Prediction and Validation of Structural Behavior in a Tensegrity Bridge Using Finite Element Analysis and AI Models

DOI

10.2991/978-94-6463-852-3_21How to use a DOI?

Keywords

Tensegrity structures; STAAD PRO; artificial intelligence; AI in civil engineering

Abstract

This study presents a comprehensive analysis and prediction of the structural behavior of a tensegrity-based Foot Over Bridge (FOB) using both finite element analysis (FEA) and artificial intelligence (AI) modeling. The bridge design featured a lightweight tensegrity framework with an 8.0-m span and 1.5-m width, utilizing circular hollow steel sections to optimize weight and load distribution. Structural analysis was performed in STAAD.Pro under a factored load combination of 1.5(DL + LL), evaluating key parameters such as displacements, support reactions, and internal forces. The maximum displacement was recorded near the central suspended cable segment, with peak support reactions at the end supports. To validate these results, a supervised machine learning model—a Random Forest Regressor—was developed in Python. The model was trained on a dataset comprising 500 simulated structural scenarios varying in geometry, material properties, and loading conditions. Input features included member lengths, cross-sectional areas, support types, and applied loads, while the output features were nodal displacements and member forces. The AI model achieved a coefficient of determination (R²) of 0.962 and a root mean square error (RMSE) of 1.72 mm for displacement predictions on the test set. The predicted maximum displacement (26.17 mm) closely matched the STAAD.Pro output (28.48 mm), with similar alignment observed in axial forces and bending moments for diagonal and bottom tension members. This study confirms the feasibility of integrating AI with FEA to accelerate structural response estimation, offering reliable, real-time validation tools for complex systems like tensegrity foot over bridges.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Shaikh Irfan Badiyoddin Shaikh
AU  - Rajendra B. Magar
PY  - 2025
DA  - 2025/10/07
TI  - Prediction and Validation of Structural Behavior in a Tensegrity Bridge Using Finite Element Analysis and AI Models
BT  - Proceedings of the MULTINOVA: First International Conference on Artificial Intelligence in Engineering, Healthcare and Sciences (ICAIEHS- 2025)
PB  - Atlantis Press
SP  - 331
EP  - 346
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-852-3_21
DO  - 10.2991/978-94-6463-852-3_21
ID  - Shaikh2025
ER  -