A sparse self-estimated sensor-network for reconstructing moving vehicle forces

Pan, Chudong; Liu, Huanlin; Yu, Ling

doi:10.1088/1361-665x/ab28ed

Cited by 7 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Chen, Qin et al, 2019;Z. Chen & Chan, 2017;Feng et al, 2015;Liu et al, 2020;C.-D. Pan et al, 2017;C.-D. Pan et al, 2018;C. Pan et al, 2019;Zhong et al, 2019; X. Q.…”

Section: Introductionunclassified

See 1 more Smart Citation

Probabilistic vehicle weight estimation using physics‐constrained generative adversarial network

Cai

Liu

2021

Computer aided Civil Eng

View full text Add to dashboard Cite

Traffic information plays an important role in the design and management of civil transportation infrastructure. Bridge weigh-in-motion (BWIM) provides an effective tool for traffic information gathering by estimating vehicle parameters including its weight through bridge responses. Most existing BWIM algorithms rarely consider the epistemic uncertainty of vehicle weight in terms of the probabilistic distribution of estimated axle weights (AWs) of the vehicle. This paper proposes a novel methodology for probabilistic vehicle weight estimation using a physics-constrained generative adversarial network (GAN). Generative models are introduced to describe the probabilistic distributions of estimated AWs and bridge responses. Physics constraints on the generative models are formulated and enforced by minimizing a physics-based loss function. The generative models are then learned by training a physics-constrained GAN using the observed bridge responses. Numerical study and field testing are conducted to demonstrate the proposed method using representative highway bridges and vehicles.The results show that the proposed method can successfully capture the uncertainty in the vehicle weight estimation and provide the probabilistic distributions of the estimated AWs for different vehicle types and loading conditions considered, which can enhance the application of BWIM for relevant tasks such as traffic data collection and truck overloading enforcement. Based on the results obtained from the numerical study and field testing, the maximum coefficient of variation obtained for the AWs and gross vehicle weight of the presented cases are 0.55 and 0.11, respectively.

show abstract

“…Chen, Qin et al, 2019;Z. Chen & Chan, 2017;Feng et al, 2015;Liu et al, 2020;C.-D. Pan et al, 2017;C.-D. Pan et al, 2018;C. Pan et al, 2019;Zhong et al, 2019; X. Q.…”

Section: Introductionunclassified

“…Pan et al., 2017; C.‐D. Pan et al, 2018; C. Pan et al, 2019; Zhong et al., 2019; X. Q. Zhu & Law, 2016). Nevertheless, the practical application of MFI methods is still limited as it requires the information on the dynamic properties of the bridge that is difficult to accurately estimate (Yu et al., 2016).…”

Section: Introductionmentioning

confidence: 99%

Probabilistic vehicle weight estimation using physics‐constrained generative adversarial network

Cai

Liu

2021

Computer aided Civil Eng

View full text Add to dashboard Cite

show abstract

“…The vehicle and bridge systems are coupled at the contact points. It is a typical moving load problem and extensive research has been conducted on the moving force identification techniques to quantify the interaction via measurements from the bridge [17][18][19]. O'Brien et al [20] identified the interaction forces from vehicle dynamic responses.…”

Section: Introductionmentioning

confidence: 99%

A Two-Step Drive-By Bridge Damage Detection Using Dual Kalman Filter

Zhu

Law

et al. 2020

Int. J. Str. Stab. Dyn.

View full text Add to dashboard Cite

Drive-by bridge inspection using acceleration responses of a passing vehicle has great potential for bridge structural health monitoring. It is, however, known that the road surface roughness is a big challenge for the practical application of this indirect approach. This paper presents a new two-step method for the bridge damage identification from only the dynamic responses of a passing vehicle without the road surface roughness information. A state-space equation of the vehicle model is derived based on the Newmark-[Formula: see text] method. In the first step, the road surface roughness is estimated from the dynamic responses of a passing vehicle using the dual Kalman filter (DKF). In the second step, the bridge damage is identified based on the interaction force sensitivity analysis with Tikhonov regularization. A vehicle–bridge interaction model with a wireless monitoring system has been built in the laboratory. Experimental investigation has been carried out for the interaction force and bridge surface roughness identification. Results show that the proposed method is effective and reliable to identify the interaction force and bridge surface roughness. Numerical simulations have also been conducted to study the effectiveness of the proposed method for bridge damage detection. The vehicle is modeled as a 4-degrees-of-freedom half-car and the bridge is modeled as a simply-supported beam. The local bridge damage is simulated as an elemental flexural stiffness reduction. Effects of measurement noise, surface roughness and vehicle speed on the identification are discussed.The results show that the proposed drive-by inspection strategy is efficient and accurate for a quick review on the bridge conditions.

show abstract