Relationship modeling between vehicle‐induced girder vertical deflection and cable tension by BiLSTM using field monitoring data of a cable‐stayed bridge

Tian, Yadi; Xu, Yang; Zhang, Dongyu; Li, Hui

doi:10.1002/stc.2667

Cited by 30 publications

(21 citation statements)

References 28 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, other machine learning-based or deep learning-based method can be introduced into the correlation modeling, such as the quantile random forest (QRF), ensemble learning, the long short-term memory (LSTM) applied for temperature-cable tension relation modeling, and the bidirectional LSTM (BiLSTM) for vertical deflection-cable tension relation modeling. 33,53 In addition, association rule learning (ARL) combined with traffic light was utilized to predict future bridge frequencies according to temperature measurements and detect anomalies. 54 A genetic programming method was applied to construct a predictor and capture temperature changes using the modal frequency as an independent variable.…”

Section: Correlation Modeling Methodsmentioning

confidence: 99%

“…To consider the non‐Gaussianity of data distribution and the nonlinearity between temperature and modal frequency, Bayesian mixture of experts (MoE) model was developed to automatically switch among different regimes represented by experts 51,52 ; Wang et al 30 developed local PLSR for frequency refinement modeling in each linear region. Besides, other machine learning‐based or deep learning‐based method can be introduced into the correlation modeling, such as the quantile random forest (QRF), ensemble learning, the long short‐term memory (LSTM) applied for temperature–cable tension relation modeling, and the bidirectional LSTM (BiLSTM) for vertical deflection–cable tension relation modeling 33,53 …”

Section: Elimination Of Modal Variability Based On Input–output Model...mentioning

confidence: 99%

See 1 more Smart Citation

Eliminating environmental and operational effects on structural modal frequency: A comprehensive review

Wang

Yang

et al. 2022

Structural Contr & Hlth

View full text Add to dashboard Cite

Modal frequencies are widely used for vibration-based structural health monitoring (SHM) and for capturing the dynamics of a monitored structure to reveal possible failures. However, changing environmental and operational conditions (i.e., temperature, humidity, wind load, and traffic load) may submerge the modal variability induced by structural damage, thereby falsely identifying damage of interest. This paper presents a comprehensive summary review of SHM for the prediction of modal frequency and the elimination of environment-induced masking effects based on the data normalization method. The influence mechanisms of external variations on modal frequencies extensively reported in the literature are first described. Next, the research progress in predicting and eliminating the operational modal variability is reviewed emphatically; this progress can be primarily divided into an inputoutput method that focuses on the establishment of the relationship model between structural frequency and environmental conditions and an outputonly method that separates the embedded environmental variable-induced changes depending on whether the environmental measurements are measured. Finally, the conclusions and future studies are summarized and discussed. As an overview, the major contribution of this paper is to provide objective technical references for engineers and owners and to further evaluate structural safety conditions more effectively and in a timely manner.

show abstract

Section: Correlation Modeling Methodsmentioning

confidence: 99%

Section: Elimination Of Modal Variability Based On Input–output Model...mentioning

confidence: 99%

Eliminating environmental and operational effects on structural modal frequency: A comprehensive review

Wang

Yang

et al. 2022

Structural Contr & Hlth

View full text Add to dashboard Cite

show abstract

“…To mitigate this, bidirectional RNN was proposed. To fix the problems of variation in structural response due to initial residual stress, coupling effects of structure damage, and external loads, Tian et al 238 (Level 1) proposed a global and partial bidirectional LSTM model to relate the girder vertical deflection to cable tension. It was found out that the partial model performed better with relative root mean square error (RRMSE) of 3.24% in addition to performing consistently with noise levels and traffic volumes under normal operational conditions.…”

Section: Neural Network (Supervised/unsupervised)mentioning

confidence: 99%

Machine learning and structural health monitoring overview with emerging technology and high-dimensional data source highlights

Malekloo

Özer

AlHamaydeh

et al. 2021

Structural Health Monitoring

235

View full text Add to dashboard Cite

Conventional damage detection techniques are gradually being replaced by state-of-the-art smart monitoring and decision-making solutions. Near real-time and online damage assessment in structural health monitoring (SHM) systems is a promising transition toward bridging the gaps between the past’s applicative inefficiencies and the emerging technologies of the future. In the age of the smart city, Internet of Things (IoT), and big data analytics, the complex nature of data-driven civil infrastructures monitoring frameworks has not been fully matured. Machine learning (ML) algorithms are thus providing the necessary tools to augment the capabilities of SHM systems and provide intelligent solutions for the challenges of the past. This article aims to clarify and review the ML frontiers involved in modern SHM systems. A detailed analysis of the ML pipelines is provided, and the in-demand methods and algorithms are summarized in augmentative tables and figures. Connecting the ubiquitous sensing and big data processing of critical information in infrastructures through the IoT paradigm is the future of SHM systems. In line with these digital advancements, considering the next-generation SHM and ML combinations, recent breakthroughs in (1) mobile device-assisted, (2) unmanned aerial vehicles, (3) virtual/augmented reality, and (4) digital twins are discussed at length. Finally, the current and future challenges and open research issues in SHM-ML conjunction are examined. The roadmap of utilizing emerging technologies within ML-engaged SHM is still in its infancy; thus, the article offers an outlook on the future of monitoring systems in assessing civil infrastructure integrity.

show abstract

“…In this section, correlation modeling between different bridge responses is investigated in a datadriven manner, including the time-space domain and the probability distribution domain. The time-series relationship between different response groups for long-span bridges was modeled by establishing global and partial bi-directional long short-term memory (BiLSTM) networks (Tian et al, 2021), as shown in Figure 11. The input and output were time-history of gird vertical displacement (GVD) and cable tension (CT).…”

Section: Correlation-pattern-based Structural Condition Assessmentmentioning

confidence: 99%

Typical advances of artificial intelligence in civil engineering

Qian

et al. 2022

Advances in Structural Engineering

Self Cite

View full text Add to dashboard Cite

Artificial intelligence (AI) provides advanced mathematical frameworks and algorithms for further innovation and vitality of classical civil engineering (CE). Plenty of complex, time-consuming, and laborious workloads of design, construction, and inspection can be enhanced and upgraded by emerging AI techniques. In addition, many unsolved issues and unknown laws in the field of CE can be addressed and discovered by physical machine learning via merging the data paradigm with physical laws. Intelligent science and technology in CE profoundly promote the current level of informatization, digitalization, autonomation, and intellectualization. To this end, this paper provides a systematic review and summarizes the state-of-the-art progress of AI in CE for the entire life cycle of civil structures and infrastructure, including intelligent architectural design, intelligent structural health diagnosis, intelligent disaster prevention and reduction. A series of examples for intelligent architectural art shape design, structural topology optimization, computer-vision-based structural damage recognition, correlation-pattern-based structural condition assessment, machine-learning-enhanced reliability analysis, vision-based earthquake disaster evaluation, and dense displacement monitoring of structures under wind and earthquake, are given. Finally, the prospects of intelligent science and technology in future CE are discussed.

show abstract

Relationship modeling between vehicle‐induced girder vertical deflection and cable tension by BiLSTM using field monitoring data of a cable‐stayed bridge

Cited by 30 publications

References 28 publications

Eliminating environmental and operational effects on structural modal frequency: A comprehensive review

Eliminating environmental and operational effects on structural modal frequency: A comprehensive review

Machine learning and structural health monitoring overview with emerging technology and high-dimensional data source highlights

Typical advances of artificial intelligence in civil engineering

Contact Info

Product

Resources

About