Zhen Liu

Verified

Zhen verified their affiliation via an institutional email.

Learn more

Verified

Zhen verified their affiliation via an institutional email.

Learn more

• Doctor of Philosophy
• Postdoctoral Scholar at Pennsylvania State University

Ground-Penetrating Radar (GPR) has demonstrated significant advantages in the non-destructive detection of road structural defects due to its speed, safety, and efficiency. This paper proposes a three-dimensional (3D) reconstruction method for GPR images, integrating the back-projection (BP) imaging algorithm to accurately determine the size, locat...

The PaveDistress dataset contains high-resolution images of road surface distresses, including cracks, repairs, potholes, and background images without defects. The data were collected using a specialized pavement inspection vehicle along the S315 highway in China. The vehicle was equipped with a Basler raL2048-80km line scan camera and infrared la...

Urban transportation systems, particularly underground interchanges, present significant challenges for sustainable and resilient urban design due to their complex road geometries and dense traffic signage. These challenges are further compounded by the interaction of diverse road users, which heightens the risk of accidents. To enhance both safety...

Dear Colleagues, I am excited to announce the call for papers for a Special Issue of Remote Sensing, titled "Advances in Remote Sensing and Digital Twin Technologies for Transportation Infrastructure." As we strive to explore the forefront of research and development in the amalgamation of remote sensing technologies and digital twin concepts with...

The extraction of roads from UAV images is challenged by lighting, noise, occlusions, and similar non-road objects, making high-quality road extraction difficult. To addressing these issues, this study proposes an enhanced U-Net network to automate the extraction and 3D modeling of real road scenes using UAV imagery. Initially, a cascaded atrous sp...

Traditional road structural detection and evaluation is inefficient, imprecise, and destructive. To address these issues, a feature-enhanced multiscale vision transformer (FeMViT) for road distress classification from ground penetrating radar (GPR) images was proposed. FeMViT model used the feature-enhanced feature pyramid network (FPN) and feature...

Aiming at the requirements of nondestructive testing and intelligent recognition of cracks inside the pavement structures, a ground penetrating radar (GPR) detection and automatic identification method based on improved you only look once version 8 (YOLOv8) and AutoAugment enhancement was proposed. Combined with Gprmax numerical simulation, laborat...

Addressing the constraints inherent in traditional primary Air Quality Index (AQI) forecasting models and the shortcomings in the exploitation of meteorological data, this research introduces a novel air quality prediction methodology leveraging machine learning and the enhanced modeling of secondary data. The dataset employed encompasses forecast...

The Structural Health Monitoring (SHM) of pavement infrastructures holds paramount significance in the assessment and prognostication of the remaining service life of roadways. In response to this imperative, a methodology for surveilling the surface and internal mechanical responses of pavements was devised through the amalgamation of Accelerated...

In the process of driving in an underground interchange, drivers are faced with many challenges, such as being in a closed space, visual changes alternating between light and dark conditions, complex road conditions in the confluence section, and dense signage, which directly affect the safety and comfort of drivers in an underground interchange. T...

Aiming at the problems such as low degree of automation, incomplete road information, and disconnected road intersections in UAV image extraction, a topology and global context-aware aggregate network (TGCA-Net) was proposed for the automatic extraction and 3D modeling of real-road scenes using UAV imagery in this paper. Automated extraction was ac...

the pavement structures, a ground penetrating radar (GPR) detection and automatic identification method based on improved YOLOv8 and AutoAugment enhancement was proposed. Combined with Gprmax numerical simulation, laboratory model test, and field GPR measurement, it is concluded that the internal cracks showed a prominent “hyperbola” feature on GPR...

Traditional road structural detection and evaluation is inefficient, imprecise, and destructive. To address this issue, a feature-enhanced multiscale vision transformer (FeMViT) for road distress classification from ground penetrating radar (GPR) images was proposed. FeMViT model used the feature-enhanced feature pyramid network (FPN) and feature e...

During underground interchange driving, drivers are faced with challenges such as complex road conditions and dense markings, which directly affect the safety and comfort of driving. To address the above problems, a driving safety analysis of underground interchange using driving simulator and machine learning was proposed. Considering the influenc...

