Deep learning-based condition assessment for bridge elastomeric bearings

Cui, Mida; Wu, Gang; Dang, Ji; Chen, Zhiqiang; Ming-hua, Zhou

doi:10.1007/s13349-021-00540-6

Cited by 10 publications

(2 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To clarify the effect of varying the parameters of BSs on the dynamic response of vehicle-bridge coupling vibration, many researchers have conducted active experiments [19][20][21][22][23][24][25][26][27]. Through field testing and numerical simulation, Roeder et al [28] pointed out that the bearing force of a BS near the beam end of a steel box girder was obviously affected by the vehicle-induced impact effect, and that BSs near the beam end were susceptible to fatigue failure under vehicle impact loads.…”

Section: Introductionmentioning

confidence: 99%

Impact of Variable Parameters of Expansion Joints and Bearing Supports on the Vehicle-Induced Vibration of Curved Girder Bridges

Zheng,

Lu,

Huang

et al. 2024

Buildings

View full text Add to dashboard Cite

To study how varying the parameters of expansion joints and bearing supports (E-B parameters) affects the dynamic response of a coupled vehicle–bridge system for curved girder bridges, a dynamic response analysis method for the coupled vehicle–joint (bearing)–bridge system, which takes into account centrifugal forces, was proposed and verified. Subsequently, taking a continuous curved box girder bridge as the prototype, the influence of the E-B parameters on the vehicle-induced dynamic response of the curved girder bridge was explored. The results showed that the dynamic amplification factor (DAF) of the middle beam of the expansion joint (DAF-EJ) and the main girder of the curved bridge (DAF-MG) were both significantly influenced by the E-B parameters. When there were height differences between the middle beam and side beam in the EJ, the DAF-EJ obviously varied, and the DAF-MG increased. When the EJ was damaged, the impact effect of the vehicle on the bearing support increased. The DAF-EJ and DAF-MG both increased with the decrease of the vertical support stiffness of the bearing support. The DAF-EJ was greatly affected by the single-support void at the near-slit end of the lane. The DAF-MGs at the beam end, the 1/4 point and 1/2 point of the first span, and the 1/2 point of the second span, were significantly affected by the single-support void near the measuring point. Compared with the single-support void, the DAF-EJ and DAF-MG more significantly increased under the double-support void. Variation in the height difference of the EJ had a more significant effect on the DAF-EJ and DAF-MG at the beam end, while a vertical stiffness reduction in the bearing support had a more significant effect on the DAF-MG.

show abstract

Section: Introductionmentioning

confidence: 99%

Impact of Variable Parameters of Expansion Joints and Bearing Supports on the Vehicle-Induced Vibration of Curved Girder Bridges

Zheng,

Lu,

Huang

et al. 2024

Buildings

View full text Add to dashboard Cite

show abstract

“…The trained neural network model can improve the accuracy and precision of identification to a certain degree, but it also needs the support of rich and diverse training data. Cui et al 17 used convolutional neural network frameworks (AlexNet, 18 VGG-11, 19 and ResNet-18 20 ) to train them on the elastic bearings data set, and achieved a good recognition effect. The principle of force sensors is to embed the force sensors in bridge bearings during construction.…”

Section: Introductionmentioning

confidence: 99%

Bridge-bearing disengagement identification based on flexibility matrix diagonal matrix change rate: an indoor physical simulation experiment

Ma,

Qiao,

2023

Structural Health Monitoring

View full text Add to dashboard Cite

The disengagement of bridge bearings is a pervasive issue encountered in the realm of bridges, which can potentially lead to changes in operational circumstances, diminished longevity, and compromised traffic safety. The current methods employed for detecting such disconnections primarily rely on force sensors, cameras, and acceleration sensors. However, their practical implementation on-site and effectiveness in accurately identifying disengagement require enhancement. To address the challenges associated with the installation and layout of conventional contact sensors, as well as the potential introduction of additional mass, a sophisticated “bridge-bearing disconnection detection system” has been devised. This innovative system is based on laser Doppler vibrometer technology, which eliminates the need for physical contact. The feasibility of employing non-contact laser Doppler vibration measurement technology in the detection of bridge-bearing disconnection has been successfully verified within the framework of this study. Furthermore, a comprehensive analysis of the sensitivity of key dynamic parameters, specifically natural frequencies and vibration modes, to bridge-bearing disengagement has been conducted. The verification process included evaluating the identification effectiveness of regularized combined absolute changes in vibration modes and flexibility matrix diagonal matrix change rate (FDMCR) under diverse working conditions simulating complete disconnection. This assessment involved using both finite element analysis and empirical measurements. The findings unequivocally demonstrate that the disconnection of bridge bearings results in a reduction in the natural frequencies for each mode order, with an observed cumulative effect. In addition, it is noteworthy that the vibration mode indices typically exhibit greater sensitivity toward the disconnection of outer bearings. By contrast, FDMCR demonstrates commendable positioning capabilities and exceptional noise resistance in identifying bridge-bearing disengagement. The empirical insights gleaned from these research findings hold significant value in terms of on-site identification of bridge-bearing disengagement, ultimately contributing to the preservation of bridges’ long-term operational integrity.

show abstract

Non-contact vehicle weight identification method based on explainable machine learning models and computer vision

Feng,

Gao,

Zhang

et al. 2024

J Civil Struct Health Monit

View full text Add to dashboard Cite

Deep learning-based condition assessment for bridge elastomeric bearings

Cited by 10 publications

References 48 publications

Impact of Variable Parameters of Expansion Joints and Bearing Supports on the Vehicle-Induced Vibration of Curved Girder Bridges

Impact of Variable Parameters of Expansion Joints and Bearing Supports on the Vehicle-Induced Vibration of Curved Girder Bridges

Bridge-bearing disengagement identification based on flexibility matrix diagonal matrix change rate: an indoor physical simulation experiment

Non-contact vehicle weight identification method based on explainable machine learning models and computer vision

Contact Info

Product

Resources

About