Fault Detection with Crosshole and Reflection Geo-Radar for Underground Mine Safety

Kulich, Jakob; Bleibinhaus, Florian

doi:10.3390/geosciences10110456

Cited by 7 publications

(4 citation statements)

References 15 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, it optimizes the performance of the generator by producing virtual samples to obtain real labels from the discriminator, that is, D(G(z)) = 1. Therefore, the optimization process of the generator's performance is to minimize the mathematical expectation of the logarithmic loss in Equation (3). It can be seen from Equations ( 2) and (3) that network training is a game between discriminator and generator.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

GAN-Based Inversion of Crosshole GPR Data to Characterize Subsurface Structures

et al. 2023

View full text Add to dashboard Cite

The crosshole ground-penetrating radar (GPR) technique is widely used to characterize subsurface structures, yet the interpretation of crosshole GPR data involves solving non-linear and ill-posed inverse problems. In this work, we developed a generative adversarial network (GAN)-based inversion framework to translate crosshole GPR images to their corresponding 2D defect reconstruction images automatically. This approach uses fully connected layers to extract global features from crosshole GPR images and employs a series of cascaded U-Net structures to produce high-resolution defect reconstruction results. The feasibility of the proposed framework was demonstrated on a synthetic crosshole GPR dataset created with the finite-difference time-domain (FDTD) method and real-world data from a field experiment. Our inversion network obtained recognition accuracy of 91.36%, structural similarity index measure (SSIM) of 0.93, and RAscore of 91.77 on the test dataset. Furthermore, comparisons with ray-based tomography and full-waveform inversion (FWI) suggest that the proposed method provides a good balance between inversion accuracy and efficiency and has the best generalization when inverting actual measured crosshole GPR data.

show abstract

Section: Methodsmentioning

confidence: 99%

“…As a fast and accurate non-destructive testing method, crosshole ground-penetrating radar (GPR) has been increasingly used in deep-foundation defect detection [1], engineering geology investigation [2,3], water-resource exploration, etc. [4][5][6].…”

Section: Introductionmentioning

confidence: 99%

GAN-Based Inversion of Crosshole GPR Data to Characterize Subsurface Structures

et al. 2023

View full text Add to dashboard Cite

show abstract

“…So, we do not consider using 5G technology in the monitoring and control of the underground mines because of the limitations mentioned above. Similarly, although Radar Sensor [50,51] has also been successfully used in the safety monitoring and location in the underground mines in recent years, its limitations are the same as 5G technology-that is, high-cost and non-universal.…”

Section: The Comparison Of Zigbee Wsn Technology and Other Technologiesmentioning

confidence: 99%

Engineering Project: The Method to Solve Practical Problems for the Monitoring and Control of Driver-Less Electric Transport Vehicles in the Underground Mines

Wang

et al. 2021

WEVJ

View full text Add to dashboard Cite

With the continuous development of Artificial Intelligence technology and Internet of Things engineering, more and more driver-less vehicles have been developed and put into industrial production. The birth of driver-less vehicles undoubtedly brings new vitality to a large amount of industries, particularly in transportation. For the mining industry, transportation is undoubtedly an extremely important link in the whole production process. If the driver-less vehicles can be applied to the underground mines, it can not only improve the production and transportation capacity of the whole mine but also can reduce the occurrence of many mine safety accidents. ZigBee WSN technology can play a greater role in the narrow environment such as underground mines according to the relevant literature; this concept paper, similar to an engineering project plan, mainly tries to integrate the ZigBee WSN technology and the communication-based train control (CBTC) system to explore the possibility of the driver-less vehicles to be used in the underground mines, which aims to solve practical engineering problems for the engineering projects. As the mining engineers, we put forward the concept of this integrated system in this concept paper, but we need to continue to work hard for the future of the underground mines. This concept paper serves as a guide to Tossing out a brick to get a jade gem, and it has a few implications for the development of underground mine transportation.

show abstract

“…The GPR is a geophysical method that can map soil and rock in a relatively rapid and reliable manner and can be used to detect series of features directly linked to the condition of infrastructure using a range of antennas that measure at different frequencies and depths. Kulich and Bleibinhaus [3] used GPR in combination with a cross-hole radar to successfully delineate the fault and karstification zones with higher water content due to their strong dielectric permittivity contrast compared to the surrounding geology, while Sokolov et al [4] used the GPR to prospect and evaluate massive ice in a frozen rock mass, thus obtaining a set of criteria for identifying massive ice according to GPR measurements. As the authors note, the developed criteria will allow the use of GPR for a detailed study of permafrost rock's structure to prevent the development of dangerous cryogenic processes in undisturbed and urban areas of the Arctic.…”

mentioning

confidence: 99%