Monitoring System for the Treatment of the Bedding Plane of Roller Compacted Concrete Gravity Dam

Abstract

The present invention belongs to the technical field of concrete engineering monitoring, and specifically discloses a monitoring system for the treatment of the bedding plane of a roller-compacted concrete gravity dam, including a data acquisition module for acquiring surface image information and internal cross-section image information; a data processing module for processing the surface image information and the internal cross-section image information; a three-dimensional construction module for constructing a virtual scene of the gravity dam, a virtual roller-compacted concrete layer, and a 3D model; a coordinate conversion module for converting three-dimensional coordinates into GPS coordinates; and a data analysis module for real-time regulating the concrete discharging point positions and the bedding strategies based on the parameter information of the previous roller-compacted concrete layer. The present invention anticipates problems in advance, provides positive guidance for the construction process, and by timely discovering and solving quality problems in the construction process, it avoids rework and repair costs caused by unqualified quality, and reduces the cost of the entire gravity dam construction.

Description

Technical Field

[0001] The present invention belongs to the technical field of concrete engineering monitoring, and particularly relates to a monitoring system for the treatment of the bedding plane of a roller-compacted concrete gravity dam. Background Art

[0002] The construction of a reservoir project is an effective engineering measure to solve the production and domestic water use of some main urban areas and surrounding townships. It provides a reliable guarantee for the water use in the development of social economy, can effectively solve the contradiction of medium- and long-term water shortage in the county seat, and can also promote the development of local social economy. In the current construction of reservoir facilities, roller-compacted concrete has been widely used due to its advantages such as fast construction speed, low cost, and good mechanical properties. However, the quality of the roller-compacted concrete layer is directly related to the safety, stability, and durability of the entire engineering structure.

[0003] Traditional detection methods for roller-compacted concrete layers, such as the core drilling method, although they can obtain actual samples inside the concrete, this method is not only time-consuming and laborious, with low detection efficiency, but also causes irreparable damage to the concrete structure, affecting the integrity and safety of the structure; when using the buried method to detect the thickness of the roller-compacted concrete layer and the internal structure of the concrete layer, equipment such as rollers and vibrating rods may damage the buried sensing equipment. In recent years, with the rapid development of computer technology and information technology, detection methods based on image recognition and data analysis have gradually emerged. However, there are still many problems in the actual application of these methods. For example, the detection accuracy is difficult to meet the requirements of complex projects, the real-time performance is poor, it cannot intuitively feedback the quality of the concrete layer, and it cannot provide positive guidance for construction before the roller-compacted concrete layer is formed. Summary of the Invention

[0004] The purpose of the present invention is to overcome the defects existing in the prior art and provide a monitoring system for the treatment of the bedding plane of a roller-compacted concrete gravity dam.

[0005] The present invention provides a monitoring system for the treatment of the bedding plane of a roller-compacted concrete gravity dam, including:

[0006] A data acquisition module for acquiring the surface image information and internal cross-section image information of the roller-compacted concrete layer;

[0007] A data processing module, connected to the data acquisition module, for processing the surface image information and internal cross-section image information so that the surface image information and internal cross-section image information reflect the true information of the roller-compacted concrete layer;

[0008] A three-dimensional construction module is used to construct a virtual scene of a gravity dam. Based on the virtual scene of the gravity dam, a virtual roller compacted concrete layer is configured according to the design requirements. The three-dimensional construction module is also connected to the data processing module, performs hierarchical modeling on the roller compacted concrete layer based on the information of the actual roller compacted concrete layer, and places the 3D models of each roller compacted concrete layer in the corresponding virtual scene of the gravity dam. A dynamic stress zone is set based on the preset rolling trajectories of each group of rolling equipment to simulate the pressing of the rolling equipment on each roller compacted concrete layer in the virtual scene of the gravity dam;

[0009] A coordinate conversion module is used to convert and match the three-dimensional coordinates in the virtual scene of the gravity dam with the measured GPS coordinates of the gravity dam;

[0010] A data analysis module is respectively connected to the three-dimensional construction module and the data processing module, extracts parameters from the processed surface image information and internal cross-section image information, obtains the parameter information of each roller compacted concrete layer, adjusts the 3D models of each roller compacted concrete layer based on the parameter information, and adjusts the concrete discharging points and leveling strategies in real time based on the parameter information of the previous roller compacted concrete layer, and simulates the next roller compacted concrete layer in the virtual scene of the gravity dam based on the concrete discharging points and leveling strategies;

[0011] A judgment module is used to compare the simulated next roller compacted concrete layer with the virtual roller compacted concrete layer configured according to the design requirements, output a comparison value, and fine-tune the concrete discharging points and leveling strategies based on the comparison value.

[0012] In a further solution, the data acquisition module includes a high-definition camera unit and an X-ray and CT scanning unit;

[0013] The high-definition camera unit is equipped with multiple high-definition cameras for obtaining surface image information of the roller compacted concrete layer from different angles and positions;

[0014] The X-ray and CT scanning unit uses X-ray and CT scanning equipment to perform internal scanning on the roller compacted concrete layer to obtain internal cross-section image information of the roller compacted concrete layer.

[0015] In a further solution, the data processing module includes a geometric correction unit, a radiation correction unit, an image enhancement unit, and a data enhancement unit;

[0016] The geometric correction unit is used to perform geometric correction on the surface image information and internal cross-section image information, eliminate image distortion caused by the shooting angle and lens distortion, and restore the shape and position of the objects in the image to the real state;

[0017] The radiation correction unit is used to perform radiation correction on the image by statistically analyzing the brightness distribution of the surface image information, and adjust the brightness and contrast of the image;

[0018] The image enhancement unit processes the image using histogram equalization to highlight the edge and texture features in the image;

[0019] The data enhancement unit scales, rotates, and flips the image according to a preset ratio to generate a large amount of new image data.

