• Smart Structures and Systems
• /
• 제12권3_4호
• /
• pp.427-440
• /
• 2013

A growing need has developed in the United States to obtain more specific knowledge on the structural integrity of infrastructure due to aging service lives, heavier and more frequent loading conditions, and durability issues. This need has spurred extensive research in the area of structural health monitoring over the past few decades. Several structural health monitoring techniques have been developed that are capable of locating damage in structures using modal strain energy of mode shapes. Typically in the past, bending strain energy has been used in these methods since it is a dominant vibrational mode in many structures and is easily measured. Additionally, there may be cases, such as pipes, shafts, or certain bridges, where structures exhibit significant torsional behavior as well. In this research, torsional strain energy is used to locate damage. The damage index method is used on two numerical models; a cantilevered steel pipe and a simply-supported steel plate girder bridge. Torsion damage indices are compared to bending damage indices to assess their effectiveness at locating damage. The torsion strain energy method is capable of accurately locating damage and providing additional valuable information to both of the structures' behaviors.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.53-62
• /
• 2022

The deployment of advanced structural health monitoring (SHM) systems in large-scale civil structures collects large amounts of data. Note that these data may contain multiple types of anomalies (e.g., missing, minor, outlier, etc.) caused by harsh environment, sensor faults, transfer omission and other factors. These anomalies seriously affect the evaluation of structural performance. Therefore, the effective analysis and mining of SHM data is an extremely important task. Inspired by the deep learning paradigm, this study develops a novel generative adversarial network (GAN) and convolutional neural network (CNN)-based data anomaly detection approach for SHM. The framework of the proposed approach includes three modules : (a) A three-channel input is established based on fast Fourier transform (FFT) and Gramian angular field (GAF) method; (b) A GANomaly is introduced and trained to extract features from normal samples alone for class-imbalanced problems; (c) Based on the output of GANomaly, a CNN is employed to distinguish the types of anomalies. In addition, a dataset-oriented method (i.e., multistage sampling) is adopted to obtain the optimal sampling ratios between all different samples. The proposed approach is tested with acceleration data from an SHM system of a long-span bridge. The results show that the proposed approach has a higher accuracy in detecting the multi-pattern anomalies of SHM data.

• Structural Monitoring and Maintenance
• /
• 제5권1호
• /
• pp.51-65
• /
• 2018

A number of sensing techniques have been implemented for detecting defects in civil infrastructures instead of onsite human inspections in structural health monitoring. However, the issue of faults in sensors has not received much attention. This issue may lead to incorrect interpretation of data and false alarms. To overcome these challenges, this article presents a deep learning-based method with a new architecture of Stateful Long Short Term Memory Neural Networks (S-LSTM NN) for detecting sensor fault without going into details of the fault features. As LSTMs are capable of learning data features automatically, and the proposed method works without an accurate mathematical model. The detection of four types of sensor faults are studied in this paper. Non-stationary acceleration responses of a three-span continuous bridge when under operational conditions are studied. A deep network model is applied to the measured bridge data with estimation to detect the sensor fault. Another set of sensor output data is used to supervise the network parameters and backpropagation algorithm to fine tune the parameters to establish a deep self-coding network model. The response residuals between the true value and the predicted value of the deep S-LSTM network was statistically analyzed to determine the fault threshold of sensor. Experimental study with a cable-stayed bridge further indicated that the proposed method is robust in the detection of the sensor fault.

• Structural Monitoring and Maintenance
• /
• 제7권2호
• /
• pp.109-124
• /
• 2020

Benefiting from the massive monitoring data collected by the Structural health monitoring (SHM) system, scholars can grasp the complex environmental effects and structural state during structure operation. However, the monitoring data is often missing due to sensor faults and other reasons. It is necessary to study the recovery method of missing monitoring data. Taking the structural temperature monitoring data of Nanjing Dashengguan Yangtze River Bridge as an example, the long short-term memory (LSTM) network-based recovery method for missing structural temperature data is proposed in this paper. Firstly, the prediction results of temperature data using LSTM network, support vector machine (SVM), and wavelet neural network (WNN) are compared to verify the accuracy advantage of LSTM network in predicting time series data (such as structural temperature). Secondly, the application of LSTM network in the recovery of missing structural temperature data is discussed in detail. The results show that: the LSTM network can effectively recover the missing structural temperature data; incorporating more intact sensor data as input will further improve the recovery effect of missing data; selecting the sensor data which has a higher correlation coefficient with the data we want to recover as the input can achieve higher accuracy.

• Smart Structures and Systems
• /
• 제17권6호
• /
• pp.1031-1053
• /
• 2016

The health conditions of in-service civil infrastructures can be evaluated by employing structural health monitoring technology. A reliable health evaluation result depends heavily on the quality of the data collected from the structural monitoring sensor network. Hence, the problem of sensor fault diagnosis has gained considerable attention in recent years. In this paper, an innovative sensor fault diagnosis method that focuses on fault detection and isolation stages has been proposed. The dynamic or auto-regressive characteristic is firstly utilized to build a multivariable statistical model that measures the correlations of the currently collected structural responses and the future possible ones in combination with the canonical correlation analysis. Two different fault detection statistics are then defined based on the above multivariable statistical model for deciding whether a fault or failure occurred in the sensor network. After that, two corresponding fault isolation indices are deduced through the contribution analysis methodology to identify the faulty sensor. Case studies, using a benchmark structure developed for bridge health monitoring, are considered in the research and demonstrate the superiority of the new proposed sensor fault diagnosis method over the traditional principal component analysis-based and the dynamic principal component analysis-based methods.