Ground penetrating radar (GPR) has shown its advantages in non-destructive detection of road structural defects for its fast, safe, and efficient characteristics. To accurately obtain various parameters of road structural defects, a three-dimensional(3D) reconstruction method combined with the back-projection (BP) imaging algorithm for GPR images w...

This study investigates the application of foam asphalt (FA) to enhance the compaction effectiveness of a hot in-place recycling asphalt mixture (HIR-AM) during the HIR process of old road surfaces. Initially, the process parameters for FA preparation were determined through expansion-rate and half-life tests. Subsequently, the study focused on eva...

Recycling agents (RAs) can mitigate the adverse effects of reclaimed asphalt pavement (RAP) on recycled asphalt, which can result in more RAP being added. To explore the effects of four RAs on recycled asphalt, this study used asphalt rheological performance experiments, including the bending beam rheometer (BBR) test, the dynamic shear rheological...

Special Issue: Toward Green and Intelligent Transportation Infrastructure: Road Non-destructive Testing and Structural Health Monitoring Technologies Submission Deadline: 20 November 2024 Special Issue Website: https://www.mdpi.com/journal/sensors/special_issues/U7811KJ2RN Guest Editors: Prof. Dr. Xingyu Gu and Dr. Zhen Liu

The application of reclaimed asphalt pavement (RAP) can help reduce resource waste and environmental pollution in road construction. However, so far, only a small percentage of RAP materials can be used in road construction. The key obstacles to the application of a recycled asphalt mixture (RAM) with high RAP content are the variability of RAP mat...

An improved Hybrid Task Cascade (HTC) instance segmentation model was proposed to segment pavement surface distress intelligently and accurately. First, the automatic color equalization (ACE) algorithm was performed to preprocess the dataset. Then, HTC and the proposed HTC were described. The proposed HTC was modified using the ResNeXt101 network,...

The technology of warm-mix regeneration has been frequently used in the production of asphalt pavement; however, the viscosity and self-healing properties of warm-mix recycled asphalt (WMRA) need further study. Therefore, the viscosity and self-healing properties of WMRA were analyzed by combining laboratory tests and molecular dynamics (MD) simula...

A rutting prediction method for semi-rigid pavement structures using accelerated loading tests and finite element analysis was proposed in this study. Firstly, dynamic modulus and creep tests of three pavement materials were performed by changing sizes and temperatures. The prediction equation was obtained and verified using the falling weight defl...

The inspection and monitoring of structural conditions are crucial for the maintenance of semi‑rigid base pavement. To achieve the inverse calculation of material parameters and obtain the mechanical response of asphalt pavement, a method of modulus correction by reducing the error between tested and simulated strains was first developed. The relat...

Reclaimed asphalt pavement (RAP) applications are largely limited by the insufficient performance of reclaimed asphalt (RA). To address this challenge, the composite crumb rubber-modified asphalt (CCRMA) with styrene-butadiene styrene (SBS) and styrene-butadiene rubber (SBR) modifiers was mixed with RA to prepare the reconciling and reclaimed modif...

Permanent deformation (rutting) is one of the typical failure modes of asphalt pavement with a semirigid base in high-temperature areas. To address issues of pavement structure deformation and remaining life prediction, a method of combining accelerated pavement testing and fnite element (FE) simulation was proposed. A modifed Burgers model conside...

Road detection and maintenance has become the research hot: How to quickly and accurately judge the type and location of the distress; Aiming at the assessment of road structural conditions. Road internal distress is an important problem in road detection: FWD: detect instantaneous loads response for pavement internal strength; GPR: fast, non-d...

Highway development status •Rapid construction and development •Overload high temperature, wear, aging, and other factors •Highways have begun to enter the maintenance stage Maintenance •Obtain maintenance data •Accurate and efficient detection of pavement distress

Maintenance of typical pavement structures is critical in Jiangsu, China. Therefore, a method combining accelerated testing, non-destructive testing, and laboratory tests was proposed in this study to achieve the performance evaluation and conservation measures analysis. After loading one million times on a full-scale road section of asphalt paveme...

