Computational Technology Resources - CCC

A. Montisci¹, F. Pibi² and M.C. Porcu²

¹Dept. of Electrical and Electronic Engineering, University of Cagliari, Italy
²Department of Civil, Environmental Engineering and Architecture, University of Cagliari, Italy

doi:10.4203/ccc.11.2.2

A. Montisci, F. Pibi, M.C. Porcu, "MLP Neural Networks To Identify Damage in Bridges From SHM Data", in P. Iványi, J. Kruis, B.H.V. Topping, (Editors), "Proceedings of the Seventh International Conference on Artificial Intelligence, Soft Computing, Machine Learning and Optimization in Engineering", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 11, Paper 2.2, 2025, doi:10.4203/ccc.11.2.2

Keywords: artificial neural networks, machine learning, multi-layer perceptron, structural health monitoring, damage identification, concrete bridges.

Abstract

Multi-layer perceptron neural networks may be applied to improve structural health monitoring of existing structures. The present paper presents a preliminary application of a MLP neural network-based procedure to identify damage scenarios of concrete bridges. Reference was made to the well-known benchmark Z24 bridge, where full-scale different damage scenarios (such as pier settlement, concrete spalling and tendon rupture) were progressively produced on purpose. The proposed methodology trains MLP neural networks on databases of experimental acceleration time histories and classifies each damage type based on the frequency response spectrum. The results show the likely ability of MLP networks to categorize different kinds of structural damage in existing bridges, thereby contributing to advancements in automated structural health monitoring.

download the full-text of this paper (PDF, 14 pages, 1017 Kb)

go to the previous paper
go to the next paper
return to the table of contents
return to the volume description

	Computational & Technology Resources an online resource for computational, engineering & technology publications
	not logged in - login
Front Page Browse CCC CCP CSETS CTR IJRT Other Authors Search Purchase Guide FAQ Contact us	Civil-Comp Conferences ISSN 2753-3239 CCC: 11 PROCEEDINGS OF THE SEVENTH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, SOFT COMPUTING, MACHINE LEARNING AND OPTIMIZATION IN ENGINEERING Edited by: P. Iványi, J. Kruis and B.H.V. Topping Paper 2.2 MLP Neural Networks To Identify Damage in Bridges From SHM Data A. Montisci¹, F. Pibi² and M.C. Porcu² ¹Dept. of Electrical and Electronic Engineering, University of Cagliari, Italy ²Department of Civil, Environmental Engineering and Architecture, University of Cagliari, Italy doi:10.4203/ccc.11.2.2 Full Bibliographic Reference for this paper A. Montisci, F. Pibi, M.C. Porcu, "MLP Neural Networks To Identify Damage in Bridges From SHM Data", in P. Iványi, J. Kruis, B.H.V. Topping, (Editors), "Proceedings of the Seventh International Conference on Artificial Intelligence, Soft Computing, Machine Learning and Optimization in Engineering", Civil-Comp Press, Edinburgh, UK, Online volume: CCC 11, Paper 2.2, 2025, doi:10.4203/ccc.11.2.2 Keywords: artificial neural networks, machine learning, multi-layer perceptron, structural health monitoring, damage identification, concrete bridges. Abstract Multi-layer perceptron neural networks may be applied to improve structural health monitoring of existing structures. The present paper presents a preliminary application of a MLP neural network-based procedure to identify damage scenarios of concrete bridges. Reference was made to the well-known benchmark Z24 bridge, where full-scale different damage scenarios (such as pier settlement, concrete spalling and tendon rupture) were progressively produced on purpose. The proposed methodology trains MLP neural networks on databases of experimental acceleration time histories and classifies each damage type based on the frequency response spectrum. The results show the likely ability of MLP networks to categorize different kinds of structural damage in existing bridges, thereby contributing to advancements in automated structural health monitoring. download the full-text of this paper (PDF, 14 pages, 1017 Kb) go to the previous paper go to the next paper return to the table of contents return to the volume description
Back to top	©Civil-Comp Limited 2023 - terms & conditions