Digital modeling on the nonlinear mapping between multi‐source monitoring data of in‐service bridges

Zhao, Hanwei; Li, Aiqun; Wei, Sheng; Geng, Fangfang

doi:10.1002/stc.2618

Cited by 43 publications

(13 citation statements)

References 56 publications

(60 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using the network structures shown in Figure 2, the number of training iterations is set to 500. An Adam optimizer is used in network back propagation 45 . SD 1 is taken as an example to illustrate the optimization process of the hyperparameters.…”

Section: Case Study: a Suspension Bridgementioning

confidence: 99%

See 1 more Smart Citation

Correlation model of deflection, vehicle load, and temperature for in‐service bridge using deep learning and structural health monitoring

Deng

Zhai

et al. 2022

Structural Contr & Hlth

Self Cite

View full text Add to dashboard Cite

Deflection is an important issue in bridge structural health monitoring. An accurate deflection-vehicle load-temperature correlation model is critical to abnormal data identification, deflection prediction under extreme conditions, and bridge structural assessment. However, because of the discrete distribution in time domain of vehicle load and the extreme complexity of the deflectionvehicle load-temperature correlation, the correlation modeling method needs further studies. A novel deflection-vehicle load-temperature correlation modeling method is developed in this study. Based on the concept of deflection influence line (DIL), the raw vehicle load monitoring data are transformed into time-continuous vehicle influence coefficient (VIC). By using gated recurrent unit (GRU) neural network, a correlation model with inputs of VIC and environmental temperature data and output of deflection data is established.Taking a suspension bridge in China as an example, the prediction accuracy of short-, medium-, and long-term correlation models is tested. Moreover, based on the correlation model, a decomposition method of temperature-and vehicle-induced deflection components is proposed. The results show that the predicted deflection of the short-term correlation model is basically consistent with the real-time monitoring data, while the medium-and long-term correlation models have accurate prediction ability for the deflection extreme values in a certain time window. The temperature-and vehicle-induced deflection components separated by using the correlation model are in good agreement with the wavelet decomposition (WD) results, with clear physical meaning and independent of empirical judgment.

show abstract

Section: Case Study: a Suspension Bridgementioning

confidence: 99%

“…An Adam optimizer is used in network back propagation. 45 SD 1 is taken as an example to illustrate the optimization process of the hyperparameters. Figure 9 shows the predicted root mean square errors (RMSE) of the test set.…”

Section: Short-term Correlation Modelmentioning

confidence: 99%

Correlation model of deflection, vehicle load, and temperature for in‐service bridge using deep learning and structural health monitoring

Deng

Zhai

et al. 2022

Structural Contr & Hlth

Self Cite

View full text Add to dashboard Cite

show abstract

“…Oh et al 52 proposed a damage localization method for building structures based on the interrelationships of structural responses by using a CNN. Zhao et al 14 completed digital modeling of a nonlinear mapping between multisource monitoring data for in-service bridges by using a long short-term memory (LSTM) network. However, these methods focus on damage detection based on monitoring data from a single bridge, and little research has addressed damage localization for a group of bridges by utilizing the characteristics of similar environmental conditions.…”

Section: Introductionmentioning

confidence: 99%

Damage localization for bridges monitored within one cluster based on a spatiotemporal correlation model of strain monitoring data

Cao

Liu

2022

Structural Health Monitoring

View full text Add to dashboard Cite

The bridges monitored within one cluster refer to several medium- and small-span beam bridges with similar structural characteristics located in a continuous elevated corridor. The variation in the strain monitoring data of these bridges comprehensively reflects diverse coupling effects. These complex coupling factors present great challenges for the damage diagnosis of bridges. To address this issue, a damage localization method for bridges monitored within one cluster is proposed based on a spatiotemporal correlation model of strain monitoring data between bridges. First, a deep learning architecture combining a convolutional neural network (CNN) with a long short-term memory (LSTM) network is established, which can reveal the complex time-varying mapping relationship between the strain monitoring data for similar bridges within one cluster to obtain an accurate spatiotemporal correlation model. Second, a strain prediction framework is presented that uses the proposed spatiotemporal correlation model after training. On this basis, the predicted and measured strains can be utilized to calculate a damage localization index that is not affected by complex coupling factors. Then, combined with abnormal diagnosis theory, the proposed index is implemented to accurately localize damage in all bridges within one cluster. Finally, the application of the proposed method to three actual bridges monitored within one cluster demonstrates the accuracy of the spatiotemporal correlation model and the effectiveness of structural damage localization.

show abstract

“…Typically, the raw sensor data are first preprocessed to enhance the data quality, then identify the fault-relevant features, and utilize techniques such as machine learning-based approaches to formulate a predictive model for diagnostic and prognostic purposes. Most PHM studies focus on critical machinery components and infrastructures including bearings, 4,5 gears, 6,7 batteries, 8,9 bridges, 10,11 and railway. 12 However, these studies are mainly developed based on conventional machine learning models with shallow configurations.…”

Section: Introductionmentioning

confidence: 99%

A probabilistic Bayesian recurrent neural network for remaining useful life prognostics considering epistemic and aleatory uncertainties

Caceres

González

Zhou

et al. 2021

Struct Control Health Monit

View full text Add to dashboard Cite

Deep learning-based approach has emerged as a promising solution to handle big machinery data from multi-sensor suites in complex physical assets and predict their remaining useful life (RUL). However, most recent deep learningbased approaches deliver a single-point estimate of RUL as these models represent the weights of a neural network as a deterministic value and hence cannot convey uncertainty in the RUL prediction. This practice usually provides overly confident predictions that might cause severe consequences in safetycritical industries. To address this issue, this paper proposes a probabilistic Bayesian recurrent neural network (RNN) for RUL prognostics considering epistemic and aleatory uncertainties. The epistemic uncertainty is handled by Bayesian RNN layers as extensions from the Frequentist RNN layers using the Flipout method. The aleatory uncertainty is covered by a probabilistic output that follows a Gaussian distribution parameterized by the two neurons in the output layer. The network is trained using Bayes by backprop with the Flipout method. The proposed model is demonstrated by the open-access Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset of turbofan engines and a comparative study of the Frequentist RNN counterparts, the Monte Carlo Dropout-based RNN, and the state-of-the-art models for C-MAPSS datasets. The results demonstrate the promising performance and robustness of the proposed model in RUL prognostics.

show abstract

Digital modeling on the nonlinear mapping between multi‐source monitoring data of in‐service bridges

Cited by 43 publications

References 56 publications

Correlation model of deflection, vehicle load, and temperature for in‐service bridge using deep learning and structural health monitoring

Correlation model of deflection, vehicle load, and temperature for in‐service bridge using deep learning and structural health monitoring

Damage localization for bridges monitored within one cluster based on a spatiotemporal correlation model of strain monitoring data

A probabilistic Bayesian recurrent neural network for remaining useful life prognostics considering epistemic and aleatory uncertainties

Contact Info

Product

Resources

About