Ground Penetrating Radar Fourier Pre-processing for Deep Learning Tunnel Defects’ Automated Classification

Marasco, Giulia; Rosso, Marco Martino; Aiello, Salvatore; Aloisio, Angelo; Cirrincione, Giansalvo; Chiaia, Bernardino; Marano, Giuseppe Carlo

doi:10.1007/978-3-031-08223-8_14

Cited by 17 publications

(11 citation statements)

References 31 publications

(36 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In GPR tunnel lining assessment, Rosso et al (2022) proposed to use the GPR data-based deep learning model to classify the internal damage degree of tunnel lining, and they find that compared with the ResNet-50, the more advanced vision transformer model showing an overwhelming advantage in classification accuracy. Marasco et al (2022) studied the Fourier transform GPR pre-processing for data compression to improve the efficiency of deep learning model.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A deep learning framework based on improved self‐supervised learning for ground‐penetrating radar tunnel lining inspection

Huang

Yang

Zhou

et al. 2023

Computer aided Civil Eng

View full text Add to dashboard Cite

It is not practical to obtain a large number of labeled data to train a supervised learning network in tunnel lining nondestructive testing with ground‐penetrating radar (GPR). To decrease the dependence of supervised learning on the number of labeled data, an improved self‐supervised learning algorithm—self‐attention dense contrastive learning (SA‐DenseCL)—is proposed and incorporated with a mask region‐convolution neural network (Mask R‐CNN), which is trained by unlabeled and labeled GPR data. The proposed SA‐DenseCL adds a self‐attention‐based relevant projection head to the DenseCL architecture of self‐supervised learning, capturing the spatially continuing information between adjacent GPR traces. In the workflow, some unlabeled GPR images are used to pre‐train the SA‐DenseCL network for feature extraction and obtaining the backbone weights, which is superior to the conventional pre‐training methods of supervised learning pre‐trained by ImageNet images. The weights of the pre‐trained backbone are then used to initialize the Mask R‐CNN through transfer learning. Subsequently, a limited number of labeled GPR images are used to fine‐tune the Mask R‐CNN for automatically identifying the locations of the reinforcement bars and voids and estimating the secondary lining thickness. The experimental results show that the average precision reaches 96.70%, 81.04%, and 94.67% in identifying reinforcement bar locations, detecting void defects, and estimating secondary lining thickness, respectively, which outperform the conventional methods that use ImageNet‐based supervised learning or GPR image‐based DenseCL for initializing the Mask R‐CNN backbone weights. It is observed that the improved self‐supervised learning‐based framework can improve the detection and estimation accuracy in GPR tunnel lining inspection.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Marasco et al. (2022) studied the Fourier transform GPR pre‐processing for data compression to improve the efficiency of deep learning model.…”

Section: Introductionmentioning

confidence: 99%

A deep learning framework based on improved self‐supervised learning for ground‐penetrating radar tunnel lining inspection

Huang

Yang

Zhou

et al. 2023

Computer aided Civil Eng

View full text Add to dashboard Cite

show abstract

“…Thus, in Du et al (2022), a speed control framework on rough pavements based on deep reinforcement learning is developed; in Rosso et al (2023), artificial intelligence is used for the automatic detection of defects in tunnels, or in Chen et al (2022), an automatic rock mass condition assessment during tunnel excavation is developed. Other applications of artificial intelligence focused on tunnel construction are structural defect classification (Marasco et al, 2022), tunnel localization (Jongbae Kim, 2020), tunnel road scene recognition (Zheng et al, 2020), lining crack evaluation (Dang et al, 2022), or health monitoring of buildings (Oh et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

“…(2022), an automatic rock mass condition assessment during tunnel excavation is developed. Other applications of artificial intelligence focused on tunnel construction are structural defect classification (Marasco et al., 2022), tunnel localization (Jongbae Kim, 2020), tunnel road scene recognition (Zheng et al., 2020), lining crack evaluation (Dang et al., 2022), or health monitoring of buildings (Oh et al., 2017).…”