[0020] Furthermore, the data analysis module includes a thickness analysis unit, a pore and crack analysis unit, an aggregate distribution analysis unit, and a color and texture analysis unit;

[0021] The thickness analysis unit is used to obtain the thickness distribution information of the actual roller-compacted concrete layer, compare it with the designed thickness, and determine whether the thickness of the concrete layer meets the design requirements;

[0022] The pore and crack analysis unit is used to count the number, area, and length parameters of pores and cracks, and determine whether the severity of pores and cracks exceeds the allowable range;

[0023] The aggregate distribution analysis unit is used to identify the position, category, and distribution density of aggregates, and quantitatively evaluate the uniformity of aggregate distribution;

[0024] The color and texture analysis unit is used to compare the color and texture with preset values, determine whether the color and texture on the surface of the concrete layer meet the design requirements and quality standards, and then infer the construction process and quality status of the concrete layer.

[0025] Furthermore, the thickness distribution information, the number, area, and length parameters of pores and cracks are determined by the first recognition model. The construction process of the first recognition model is as follows:

[0026] The cross-sectional image information processed by the data processing module is labeled for thickness, pores, and cracks by professionals. After labeling, the cross-sectional image information is input into the first neural network unit for iterative training, and the thickness distribution information, the number, area, and length parameters of pores and cracks of the current roller-compacted concrete layer are output to obtain the first recognition model.

[0027] The cross-sectional image information includes images of different construction stages and different quality conditions.

[0028] Furthermore, the aggregate distribution, color, and texture are determined by the second recognition model. The construction process of the second recognition model is as follows:

[0029] The surface image information processed by the data processing module is labeled for aggregate distribution, color, and texture by professionals. After labeling, the surface image information is input into the second neural network unit for iterative training, and the aggregate distribution, color, and texture information of the current roller-compacted concrete layer are output to obtain the second recognition model.

[0030] A further solution is that the data analysis module further includes a point determination unit and a leveling strategy unit;

[0031] The point determination unit is respectively connected to the thickness analysis unit and the coordinate conversion module, determines the three-dimensional coordinates of the unloading point on the 3D model based on the thickness differences at different positions of the previous roller compacted concrete layer, and converts the three-dimensional coordinates into GPS coordinates through the coordinate conversion module;

[0032] The leveling strategy unit is respectively connected to the color and texture analysis unit, and determines the leveling strategy based on the color and texture of the concrete layer surface;

[0033] The leveling strategy is the working strategy of the rolling equipment.

[0034] A further solution is that the process of obtaining the three-dimensional coordinates of the unloading point is as follows:

[0035] Set the three-dimensional coordinates of the measurement point based on the thickness distribution information as (x i , y i , z i ), the corresponding thickness is h i , i = 1, 2,..., n, where n is the number of measurement points;

[0036] For the measurement point (x j , y j , z j ), the three-dimensional spatial distance between other measurement points (x k , y k , z k ) in its neighborhood and the measurement point (x j , y j , z j ) is:

[0037] ;

[0038] where both j and k are integers less than or equal to n;

[0039] Calculate the thickness change rate within the neighborhood: ;

[0040] where is the thickness of the measurement point (x k , y k , z k ), is the thickness of the measurement point (x j , y j , z j );

[0041] The thickness change rate represents the thickness change per unit distance. The average thickness change rate at a point is obtained by averaging all the thickness change rates in the neighborhood. ;

[0042] Based on the designed thickness H of each roller-compacted concrete layer, for the area where the current thickness is less than the target thickness, determine the three-dimensional coordinates of the unloading point: The increased thickness at the measurement point (x j , y j , z j ) is: , then the three-dimensional space distance offset is ;

[0043] By analyzing the thickness difference between each point in the neighborhood and the thickness of the measurement point (x j , y j , z j ), determine the offset direction vector (a, b, c) in three-dimensional space. Unitize the offset direction vector (a, b, c) to obtain the unit vector ( ), then the three-dimensional coordinates of the next unloading point in the 3D model are (x new , y new , z new ), where:

[0044] ;

[0045] Convert the three-dimensional coordinates (x new , y new , z new ) of the next unloading point through the coordinate conversion module into GPS coordinates, that is, obtain the actual position of the next unloading point.

[0046] A further solution is that the determination process of the leveling strategy is:

[0047] Convert the surface image information processed by the data processing module into the CIELAB color space and set the color deviation threshold . When , for the light-colored area, increase the vibration frequency of the rolling equipment by 5 Hz and the amplitude by 0.1 mm; for the dark-colored area, reduce the vibration frequency by 3 Hz and the amplitude by 0.05 mm; when : For the light-colored area, increase the vibration frequency by 10 Hz, increase the amplitude by 0.2 mm, and at the same time increase the number of rolling passes by 2; for the dark-colored area, reduce the vibration frequency by 5 Hz, reduce the amplitude by 0.1 mm, and reduce the number of rolling passes by 1;

[0048] Calculate the clarity index and direction consistency index of the texture based on the texture information output by the second recognition model;

[0049] Set the texture clarity threshold is 15, and the direction standard deviation threshold is 10°;

[0050] When the texture clarity : Increase the compaction power of the rolling equipment by 20% or replace it with a heavier rolling wheel to enhance the compaction effect and make the texture clearer;

[0051] When the direction standard deviation of the texture : Re-plan the driving route of the rolling equipment to ensure that the deviation of each rolling direction from the designed direction is less than 5°, and at the same time increase the overlapping width of the rolling wheels.

