Probabilistic vehicle weight estimation using physics‐constrained generative adversarial network

Abstract

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.

A literature review: Generative adversarial networks for civil structural health monitoring

“…To identify and clarify the position of GANs in the civil SHM field, in terms of the type of GAN applications studied by the researchers, an illustrative figure is made (Figure 9) which shows the classification of the applications of GANs in civil SHM and the corresponding studies with the GAN models used in each study. As the main concept of GAN is to learn data domain and data generation, some studies solely studied data generation [ (Kanghyeok and do Hyoung, 2019;Xiong and Chen, 2019;Zhang and Wang, 2019;Tsialiamanis et al, 2020;Xu et al, 2021;Yu et al, 2021;Tsialiamanis et al, 2022a;Heesch et al, 2021;Colombera et al, 2021;Luleci et al, 2022b;Luleci et al, 2023)] (a total of 11 studies) by using original GAN or other GAN variants. Thus, the data generation category is separated from other categories.…”

“…The authors in Yu et al (2021) studied a probabilistic weight estimation using physics-constrained GAN where they address the issue of existing bridge weight-in-motion (BWIM) approaches that seldom account for the uncertainty of vehicle weight in terms of the probabilistic distribution of vehicles. The used GAN model, which is constrained by the known physics knowledge, is trained to learn the distributions of vehicle weights from the observed bridge response under the traffic loading.…”

Feasibility of energy harvesting from vertical pedestrian‐induced vibrations of footbridges for smart monitoring applications

“…(2020), Yu et al. (2021), and Zhang and Lin (2021). A useful discussion about the state‐of‐the‐art is provided in Qarib and Adeli (2014).…”

“…Further investigations about the employment of self-powered wireless sensors in structural applications are presented, for instance, in Lajnef et al (2014) and Alavi et al (2016). Intelligent methods and smart solutions for structural monitoring applications are proposed, for example, in Amezquita-Sanchez and Adeli (2015a), Amezquita-Sanchez and Adeli (2015b), Amezquita-Sanchez et al ( 2017), Hampshire and Adeli (2000), Jauhiainen et al (2021), Li et al (2017), Luo et al (2021), Narazaki et al (2020), Ngeljaratan et al (2021), Oh et al (2017), Perez-Ramirez et al (2019), Sajedi and Liang (2021), Tian et al (2021), Weng et al (2020), Xu et al (2021), Yan et al (2020), Yu et al (2021), and Zhang and Lin (2021).…”

Deep convolutional generative adversarial networks for the generation of numerous artificial spectrum‐compatible earthquake accelerograms using a limited number of ground motion records

“…A few researchers employed GANs for the augmentation of available datasets by producing new synthetic images to enhance the applicability of the given models (Zhang et al, 2021). Yu et al (2021) used a GAN to propose a probabilistic vehicle weight estimation approach.…”