Section: Introductionmentioning

confidence: 99%

Automation of haulers for debris removal in tunnel construction

Naranjo

Valle

Cruz

et al. 2023

Computer aided Civil Eng

View full text Add to dashboard Cite

Tunnel construction is one of the areas of civil engineering where automation systems can increase both safety and productivity. That is why, to promote a continuous improvement and optimization of construction processes, the implementation of intelligent transport systems and, specifically, autonomous vehicles has been proposed as a catalyst for public works construction activity, including tunnels, reducing personnel, and operation costs, as well as improving safety. Under this scope, this paper presents the development of the automation system for a 25‐ton hauler truck, focusing on the task of removing debris from public works, including tunnels. This automation system has been designed, developed, and tested under real conditions in the facilities of two companies dedicated to civil engineering works, including vehicle guidance with and without gobal positioning system, obstacle detection, and tele‐operation for load/unload tasks. The main novelty of the system is the capacity of easy integration into the production system of the works, with a capacity to switch between manual, tele‐operation, or autonomous driving modes, and with specific sensors and control systems for combining indoor and outdoor navigation. The presented work includes the description of the automation of the vehicle, the general architecture, the environment perception, and the tele‐operation capacity, including indoor navigation and obstacle detection algorithms. The proposed system has been implemented and tested in real conditions, demonstrating the performance of the system and the benefit of the automation for this application.

show abstract

“…The track was scanned with a camera and the images were fed into a deep neural network, trained to classify different components such as fasteners, ties, etc., and identify missing fasteners. A similar inspection approach based on Convolutional Neural Networks (CNN) was used by Marasco et al [ 22 ] to inspect and classify tunnel defects. In this study the Fourier Transform of the tunnel images were fed into the CNN to identify damages and cracks in the tunnel lining.…”

Section: Introductionmentioning

confidence: 99%

Vibration-Based Approach to Measure Rail Stress: Modeling and First Field Test

Belding

Enshaeian

Rizzo

2022

Sensors

View full text Add to dashboard Cite

This paper describes a non-invasive inspection technique for the estimation of longitudinal stress in continuous welded rails (CWR) to infer the rail neutral temperature (RNT), i.e., the temperature at which the net longitudinal force in the rail is zero. The technique is based on the use of finite element method (FEM), vibration measurements, and machine learning (ML). FEM is used to model the relationship between the boundary conditions and the longitudinal stress of any given CWR to the vibration characteristics (mode shapes and frequencies) of the rail. The results of the numerical analysis are used to train a ML algorithm that is then tested using field data obtained by an array of accelerometers polled on the track of interest. In the study presented in this article, the proposed technique was proven in the field during an experimental campaign conducted in Colorado. A commercial FEM software was used to model the rail track as a short rail segment repeated indefinitely and under varying boundary conditions and stress. Three datasets were prepared and fed to ML models developed using hyperparameter search optimization techniques and k-fold cross validation to infer the stress or the RNT. The frequencies of vibration were extracted from the time waveforms obtained from two accelerometers temporarily attached to the rail. The results of the experiments demonstrated that the success of the technique is dependent on the accuracy of the model and the ability to properly identify the modeshapes. The results also proved that the ML was also able to predict successfully the neutral temperature of the tested rail by using only a limited number of experimental data for the training.

show abstract

Ground Penetrating Radar Fourier Pre-processing for Deep Learning Tunnel Defects’ Automated Classification

Cited by 17 publications

References 31 publications

A deep learning framework based on improved self‐supervised learning for ground‐penetrating radar tunnel lining inspection

A deep learning framework based on improved self‐supervised learning for ground‐penetrating radar tunnel lining inspection

Automation of haulers for debris removal in tunnel construction

Vibration-Based Approach to Measure Rail Stress: Modeling and First Field Test

Contact Info

Product

Resources

About