[0052] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0053] The present invention discloses a comprehensive monitoring and control system. The data acquisition module collects surface and internal cross-sectional image information in multiple dimensions. The data processing module processes it to ensure the authenticity and accuracy of the information, providing a reliable basis for subsequent analysis. The three-dimensional construction module creates a virtual scene of the gravity dam and conducts layered modeling, simulating the pressure exerted by the rolling equipment, enabling construction personnel to intuitively understand the structure of the gravity dam and the construction effect, and foresee problems in advance. The data analysis module adjusts the unloading points and leveling strategies of the subsequent layer in real time according to the information of the previous layer, providing positive guidance for the construction process, avoiding blind construction and repeated operations that may occur in traditional construction, and improving the construction efficiency. By promptly discovering and solving quality problems during the construction process, it avoids rework and repair costs caused by unqualified quality, and reduces the cost of the entire gravity dam construction.

[0054] The present invention uses a high-definition camera unit and an X-ray and CT scanning unit to obtain surface image information and internal cross-sectional image information of the roller-compacted concrete layer from different angles and positions respectively. The high-definition camera can comprehensively capture the situation on the surface of the concrete layer, while X-ray and CT scanning can deeply understand the internal structure, realizing all-round monitoring of the roller-compacted concrete layer from the outside to the inside, and providing a rich and accurate data basis for subsequent analysis.

[0055] The geometric correction unit in the data processing module of the present invention can eliminate image distortion caused by shooting angles and lens distortion. The radiation correction unit adjusts the brightness and contrast of the image. The image enhancement unit highlights the edge and texture features in the image. The data enhancement unit generates a large amount of new image data. These processing steps enable the collected image information to more accurately reflect the true information of the roller-compacted concrete layer, improving the quality and usability of the data.

[0056] The data analysis module of the present invention extracts parameters from the processed image information to obtain parameter information of each roller-compacted concrete layer, such as thickness, pores and cracks, aggregate distribution, color and texture, etc. Based on this parameter information, the 3D model of each roller-compacted concrete layer can be adjusted to make it more in line with the actual situation, and at the same time provide accurate data support for subsequent construction decisions.

[0057] By analyzing the parameter information of the previous roller-compacted concrete layer, the present invention can adjust the concrete discharging point position and the leveling strategy in real time. For example, the point determination unit determines the three-dimensional coordinates of the discharging point position according to the thickness difference and converts them into GPS coordinates to ensure the accuracy of the discharging position; the leveling strategy unit determines the working strategy of the rolling equipment according to the color and texture of the concrete layer surface, such as adjusting the vibration frequency, amplitude, number of rolling passes, etc., so as to ensure the construction quality of each layer of concrete.

[0058] By constructing the first recognition model and the second recognition model, the thickness distribution, pore and crack parameters, aggregate distribution, color and texture and other information of the roller-compacted concrete layer are determined respectively. These models are iteratively trained using a large number of labeled images, can accurately and quickly identify relevant parameters, improve the efficiency and accuracy of quality inspection, and help to timely detect potential quality problems.

[0059] In the construction of gravity dams, the accuracy of the concrete discharging point position has a significant impact on the quality of gravity dams. By analyzing the thickness difference, calculating the change rate of the neighborhood thickness, and determining the offset and direction vector, the present invention can accurately adjust the discharging point position according to actual needs. For example, when the thickness of a certain area is less than the design value, the position where concrete needs to be supplemented can be accurately found, avoiding local over-thinning or over-thickening, ensuring uniform thickness of each part of the gravity dam, effectively preventing stress concentration problems caused by uneven thickness, and enhancing the structural stability of the gravity dam. Moreover, after the coordinates are converted into the GPS coordinates of the gravity dam, construction workers can quickly locate the discharging point on the actual construction site with the help of the global positioning system, improve the construction efficiency, reduce errors, and ensure that the construction is carried out efficiently and accurately according to the design requirements.

[0060] The present invention determines the leveling strategy based on the surface color and texture of concrete, achieving refined control of the working parameters of the rolling equipment. The processed surface image information is converted into the CIELAB color space of the gravity dam, and the vibration frequency, amplitude, and number of rolling passes are adjusted according to the color deviation threshold, which can improve the compaction effect and surface quality of the concrete. Different adjustment strategies are adopted for light and dark areas respectively, which can make the concrete compaction more uniform and avoid quality problems caused by insufficient or excessive compaction. By calculating the clarity and direction consistency indexes based on the texture information and adjusting the rolling equipment accordingly, the construction quality of the gravity dam can be further guaranteed. When the texture clarity is insufficient, increasing the compaction power or replacing the rolling wheel can enhance the compaction effect and improve the density and uniformity of the concrete; when the standard deviation of the texture direction does not meet the standard, re-planning the driving route and increasing the overlapping width of the rolling wheel can make the rolling direction more regular, ensure uniform stress on each part of the gravity dam, and effectively improve the overall quality and stability of the gravity dam. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The following drawings are only schematic illustrations and explanations of the present invention, and are not used to limit the scope of the present invention, where:

[0062] Figure 1 : Principle block diagram of the monitoring system of the present invention;

[0063] Figure 2 : Schematic diagram of the virtual gravity dam of the present invention;

