Search

The crack detection of concrete bridges is an important link in the safety evaluation of bridge structures, and the rapid and accurate identification and detection of bridge cracks is a prerequisite for ensuring the safety and long-term stable use of bridges. To solve the incomplete crack detection and segmentation caused by the complex background and small proportion in the actual bridge crack images, this paper proposes a coarse–fine combined bridge crack detection method of "double detection + single segmentation" based on deep learning. To validate the effect and practicality of fine crack detection, images of old civil bridges and viaduct bridges against a complex background and images of a bridge crack against a simple background are used as datasets. You Only Look Once V5(x) (YOLOV5(x)) was preferred as the object detection network model (ODNM) to perform initial and fine detection of bridge cracks, respectively. Using U-Net as the optimal semantic segmentation network model (SSNM), the crack detection results are accurately segmented for fine crack detection. The test results showed that the initial crack detection using YOLOV5(x) was more comprehensive and preserved the original shape of bridge cracks. Second, based on the initial detection, YOLOV5(x) was adopted for fine crack detection, which can determine the location and shape of cracks more carefully and accurately. Finally, the U-Net model was used to segment the accurately detected cracks and achieved a maximum accuracy (AC) value of 98.37%. The experiment verifies the effectiveness and accuracy of this method, which not only provides a faster and more accurate method for fine detection of bridge cracks but also provides technical support for future automated detection and preventive maintenance of bridge structures and has practical value for bridge crack detection engineering. [ABSTRACT FROM AUTHOR]

The radio imaging method (RIM) can be used in underground mines to identify geologically hazardous areas; however, it does not yield accurate results. To address this issue, a high-frequency (1–8 MHz) RIM is proposed here for the fine detection of geological anomalies in coal seams, and its feasibility is evaluated. A reliable forward model is established based on the propagation characteristics of electromagnetic waves in lossy media and the functional relation between the electrical parameters of coal and electromagnetic wave frequency. Numerical simulations were performed using a frame antenna at high frequencies; the field strengths of electromagnetic waves in coal seams with and without geological abnormal areas were compared. The difference diagram demonstrates the field strength attenuation “shadow area” formed by the geological abnormal area. The attenuation coefficient, wavelength, and far-field radiation characteristics of the frame antenna were used to discuss if the detected geologically hazardous location is accurate. The feasibility of high-frequency detection is further supported by the electromagnetic wave signal strength in the receiving tunnel.

The crack detection of concrete bridges is an important link in the safety evaluation of bridge structures, and the rapid and accurate identification and detection of bridge cracks is a prerequisite for ensuring the safety and long-term stable use of bridges. To solve the incomplete crack detection and segmentation caused by the complex background and small proportion in the actual bridge crack images, this paper proposes a coarse–fine combined bridge crack detection method of “double detection + single segmentation” based on deep learning. To validate the effect and practicality of fine crack detection, images of old civil bridges and viaduct bridges against a complex background and images of a bridge crack against a simple background are used as datasets. You Only Look Once V5(x) (YOLOV5(x)) was preferred as the object detection network model (ODNM) to perform initial and fine detection of bridge cracks, respectively. Using U-Net as the optimal semantic segmentation network model (SSNM), the crack detection results are accurately segmented for fine crack detection. The test results showed that the initial crack detection using YOLOV5(x) was more comprehensive and preserved the original shape of bridge cracks. Second, based on the initial detection, YOLOV5(x) was adopted for fine crack detection, which can determine the location and shape of cracks more carefully and accurately. Finally, the U-Net model was used to segment the accurately detected cracks and achieved a maximum accuracy (AC) value of 98.37%. The experiment verifies the effectiveness and accuracy of this method, which not only provides a faster and more accurate method for fine detection of bridge cracks but also provides technical support for future automated detection and preventive maintenance of bridge structures and has practical value for bridge crack detection engineering.

