Submit to Applied Sciences Review for Applied Sciences Propose a Special Issue

Journal Browser

► Journal Browser

Advances in Nondestructive Testing and Evaluation

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Applied Sciences (ISSN 2076-3417).

Deadline for manuscript submissions: closed (20 February 2024) | Viewed by 23280

Share This Special Issue

Special Issue Editors

Prof. Dr. Jinyi Lee

E-Mail Website
Guest Editor

Department of Electronic Engineering, Chosun University, Gwangju 61452, Korea
Interests: corrosion; crack; nondestructive testing; NDT; magnetization; Hall sensor, GMR sensor; magnetic field; eddy current; magnetic camera; steel manufacturing; express train; nuclear power generation; heat exchanger; aerospace; NDE; ultrasonic non destructive
Special Issues, Collections and Topics in MDPI journals

Dr. Azouaou Berkache

E-Mail
Guest Editor

IT-based Real-Time NDT Center, Chosun University, Gwangju 61452, Korea
Interests: nondestructive testing; nondestructive evaluation; electromagnetic; numerical simulation
Special Issues, Collections and Topics in MDPI journals

Dr. Minhhuy Le

E-Mail Website
Guest Editor

Electrical and Electronic Engineering, Phenikaa University, Hanoi 12116, Vietnam
Interests: nondestructive testing and evaluation; eddy current testing; artificial intelligence; ultra-wideband radar; smart sensing

Dr. Zheng Tong

E-Mail Website
Guest Editor

School of Transportation, Southeast University, Nanjing 211189, China
Interests: ground-penetrating radar and nondestructive testing; signal and image processing; deep learning; Dempster-Shafer theory and uncertainty reasoning
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Non-destructive testing and evaluation (NDT&E) is the leading technique for determining the appropriate quality and reliability of various materials, especially components, devices, and structures, by enabling the evaluation and localization of anomalies (manufacturing imperfections, defects, corrosion, deformation, discontinuities, external and internal cracks, etc.) during production and fabrication, and during products’ life cycles, without harming the original part. NDT&E technologies include ultrasonic testing (UT), magnetic particle testing (MT), magnetic flux leakage testing (MFLT), eddy current testing (ECT), radiation testing (RT), penetrant testing (PT) and visual testing (VT), along with a set of other testing techniques for industrial applications. Additionally, NDT&E technologies offer a high level of safety, sustainability and economic efficiency. On the other hand, they play an important role in today's manufacturing industry, primarily in Industry 4.0.

The purpose of this special issue is to shed light on recent advances in the field of non-destructive testing and evaluation, including novel and emerging approaches for non-destructive testing and evaluation, inverse problem evaluation, and pioneering applications for a vast array of industries and laboratories.

Owing to the requirement for technical breakthrough in the field of non-destructive testing and evaluation, numerous endeavors are being undertaken, including but not limited to:

(1) Materials characterization;

(2) Innovation application and methodologies in the field of NDT;

(3) Evaluation using inverse problem;

(4) Integration of test methods using conventional NDT&E methods;

(5) Ultra-precise sensor (sensitivity and resolution) development using advanced technology in electrical and electronic fields;

(6) Ultra-fast inspection (real-time NDT and high-speed flaw recognition);

(7) Automation of the inspection process (applying robot technology);

(8) Visualization of test results (2-D or 3-D visualization);

(9) Preservation and management of test results;

(10) Application of artificial intelligence.

Applied Sciences has scheduled a Special Issue titled "Advances in Non-destructive Testing and Evaluation" which will gather the results of a great number of researchers and engineers to address the ongoing challenges and technological advances in NDT&E.

For articles published in Applied Sciences (Impact Factor 2.679), the authors are required to support the financial charge associated with the open-access format. We believe that this Special Issue will be an excellent opportunity to contribute to the future development of the non-destructive testing and evaluation industry and laboratories.

We look forward to your involvement.