[0064] In the figure: 1, virtual scene of the gravity dam; 2, virtual roller compacted concrete layer; 3, 3D model; 4, data acquisition module; 5, data processing module; 6, three-dimensional construction module; 7, coordinate conversion module; 8, data analysis module; 9, judgment module; 10, high-definition camera unit; 11, X-ray and CT scanning unit; 12, geometric correction unit; 13, radiation correction unit; 14, image enhancement unit; 15, data enhancement unit; 16, first recognition model; 17, second recognition model; 18, thickness analysis unit; 19, pore and crack analysis unit; 20, aggregate distribution analysis unit; 21, color and texture analysis unit; 22, point position determination unit; 23, leveling strategy unit. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0065] In order to make the purpose, technical solutions, design methods, and advantages of the present invention clearer, the present invention will be further described in detail below through specific embodiments with reference to the drawings. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0066] As Figure 1 shown, the present invention provides a monitoring system for the treatment of the layer surface of roller compacted concrete gravity dams, including:

[0067] The data acquisition module 4 is used to acquire the surface image information and the internal cross-section image information of the roller-compacted concrete layer;

[0068] The data processing module 5 is connected to the data acquisition module 4 and is used to process the surface image information and the internal cross-section image information so that the surface image information and the internal cross-section image information reflect the real roller-compacted concrete layer information;

[0069] The three-dimensional construction module 6 is used to construct the gravity dam virtual scene 1, as Figure 2 shown. Based on the gravity dam virtual scene 1, the virtual roller-compacted concrete layer 2 is configured according to the design requirements. The three-dimensional construction module 6 is also connected to the data processing module 5. Based on the real roller-compacted concrete layer information, the roller-compacted concrete layer is modeled in layers, and the 3D models 3 of each roller-compacted concrete layer are placed in the corresponding gravity dam virtual scene 1. The dynamic stress zones are set based on the preset rolling trajectories of each group of rolling equipment to simulate the pressing of the rolling equipment on each roller-compacted concrete layer in the gravity dam virtual scene 1. Among them, the dynamic stress zone is divided into several continuous stress regions according to parameters such as the preset rolling trajectory and the wheel width of the rolling equipment. Each stress region can be regarded as the coverage range of the rolling equipment during one rolling process. The attributes of the dynamic stress zone are determined for each stress region, including the stress magnitude, direction, and action time, etc. The stress magnitude can be determined by mechanical calculation according to the parameters of the rolling equipment and the characteristics of the concrete. For example, according to the weight and vibration parameters of the rolling wheel, combined with the compressive strength of the concrete, etc., the pressure values applied to the concrete layer at different rolling stages are calculated. The stress direction is perpendicular to the surface of the roller-compacted concrete layer, and the action time is related to the traveling speed and the length of the rolling trajectory of the rolling equipment, and is determined by calculating the residence time of the equipment in each stress region. The stress analysis is as follows: The self-gravity of the rolling equipment G = Mg, where g is the acceleration due to gravity, and the gravity acts vertically on the surface of the roller-compacted concrete layer and generates a uniform static pressure , where S is the contact area between the rolling wheel and the roller-compacted concrete layer.

[0070] The coordinate conversion module 7 is used to convert and match the three-dimensional coordinates in the gravity dam virtual scene 1 with the measured GPS coordinates of the gravity dam;

[0071] The data analysis module 8 is connected to the three-dimensional construction module 6 and the data processing module 5 respectively. It extracts parameters from the processed surface image information and internal cross-section image information, obtains the parameter information of each roller-compacted concrete layer, adjusts the 3D models 3 of each roller-compacted concrete layer based on the parameter information, and adjusts the concrete discharging points and the leveling strategy in real time based on the parameter information of the previous roller-compacted concrete layer, and simulates the next roller-compacted concrete layer in the gravity dam virtual scene 1 based on the concrete discharging points and the leveling strategy;

[0072] The judgment module 9 is used to compare the simulated next-layer roller-compacted concrete layer with the virtual roller-compacted concrete layer 2 configured based on the design requirements, output a comparison value, and fine-tune the concrete discharging points and the leveling strategy based on the comparison value. Specifically, if the comparison value shows that the thickness of the simulated roller-compacted concrete layer is greater than that of the virtual roller-compacted concrete layer 2 in some areas, then during subsequent discharging, the discharging points should be appropriately moved away from these areas and shifted towards the areas with insufficient thickness. For example, if it is calculated that the thickness of a certain area is 5 cm thicker than the design value, the discharging points can be shifted 2 m towards the direction with thinner thickness around this area. For the leveling strategy, in the areas with larger thickness, the operation times of the leveling equipment can be appropriately reduced or its operation intensity can be lowered to avoid excessive compaction resulting in further increase in thickness; in the areas with insufficient thickness, the operation times and intensity of the leveling equipment are increased to ensure uniform distribution of the concrete to reach the design thickness.

[0073] In the above, the data acquisition module 4 includes a high-definition camera unit 10 and an X-ray and CT scanning unit 11; among them, the high-definition camera unit 10 is equipped with multiple high-definition cameras, which are used to obtain the surface image information of the roller-compacted concrete layer from different angles and positions; the X-ray and CT scanning unit 11 uses X-ray and CT scanning equipment to perform internal scanning on the roller-compacted concrete layer to obtain the internal cross-sectional image information of the roller-compacted concrete layer.

