Two-dimensional truss analysis with artificial intelligence

Subject Areas : Information Technology in Engineering Design (ITED) Journal

sobhan barati ¹ , javad alamatian ^{2 *}

1 -
2 - Department of Civil Engineering, Islamic Azad University, Mashhad Branch, Mashhad, Iran

Received: 2024-09-12 Accepted : 2025-01-01 Published : 2024-11-24

Keywords: Artificial intelligence, two-dimensional truss, deep neural network,

Abstract :

For structures with many degrees of freedom, traditional finite element software, which is based on dividing the problem domain into smaller elements, has become less efficient due to the extensive time required. As a result, engineers have turned to nature-inspired artificial intelligence algorithms, which possess the ability to learn complex patterns from data. One of these methods is the use of deep neural networks. These networks, with their layered structure and ability to learn from input data, can model system behaviors. Initially, the deep neural network is trained using empirical data, and then it predicts new data. However, challenges such as the need for extensive and suitable training data, ensuring model accuracy, and the interpretability of results still persist. To overcome these challenges, further research is required in optimizing network structures, data preprocessing techniques, and developing hybrid methods in artificial intelligence. In this study, a deep neural network is used to estimate the displacements of a two-member truss based on past data. The results from this study demonstrate the significant impact of network architecture on this problem.

References:

1 . اسماعیلی،م. باد پی،ا. "مرجع کاربردی یادگیری ژرف با Tensor Flow و Keras"، انتشارات آتی نگر، 1402.
2. J. Naranjo-P´erez, M. Infantes, J. Fernando Jim´enez-Alonso, A. S´aez. A collaborative machine learning-optimization algorithm to improve the finite element model updating of civil engineering structures. Engineering Structures 225 (2020) 111327. https://doi.org/10.1016/j.engstruct.2020.111327
3. F. K.J. Jawad, C. Ozturk, W. Dansheng, M. Mahmood,O. Al-Azzawi, A. Al Jemely. Sizing and layout optimization of truss structures with artificial bee colony algorithm. Structures 30(2021) 546-559. https://doi.org/10.1016/j.istruc.2021.01.016
4. A. Gienger, S. Schaut, O. Sawodny, C. Tarin. Modular Distributed Fault Diagnosis for Adaptive Structures using Local Models. IFAC-PapersOnLine Volume 53, Issue 2, 2020, Pages 13631-13637. https://www.sciencedirect.com/journal/ifac-papersonline
5. B. Etaati , M. Neshat, A. Abdollahi Dehkordi , N. Salami Pargoo ,M. El-Abd , A. Sadollah , A. H. Gandomi. Shape and sizing optimisation of space truss structures using a new cooperative coevolutionary-based algorithm. Results in Engineering 21 (2024) 101859. https://doi.org/10.1016/j.rineng.2024.101859
6. N. Khodadadi , A. Özyüksel Çiftçioğlu , S. Mirjalili , A. Nanni. A comparison performance analysis of eight meta-heuristic algorithms for optimal design of truss structures with static constraints. Decision Analytics Journal 8 (2023) 100266. https://doi.org/10.1016/j.dajour.2023.100266
7. T. Vu-Huu, Sy Pham-Van, Q-Hoan Pham, T. Cuong-Le. An improved bat algorithms for optimization design of truss
structures. Structures Volume 47, January 2023, Pages 2240-2258. https://www.sciencedirect.com/journal/structures 8. M.Z. Naser. Fire resistance evaluation through artificial intelligence - A case for timber structures. Fire Safety Journal Volume 105, April 2019, Pages 1-18. https://www.sciencedirect.com/journal/fire-safety-journal
9. F.Ferreira, R. Shamass, V. Limbachiya, K. Daniel Tsavdaridis, C. Humberto Martins. Lateral–torsional buckling resistance prediction model for steel cellular beams generated by Artificial Neural Networks (ANN). Thin-Walled Structures Volume 170, January 2022, 108592 https://www.sciencedirect.com/journal/thin-walled-structures
10. H. Chen, Y. Liu, Y. Huang, J. Huang, L. Caisong, Z. Guo. Maximum displacement prediction model for steel beams with hexagonal web openings under impact loading based on artificial neural networks. Engineering Applications of Artificial Intelligence Volume 136, Part A, October 2024, 108932. https://www.sciencedirect.com/journal/engineering-applications-of-artificial-intelligence
11. S.K. Kamane, N.K. Patil, B.R. Patagundi. Use of artificial neural network to predict the bending behavior of steel I beam externally attached with FRP sheets. Materials Today: Proceedings Volume 39, Part 1, 2021, Pages 17-21. https://www.sciencedirect.com/journal/materials-today-proceedings/vol/39/part/P1