A5024545973- Asphalt Pavement Performance Evaluation
- Infrastructure Maintenance and Monitoring
- Geotechnical Engineering and Underground Structures
- Innovative concrete reinforcement materials
- Smart Materials for Construction
- Grouting, Rheology, and Soil Mechanics
- Concrete and Cement Materials Research
- Transport Systems and Technology
- Geophysical Methods and Applications
- Rock Mechanics and Modeling
- Polymer composites and self-healing
- Civil and Geotechnical Engineering Research
- Climate change and permafrost
- Soil, Finite Element Methods
- Polymer Nanocomposites and Properties
- Non-Destructive Testing Techniques
- Numerical methods in engineering
- Concrete Corrosion and Durability
- Geotechnical Engineering and Soil Stabilization
- Cryospheric studies and observations
- Structural Behavior of Reinforced Concrete
- Urban Stormwater Management Solutions
- Ultrasonics and Acoustic Wave Propagation
- Traffic Prediction and Management Techniques
- Prosthetics and Rehabilitation Robotics
Southeast University
2016-2025
Harbin Institute of Technology
2024
Southeast University
2016-2024
Sinopec (China)
2024
Changsha University of Science and Technology
2020-2023
Inner Mongolia Electric Power (China)
2018-2023
Yonsei University
2023
Chengdu University of Technology
2022
Henan University of Engineering
2019
China Railway Group (China)
2008-2018
Image-based intelligent detection of road cracks with high accuracy and efficiency is vital to the overall condition assessment pavement. However, significant problems continuous interruption background discrete noise misidentification are frequently observed in current semantic segmentation pavement cracks, which mainly caused by traditional convolutional neural networks. This paper proposes a skip-level round-trip sampling block structure implementation networks, thereby constructed novel...
The conventional surface reflection method has been widely used to measure the asphalt pavement layer dielectric constant using ground-penetrating radar (GPR). This may be inaccurate for in-service thickness estimation with variation through depth, which could addressed extended common mid-point (XCMP) air-coupled GPR antennas. However, factors affecting XCMP on prediction accuracy haven't studied. Manual acquisition of key is required, hinders its real-time applications. study investigates...
Abstract Three‐dimensional (3D) buried object detection using ground penetrating radar (GPR) benefits from the powerful capacity of image‐wise deep neural networks. However, it still faces challenge information loss raw GPR signals to two‐ and three‐dimensional images, such as frequency‐domain when normalizing into gray‐scale images spatial stacked B‐ C‐scan replace inputs. To solve challenge, this study has proposed an ENNreg‐transformer model, directly 3D perform detection. In are first...
This study focused on the property characterization of asphalt and mixtures modified by different types crumb rubber (normal desulfurized). was based chemical evaluation testing for performance analysis mixtures. Chemical fraction gel permeation chromatography tests were used to identify asphalt's microstructures; conventional Superpave performed evaluate its macroproperties; an isolation test judge storage stability. Also conducted wheel loading tests, three-point beam bending Marshall...
This study investigated the simulation of wheel tracking test and high-temperature rutting behaviour an asphalt mixture by using discrete element method (DEM). Based on DEM software named as Particle Flow Code in three dimensions (PFC3D), a micromechanical model composed coarse aggregates, mastic, air voids was built two-dimensional virtual simulated. test, distribution displacement contact forces within specimen were analysed. It is proved that can capture deformation caused combination...
The objective of this study is to design an innovative mesoscopic test for characterizing the damage evolutions and fracture performances asphalt mortar. Based on SEM-Servopulser devices improved specimens, pure mode I cracking tests were conducted successfully under scanning electron microscope (SEM). It can have a real-time online observations records surface micro-crack behaviors different loads. And it first time in road engineering capture dynamic micro-behavior micro-structure...
Abstract Distress segmentation assigns each pixel of a pavement image to one distress class or background, which provides simplified representation for detection and measurement. Even though remarkably benefiting from deep learning, still faces the problems poor calibration multimodel fusion. This study has proposed neural network by combining Dempster–Shafer theory (DST) transformer segmentation. The network, called evidential transformer, uses its backbone obtain pixel‐wise features input...