Retrieved February 13, 2025 from https:// https://globalabc.org

[101] Webb D, Alobaidi W, Sandgren E. Structural design via genetic optimization. Modern Mechanical Engineering, 2017, 7: 73-90

[102] Wilson, E. L. (1999). Three dimensional static and dynamic analysis of structures: A physical approach with emphasis on earthquake engineering. 3^rd edition, Computers and Structures.

[103] Winands MHM. Lee N. Monte-Carlo Tree Search. Encyclopedia of Computer Graphics and Games, 2015Springer16

[104] Winands MHM. MCTS in Board Games, 2017Springer Singapore

[105] Wood, R. D. (1985). Computer analysis of structures matrix structural analysis, structured programming. Siegfried M. Holzer, Elsevier, pp 426.

[106] Yan S, Liu N. Computational design of residential units’ floor layout: A heuristic algorithm. Journal of Building Engineering, 2024, 96 110546

[107] Zhang, D., Huang, X., Zhou, D., Li, Y., & Ouyang, W. (2024). Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B: A Technical Report. Retrieved February 13, 2025 from https://doi.org/10.48550/arXiv.2406.07394

[108] Zhao Y, Yan Q, Yang Z, Yu X, Jia B. A novel artificial bee colony algorithm for structural damage detection. Advances in Civil Engineering, 2020

[109] Zhou GC, Rafiq Y, Bugmann G, Easterbrook D. Cellular automata model for predicting the failure pattern of laterally loaded masonry wall panels. Journal of Computing in Civil Engineering, 2006

[110] Ziyu G, Changjiang R, Jingtai N, Peixi W, Yizi S. Great wall construction algorithm: A novel meta-heuristic algorithm for engineer problems. Expert Systems with Applications, 2023, 233 120905

RIGHTS & PERMISSIONS

The Author(s)