Prof. Dr. Jinyi Lee
Dr. Azouaou Berkache
Dr. Minhhuy Le
Dr. Zheng Tong
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

nondestructive testing
visible inspection
infrared radiation
X-ray and X-ray backscatter
electro-magnetic imaging
phase array UT
artificial intelligence
evaluation
reliability
probability of detection
ground-penetrating radar
deep learning
information fusion of multiple NDT&E methods
uncertainty on NDT&E data

Published Papers (12 papers)

Download All Papers

Research

16 pages, 4973 KiB

Open AccessArticle

Application of Classified Elastic Waves for AE Source Localization Based on Self-Organizing Map

by Katsuya Nakamura, Yoshikazu Kobayashi, Kenichi Oda and Satoshi Shigemura

Appl. Sci. 2023, 13(9), 5745; https://0-doi-org.brum.beds.ac.uk/10.3390/app13095745 - 06 May 2023

Viewed by 936

Abstract

Acoustic emission (AE) source localization has been used to visualize progress failures generated in a wide variety of materials. In the conventional approaches, AE source localization algorithms assume that the AE signal is propagated as a straight line. However, it is supposed that progress failures form heterogeneity of elastic wave velocity distributions. Hence, with the conventional source localization, it is expected that the localization accuracy is reduced in heterogeneous materials since diffraction and refraction waves are generated. Thus, if the straight propagation waves are classified, conventional source localizations are performed in the heterogeneous materials. The self-organizing map (SOM) is one of the unsupervised learning methods, and the SOM has potential to classify straight propagation waves for the source localizations. However, the application of classified AE signals in source localization is not popular. If classified AE signals are applied to the time difference of arrival (TDOA) method, which is the popular localization method, it is expected that number of visualized sources are decreased because the algorithm does not consider the selection of the propagated wave. Although ray tracing has potential to localize a larger number of sources than the TDOA method, it is expected that the localized sources are less accurate in comparison with results of the TDOA method. In this study, classified waves were applied to two of the source localizations, and model tests based on pencil-lead breaks (PLBs) generating artificial AE sources were conducted to validate the performance of the source localizations with classified waves. The results of the validation confirmed that the maximum error in the TDOA method is larger in comparison with ray tracing conducted with 20 mm intervals of source candidates. Moreover, ray tracing localizes the same number of sources as the number of PLB tests. Therefore, ray tracing is expected to more practically localize AE sources than the TDOA method if classified waves are applied. Full article

(This article belongs to the Special Issue Advances in Nondestructive Testing and Evaluation)

► Show Figures

Figure 1

25 pages, 8280 KiB

Open AccessArticle

Field Inspection of High-Density Polyethylene (HDPE) Storage Tanks Using Infrared Thermography and Ultrasonic Methods

by Amir Behravan, Thien Q. Tran, Yuhao Li, Mitchell Davis, Mohammad Shadab Shaikh, Matthew M. DeJong, Alan Hernandez and Alexander S. Brand

Appl. Sci. 2023, 13(3), 1396; https://0-doi-org.brum.beds.ac.uk/10.3390/app13031396 - 20 Jan 2023

Cited by 3 | Viewed by 2625

Abstract

High-density polyethylene (HDPE) is widely used for above-ground storage tanks (ASTs). However, there are currently no guidelines for the non-destructive testing (NDT) and evaluation (NDE) of HDPE ASTs. Moreover, the feasibility, limitations, and challenges of using NDT techniques for the field inspection of HDPE ASTs have not been well established. This study used both infrared thermography (IRT) and ultrasonic testing (UT) for the field inspection of HDPE ASTs. Highlighting the implementation challenges in the field, this study determined that: (1) ambient environmental parameters can affect IRT accuracy; (2) there is an ideal time during the day to perform IRT; (3) the heating source and infrared camera orientation can affect IRT accuracy; and (4) with proper measures taken, IRT is a promising method for flaw detection in HDPE ASTs. Additionally, UT can be used following IRT for detailed investigation to quantify the size and depth of defects. The manuscript concludes with a discussion of the limitations and best practices for the implementing of IRT and UT for HDPE AST inspections in the field. Full article

(This article belongs to the Special Issue Advances in Nondestructive Testing and Evaluation)

► Show Figures

Figure 1

22 pages, 6981 KiB

Open AccessArticle

Theoretical Model of Self-Magnetic Flux Leakage and Its Application in Estimating the Depth Direction of a Fatigue Crack

by Jinyi Lee, Dabin Wang and I Dewa Made Oka Dharmawan

Appl. Sci. 2023, 13(1), 533; https://0-doi-org.brum.beds.ac.uk/10.3390/app13010533 - 30 Dec 2022