[0074] In order to improve the monitoring accuracy, in this embodiment, the data processing module 5 includes a geometric correction unit 12, a radiation correction unit 13, an image enhancement unit 14, and a data enhancement unit 15; the geometric correction unit 12 is used to perform geometric correction on the surface image information and the internal cross-sectional image information, eliminate the image distortion caused by the shooting angle and lens aberration, and restore the shape and position of the objects in the image to the real state; the radiation correction unit 13 is used to perform radiation correction on the image by statistically analyzing the brightness distribution of the surface image information, and adjust the brightness and contrast of the image; the image enhancement unit 14 uses histogram equalization to process the image to highlight the edge and texture features in the image; the data enhancement unit 15 scales, rotates, and flips the image according to a preset ratio, generates a large number of new image data to form a large dataset for iterative training of the neural network below.

[0075] In the above, the data analysis module 8 includes a thickness analysis unit 18, a pore and crack analysis unit 19, an aggregate distribution analysis unit 20, and a color and texture analysis unit 21; the thickness analysis unit 18 is used to obtain the thickness distribution information of the actual roller-compacted concrete layer and compare it with the designed thickness for analysis to determine whether the thickness of the concrete layer meets the design requirements; the pore and crack analysis unit is used to count the quantity, area, and length parameters of pores and cracks and determine whether the severity of pores and cracks exceeds the allowable range; if the pores and cracks seriously exceed the allowable range, structural reinforcement is required. Methods such as pasting carbon fiber sheets and pasting steel plates can be used. By increasing the stress-bearing area and strength of the structure, the bearing capacity and stability of the structure can be improved. Before pasting the carbon fiber sheet or steel plate, the concrete surface needs to be treated to ensure that the pasting surface is flat, dry, and free of oil stains, and then the pasting construction is carried out according to the specification requirements. A special adhesive is used to firmly paste the carbon fiber sheet or steel plate on the concrete surface. The aggregate distribution analysis unit 20 is used to identify the positions, categories, and distribution densities of aggregates, quantitatively evaluate the uniformity of aggregate distribution. When the aggregate distribution is uneven, for the concrete that has been poured but not yet set, the vibration work is strengthened. An inserted vibrator is used to vibrate according to a certain spacing and vibration time, so that the aggregates are redistributed evenly under the action of gravity and vibration force. The color and texture analysis unit 21 is used to compare the color and texture with the preset values to determine whether the color and texture on the surface of the concrete layer meet the design requirements and quality standards, and then infer the construction process and quality status of the concrete layer. For areas with lighter colors and less cement paste, it indicates that the cement paste in this area fails to fully fill the gaps between aggregates. At this time, the vibration frequency and amplitude of the rolling equipment should be increased. Higher vibration frequency and amplitude can generate greater vibration force, prompting the cement paste to flow and fill more fully between the aggregates, thereby improving the uniformity of the concrete. If the texture clarity is insufficient, it means that the compaction effect on the concrete surface is poor. During the rolling stage, the compaction effect can be improved by increasing the compaction power of the rolling equipment to make the texture clearer.

[0076] Among them, the thickness distribution information, the quantity, area, and length parameters of pores and fissures are determined by the first recognition model 16. The construction process of the first recognition model 16 is as follows: The cross-sectional image information processed by the data processing module 5 is marked by professionals for thickness, pores, and fissures. After marking, the cross-sectional image information is input into the first neural network unit for iterative training, and the thickness distribution information, the quantity, area, and length parameters of pores and fissures of the current roller-compacted concrete layer are output, thus obtaining the first recognition model 16. The cross-sectional image information includes images of different construction stages and different quality conditions. In this embodiment, the first neural network unit selects the U-Net network structure, which has a symmetric encoder-decoder architecture. It includes: an input layer, which is used to receive the dataset (internal cross-sectional image information) preprocessed by the data processing module 5, in the format of an RGB image, with a size of 256×256×3. The function of this layer is to input the original image data into the network to prepare for subsequent feature extraction. Encoder part: It is alternately composed of multiple convolutional layers and pooling layers. Specifically, the convolutional layer uses a 3×3 convolutional kernel, with a stride set to 1 and padding of 1 to keep the image size unchanged after the convolutional operation. Each convolutional layer uses the ReLU activation function to increase the non-linear expression ability of the network. For example, the first convolutional layer performs a convolutional operation on the input image, converting the 3-channel image into a 64-channel feature map with a size still of 256×256. As the number of network layers increases, the number of output channels of the convolutional layer gradually doubles, such as the subsequent convolutional layers outputting feature maps with 128, 256, 512 channels, etc., to extract richer image features. The pooling layer follows the convolutional layer immediately and uses a 2×2 max pooling method with a stride of 2. The function of the pooling layer is to reduce the resolution of the feature map, reduce the amount of data, and at the same time expand the receptive field, enabling the network to extract more abstract features. After passing through the pooling layer, the size of the feature map is halved, such as from 256×256 to 128×128, and then to 64×64, etc., while the number of channels remains unchanged. The intermediate connection layer is located between the encoder and the decoder and is composed of multiple convolutional layers. The convolutional layers in this part also use a 3×3 convolutional kernel, with a stride of 1 and padding of 1, and use the ReLU activation function. The intermediate connection layer further extracts the deep features of the image, deepens the network's understanding of the image, and prepares for the feature restoration and segmentation of the decoder. The decoder part is symmetric to the encoder and is composed of an upsampling layer and convolutional layers. Among them, the upsampling layer uses methods such as deconvolution or interpolation to restore the low-resolution feature map to the original image size. The deconvolution kernel size is 2×2, with a stride of 2. Through the deconvolution operation, the size of the feature map is doubled, restored from 32×32 to 64×64. At the same time, the number of channels is halved, from 512 channels to 256 channels. After each upsampling, one or more convolutional layers are connected to further perform feature fusion and refinement on the restored-size feature map. The convolutional layer also uses a 3×3 convolutional kernel, with a stride of 1 and padding of 1, and uses the ReLU activation function.Through these convolution operations, the accuracy of the segmentation results is ensured, so that the output segmentation mask can accurately reflect the position and shape of pores and fractures in the image. Output layer: Output corresponding results according to different tasks. For thickness recognition, a scalar representing the thickness value is output, and thickness distribution information within a certain range is formed on the premise of determining the detection point position; for pores and fractures, the number, area, and length parameters of pores and fractures are output.

