Structural Damage Identification System Suitable for Old Arch Bridge in Rural Regions: Random Forest Approach

Abstract

A huge number of old arch bridges located in rural regions are at the peak of maintenance. The health monitoring technology of the long-span bridge is hardly applicable to the small-span bridge, owing to the absence of technical resources and sufficient funds in rural regions. There is an urgent need for an economical, fast, and accurate damage identification solution. The authors proposed a damage identification system of an old arch bridge implemented with a machine learning algorithm, which took the vehicle-induced response as the excitation. A damage index was defined based on wavelet packet theory, and a machine learning sample database collecting the denoised response was constructed. Through comparing three machine learning algorithms: Back-Propagation Neural Network (BPNN), Support Vector Machine (SVM), and Random Forest (R.F.), the R.F. damage identification model were found to have a better recognition ability. Finally, the Particle Swarm Optimization (PSO) algorithm was used to optimize the number of subtrees and split features of the R.F. model. The PSO optimized R.F. model was capable of the identification of different damage levels of old arch bridges with sensitive damage index. The proposed framework is practical and promising for the old bridge's structural damage identification in rural regions.

Comparative analysis of supervised learning algorithms for prediction of cardiovascular diseases

“…In Bagging, the Random Forest (RF) model [ 9 ] is a widely used algorithm. Its main concept is to train multiple decision trees as base classifiers and make predictions through voting in classification problems.…”

Structural damage identification method based on Swin Transformer and continuous wavelet transform

“…This better represents the characteristics of the original signal. CWT is performed using [22] : (6) where U(α, β) denotes the coefficients of the wavelet function, characterizing the similarity between the wavelet func Ation and the original signal; α, β ∈ R (α ≠ 0) are denoted as the scale parameter and translation parameter, respectively; x(t) represents the original signal; ψ(t) indicates a wavelet basis function, and ψ(t) is the conjugate function of ψ(t).…”

“…Pooya et al used the absolute difference of modal strain energy coefficients as an indicator of damage location and applied the relationship between modal strain energy and modal kinetic energy to identify the damage of beam [5] . An et al proposed a damage identification method for semi-rigid joints in frame structures based on additional virtual mass, which utilizes natural frequencies to identify the location and extent of damage [6] . Although parameter-based methods can be effective in identifying damage, they may not be sensitive enough to detect local damage and may have certain limitations.…”

Operational Modal Analysis on Bridges: A Comprehensive Review

“…The model demonstrated the prediction performance with over 90% accuracy, identifying critical parameters for seismic design and disaster prevention. Furthermore, these papers also contributed to the utilization of the RF in bridge monitoring [295][296][297].…”