Rescue and evacuation of underground interchange tunnels after a fire are challenging. Therefore, a method of integrating building information modeling (BIM) and a fire dynamic simu-lator (FDS) was proposed to analyze fire characteristics and personnel escapes in underground interchange tunnels. A BIM model of underground interchange tunnels was bu...

Rutting development and its prediction are critically important for the long-term preservation of semi-rigid pavements. A multi-scale test was developed to analyze the rutting development and its prediction model, involving triaxial, scaled loading, and full-scale loading tests. Laboratory-based triaxial tests predicted the rheological properties o...

Warm mix asphalt (WMA) with organic additive technology has been highly recommended in asphalt pavement. However, the viscosity-reduction mechanism, viscosity-temperature relationship, and field application effects have yet to be well excavated. Therefore, the characteristics, mechanisms, and environmental benefits of WMA containing sasobit warm ag...

Non-destructive testing and characterization of internal vertical cracks are critical for road maintenance by ground penetrating radar (GPR). This paper describes a mask region-based convolutional neural network (R-CNN) that automatically detects and segments small cracks in asphalt pavement at the pixel level. Simulation using Gprmax software and...

Pavement crack detection is critical for transportation infrastructure assessment using ground penetrating radar (GPR). This paper describes a YOLOv3 model with four-scale detection layers (FDL) to detect combined B-scan and C-scan GPR images subject to poor detection effects and a high missed detection rate of small crack feature sizes. Multiscale...

To study the variation rule of mechanical response of semi-rigid base asphalt pavement structure, MLS66 accelerated loading equipment is used to test the pavement under different pavement temperature field and loading speed. Results show that the relationship between the lateral strain and the location of the measuring point is greater, while the l...

A method of evaluating the asphalt pavement internal distresses and structure overall modulus, combining ground penetrating radar (GPR) and falling weight deflectometer (FWD), was proposed. First, the three-dimensional (3D) GPR was used to detect the thickness and distress of the road structure layer. After preprocessing the captured images, canny...

Rutting is one of the typical failure modes of semi-rigid base asphalt pavement in the hightemperature area. To address issues of rutting estimation and preventive maintenance, this paper analyzed the rutting evolution law from three aspects: rutting section morphology, rutting development law, and rutting deformation mechanism based on full-scale...

To realize the intelligent and accurate measurement of pavement surface potholes, an improved You Only Look Once version three (YOLOv3) detection model combining data augmentation and structure optimization was proposed in this study. First, data augmentation was performed through geometric transformation and color adjustment. Potholes’ categories...

This research combines numerical simulation and ultrasonic testing (UT) to analyze the attenuation characteristics and amplitude changes in asphalt concrete under different aggregate sizes and temperatures. Then the equipment MIRA-A1040 was utilized to test and verify the simulation results in the laboratory, and the changes in measured amplitude a...

Nanoscale materials have gradually been a hot spot in improving asphalt performance. Thus, graphene modified asphalt (GMA) was prepared and its modification mechanism and mechanical properties were analyzed in this study. Three kinds of graphene powders (A, B, and C) with different molecular sizes were selected for evaluation. Molecular dynamics (M...

Ground penetrating radar is more and more widely used in pavement maintenance detection due to its non-destructive, fast, safe and efficient advantages. In this paper, the Swedish CO4080 ground penetrating radar is used to conduct on-site measurement on the major and medium repair project of the trunk highway in Guizhou Province. First, combined wi...

To realize the intelligent and accurate measurement of pavement surface potholes, an improved You Only Look Once version three (YOLOv3) object detection model combining data augmentation and structure optimization is proposed in this study. First, color adjustment was used to enhance the image contrast, and data augmentation was performed through g...

To solve the issues that material parameters measured under specific laboratory conditions are extremely different from the actual pavement, a method of structural parameters correction in semi-rigid base asphalt pavement combining numerical simulations, laboratory tests, and accelerated pavement testing (APT) was proposed. The dynamic modulus and...

Accurately identifying and localizing concealed cracks in asphalt pavements through nondestructive ground-penetrating radar (GPR) testing has attracted much attention. However, various realistic factors restrict its detection accuracy. Therefore, this paper proposed a novel YOLOv3 model with a ResNet50vd-deformable convolution (DCN) backbone and a...

