Research on Water Seepage Detection Technology of Tunnel Asphalt Pavement Based on Deep Learning and Digital Image Processing

In order to improve the traffic safety of the tunnel pavement and reduce the impact of water seepage on the pavement structure, a convolutional neural network (CNN) model is established based on image detection technology to realize the identification, classification and statistics of pavement seepage. First, compared with the MobileNet network model, the deep learning model EfficientNet network model was built, and the accuracy of the two models was analyzed for pavement seepage recognition. The F1 Score was introduced to evaluate the accuracy and comprehensive performance of the two models for different types of seepage characteristics. Then the three gray processing methods, six threshold segmentation methods, as well as three filtering methods were compared to extract water seepage characteristics of digital image. Finally, based on the processed image, a calculation method of water seepage area was proposed to identify the actual asphalt pavement water seepage. The result shows that the recognition accuracy of the EfficientNet network model in the training set and the validation set are 99.85% and 97.53%, respectively, and the prediction accuracy is 98.00%. The accuracy of pavement water seepage recognition and prediction is better than the MobileNet network model. Using the cvtColor function for gray processing, using THRESH_BINARY for threshold segmentation, and using a combination of median filtering and morphological opening operations for image noise reduction can effectively extract water seepage characteristics. The water seepage area calculated by the proposed method has a small difference with the actual water seepage area, and the effect is agreeable.

Evaluation of Water seepage Along Proposed Baghdad Metro Tunnel Across Tigris River

Water seepage can cause serious problems in geotechnical engineering especially for construction under the water level. Baghdad metro tunnel is one of the leading vital projects to solve the major problem of crowding roadways in a highly population increase city like Baghdad. In this study, the seepage rate that will flow toward different selected points along the tunnel section across Tigris River was calculated during the excavation process, with the consideration of three different water levels of River at maximum, moderate, and minimum water depths. A three-dimensional model of the study has been modeled using the finite element software (PLAXIS 3D V20). The water seepage was observed for six different locations on each route of the tunnel. The study showed that the change of water depth in the river has no significant effect on the seepage – time curve shape. However, increasing the water level in River from minimum to maximum leads to increase the seepage rate about 15%.

Study on Stability of Tunnel Surrounding Rock and Precipitation Disaster Mitigation in Flowing Sand Body

Flowing sand is a special surrounding rock encountered by tunnel construction. Due to the looseness and low viscosity of the flowing sand, after excavation, the sand body is easy to flow along the open surface. In addition, the water seepage also causes tunnel instability. Considering the characteristics of water seepage, how to improve the stability of flowing sand bodies and prevent the instability of surrounding rocks has become a difficult problem. In this paper, a parametric experiment on the surrounding rock taken from the project site was carried out, and then, a numerical simulation of the flowing sand body was conducted to study the precipitation construction method and stability of the flowing sand body. Other than that, the tunnel face vacuum dewatering, vertical vacuum dewatering at the top of the tunnel, and the vacuum dewatering technology of the gravity well in poor geological section were systematically analyzed in our research. A radial vacuum enclosed precipitation process for the face of the tunnel was proposed, which effectively solved the problem concerning continuous seepage of water in the front. Through numerical simulation and field experiments, the basis for determining the precipitation parameters of the tunnel face was obtained, while aiming at the top position of the tunnel, a vertical vacuum negative pressure precipitation method of intercepting the top seepage water and the water supply behind the top of the tunnel was proposed. For the bottom of the tunnel, setting gravity wells on the side walls for the purpose of preventing seepage at the bottom was put forward. The application of these methods in the project ensured the safety of construction and improved the construction schedule. After the completion of the dewatering construction, the method of inserting plywood into the small pipe was adopted to avoid the collapse of the dry sand. Then, to solve the problem of borehole collapse in flowing sand bodies, pipe feeding was introduced, thus further enhancing the precipitation effect. Furthermore, in view of the problem that the dewatering hole in the flowing sand body is easy to collapse, resulting in the failure of 60% of the dewatering hole and the sand body is extracted from the dewatering pipe, causing the risk of the cavity at the top of the tunnel, a method of pipe following is presented to avoid the damage of geotextile caused by directly inserting the dewatering pipe and further improve the dewatering effect. All the above processes together form an omnidirectional three-dimensional negative pressure precipitation method that considers the special sand body flow and water seepage of unfavorable geology and that has been proved to enhance the stability of surrounding rock in practice.

Hydrochemical analysis and identification of open-pit mine water sources: a case study from the Dagushan iron mine in Northeast China

The identification of open-pit mine water sources is of great significance in preventing water disasters. Combined with hydrochemistry and multivariate statistical analysis, this paper systematically analyzed the hydraulic connections between aquifers and the complex seepage water sources in the pit and roadway of Dagushan iron mine through qualitative analysis and quantitative calculation. According to the hydrochemical characteristics of the study area, the causes of seepage water at different positions in the mining area were reasonably explained. The results show that there is a possible hydraulic connection or similar source of water body between the bedrock fissure aquifer and the eluvium pore aquifer. The water seepage of 2# roadway mainly comes from bedrock fissure aquifer in the north of mining area. The reason for serious water seepage in the 3# roadway and the western side of the pit is that the fault connects the shallow alluvial pore aquifer and bedrock fissure aquifer. The source of water on the southern side pit comes from the river and groundwater on the southern side of the mine. The results presented here provide significant guidance for the management of mine water seepage problems.