Cited by 2 | Viewed by 1015

Abstract

In this study, theoretical models were proposed to explain the changes in self-magnetic flux density (SMFD) due to fatigue cracks in the presence and absence of external magnetic fields. Three theoretical models were proposed: rotation domain model (RDM), concentration domain model (CDM), and vertical domain model (VDM), considering the deformation and non-deformation possibilities. To prove the theoretical model, fatigue cracks with different depth angles were fabricated through fatigue testing and EDM processing on the CT specimens. In addition, tunnel magnetoresistance (TMR) sensors were used to evaluate the 3-axis distribution of SMFD. Comparing the simulation and experimental results, similar tendencies of the occurrence and depth angle of fatigue cracks and their effect on the distribution of SMFD were observed. According to the RDM, the distribution of SMFD occurs in the direction of the crack length (y-direction), while the CDM explains that the SMFD does not occur if the fatigue crack is in a direction perpendicular to the surface. In addition, the VDM shows that SMFDs occur in a direction perpendicular to the crack length (x-direction) and the specimen surface (z-direction). Interestingly, these trends agree with the experimental results, which confirms the validity of the theoretical model and thus can be used to estimate the depth direction of a fatigue crack. Full article

(This article belongs to the Special Issue Advances in Nondestructive Testing and Evaluation)

► Show Figures

Figure 1

20 pages, 5932 KiB

Open AccessArticle

Acoustic Emission and Deep Learning for the Classification of the Mechanical Behavior of AlSi10Mg AM-SLM Specimens

by Claudia Barile, Caterina Casavola, Giovanni Pappalettera, Vimalathithan Paramsamy Kannan and Dany Katamba Mpoyi

Appl. Sci. 2023, 13(1), 189; https://0-doi-org.brum.beds.ac.uk/10.3390/app13010189 - 23 Dec 2022

Cited by 3 | Viewed by 2147

Abstract

In this research paper, the acoustic emission technique and a deep learning framework based on two types of pre-trained CNN models (alexNet and squeezeNet) and a new model are proposed to characterize and classify the mechanical behavior of AlSi10Mg components. Specimens are built in a Selective Laser Melting machine with different bed orientations along X, Y, Z, and 45 degrees. Tensile tests are performed, and AE signals are recorded from these tests. To characterize the elastic and plastic deformation stages, a time-frequency domain analysis was performed using CWT-based spectrograms. Three different categories of damage classification strategies were implemented, and CNN models were trained for each strategy. CNN models including AlexNet, SqueezeNet, and the new model were used. Several training modes were performed to determine the CNN model that can accurately classify AE data. Understanding the minimum set of AE signals needed to train the CNN while having 100% accuracy and understanding the parameters affecting the accuracy of a CNN and the training time for the efficient classification of AE signals are the main objectives of this work. The results obtained demonstrated that the new simplified CNN model proposed can accurately classify the AE signals in a short time compared to AlexNet and SqueezeNet. Full article

(This article belongs to the Special Issue Advances in Nondestructive Testing and Evaluation)

► Show Figures

Figure 1

15 pages, 3107 KiB

Open AccessArticle

Investigating the Influence of Embedment Length on the Anchorage Force of Rock Bolts with Modified Pile Elements

by Jianhang Chen, Shiji Wang, Guoxin Sun, Han Zhang, Krzysztof Skrzypkowski, Krzysztof Zagórski and Anna Zagórska

Appl. Sci. 2023, 13(1), 52; https://0-doi-org.brum.beds.ac.uk/10.3390/app13010052 - 21 Dec 2022

Cited by 2 | Viewed by 2253

Abstract

The embedment length (EL) of full-grouting rock bolts is a core factor in rock bolt reinforcement. Therefore, understanding the influence of EL on the reinforcement performance of rock bolts benefits the rock reinforcement quality. To realise this purpose, this paper adopted the numerical modelling method. In this numerical modelling method, the structural elements of modified piles were used. The elastic debonding law was incorporated into the modified pile elements to model the debonding behaviour of the surface between rock bolts and grout. The results showed that the sliding of modified pile elements had a marginal influence on the reinforcement performance of rock bolts. Moreover, the EL has a paramount influence on the reinforcement performance of rock bolts. Before the rock bolts reached the largest anchorage force, there was a linear relation between the largest anchorage force and the EL. It was effective to use the linear regression analysis method to predict the critical EL of rock bolts. This finding was also applicable to fibre-reinforced polymer (FRP) rock bolts. Additionally, the rock bolt type had a paramount influence on the reinforcement performance of rock bolts. Before the rock bolts reached the largest anchorage force, metal rock bolts showed much larger initial stiffness than FRP rock bolts. Full article