The lack of data and poor quality of ground penetrating radar (GPR) images have limited the development of the object detection for internal cracks in asphalt pavement. To address this issue, this paper proposed a ‘DeepAugment’ data augmentation strategy combined with object detection models. First, the characteristic of internal cracks was determi...

The traditional drill core sampling method used for pavement thickness detection is increasingly difficult to meet the increasing demand for pavement detection. At the same time, ground penetrating radar (GPR) have shown superiority in pavement non-destructive detection for its fast detection, safety and high efficiency. In this study, the traditio...

Traditional automatic pavement distress detection methods using convolutional neural networks (CNNs) require a great deal of time and resources for computing and are poor in terms of interpretability. Therefore, inspired by the successful application of Transformer architecture in natural language processing (NLP) tasks, a novel Transformer method...

This paper discusses the visibility classification and influencing-factor analysis of an airport, which were carried out through a data-driven deep learning approach and multiple nonlinear regression analysis. First, a deep integrated model for airport visibility classification was developed, and the relationship between runway visual range (RVR) a...

To address the problems associated with the validity of pavement sensor measurement, a method of combining indoor experiments with finite element (FE) simulations for strain measurement in asphalt pavement is developed in this paper to analyze the validity of strain sensors for practical measurements. First, correlation analysis and one-way analysi...

Traditional Shewhart control charts have insufficient detection capabilities for the volatility of means in asphalt mixture production. This paper proposes an exponentially weighted moving average (EWMA) control chart to achieve quality control (QC) in asphalt mixture production based on the statistical process control (SPC) theory. We established...

This paper proposes a method of combining full-scale accelerated pavement testing (APT), indoor experiments, and finite element (FE) simulations to analyze and predict the dynamic response of a typical pavement structure with an SMA overlay. First, APT was performed under different loads from various axle weights, temperatures and speeds, and the l...

Ground penetrating radar is more and more widely used in pavement maintenance detection due to its non-destructive, fast, safe and efficient advantages. In this paper, the Swedish CO4080 ground penetrating radar is used to conduct on-site measurement on the major and medium repair project of the trunk highway in Guizhou Province. First, combined wi...

Aimed at meet the detection and maintenance requirements of road internal diseases, this paper proposes a ground penetrating radar (GPR) image processing method based on object detection and three-dimensional (3D) reconstruction technology. First, GPR testing of the research road sections was carried out for subsequent works. Then, the GPR numerica...

This paper proposes a method of combining full-scale accelerated pavement testing (APT), indoor experiments, and finite element (FE) simulations to analyze and predict the dynamic response of a typical pavement structure with an SMA overlay. First, APT was performed under different loads from various axle weights, temperatures and speeds, and the l...

In this paper, the reclaimed asphalt with high SBS content (HSA) made by mixing different amounts of HSA and reclaimed asphalt pavement (RAP) with different degrees of aging was taken as the research object, and the macro mechanics test based on DSR and microscopic observation test based on AFM were conducted to research the blending and regenerati...

The automatic detection of pavement cracks can significantly improve the efficiency of road maintenance in pavement engineering. At present, artificial intelligence-based pavement crack detection may have the problem of an insufficient training dataset, which makes it difficult to train a model with high accuracy and a good generalization ability....

Digitizing the aggregate particles efficiently reduces the cost and cuts down the pollution for environment compared to traditional pavement experiments. The study realizes a novel stochastic statistical method for generating digital virtual aggregates particles with realistically complex yet controllable shapes through accurate testing and descrip...

This paper discusses the visibility identification and influencing-factor analysis of an airport through a deep learning approach and multiple nonlinear regression analysis. First, a deep integrated model for airport visibility identification was developed. To extract more low-level features from nighttime images, the original images were transform...

In the process of road maintenance, it is very important to measure the pavement thickness effectively. The traditional drill core sampling method is difficult to meet the increasing demand of testing. With the development of modern science and technology, new nondestructive testing techniques such as ground penetrating radar are gradually applied...

