Vibration and Deformation Monitoring of a Long-Span Rigid-Frame Bridge with Distributed Long-Gauge Sensors

Struct Control Health Monit

2017

Self Cite

Summary Ambient vibration test generally only outputs basic modal parameters including frequencies, damping ratios, and unscaled mode shapes, which cannot directly support decision making of structural maintenance and management. In this article, structural deep‐level parameters including unscaled and scaled flexibility identification of a posttensioned concrete continuous box girder bridge are studied by performing ambient vibration test, which is able to predict structural deflections by multiplying the static load with the identified flexibility. Ambient vibration test of the bridge and basic modal identification are firstly performed. Then, the method of unscaled flexibility identification is proposed by investigating the relationship between the frequency response function estimated from ambient test data and the analytical one. Finally, a mass‐changing strategy is utilized to identify the scaled flexibility from output‐only data, in which the key issue is to identify mass‐normalized scaling factors by performing ambient vibration tests of tested structure before and after changing its mass. Numerical simulation of a simply supported beam and field test of a three‐span bridge has been conducted to verify the capability and reliability of the proposed method. The good agreement between the predicted deflections from the identified flexibility and those measured from the static test successfully illustrates the effectiveness of the proposed method.

Section: Bridge Description and Field Testmentioning

confidence: 99%

Ambient vibration test-based deflection prediction of a posttensioned concrete continuous box girder bridge

Tian

Struct Control Health Monit

2017

Self Cite

“…Structural health monitoring (SHM) is considered to be a promising technology to improve the health and safety of civil structures; in recent years, it is also considered as a resourceful tool that aids structures and cities to achieve the goal of disaster resilience . In the past few decades, vibration and strain‐measurement‐based damage detection methods have been thoroughly investigated; nonetheless, it is generally agreed that they are either insensitive to identify or insufficient to cover local damage . Novel area‐distributed sensing technologies are being investigated for improving SHM in this regard.…”

Section: Introductionmentioning

confidence: 99%

Pixel-level crack delineation in images with convolutional feature fusion

Struct Control Health Monit

Chen

2018

Self Cite

169

Cracks in civil structures are important signs of structural degradation and may even indicate the inception of catastrophic failure. Image-based crack detection has been attempted in research communities that bear the potential of replacing human-based inspection. Among many methodologies, deep learningbased cracks detection is actively explored in recent years. However, how to automatically extract cracks quickly and accurately at a pixel level, that is, crack delineation (including both detection and segmentation), is a challenging issue. This article proposes a convolutional neural network-based framework that automates this task through convolutional feature fusion and pixel-level classification. The resulting network architecture with an empirically optimal fusion strategy, termed the crack delineation network, is trained and tested based on a concrete crack image database. The results show that the proposed framework can delineate cracks accurately and rapidly in images towards a fully autonomous machine vision approach to structural crack detection.

“…Structural damage in concrete structures subject to service and extreme loadings and environmental attacks is essentially a multiphase process. In the past few decades, vibration‐based damage detection methods have been widely investigated, but they are insensitive to local damage (Xia, Cheng, Zhang, & Zhu, ; J. Zhang et al., ; J. Zhang, Wan, & Sato, ; J. Zhang, Guo, & Zhang, ; J. Zhang et al., ). Concrete damage usually begins with the inception of cracking (showing hairline cracks), evolves to extensive cracking (major cracks or spalling), and ultimately leads to local or global structural deficiency, all of which unfold during a long time if not attacked by extreme loadings in a rapid way.…”

Section: Introductionmentioning

confidence: 99%

Zernike‐moment measurement of thin‐crack width in images enabled by dual‐scale deep learning

Computer aided Civil Eng

Chen

2018

Self Cite

134

Although crack inspection is a routine practice in civil infrastructure management (especially for highway bridge structures), it is time-consuming and safety-concerning to trained engineers and costly to the stakeholders. To automate this in the near future, the algorithmic challenge at the onset is to detect and localize cracks in imagery data with complex scenes. The rise of deep learning (DL) sheds light on overcoming this challenge through learning from imagery big data. However, how to exploit DL techniques is yet to be fully explored. One primary component of practical crack inspection is that it is not merely detection via visual recognition. To evaluate the potential risk of structural failure, it entails quantitative characterization, which usually includes crack width measurement. To further facilitate the automation of machine-vision-based concrete crack inspection, this article proposes a DL-enabled quantitative crack width measurement method. In the detection and mapping phase, dual-scale convolutional neural networks are designed to detect cracks in complex scene images with validated high accuracy. Subsequently, a novel crack width estimation method based on the use of Zernike moment operator is further developed for thin cracks. The experimental results based on a laboratory loading test agree well with the direct measurements, which substantiates the effectiveness of the proposed method for quantitative crack detection.