(This article belongs to the Special Issue Advances in Nondestructive Testing and Evaluation)

► Show Figures

Figure 1

13 pages, 3562 KiB

Open AccessArticle

Feasibility of Application for the SHG Technology of Longitudinal Wave in Quantitatively Evaluating Carbonated Concrete

by Jinzhong Zhao, Jin Wu and Kaixin Chen

Appl. Sci. 2022, 12(24), 13009; https://0-doi-org.brum.beds.ac.uk/10.3390/app122413009 - 18 Dec 2022

Cited by 2 | Viewed by 1093

Abstract

The ultrasonic transmission detection method is used to investigate the applicability for the second-harmonic generation (SHG) technology of longitudinal wave to quantitatively assess carbonated concrete. The principal of this method is to use the piezoelectric lead zirconate titanate (PZT) patch to detect the second-harmonic of longitudinal waves during the concrete carbonation process and extract non-linear parameters from observed signals. Non-linear parameters of concretes with two water–cement ratios (CI

(w / c = 0.47)

, CII

(w / c = 0.53)

), two moisture contents (CI

0 %

, CI-W

100 %

), and three ultrasonic incident frequencies (50 kHz, 75 kHz, 100 kHz) were measured in this study. Results of the experiment demonstrate that non-linear ultrasonic parameters of longitudinal ultrasonic waves with high frequencies (75 kHz, 100 kHz) exhibit a better resolution regarding changes in concrete microstructure. Moisture (CI

0 %

, CI-W

100 %

) has little effect on the rate (CI: 62.73%, CI-W: 60.25, carbonation depth: 15 mm) for the change in relative non-linear parameters in the same concrete. The carbonation depth of concrete (CI

(w / c = 0.47)

, CI-W

(w / c = 0.47)

, CII

(w / c = 0.53)

) can be well reflected by the change in relative non-linear parameters. Furthermore, there exists a good fit between the relative non-linear parameters of longitudinal waves and the concrete carbonation process. The relative non-linear parameters of longitudinal waves demonstrate feasibility in the quantitative assessment of concrete carbonation. Full article

(This article belongs to the Special Issue Advances in Nondestructive Testing and Evaluation)

► Show Figures

Figure 1

18 pages, 10704 KiB

Open AccessFeature PaperArticle

Improved Acoustic Emission Tomography Algorithm Based on Lasso Regression

by Xin Qiao, Yoshikazu Kobayashi, Kenichi Oda and Katsuya Nakamura

Appl. Sci. 2022, 12(22), 11800; https://0-doi-org.brum.beds.ac.uk/10.3390/app122211800 - 20 Nov 2022

Cited by 1 | Viewed by 1343

Abstract

This study developed a novel acoustic emission (AE) tomography algorithm for non-destructive testing (NDT) based on Lasso regression (LASSO). The conventional AE tomography method takes considerable measurement data to obtain the elastic velocity distribution for structure evaluation. However, the new algorithm in which the LASSO algorithm is applied to AE tomography eliminates these deficiencies and reconstructs equivalent velocity distribution with fewer event data to describe the defected range. Three numerical simulation models were studied to reveal the capacity of the proposed method, and the functional performance was verified by three different types of classical concrete damage numerical simulation models and compared to that of the conventional SIRT algorithm in the experiment. Finally, this study demonstrates that the LASSO algorithm can be applied in AE tomography, and the shadow parts are eliminated in resultant elastic velocity distributions with fewer measurement paths. Full article

(This article belongs to the Special Issue Advances in Nondestructive Testing and Evaluation)

► Show Figures

Figure 1

17 pages, 10485 KiB

Open AccessArticle

Defect Shape Classification Using Transfer Learning in Deep Convolutional Neural Network on Magneto-Optical Nondestructive Inspection

by I Dewa Made Oka Dharmawan, Jinyi Lee and Sunbo Sim

Appl. Sci. 2022, 12(15), 7613; https://0-doi-org.brum.beds.ac.uk/10.3390/app12157613 - 28 Jul 2022

