Browse > Article
http://dx.doi.org/10.7734/COSEIK.2021.34.6.403

Interface Establishment between Reinforcement Learning Algorithm and External Analysis Program for AI-based Automation of Bridge Design Process  

Kim, Minsu (School of Railroad Engineering, Korea National University of Transportation)
Choi, Sanghyun (School of Railroad Engineering, Korea National University of Transportation)
Publication Information
Journal of the Computational Structural Engineering Institute of Korea / v.34, no.6, 2021 , pp. 403-408 More about this Journal
Abstract
Currently, in the design process of civil structures such as bridges, it is common to make final products by repeating the process of redesigning, if the initial design is found to not meet the standards after a structural review. This iterative process extends the design time, and causes inefficient consumption of engineering manpower, which should be put into higher-level design, on simple repetitive mechanical work. This problem can be resolved by automating the design process, but the external analysis program used in the design process has been the biggest obstacle to such automation. In this study, we constructed an AI-based automation system for the bridge design process, including an interface that could control both a reinforcement learning algorithm, and an external analysis program, to replace the repetitive tasks in the current design process. The prototype of the system built in this study was developed for a 2-span RC Rahmen bridge, which is one of the simplest bridge systems. In the future, it is expected that the developed interface system can be utilized as a basic technology for linking the latest AI with other types of bridge designs.
Keywords
reinforcement learning; deep q-learning; bridge design; structural analysis;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Park, J.-G., Kim, M.-H., Lee, K.-M., Choi, J.-H., Shijn, H.-M. (2008) Design of Interface between 3D Object Model and Structure Analysis Program, J. Comput. Struct. Eng. Inst. Korea, 21(3), pp.247~252.
2 Sutton, R.S., Barto, A.C. (2018) Reinforcement Learning: An Introduction, Second edition, Bradford Book.
3 Park, S.J. (2006) Optimum Design of Reinforced Concrete Rahmen Bridges with 3-spans, Master's Thesis, Kyungpook National University.
4 Kim, B.S., Kwon, S.H. (2009) The Conceptual Estimate Model on Preliminary Design Phase for RC Rahmen Bridge, Korean J. Constr. Eng. & Manag., 10(2), pp.111~120.
5 Sim, E.-A., Lee, S., Lee, J. (2018) Prediction of Static and Dynamic Behavior of Truss Structures Using Deep Learning, J. Korean Assoc. Spat. Struct., 18(4), pp.69~80.
6 Kang, I.S., Moon, J.W., Park, J.C. (2017) Recent Research Trends of Artificial Intelligent Machine Learning in Architectural Field, J. Arch. Inst. Korea - Struct. & Constr., 33(4), pp.63~68.   DOI
7 Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., Legg, S., Hassabis, D (2015) Human-level Control through Deep Reinforcement Learning, Nature, 518(7540), pp.529~533.   DOI
8 Park, H.J., Seok, K.H., Shim, J.Y., Hwang, C.H. (2019) Deep Learning with TensorFlow, Hanbit Academy, Seoul, p.381.
9 An, K. (2018) Model-free Optimal Control for Building Energy System Using Deep Q-learning, Dissertation, Sungkyunkwan University.
10 Gu, H.-M., Seo, J.-H., Choo, S.-Y. (2018) A Study on Automation for 2D Drawings to 3D Modeling Using Deep Learning, Proceedings of Fall Conference, Architectural Institute of Korea, 38(2).
11 Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M. (2013) Playing Atari with Deep Reinforcement Learning. Technical Report, arXiv:1312.5602 [cs.LG], Deepmind Technologies.
12 MOLIT (Ministry of Land Infrastructure and Transport) (2019) AI-Based Architectural Design Automation Technology Development, Final Report, 18RDPP-C150335-01.
13 Noh, D.O. (2002) A Development of the Automatic Design Program of the RC Rahmen Bridge. Master's Thesis, Pusan National University.