Full-scale bridge damage identification using time series analysis of a dense array of geophones excited by drop weight

Farahani, Reza V.; Penumadu, Dayakar

doi:10.1002/stc.1820

Cited by 10 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, during the monitoring period for bridge reconstruction or modification construction, monitoring data usually have linkage changes, which make the damage identification more complex. To identify bridge damage, methods for damage identification using the dynamic response of bridges induced by moving vehicles and static test data are proposed by many researchers [18][19][20][21][22]. The early warning damage of bridges has been introduced in bridge structure safety monitoring [21][22][23][24], and monitoring bridges is a key part of the maintenance strategy if the bridge becomes unsafe.…”

Section: Introductionmentioning

confidence: 99%

Research on the Application of Multi-Source Data Analysis for Bridge Safety Monitoring in the Reconstruction and Demolition Process

Liang

Feng

et al. 2022

Buildings

View full text Add to dashboard Cite

With the increase of bridge-required demolition/dismantling for reconstruction or modification, the early warning of construction emergencies is greatly needed for monitoring the structural safety of bridges under construction. In this paper, based on the multi-source data of nearby construction and demolition construction of a large-span RC arch bridge in China, the Analytic Hierarchy Process (AHP) method is adopted to analyze the multi-source data and set the early warning threshold for bridge safety in construction. According to the analytical results, a reasonable evaluation of AHP factors can improve the accuracy and timeliness of safety early warning in the structural safety monitoring of bridges during the construction process. The weight of the monitoring data in AHP should be assigned according to its reliability, stability, and importance. Bridge safety assessment of nearby construction having harmful vibration should prioritize dynamic bridge monitoring by cooperating with multi-source data, including stress, and deformation monitoring of the bridge is necessary. The assessment results proved that multi-source data, including but not limited to structural stress and deformation monitoring data, vibration data, theoretical prediction data, environment data such as temperature data, and construction/maintenance history data, are necessary for safety monitoring and early warning of construction with specifications related to bridge construction. The early warnings triggered by the evaluation results successfully ensure the safety status of the bridge during nearby construction and demolition construction, which shows the proposed method can provide a guideline for comprehensively evaluating and early warning of the status of bridge construction.

show abstract

Section: Introductionmentioning

confidence: 99%

Research on the Application of Multi-Source Data Analysis for Bridge Safety Monitoring in the Reconstruction and Demolition Process

Liang

Feng

et al. 2022

Buildings

View full text Add to dashboard Cite

show abstract

“…Subsequently, Nair et al [9] improved this algorithm using a normalized relative inter-story acceleration instead of a single floor acceleration, making the algorithm more robust and capable of detecting minor damage patterns. Other studies [10][11][12][13] modified the processing procedure and format of the residuals for simulated or experimental data.…”

Section: Introductionmentioning

confidence: 99%

“…Mei et al [6] used both numerically simulated structure and laboratory test of a smallscale five-story frame where damage patterns were designed by replacing some components. In addition, there exist few studies that used the data from full-scale structures, e.g., [13,17] used full-scale instrumented bridges under normal operational and environmental conditions with minor damage levels. In summary, past applications are limited, and more realistic damage patterns of full-scale structures due to real or simulated hazards, e.g., using shaking table tests, are needed for further development of SHM using ML.…”

Section: Introductionmentioning

confidence: 99%

Auto-Regressive Integrated Moving-Average Machine Learning for Damage Identification of Steel Frames

et al. 2021

View full text Add to dashboard Cite

Auto-regressive (AR) time series (TS) models are useful for structural damage detection in vibration-based structural health monitoring (SHM). However, certain limitations, e.g., non-stationarity and subjective feature selection, have reduced its wide-spread use. With increasing trends in machine learning (ML) technologies, automated structural damage recognition is becoming popular and attracting many researchers. In this paper, we combined TS modeling and ML classification to automatically extract damage features and overcome the limitation of non-stationarity. We propose a two-stage framework, namely auto-regressive integrated moving-average machine learning (ARIMA-ML) with modules for pre-processing, model parameter determination, feature extraction, and classification. Based on shaking table tests of a space steel frame, floor acceleration data were collected and labeled according to experimental observations and records. Subsequently, we designed three damage classification tasks for: (1) global damage detection, (2) local damage detection, and (3) local damage pattern recognition. The results from these three tasks indicated the robustness and accuracy of the proposed framework where 97%, 98%, and 80% average segment accuracy were achieved, respectively. The confusion matrix results showed the unbiased model performance even under an imbalanced-class distribution. In summary, the presented study revealed the high potential of the proposed ARIMA-ML framework in vibration-based SHM.

show abstract

“…ese techniques such as mean, root mean square, skewness, kurtosis, and productivity ratio can directly perform on time-series data [5][6][7]. Frequency-domain features represent frequency content and spectral aspects obtained by fast Fourier transform (FFT) such as energy in different frequency bands, frequency bands, and Fourier coefficient [8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Ensemble Classifiers and Feature-Based Methods for Structural Damage Assessment

Bisheh

Amiri

Darvishan

2020

Shock and Vibration

View full text Add to dashboard Cite

In this paper, a new structural damage detection framework is proposed based on vibration analysis and pattern recognition, which consists of two stages: (1) signal processing and feature extraction and (2) damage detection by combining the classification result. In the first stage, discriminative features were extracted as a set of proposed descriptors related to the statistical moment of the spectrum and spectral shape properties using five competitive time-frequency techniques including fast S-transform, synchrosqueezed wavelet transform, empirical wavelet transform, wavelet transform, and short-time Fourier transform. Then, forward feature selection was employed to remove the redundant information and select damage features from vibration signals. By applying different classifiers, the capability of the feature sets for damage identification was investigated. In the second stage, ensemble-based classifiers were used to improve the overall performance of damage detection based on individual classifiers and increase the number of detectable damages. The proposed framework was verified by a suite of numerical and full-scale studies (a bridge health monitoring benchmark problem, IASC-ASCE SHM benchmark structure, and a cable-stayed bridge in China). The results showed that the proposed framework was superior to the existing single classifier and could assess the damage with reduced false alarms.

show abstract

Full-scale bridge damage identification using time series analysis of a dense array of geophones excited by drop weight

Cited by 10 publications

References 20 publications

Research on the Application of Multi-Source Data Analysis for Bridge Safety Monitoring in the Reconstruction and Demolition Process

Research on the Application of Multi-Source Data Analysis for Bridge Safety Monitoring in the Reconstruction and Demolition Process

Auto-Regressive Integrated Moving-Average Machine Learning for Damage Identification of Steel Frames

Ensemble Classifiers and Feature-Based Methods for Structural Damage Assessment

Contact Info

Product

Resources

About