[0077] In the above, the aggregate distribution, color, and texture are determined by the second recognition model 17. The construction process of the second recognition model 17 is as follows: The surface image information processed by the data processing module 5 is annotated by professionals for the aggregate distribution, color, and texture. After annotation, the surface image information is input into the second neural network unit for iterative training to output the aggregate distribution, color, and texture information of the current roller-compacted concrete layer, thereby obtaining the second recognition model 17. In this embodiment, the second neural network unit selects the ResNet residual network structure, including: An input layer for receiving the dataset (surface image information) preprocessed by the data processing module 5, with a size of 256×256×3. This layer passes the original image data to subsequent network layers for processing. Convolutional layer and pooling layer: At the beginning of the network, a 7×7 convolutional layer is set with a stride of 2 and a padding of 3 to perform preliminary feature extraction and downsampling on the 256×256×3 input image, outputting a feature map of 127×127×64. Then, a 3×3 max pooling layer with a stride of 2 is used to further reduce the resolution of the feature map, outputting a feature map of 63×63×64. Residual block part: Stacked by multiple residual blocks. Each residual block contains two or more convolutional layers, and skip connections are used between the convolutional layers. Convolutional layer: A 3×3 convolutional kernel is used. Before the first convolutional layer, there is also a 1×1 convolutional layer to adjust the number of channels to match the dimensions of the skip connection. After each convolutional layer, a batch normalization layer and a ReLU activation function are connected. The batch normalization layer is used to accelerate network convergence, and the ReLU activation function increases the non-linearity of the network. Specifically, in a residual block, the first 3×3 convolutional layer converts the 64-channel feature map into a 128-channel one. After batch normalization and ReLU activation, the second 3×3 convolutional layer then converts the 128-channel feature map back to 64 channels, and then adds it to the input feature map. After ReLU activation, a 64-channel feature map is output. Skip connection: Directly adds the input feature to the feature after convolutional operation. This connection method effectively solves the problems of gradient disappearance and gradient explosion in the training process of deep neural networks, enabling the network to be trained to deeper layers and improving the network's ability to extract complex features. After the stacking of residual blocks is completed, a global average pooling layer is connected to compress the spatial size of the feature map to 1×1, only retaining the information of the channel dimension. Fully connected layer For aggregate category recognition, the number of output neurons is equal to the number of aggregate categories; for color feature vector output, the number of neurons is determined according to the color space dimension. For example, in the RGB color space, it is 3; for texture feature vector output, the number of neurons is determined according to the number of extracted texture features. The fully connected layer maps the feature vector after global average pooling to the corresponding output dimension, outputting the results including the aggregate distribution position, category, and color and texture feature vectors.

[0078] In order to achieve real-time regulation of the concrete discharging point and the leveling strategy, in this embodiment, the data analysis module 8 further includes a point determination unit 22 and a leveling strategy unit 23. Among them, the point determination unit 22 is respectively connected to the thickness analysis unit 18 and the coordinate conversion module 7, determines the three-dimensional coordinates of the discharging point on the 3D model 3 based on the thickness differences at different positions of the previous roller-compacted concrete layer, and converts the three-dimensional coordinates into GPS coordinates through the coordinate conversion module 7. The leveling strategy unit 23 is respectively connected to the color and texture analysis unit 21, and determines the leveling strategy based on the color and texture of the concrete layer surface. The leveling strategy is the working strategy of the rolling equipment.

[0079] Specifically, the process of obtaining the three-dimensional coordinates of the discharging point is as follows:

[0080] Based on the thickness distribution information, set the three-dimensional coordinates of the measurement point as (x i , y i , z i ), and the corresponding thickness is h i , i = 1, 2,..., n, where n is the number of measurement points;

[0081] For the measurement point (x j , y j , z j ), the three-dimensional spatial distance between other measurement points (x k , y k , z k ) in its neighborhood and the measurement point (x j , y j , z j ) is:

[0082] ;

[0083] Among them, both j and k are integers less than or equal to n. In this implementation, the neighborhood refers to a specific area around a certain measurement point. This area contains multiple other measurement points and is used to analyze the change in the thickness of the roller-compacted concrete within this area. Taking the measurement point (x j , y j , z j ) as an example, its neighborhood is the area within a certain spatial range around it, and the points (x k , y k , z k ) within this range form a neighborhood relationship with it. In actual operation, the size of the neighborhood range is set according to the actual situation of the construction site and the accuracy requirements. For example, it is set to be centered around the measurement point (x j , y j , z jTaking a circular area centered at a point with a radius of 3 meters, all measurement points within this circular area belong to the neighborhood of this point. By analyzing the thickness differences and distances between each point in the neighborhood and this point, the thickness change rate is calculated, and then the average thickness change rate is obtained, providing a basis for determining the offset amount and direction of the discharge coordinates later.

