Yongsheng Bai

Dr. Yongsheng Bai

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 May 2022 in Structural Health Monitoring
Verified
Journal Article
Closed access
YBYongsheng Bai
Yongsheng Bai
BZBing Zha
Bing Zha
HSHalil Sezen
Halil Sezen
AYAlper Yilmaz
Alper Yilmaz
This paper presents a few comprehensive experimental studies for automated Structural Damage Detection (SDD) in extreme events using deep learning methods for processing 2D images. In the first study, a 152-layer Residual network (ResNet) is utilized to classify multiple classes in eight SDD tasks, which include identification of scene levels, damage levels, and material types. The proposed ResNet achieved high accuracy for each task while the positions of the damage are not identifiable. In the second study, the existing ResNet and a segmentation network (U-Net) are combined into a new pipeline, cascaded networks, for categorizing and locating structural damage. The results show that the accuracy of damage detection is significantly improved compared to only using a segmentation network. In the third and fourth studies, end-to-end networks are developed and tested as a new solution to directly detect cracks and spalling in the image collections of recent large earthquakes. One of the proposed networks can achieve an accuracy above 67 .6% for all tested images at various scales and resolutions, and shows its robustness for these human-free detection tasks. As a preliminary field study, we applied the proposed method to detect damage in a concrete structure that was tested to study its progressive collapse performance. The experiments indicate that these solutions for automatic detection of structural damage using deep learning methods are feasible and promising. The training datasets and codes will be made available for the public upon the publication of this paper.

13 February 2025 in Sensors
Verified
Journal Article
Open access
PDF file
CSCarlos Daniel Sanchez
Carlos Daniel Sanchez
FWFeng Wang
Feng Wang
YBYongsheng Bai
Yongsheng Bai
HGHaitao Gong
Haitao Gong
Pavement surface distresses are analyzed by transportation agencies to determine section performance across their pavement networks. To efficiently collect and evaluate thousands of lane-miles, automated processes utilizing image-capturing techniques and detection algorithms are applied to perform these tasks. However, the precision of this novel technology often leads to inaccuracies that must be verified by pavement engineers. Developments in artificial intelligence and machine learning (AI/ML) can aid in the progress of more robust and precise detection algorithms. Deep learning models are efficient for visual distress identification of pavement. With the use of 2D/3D pavement images, surface distress analysis can help train models to efficiently detect and classify surface distresses that may be caused by traffic loading, weather, aging, and other environmental factors. The formation of these distresses is developing at a higher rate in coastal regions, where extreme weather phenomena are more frequent and intensive. This study aims to develop a YOLOv5 model with 2D/3D images collected in the states of Louisiana, Mississippi, and Texas in the U.S. to establish a library of data on pavement sections near the Gulf of Mexico. Images with a resolution of 4096 × 2048 are annotated by utilizing bounding boxes based on a class list of nine distress and non-distress objects. Along with emphasis on efforts to detect cracks in the presence of background noise on asphalt pavements, six scenarios for augmentation were made to evaluate the model’s performance based on flip probability in the horizontal and vertical directions. The YOLOv5 models are able to detect defined distresses consistently, with the highest mAP50 scores ranging from 0.437 to 0.462 throughout the training scenarios.

11 February 2026 in Journal of Civil Structural Health Monitoring
Verified
Journal Article
Open access
PDF file
YBYongsheng Bai
Yongsheng Bai
Halil SezenHalil Sezen
Halil Sezen
AYAlper Yilmaz
Alper Yilmaz
RQRongjun Qin
Rongjun Qin
This paper introduces a novel application of remote sensing systems and digital twins to investigate the collapse potential of existing buildings. As the first multi-disciplinary team to approach the monitoring of existing structures from this perspective, we focused on the building’s performance after a sudden loss of its critical components. A field experiment was conducted for a six-story reinforced concrete (RC) building, distantly monitoring the structure’s performance using various camera placements (in-situ and remote cameras, cell phones, and drones) and LiDAR. To address damage from the loss of columns and floors, deep learning methods are employed for both damage detection and vibration measurement using the captured camera data. We created digital twins of the building before and after a column was removed, allowing us to accurately measure residual deflections of damaged beams and slabs. During the test, vibration signals were recorded by wireless accelerometers to verify the building’s dynamic response to impacts from the removal equipment, while remote cameras were placed to automatically survey these same vibrations. Non-linear structural analyses and acceleration measurements validated our observations from the remote sensing systems. This research offers practical solutions for remotely monitoring full-scale RC structures and evaluating their real performance using these advanced technologies, bridging a significant remote-monitoring gap for inaccessible buildings. These new insights will provide substantial benefits for engineers and researchers and meet their practical needs.


7 July 2026 in Transportation Research Record: Journal of the Transportation Research Board
Verified
Journal Article
Closed access
YBYongsheng Bai
Yongsheng Bai
FWFeng Wang
Feng Wang
HGHaitao Gong
Haitao Gong
XLXiaohua Luo
Xiaohua Luo
This paper investigates strategies to enhance the performance of deep learning models in pavement distress detection by utilizing two distinct datasets collected and annotated from different sources (vendors). The datasets consist of two- and three-dimensional images scanned from asphalt/concrete pavements and manually labeled for multiple surface distresses. Despite using the same base model to train individually, the performance of new models varies between the two datasets for the same pavement type. It remains a question whether transfer learning, knowledge distillation, or data merging will improve weaker models by leveraging stronger ones and increase the models’ robustness across different data sources. Experiments are conducted using these strategies to assess their applicability for single-source data (e.g., from a single vendor) and their generalization for multiple sources (e.g., from two or more vendors). This paper bridges a knowledge gap by qualitatively and quantitatively evaluating the effects of these strategies on current pavement distress detection practices using image data. Optimal approaches, such as fine-tuning or data merging, are recommended for various use cases aimed at real applications.