Traditional pavement diseases detection technology cannot meet the current requirements of rapid and intelligent detection of pavement diseases. Meanwhile, Computer Vision (CV) technology has provided the possibility for the intelligent detection. Therefore, aimed at the intelligent detection of pavement diseases, this paper proposes an intelligent...

As an efficient means of nondestructive testing, ground penetrating radar (GPR) has been widely used in pavement testing and maintenance. Meanwhile, the following issues of GPR images detection and recognition needs to be solved urgently. Therefore, this paper develops a method for combining the object detection algorithms with GPR images to recogn...

The accelerated loading test is more and more favored by researchers because it can obtain thechange trend of pavement structure and material performance in a relatively short period of time.This paper first introduces the experimental scheme adopted in this accelerated loading test. Thedynamic response under specific parameters is obtained by cons...

There is no storage rule for massive engineering data generated during the detection of Airport pavement, and the data management efficiency is low. Meanwhile, Building Information Modeling (BIM) and Geo-graphic Information System (GIS) have already been well recognized for its efforts in improving the high-efficiency of AEC (Architecture, Engineer...

New nondestructive testing technologies such as ground penetrating radar (GPR) and image recognition technology based on artificial intelligence (AI) have been gradually applied in the process of road inspection and maintenance. Aimed at practical requirements for nondestructive testing of road diseases, this paper develops an intelligent recogniti...

Building Information Modeling (BIM) is well-known for improving the efficiency of the Architecture, Engineering, and Construction (AEC) industries. Currently, the support for web displays using Web Graphics Library (WebGL) technology in BIM has gained popularity. To address the issues of insufficient display for the airport pavement by two-dimensio...

Aiming at the problems of insufficient dynamic control and data mining of Expressway pavement construction quality in Yunnan, this paper analyzes the application of Exponentially Weighted Moving Average (EWMA) control chart in dynamic control of Expressway asphalt pavement construction quality. Firstly, the quality characteristic value of pavement...

Aimed at the "smart individual" of the road, the functional and performance requirements in the process of Planning, Construction, and Maintenance for the whole life cycle of Smart Road is analyzed. Next, BIM, GIS, IoT, Big Data and AI and other advanced information technologies are integrating these technologies into the life-cycle management of s...

Improving the detection efficiency and maintenance benefits is one of the greatest challenges in road testing and maintenance. To address this problem, this paper presents a method for combining the you only look once (YOLO) series with 3D ground-penetrating radar (GPR) images to recognize the internal defects in asphalt pavement and compares the e...

Concealed cracks are the cracks originating below the surface of asphalt pavement. These cracks could accelerate pavement damage and cause poor driving quality. However, the detection of concealed cracks has been a challenging task due to the nonvisibility of the crack. This study proposes an effective method to automatically complete the recogniza...

Detecting concealed cracks in asphalt pavement has been a challenging task due to the nonvisibility of the location of these cracks. This study proposes an effective method to automatically perform the recognition and location of concealed cracks based on 3-D ground penetrating radar (GPR) and deep learning models. Using a 3-D GPR and a filtering p...

Building Information Modeling (BIM) has already been well recognized for its efforts in improving the high-efficiency of AEC (Architecture, Engineering, and Construction) industry. Meanwhile, there has been a rising trend for the support of a web display developed by HTML5 (HyperText Markup Language 5.0) and WebGL (Web Graphics Library) technology...

Owing to complex composition and viscoelasticity of asphalt concrete, the mechanism of ultrasonic propagation has been not explicit. The research examined the coupling mechanism between ultrasonic waves and asphalt concrete from the perspective of meso-structure based on finite element method. According to the composition, three 2D models were buil...

BIM (Building Information Modeling) has already been well known for its efforts in improving the high-efficiency of the AEC (Architecture, Engineering, and Construction) industry. Meanwhile, there has been a rising trend for the support of a web display developed by HTML 5 (HyperText Markup Language) and WebGL (Web Graphics Library) technology in B...

This paper investigates the multi-scale 3D display of the internal status of pavements based on building information modeling (BIM) technology. A 3D solid model of the pavement based on AutoCAD Civil 3D software was built to visualize the pavement internal quality status. The BIM based modeling software Revit was chosen as the development platform...