ARTIFICIAL INTELLIGENCE IN STRUCTURAL DESIGN, AN INTRODUCTION TO NEURAL NETWORKS
DOI:
https://doi.org/10.31650/2707-3068-2025-29-60-67Keywords:
machine learning, pattern recognition, artificial neural networks, engineering structures, parabolic arc, elliptic arc, circular arcAbstract
This article presents the potential application of artificial intelligence, particularly
artificial neural networks (ANNs), in the design of engineering structures. The subject of the paper is the automatic recognition of the geometric shape of an arc as circular, elliptical or parabolic. Correct identification of the arc shape is fundamental to the creation of the static scheme and computational model of the structure, which is necessary for strength analysis of the structure. This paper analyzes two identification methods based on ANN: multilayer perceptron (MLP) and convolutional neural network (CNN). The MLP network classifies the type of arc based on the geometric features of selected points lying on the arc, while the CNN network makes recognition based on the graphical representation of the arc as a black and white image. The prospects for AI applications in civil engineering are also discussed, with a focus on generative models and their potential use in the design, simulation and automation of construction processes.
References
[1] W.S. McCulloch, W. Pitts. “A logical calculus of the ideas immanent in nervous activity”. Bulletin of Mathematical Biophysics 5, 115–133 (1943).
[2] F. Rosenblatt. “The perceptron: A perceiving and recognizing automaton”. Report, Project PARA, Cornell Aeronautical Laboratory, 85-460-1 (1957).
[3] C. Bishop. “Pattern Recognition and Machine Learning (Information Science and Statistics)”. Springer-Verlag (2006).
[4] I. Goodfellow, Y. Bengio, A. Courville. “Deep learning”. MIT Press (2016).
[5] A. Vaswani et al. “Attention is All you Need”. Advances in Neural Information Processing Systems 30 (2017).
[6] W. Peebles, S. Xie. “Scalable Diffusion Models with Transformers”. arXiv cs.CV 2212.09748 (2023).
[7] I. Goodfellow et al. “Generative Adversarial Networks”. arXiv stat.ML 1406.2661 (2014).
[8] J. Ho, A. Jain, P. Abbeel. “Denoising diffusion probabilistic models”. Proceedings of the 34th International Conference on Neural Information Processing Systems 574 (2020).
[9] M. Raissi, P. Perdikaris, G. Karniadakis. “Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations”. arXiv cs.AI 1711.10561 (2017).
+38 (067) 962-83-55