Eksplorasi dan analisis kondisi perkerasan jalan pada jembatan rangka baja Soekarno-Hatta Malang pada bulan Maret 2015 menggunakan metode ground penetrating radar (GPR)

This research that purpose to explore and analyz the structure condition of pavement on the Soekarno-Hatta’s Malang truss bridge by using GPR method. GPR is used to knowing type of material objects based on dielectric constant of every materials, and to showing deformation, cracking, release structure, and water seepage. Data collected by observation techniques and retrieval of data sanples at 101 point of the track. Analysis starts from the stage of processing by using Ms.Excel, notepad, paint, software GeoScan32, and interpreted using software Surfer 9.0. The result is showing that the road pavement structure consists of a flexible pavement asphalt and rigid pavement concrete by identified the type of material is dry asphalt, wet asphalt, dry concrete, wet concrete, and air on surface. Deformation occurred in all of track pavement and there are a few sample points are experienced track surface defect such as cracks and release the structure. The most damage with average value 1.67and 1.69 that occur on the second and third of track, start from track 34-67 and 68-100. The postiton is located in point 33-66 m dan 67-99 m from Surabaya (north of bridge). Mapping result of cracking and release structure showing that 90 percent of pavement on Soekarno-Hatta’s bridge are damage. Water seepage that occur when the water breaking through the subsurface layers (asphalt) until concrete layer in base ground by content wet materal. Data distribution of pavement area that most occur water seepage on track 35-67 it’s on point 33-66 m. Penelitian ini bertujuan untuk mengeksplorasi dan menganalisis kondsi struktur lapisan perkerasan jalan pada jembatan rangka baja Soekarno-Hatta Malang dengan metode Ground Penetratig Radar (GPR). GPR digunakan untuk mengetahui jenis material objek berdasarkan konstanta dielektrik yang dimiliki setiap material, serta untuk melihat adanya defomasi, retak, pelepasan struktur, serta rembesan air. Pengumpulan data dilakukan dengan menggunakan teknik observasi lapangan dan pengambilan data sampel pada 101 titik lintasan di analisis dengan teknik deskriptif kuantitaif menggunakan Ms.Excel, notepad, paint, software GeoScan32, dan di interpretasikan dalam software Surfer 9.0. Hasil penelitian menunjukkan bahwa struktur perkerasan jalan terdiri dari perkerasan lentur aspal dan perkerasan kaku beton yang diketahui berupa lantai kendaraan dengan jenis material pada perkerasan yang dapat teridentifikasi adalah aspal kering, aspal basah, beton kering, beton basah,dan adanya udara dipemukaan. Deformasi terjadi pada semua lintasan dan di beberapa titik lintasan teridentifikasi mengalami retak dan pelepasan struktur. Kerusakan terbanyak dengan nilai rata-rata 1,67 dan 1,69 diketahui terjadi pada bagian yang kedua dan ketiga, yaitu dimulai pada lintasan ke 34-67 dan 68-100. Posisi terletak pada bentang ke 33-66 meter dan 67-99 meter dari arah Surabaya (utara jembatan). Hasil pemetaan retak dan pelepasan lapisan menunjukkan 90 persen dari perkerasan jalan pada Jembatan Soekaro-Hatta telah mengalami kerusakan. Rembesan terjadi ketika air menerobos lapisan permukaan (aspal) bagian bawah hingga menembus lapisan beton di dasar permukaan dengan indikator konten material basah. Data persebaran daerah perkerasan jalan yang banyak mengalami rembesan air terjadi pada lintasan 35-67 yaitu pada posisi bentang ke 33-66 meter.

RISK PREDICTION AND DIAGNOSIS OF WATER SEEPAGE IN OPERATIONAL SHIELD TUNNELS BASED ON RANDOM FOREST

Water seepage (WS) is a paramount defect during tunnel operation and directly affects the operational safety of tunnels. Effectively predicting and diagnosing WS are problems that urgently need to be solved. This paper presents a standard and an evaluation index system for WS grades and constructs a sample dataset from monitoring recoreds for demonstration purposes. First, we use bootstrap resampling to build a random forest (RF) seepage risk prediction model. Second, the optimal branch and parameters are selected by the 5-fold cross-validation method to establish the RF prediction training model. Additionally, to illustrate the effectiveness of the method, the operational stage of Wuhan Metro Line 3 in China is taken as a case study. The results conclude that the segment spalling area, crack width, and loss rate of the rebar cross-section have a strong influence on WS. Finally, the test data are predicted, and the prediction result error index is calculated. Compared with the predictions of some traditional machine learning methods, such as support vector machines and artificial neural networks, RF prediction has the highest accuracy and is the closest to the true value, which demonstrates the accuracy of the model and its application potential.