Abstract
In the application of a bridge weigh-in-motion (WIM) system, the collected data may be temporarily or permanently lost due to sensor failure or system transmission failure. The high data loss rate weakens the distribution characteristics of the collected data and the ability of the monitoring system to conduct assessments on bridge condition. A deep learning-based model, or generative adversarial network (GAN), is proposed to reconstruct the missing data in the bridge WIM systems. The proposed GAN in this study can model the collected dataset and predict the missing data. Firstly, the data from stable measurements before the data loss are provided, and then the generator is trained to extract the retained features from the dataset and the data lost in the process are collected by using only the responses of the remaining functional sensors. The discriminator feeds back the recognition results to the generator in order to improve its reconstruction accuracy. In the model training, two loss functions, generation loss and confrontation loss, are used, and the general outline and potential distribution characteristics of the signal are well processed by the model. Finally, by applying the engineering data of the Hangzhou Jiangdong Bridge to the GAN model, this paper verifies the effectiveness of the proposed method. The results show that the final reconstructed dataset is in good agreement with the actual dataset in terms of total vehicle weight and axle weight. Furthermore, the approximate contour and potential distribution characteristics of the original dataset are reproduced. It is suggested that the proposed method can be used in real-life applications. This research can provide a promising method for the data reconstruction of bridge monitoring systems.
Highlights
The collected data from the bridge WIM system were organized by month and procollected data from the bridge WIM system were organized by month and processed The using the method described in the previous section
Basedresults, on the training results, scatter plots of data the traffic flow gendata that were generBased on the training the scatter plots the of the traffic flow that were ated byof the generator of the GANtraining after 700,000 training sessions for June, July, September, erated by the generator the
= x for two weeks, that the proposed uted over the imagereconstructed of y = x forthe two weeks, which the proposed gross vehicle weightdemonstrates data adequately.that
Summary
Weigh-in-motion (WIM) systems have been increasingly used in bridge structural health monitoring (SHM) [1,2]. Grakovski and Pilipovec et al reconstructed the weight data of each wheel in a vehicle dynamic weighing measurement by a fiber optic sensor (FOS), based on the function of the change of the optical signal parameters caused by the deformation of the fiber under the action of the weight of the traversing vehicle [21]. Wang and Cha proposed an unsupervised deep learning method to detect impairment using autoencoders by reconstructing the data and comparing it with the impaired response [34]. This unsupervised deep learning approach provided a stable and robust damage detection performance using acceleration measurements that were collected from the intact structure. The discriminator tries to optimize the generator by discriminating the generated data to make the reconstruction look realistic
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
