A Review of Artificial Intelligence and Machine Learning Applications in Structural Health Monitoring of Buildings and Bridges

A Review of Artificial Intelligence and Machine Learning Applications in Structural Health Monitoring of Buildings and Bridges

Mozhdeh Hadadizadeh1

1) M.Sc. in Civil Engineering, Independent Researcher

IOI Code : ABFG-ACADBC
Publication : 12th.international Congress on Civil Engineering, Architecture, Art and Urban Development(12icsau.ir)
Abstract :
    Abstract Structural health monitoring (SHM) aims to continuously assess the integrity of structures and detect damage at an early stage. Advances in sensing hardware and computing power, particularly the low cost of accelerometers, have enabled the use of machine-learning algorithms in this field. This review summarizes and compares studies from 2011 to 2022 that applied artificial neural networks (ANN), convolutional neural networks (CNN), and support vector machines (SVM) to damage identification in buildings and bridges. The levels of damage identification and damage-sensitive feature extraction methods, including principal component analysis, wavelet transform, empirical mode decomposition, and the Hilbert–Huang transform, are introduced first. Physics-based and data-driven models are then examined, together with approaches for mitigating noise and environmental uncertainty. Finally, recent trends from 2023 to 2026, especially physics-informed learning and digital twins, are reviewed. The findings show that combining these algorithms with signal preprocessing and multi-sensor data fusion improves the accuracy and robustness of monitoring systems. However, the scarcity of real damage data, dependence on finite element models, training cost, and the difficulty of real-time monitoring remain the main challenges. Hybrid physics–data approaches, both for data generation and model updating, are recommended for future research.

Keywords : structural health monitoring artificial intelligence machine learning damage identification neural network buildings