Copyright of World Nuclear Geoscience is the property of World Nuclear Geoscience Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In view of the current technical difficulties in the detection of unfavorable geological bodies in karst areas, this paper starts with the fine detection of a borehole wall, near-field of the borehole wall rock and far-field of the borehole wall rock, deeply excavates the correlation characteristics between multi-source borehole data, and proposes detection technology for unfavorable geological bodies in karst development areas based on multi-source borehole data. This is used to establish a multi-source data depth mining model. The correlation characteristics between multi-source data are clarified. The borehole multi-source heterogeneous detection technology is proposed to realize the organic fusion between the detection data of different scales, and effectively estimate the extension range of structural planes and cavities. The joint interpretation method of multi-source drilling data can effectively realize the three-dimensional visualization of unfavorable geological bodies in karst development areas. Through a case analysis, it is shown that this technology is a new and effective exploration method in the engineering geological exploration of karst development areas, and can provide more abundant and reliable exploration data for the fine exploration of geological bodies in the exploration area. [ABSTRACT FROM AUTHOR]

In view of the current technical difficulties in the detection of unfavorable geological bodies in karst areas, this paper starts with the fine detection of a borehole wall, near-field of the borehole wall rock and far-field of the borehole wall rock, deeply excavates the correlation characteristics between multi-source borehole data, and proposes detection technology for unfavorable geological bodies in karst development areas based on multi-source borehole data. This is used to establish a multi-source data depth mining model. The correlation characteristics between multi-source data are clarified. The borehole multi-source heterogeneous detection technology is proposed to realize the organic fusion between the detection data of different scales, and effectively estimate the extension range of structural planes and cavities. The joint interpretation method of multi-source drilling data can effectively realize the three-dimensional visualization of unfavorable geological bodies in karst development areas. Through a case analysis, it is shown that this technology is a new and effective exploration method in the engineering geological exploration of karst development areas, and can provide more abundant and reliable exploration data for the fine exploration of geological bodies in the exploration area.

Fine detection for the deformation failure of overburden strata caused by underground mining may provide reliable guidance for safety,high efficient and green coal mining.Firstly,the principle of overburden detection based on time lapse high density resistivity method was investigated.Then 3D geologic-geophysical models of overburden strata before and after mining were constructed,and the corresponding numerical simulation was carried out by using these models.It is demonstrated that deformation failure of overburden strata is hourglass-like in the resistivity change rate profile and orifice is the separatrix between the fractured zone and the bending zone.Furthermore,field tests were carried out,results show that the surface subsidence caused positive anomaly and precipitation caused negative anomaly in the resistivity change rate profile.Based on the hourglass-like anomaly morphology and key stratum layer,the height of fractured zone was determined to be 98 m.Finally,the results from time lapse detection were verified by drilling results.

Copyright of Coal Science & Technology (0253-2336) is the property of Coal Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Highlights • The electric characteristics of coal samples were tested in the laboratory. • Fine division was performed on outburst danger areas. • Electrical characteristics of coal samples obtained in the laboratory correspond well with the site detection. Abstract In this study, with No. II 1051 working face of Zhuxianzhuang Coal Mine taken as the research object, the electric characteristics of coal samples were tested in the laboratory, and the resistivity imaging was carried out on the working surface via direct current (DC) prospecting instrument on site. Then, fine division was performed on outburst danger areas through gas geological analysis. Finally, mining verification and analysis were conducted. The results suggest that the variation laws of electrical characteristics of samples obtained in the laboratory test correspond well to those gained through site detection. Resistance does not distribute homogeneously in the working face, demonstrating regional significant high and low resistance, which is jointly induced by gas, stress, structure and water. Based on the aforesaid analyses, five outburst areas are determined, including high- and low-resistance regions and the mixed zone. The analysis results of gas occurrence regularity agree with the on-site situation, proving that the result of DC prospecting can reflect the distribution of outburst danger areas. The finding is of great importance for realizing fine detection of gas outburst. [ABSTRACT FROM AUTHOR]

There are many kinds of defects in pipes, which are difficult to detect with a low degree of automation. In this work, a novel omnidirectional vision inspection system for detection of the morphology defects is presented. An active stereo omnidirectional vision sensor is designed to obtain the texture and depth information of the inner wall of the pipeline in real time. The camera motion is estimated and the space location information of the laser points are calculated accordingly. Then, the faster region proposal convolutional neural network (Faster R‐CNN) is applied to train a detection network on their image database of pipe defects. Experimental results demonstrate that system can measure and reconstruct the 3D space of pipe with high quality and the retrained Faster R‐CNN achieves fine detection results in terms of both speed and accuracy. [ABSTRACT FROM AUTHOR]

Considering the effects of primary user traffic, timing misalignment and multiple arrival and departure issues in a sensing period should be addressed for spectrum sensing in future overlay cognitive radio (CR) networks, such as femtocell networks. To achieve this goal, division of the whole sensing duration into multiple windows is proposed. For each window, a two‐step detection scheme, i.e. coarse and fine detection, is proposed to improve the performance of the conventional energy detector (ED) in the overlay CR scenario. [ABSTRACT FROM AUTHOR]