[0084] Calculate the thickness change rate within the neighborhood: ;

[0085] Where, is the thickness of the measurement point (x k , y k , z k ), is the thickness of the measurement point (x j , y j , z j );

[0086] The thickness change rate represents the thickness change per unit distance. The average value of all thickness change rates within the neighborhood is calculated to obtain the average thickness change rate of this point ;

[0087] Based on the designed thickness H of each roller compacted concrete layer, for the area where the current thickness is less than the target thickness, determine the three-dimensional coordinates of the discharge point: The increased thickness of the measurement point (x j , y j , z j ) is: , then the three-dimensional space distance offset is ;

[0088] By analyzing the thickness differences between each point in the neighborhood and the thickness of the measurement point (x j , y j , z j ), determine the offset direction vector (a, b, c) in three-dimensional space. Unitize the offset direction vector (a, b, c) to obtain the unit vector ( ), then the three-dimensional coordinates of the next discharge point in the 3D model 3 are (x new , y new , z new ), where:

[0089] ;

[0090] Convert the three-dimensional coordinates (x new , y new , z new ) of the next discharge point through the coordinate conversion module 7 into GPS coordinates, that is, obtain the actual position of the next discharge point.

[0091] The determination process of the leveling strategy is as follows:

[0092] Convert the surface image information processed by the data processing module 5 into the CIELAB color space, and set the color deviation threshold , when , for the light-colored area, increase the vibration frequency of the rolling equipment by 5 Hz and the amplitude by 0.1 mm; for the dark-colored area, decrease the vibration frequency by 3 Hz and the amplitude by 0.05 mm; when : For the light-colored area, increase the vibration frequency by 10 Hz, increase the amplitude by 0.2 mm, and at the same time increase the number of rolling passes by 2; for the dark-colored area, decrease the vibration frequency by 5 Hz, decrease the amplitude by 0.1 mm, and reduce the number of rolling passes by 1;

[0093] Calculate the clarity index and direction consistency index of the texture based on the texture information output by the second recognition model;

[0094] Set the texture clarity threshold to 15, and the direction standard deviation threshold to 10°;

[0095] When the texture clarity : Increase the compaction power of the rolling equipment by 20% or replace it with a heavier rolling wheel to enhance the compaction effect and make the texture clearer;

[0096] When the texture direction standard deviation : Re-plan the driving route of the rolling equipment to ensure that the deviation of each rolling direction from the designed direction is less than 5°, and at the same time increase the overlapping width of the rolling wheels.

[0097] The embodiments of the present invention have been described above. The above description is exemplary and not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations are obvious to those of ordinary skill in the art in the technical field without departing from the scope and spirit of the described embodiments. The selection of the terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other ordinary skilled persons in the technical field to understand the embodiments disclosed herein.

Claims

1. Roller compacted concrete gravity dam layer treatment monitoring system, characterized by: include: A data acquisition module, used to acquire surface image information and internal cross-sectional image information of the RCC layer; A data processing module, connected to the data acquisition module, for processing the surface image information and the internal cross-sectional image information so that the surface image information and the internal cross-sectional image information reflect the real RCC layer information; A three-dimensional construction module is used to construct a virtual scene of a gravity dam, and configure a virtual roller compacted concrete layer based on the design requirements based on the virtual scene of the gravity dam. The three-dimensional construction module is also connected to the data processing module, and the roller compacted concrete layer is modeled in layers based on the real roller compacted concrete layer information, and the 3D model of each roller compacted concrete layer is placed in the corresponding virtual scene of the gravity dam, and a dynamic stress belt is set based on the preset rolling trajectory of each group of rolling equipment, so as to simulate the roller compaction equipment in the virtual scene of the gravity dam to pressurize each roller compacted concrete layer; A coordinate conversion module is used to convert and match the three-dimensional coordinates in the gravity dam virtual scene with the measured GPS coordinates of the gravity dam; a data analysis module, connected to the three-dimensional construction module and the data processing module respectively, extracting parameters of the processed surface image information and the internal cross-sectional image information, obtaining parameter information of each RCC layer, regulating the 3D model of each RCC layer based on the parameter information, regulating the concrete unloading point and the liquidation strategy in real time based on the parameter information of the previous RCC layer, and simulating the next RCC layer in the gravity dam virtual scene based on the concrete unloading point and the liquidation strategy; A judgment module is used to compare the next RCC layer generated by simulation with the virtual RCC layer configured based on design requirements, output a comparison value, and fine-tune the concrete unloading point and the closing strategy based on the comparison value; The data analysis module includes a thickness analysis unit, a color and texture analysis unit, a point determination unit and a position closing strategy unit; The thickness analysis unit is used to obtain the thickness distribution information of the actual rolled concrete layer, and compare and analyze it with the designed thickness to determine whether the thickness of the concrete layer meets the design requirements; The color and texture analysis unit is used to compare the color and texture with the preset value, determine whether the color and texture of the concrete layer surface meet the design requirements and quality standards, and then infer the construction process and quality status of the concrete layer; The point determination unit is connected to the thickness analysis unit and the coordinate conversion module respectively, determines the three-dimensional coordinates of the unloading point on the 3D model based on the thickness difference of different positions of the previous rolled concrete layer, and converts the three-dimensional coordinates into GPS coordinates through the coordinate conversion module; The closing strategy unit is connected to the color and texture analysis unit respectively, and determines the closing strategy based on the color and texture of the concrete layer surface. The closing strategy is the working strategy of the rolling equipment.

2. The roller compacted concrete gravity dam surface treatment monitoring system according to claim 1 is characterized in that: The data acquisition module includes a high-definition camera unit, an X-ray and CT scanning unit; The high-definition camera unit is equipped with a plurality of high-definition cameras for acquiring surface image information of the RCC layer from different angles and positions; The X-ray and CT scanning unit uses X-ray and CT scanning equipment to perform internal scanning on the RCC layer to obtain internal cross-sectional image information of the RCC layer.