Cited by 2 | Viewed by 2180

Abstract

To implement a magneto-optic (MO) nondestructive inspection (MONDI) system for robot-based nondestructive inspections, quantitative evaluations of the presence, locations, shapes, and sizes of defects are required. This capability is essential for training autonomous nondestructive testing (NDT) devices to track material defects and evaluate their severity. This study aimed to support robotic assessment using the MONDI system by providing a deep learning algorithm to classify defect shapes from MO images. A dataset from 11 specimens with 72 magnetizer directions and 6 current variations was examined. A total of 4752 phenomena were captured using an MO sensor with a 0.6 mT magnetic field saturation and a 2 MP CMOS camera as the imager. A transfer learning method for a deep convolutional neural network (CNN) was adapted to classify defect shapes using five pretrained architectures. A multiclassifier technique using an ensemble and majority voting model was also trained to provide predictions for comparison. The ensemble model achieves the highest testing accuracy of 98.21% with an area under the curve (AUC) of 99.08% and a weighted F1 score of 0.982. The defect extraction dataset also indicates auspicious results by increasing the training time by up to 21%, which is beneficial for actual industrial inspections when considering fast and complex engineering systems. Full article

(This article belongs to the Special Issue Advances in Nondestructive Testing and Evaluation)

► Show Figures

Figure 1

16 pages, 6351 KiB

Open AccessArticle

Distribution of Magnetic Flux Density under Stress and Its Application in Nondestructive Testing

by Azouaou Berkache, Jinyi Lee, Dabin Wang and Sunbo Sim

Appl. Sci. 2022, 12(15), 7612; https://0-doi-org.brum.beds.ac.uk/10.3390/app12157612 - 28 Jul 2022

Cited by 4 | Viewed by 1340

Abstract

Carbon steels are commonly used in railroad, shipment, building, and bridge construction. They provide excellent ductility and toughness when exposed to external stresses. They are able to resist stresses and strains effectively, and guarantee safe operation of the devices through nondestructive testing (NDT). The magnetic metal memory (MMM) can be used as an NDT method to measure the residual stress. The ability of carbon steel to produce a magnetic memory effect under stress is explored here, and enables the magnetic flux density to be analyzed. The relationship between stress and magnetic flux density has not been fully presented until now. The purpose of this paper is to assess the relationship between stress distribution and the magnetic flux density measured by the experiment. For this, an experimental method for examining a carbon steel plate (SA 106), based on the four-point loading test, was used. The effect of stresses resulting from the applied loads on the response of the experimented SA 106 specimen was examined. A three directional tunnel magnetoresistance (TMR) measurement system was used to collect the triaxial magnetic flux density distribution in the SA 106 specimen. In addition, finite element method (FEM) analyses were performed, and provided information on the direction and distribution of the stress over the studied SA 106 specimen. Indeed, a correlation was derived by comparing the stress analysis by FEM and the measured triaxial magnetic flux density. Full article

(This article belongs to the Special Issue Advances in Nondestructive Testing and Evaluation)

► Show Figures

Figure 1

11 pages, 6948 KiB

Open AccessArticle

Simulation Dataset Preparation and Hybrid Training for Deep Learning in Defect Detection Using Digital Shearography

by Weixian Li, Dandan Wang and Sijin Wu

Appl. Sci. 2022, 12(14), 6931; https://0-doi-org.brum.beds.ac.uk/10.3390/app12146931 - 08 Jul 2022

Cited by 3 | Viewed by 1474

Abstract

Since real experimental shearography images are usually few, the application of deep learning for defect detection in digital shearography is limited. A simulation dataset preparation method of shearography images is proposed in this paper. Firstly, deformation distributions are estimated by finite element analysis (FEA); secondly, phase maps are calculated according to the optical shearography system; finally, simulated shearography images are obtained after 2π modulus and gray transform. Various settings in the parameters of object, defect, load and shearing in those three steps could prepare a diverse simulation dataset for deep learning. Together with the real experimental images taken from a shearography setup, hybrid trainings of deep learning for defect detection are performed and discussed. The results show that a simulation dataset, generated without any real defective specimen, shearography system or manual experiment, can greatly improve the generalization of a deep learning network when the number of experimental training images is small. Full article