• 한국지진공학회논문집
• /
• 제10권6호
• /
• pp.9-18
• /
• 2006

영종대교에 설치된 교량 모니터링 시스템의 구성특징을 살펴보고 이로부터 계측, 수집된 각 신호들의 특성을 조사 분석하였다. 3차원 자정식 현수교인 영종대교에 설치, 운영되는 모니터링 시스템의 구성은 센서-현장하드웨어-계측서버-관리자로 연결되는 자동화된 시스템으로써 개통 이후부터 교량의 거동 및 하중효과를 대변하는 물리량을 측정하고 있다. 이 논문에서는 시스템의 구성 및 측정항목에 대한 소개와 온도변화에 의한 시그널에의 영향을 감시 할 수 있는 알고리즘의 개발과정을 언급한다. 또한, 행어 케이블의 장력측정 방법의 일환으로 길이가 짧고 장력이 큰 케이블에 대해 정적으로 장력산정이 가능한 장치 및 알고리즘의 개발에 대해 소개한다. 특히 이 교량의 공용중에 이루어진 철도통행을 위한 설비의 추가로 교량 구조계의 변화를 계측 신호를 바탕으로 분석, 제시하였다. 이러한 각종 계측 및 모니터링 결과는 향후 교량의 상태판정의 기본자료로 활용되어 효율적 유지관리를 가능하게 할 것으로 기대된다.

• Structural Engineering and Mechanics
• /
• 제46권3호
• /
• pp.433-445
• /
• 2013

Vibration-based structural identification has become an important tool for structural health monitoring and safety evaluation. However, various kinds of uncertainties (e.g., observation noise) involved in the field test data obstruct automation system identification for accurate and fast structural safety evaluation. A practical way including a data preprocessing procedure and a vector backward auto-regressive (VBAR) method has been investigated for practical bridge identification. The data preprocessing procedure serves to improve the data quality, which consists of multi-level uncertainty mitigation techniques. The VBAR method provides a determinative way to automatically distinguish structural modes from extraneous modes arising from uncertainty. Ambient test data of a cantilever beam is investigated to demonstrate how the proposed method automatically interprets vibration data for structural modal estimation. Especially, structural identification of a truss bridge using field test data is also performed to study the effectiveness of the proposed method for real bridge identification.

• Wind and Structures
• /
• 제16권4호
• /
• pp.373-391
• /
• 2013

This is the first of two companion papers that analyse ten years of on-site monitoring data for the Confederation Bridge to determine the validity of the original wind speeds and wind loads predicted in 1994 when the bridge was being designed. The check of the original design values is warranted because the design wind speed at the middle of Northumberland Strait was derived from data collected at shore-based weather stations, and the design wind loads were based on tests of section and full-aeroelastic models in the wind tunnel. This first paper uses wind, tilt, and acceleration monitoring data to determine the static and dynamic responses of the bridge, which are then used in the second paper to derive the static and dynamic wind loads. It is shown that the design ten-minute mean wind speed with a 100-year return period is 1.5% less than the 1994 design value, and that the bridge has been subjected to this design event once on November 7, 2001. The dynamic characteristics of the instrumented spans of the bridge including frequencies, mode shapes and damping are in good agreement with published values reported by others. The on-site monitoring data show bridge response to be that of turbulent buffeting which is consistent with the response predicted at the design stage.

• Earthquakes and Structures
• /
• 제2권2호
• /
• pp.189-206
• /
• 2011

In this study, the subspace stochastic realization theories (SSR model I and SSR model II) have been applied to a real bridge for estimating its dynamic characteristics (natural frequencies, damping constants, and vibration modes) under ambient vibration. A numerical simulation is carried out for an arch-type steel truss bridge using a white noise excitation. The estimates obtained from this simulation are compared with those obtained from the Finite Element (FE) analysis, demonstrating good agreement and clarifying the excellent performance of this method in estimating the structural dynamic characteristics. Subsequently, these methods are applied to the vibration induced by both strong and weak winds as obtained by remote monitoring of the Kabashima bridge (an arch-type steel truss bridge of length 136 m, and situated in Nagasaki city). The results obtained with this experimental data reveal that more accurate estimates are obtained when strong wind vibration data is used. In contrast, the vibration data obtained from weak wind provides accurate estimates at lower frequencies, and inaccurate accuracy for higher modes of vibration that do not get excited by the wind of lower intensity. On the basis of the identified results obtained using both simulated data and monitored data from a real bridge, it is determined that the SSR model II realizes more accurate results than the SSR model I. In general, the approach investigated in this study is found to provide acceptable estimates of the dynamic characteristics of highway bridges as well as for the vibration monitoring of bridges.

• Smart Structures and Systems
• /
• 제15권3호
• /
• pp.555-576
• /
• 2015

The large number of long-span bridges constructed in China motivates the applications of structural health monitoring (SHM) technology. Many bridges have been equipped with sophisticated SHM systems in the mainland of China and in Hong Kong of China. Recently, SHM technology has been extended to field test systems. In this view, SHM can serve as a tool to develop the methods of life-cycle performance design, evaluation, maintenance and management of bridges; to develop new structural analysis methods through validation and feedback from SHM results; and to understand the behavior of bridges under natural and man-made disasters, rapidly assess the damage and loss of structures over large regions after disasters, e.g., earthquake, typhoon, flood, etc. It is hoped that combining analytical methods, numerical simulation, small-scale tests and accelerated durability tests with SHM could become the main engine driving the development of bridge engineering. This paper demonstrates the above viewpoint.