3. The roller compacted concrete gravity dam surface treatment monitoring system according to claim 2 is characterized in that: The data processing module includes a geometric correction unit, a radiation correction unit, an image enhancement unit and a data enhancement unit; The geometric correction unit is used to perform geometric correction on the surface image information and the internal cross-sectional image information, eliminate the image deformation caused by the shooting angle and lens distortion, and restore the shape and position of the object in the image to the real state; The radiation correction unit is used to perform radiation correction on the image and adjust the brightness and contrast of the image by counting the brightness distribution of the surface image information; The image enhancement unit processes the image using histogram equalization to highlight edge and texture features in the image; The data enhancement unit scales, rotates, and flips the image according to a preset ratio to generate a large amount of new image data.

4. The roller compacted concrete gravity dam surface treatment monitoring system according to claim 3 is characterized in that: The data analysis module includes a pore and crack analysis unit and an aggregate distribution analysis unit; The pore and crack analysis unit is used to count the number, area, and length parameters of pores and cracks, and determine whether the severity of the pores and cracks exceeds the allowable range; The aggregate distribution analysis unit is used to identify the location, type and distribution density of aggregates and quantitatively evaluate the uniformity of aggregate distribution.

5. The roller compacted concrete gravity dam surface treatment monitoring system according to claim 4, characterized in that: The thickness distribution information, the number, area, and length parameters of pores and cracks are determined by a first recognition model, and the construction process of the first recognition model is as follows: The cross-sectional image information processed by the data processing module is annotated by professionals for thickness, pores, and cracks. After annotated, the cross-sectional image information is input into the first neural network unit for iterative training, and the thickness distribution information, the number, area, and length parameters of the pores and cracks of the current roller compacted concrete layer are output to obtain a first recognition model; The cross-sectional image information includes images at different construction stages and in different quality conditions.

6. The roller compacted concrete gravity dam surface treatment monitoring system according to claim 5, characterized in that: The aggregate distribution, color and texture are determined by a second recognition model, and the construction process of the second recognition model is: The surface image information processed by the data processing module is annotated by professionals for aggregate distribution, color and texture. After annotation, the surface image information is input into the second neural network unit for iterative training, and the aggregate distribution, color and texture information of the current roller compacted concrete layer is output to obtain the second recognition model.

7. The roller compacted concrete gravity dam surface treatment monitoring system according to claim 6, characterized in that: The process of obtaining the three-dimensional coordinates of the unloading point is as follows: The three-dimensional coordinates of the measurement point are set based on the thickness distribution information as (x i ,y i , z i ), corresponding to a thickness of h i , i=1,2,…,n, n is the number of measurement points; For the measurement point (x j ,y j , z j ), other measurement points in its neighborhood (x k ,y k , z k ) and the measuring point (x j ,y j , z j ) is: Wherein, j and k are both integers less than or equal to n; Calculate the thickness change rate within the neighborhood: Among them, h k is the measuring point (x k ,y k , z k ) thickness, h j is the measuring point (x j ,y j , z j ) thickness; The thickness change rate represents the thickness change per unit distance. The average thickness change rate of all thickness change rates in the neighborhood is obtained to obtain the average thickness change rate r of the point. j ; Based on the design thickness H of each RCC layer, for areas where the current thickness is less than the target thickness, determine the three-dimensional coordinates of the unloading point: the measurement point (x j ,y j , z j )The increased thickness is: Δh = Hh j , then the three-dimensional space distance offset is By analyzing the thickness of each point in the neighborhood and the measured point (x j ,y j , z j ) thickness difference, determine the offset direction vector (a, b, c) in three-dimensional space, normalize the offset direction vector (a, b, c) to obtain the unit vector (cosα, cosβ, cosγ), then the three-dimensional coordinates of the next unloading point of the 3D model are (x new ,y new , z new ),in: x new =x j +Δd cosα and new =and j +Δd cosβ With new =from j +Δd cosγ The coordinate conversion module converts the three-dimensional coordinates (x new ,y new , z new ) is converted into GPS coordinates to obtain the actual location of the next unloading point.

8. The roller compacted concrete gravity dam surface treatment monitoring system according to claim 7, characterized in that: The process of determining the closing strategy is as follows: The surface image information processed by the data processing module is converted into the CIELAB color space, and the color deviation threshold ΔE is set. When 3≤ΔE<6, for light-colored areas, the vibration frequency of the rolling equipment is increased by 5Hz and the amplitude is increased by 0.1mm; for dark-colored areas, the vibration frequency is reduced by 3Hz and the amplitude is reduced by 0.05mm; When ΔE≥6: for light-colored areas, the vibration frequency is increased by 10Hz, the amplitude is increased by 0.2mm, and the number of rolling passes is increased by 2 times; for dark-colored areas, the vibration frequency is reduced by 5Hz, the amplitude is reduced by 0.1mm, and the number of rolling passes is reduced by 1 time; Calculating a texture clarity index and a direction consistency index based on the texture information output by the second recognition model; Set the texture clarity threshold G th is 15, the direction standard deviation threshold σ th is 10°; When the texture clarity G<G th : Increase the compaction power of the rolling equipment by 20% or replace it with a heavier rolling wheel to enhance the compaction effect and make the texture clearer; When the standard deviation of the grain direction σ<σ th : Re-plan the driving route of the rolling equipment to ensure that the deviation between the rolling direction and the design direction each time is less than 5°, and at the same time increase the overlapping width of the rolling wheels.

Images