(This article belongs to the Special Issue Advances in Nondestructive Testing and Evaluation)

► Show Figures

Figure 1

10 pages, 2931 KiB

Open AccessArticle

Reliability Assessment of PAUT Technique in Lieu of RT for Tube Welds in Thermal Power Plant Facilities

by Yu Min Choi, Dongchan Kang, Young Lae Kim, Sungjong Cho, Taesung Park and Ik Keun Park

Appl. Sci. 2022, 12(12), 5867; https://0-doi-org.brum.beds.ac.uk/10.3390/app12125867 - 09 Jun 2022

Cited by 4 | Viewed by 2037

Abstract

In this study, a reliability evaluation of the phased array ultrasonic testing (PAUT) method was performed to examine the applicability of the method for tube weld specimens with flaws having the same specifications as the tubes in the boilers of thermal power plant facilities. To this end, test specimens were fabricated by inserting flaws into tube welds with identical materials and specifications to those used in the thermal power plant. PAUT data acquisition was obtained using a round robin test (RRT) on the fabricated specimen, and the data were compared with the results of radiographic testing (RT) for a comparative evaluation of the flaw detection performance. In addition, for quantitative reliability analysis, the flaw detection performance (probability of detection; POD) and the error in the sizing accuracy (root-mean-square error; RMSE) were calculated with different materials of the specimens (carbon steel, stainless steel, dissimilar metal) and flaw types (volumetric, planar). In the analysis results, for high-risk planar defects, the PAUT technique exhibited superior flaw detection performance to the RT technique. A POD analysis of the PAUT technique indicated that flaws of 6.9 mm length were detected at 80% probability for total tube specimens. Furthermore, a reliability analysis was performed for test specimens of different materials and flaw types, and the results were derived. Through the findings of this study, the applicable range of the PAUT technique was examined, and a technical basis for PAUT in lieu of RT was established. Full article

(This article belongs to the Special Issue Advances in Nondestructive Testing and Evaluation)

► Show Figures

Figure 1

23 pages, 23884 KiB

Open AccessArticle

Pavement Distress Detection Using Three-Dimension Ground Penetrating Radar and Deep Learning

by Jiangang Yang, Kaiguo Ruan, Jie Gao, Shenggang Yang and Lichao Zhang

Appl. Sci. 2022, 12(11), 5738; https://0-doi-org.brum.beds.ac.uk/10.3390/app12115738 - 05 Jun 2022

Cited by 11 | Viewed by 2076

Abstract

Three-dimensional ground penetrating radar (3D GPR) is a non-destructive examination technology for pavement distress detection, for which its horizontal plane images provide a unique perspective for the task. However, a 3D GPR collects thousands of horizontal plane images per kilometer of the investigated pavement. The existing detection methods using GPR images are time-consuming and risky for subjective judgment. To solve the problem, this study used deep learning methods and 3D GPR horizontal plane images to detect pavement structural distress, including cracks, repairs, voids, poor interlayer bonding, and mixture segregation. In this study, two deep learning methods, called CP-YOLOX and SViT, were used to achieve the aim. A dataset for anomalous waveform localization (3688 images) was first created by pre-processing 3D-GPR horizontal plane images. A CP-YOLOX model was then trained to localize anomalous waveforms. Five SViT models with different numbers of encoders were adopted to perform the classification of anomalous waveforms using the localization results from the CP-YOLOX model. The numerical experiment results showed that 3D GPR horizontal plane images have the potential to be an assistant for pavement structural distress detection. The CP-YOLOX model achieved 87.71% precision, 80.64% mAP, and 33.57 sheets/s detection speed in locating anomalous waveforms. The optimal SViT achieved 63.63%, 68.12%, and 75.57% classification accuracies for the 5-category, 4-category, and 3-category datasets, respectively. The proposed models outperformed other deep learning methods on distress detection using 3D GPR horizontal plane images. In the future, more radar images should be collected to improve the accuracy of SViT. Full article

(This article belongs to the Special Issue Advances in Nondestructive Testing and Evaluation)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Advances in Nondestructive Testing and Evaluation

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (12 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI