Rapid evaluation method for microcrack defect of concrete diaphragm wall

Abstract

The invention discloses a concrete diaphragm wall micro-crack defect rapid evaluation method, which comprises the following steps: S1, scanning a concrete diaphragm wall to obtain an initial micro-crack defect area; s2, arranging an electrode layer on the surface of the initial micro-crack defect area, obtaining the edge of a target micro-crack defect area, forming the target micro-crack defect area, and dividing the target micro-crack defect area into sub-areas; s3, applying thermal excitation, collecting a sub-region thermogram, and obtaining sub-region temperature abnormal points and an optimal scanning route; s4, scanning is carried out along the optimal scanning route, obtained signals are input into the sub-region crack signal model, and suspected micro-crack points are output; s5, scanning the positions of the suspected micro-crack points, and screening out non-micro-crack points; and S6, obtaining the overall structure information of the concrete diaphragm wall, combining the feature information of the micro-crack points, and inputting the micro-crack risk assessment model to obtain the risk value of the micro-crack. According to the method, rapid detection and evaluation are realized, influence factors are screened out, and the detection accuracy is improved.

Description

Technical Field

[0001] The invention relates to the technical field of anti-seepage wall crack detection, and in particular to a method for quickly evaluating micro-crack defects in concrete anti-seepage walls. Background Art

[0002] As a critical water-stopping structure, the quality of concrete cutoff walls is directly related to the safe and stable operation of water conservancy projects. Microcracks are a common form of damage in concrete cutoff walls. Initially tiny cracks, under the influence of factors such as long-term water erosion, water pressure fluctuations, and temperature changes, gradually develop into through-cracks, significantly reducing the wall's anti-seepage performance. In severe cases, leakage accidents can occur, endangering the safety of the entire water conservancy project and causing huge economic losses and safety hazards.

[0003] Traditionally, microcrack detection in concrete cut-off walls has typically involved visual inspection and core drilling. Visual inspection primarily relies on direct observation of the cut-off wall surface using simple tools. This method offers low operational requirements and low costs, and can detect some relatively obvious surface cracks. However, it has significant limitations. For one thing, it can only detect surface cracks, completely unaware of microcracks hidden within the concrete. These internal microcracks can also develop and expand under the influence of external factors, impacting the performance of the cut-off wall. Furthermore, detection accuracy relies on the experience of the inspector, which is highly subjective. This makes it difficult to accurately identify minute cracks and can easily miss key defect information, leading to misjudgments of the cut-off wall's actual condition.

[0004] The core drilling test involves drilling holes in the anti-seepage wall to obtain core samples, and then analyzing the core samples to determine the condition of microcracks. This method can visually observe the internal structure of the concrete and determine, to a certain extent, parameters such as the depth and width of microcracks. However, this method is a destructive test. The drilling process will destroy the overall structure of the anti-seepage wall, weaken its bearing capacity and anti-seepage performance, and bring serious safety risks, especially in important water conservancy projects with high requirements for structural integrity. Moreover, core drilling testing is inefficient and costly. Each drilling and subsequent core sample analysis requires a lot of time and resources. In addition, the number of drilling holes is limited, and the anti-seepage wall cannot be fully covered. There are large blind spots in the detection range, and it is difficult to grasp the overall distribution of microcracks.

[0005] With technological advancements, technologies such as ultrasonic testing and geological radar testing have been gradually applied to the detection of microcracks in concrete cut-off walls. When microcracks are encountered, acoustic parameters such as wave velocity and amplitude change, and these changes are analyzed to infer information about the microcracks. This method is fast, enables non-contact testing, and can perform preliminary screening of large areas, overcoming some of the shortcomings of traditional methods to a certain extent. However, it has significant drawbacks. Factors such as aggregate distribution and humidity differences within the concrete can interfere with ultrasonic propagation, leading to deviations in test results and making it difficult to accurately determine the location, size, and direction of microcracks. Furthermore, the ability to resolve microcracks in depth is limited. When microcracks are located in complex structures or deep areas, signal interpretation is difficult, making detection accuracy difficult to guarantee.

[0006] In summary, the accuracy and efficiency of microcrack defect detection using existing and traditional technologies are difficult to meet the needs of actual engineering for fast and precise detection. Summary of the Invention

[0007] Based on the above content, this application discloses a method for rapid assessment of micro-crack defects in concrete anti-seepage walls, which solves the above-mentioned technical problems, including:

[0008] S1. Perform a comprehensive scan of the concrete anti-seepage wall to obtain a received signal, calculate the difference between the received signal and the original transmitted signal, input the pre-established micro-crack signal model, and obtain the initial micro-crack defect area on the concrete anti-seepage wall;

[0009] S2. Arranging an electrode layer on the surface of the initial microcrack defect area, measuring the potential difference between different electrodes, calculating the resistivity distribution of the microcrack defect area, obtaining the edge of the target microcrack defect area, forming a target microcrack defect area, and dividing the defect area into sub-areas according to the resistivity change gradient;

[0010] S3, applying thermal excitation to each divided sub-region, collecting thermal images of the sub-region, obtaining temperature anomalies in the sub-region, and obtaining the optimal scanning route through a genetic algorithm;

[0011] S4. Scan along the optimal scanning route to obtain sub-region optical signals, convert the optical signals into electrical signals, input the electrical signals into the sub-region crack signal model for monitoring, output suspected micro-crack points and mark the locations of the suspected micro-crack points in real time;

[0012] S5. Scan the suspected microcrack point location to obtain the modal change value, amplitude attenuation value, and propagation time delay of the signal, and use the signal processing algorithm to filter out non-microcrack points to determine the microcrack point;

[0013] S6. Obtain the overall structural information of the concrete cut-off wall, combine the size, depth, and location characteristics of the microcrack points, build a microcrack risk assessment model, and output the risk value of the microcracks.

[0014] Preferably, in said S1, the received signal and the original transmitted signal of the cut-off wall area are obtained, and the difference value is calculated, and the formula is: ,in, is the original transmitted signal, To receive the signal, is the signal acquisition time, is the time delay, according to the minimum value value, get the time delay when the difference is the largest ,calculate The difference between the time , the formula is: ,Will The difference between the time Input pre-established microcrack signal model , obtain the initial microcrack defect area.

[0015] Preferably, the pre-established microcrack signal model is constructed by a convolutional neural network, specifically:

[0016] For a large number of different microcrack conditions, the difference values and signal data Preprocess the difference Arranged into a two-dimensional matrix according to time series Input convolutional neural network for feature extraction, the formula is: ,in The output feature map of the first convolutional layer is The value of the position, It is The convolution kernel in the layer The weight of the position, It is a bias term. After multi-layer convolution and pooling operations, the signal features are extracted and the probability value of microcrack defects is output through the fully connected layer. , according to the pre-set threshold When judging, if , is the initial microcrack defect area.

[0017] Preferably, a regular grid-shaped electrode layer is arranged on the surface of the initial microcrack defect area in S2, the adjacent potential difference is measured, the resistivity distribution of the microcrack defect area is calculated, and the edge of the target microcrack defect area is obtained, specifically:

[0018] By measuring the potential difference between adjacent electrodes, the electrode and electrodes The potential difference between , injecting a steady current into the electrode , calculate the resistivity between adjacent electrodes , the formula is ,in is the electrode spacing, is the correction coefficient; when obtaining the edge of the target microcrack defect area by calculating the resistivity change rate, the resistivity change rate is defined as , the formula is: ,in is the resistivity between electrodes at adjacent positions, when Greater than the preset edge judgment threshold When the electrode is at the edge of the microcrack defect area, the edge contour of the target microcrack defect area is determined by traversing the resistivity change rate between all electrode pairs to form the target microcrack defect area.

[0019] Preferably, the target microcrack defect area is obtained and divided into sub-areas according to the resistivity change gradient of the defect area, specifically;

[0020] Calculate the points within the target microcrack defect area Resistivity gradient , the formula is: ,in and for and The resistivity change rate in the direction is: ,in and For and Small displacement in direction; setting gradient threshold , two adjacent points and satisfy When the target microcrack defect area is reached, it is divided into the same sub-area, and the sub-area division is completed by traversing all points in the target microcrack defect area.

[0021] Preferably, in S3, after scanning each divided sub-region and applying thermal excitation, the theoretical temperature distribution in the sub-region is obtained through the sub-region heat conduction model, and the infrared thermal imager is used to collect thermal images to obtain actual temperature data. The theoretical temperature data and the actual temperature data are matched by pixel points to form a temperature difference matrix, and the temperature difference matrix is used as the input of the deep learning model. Through the convolutional autoencoder and the addition of the attention mechanism module, the model automatically focuses on the area with significant temperature difference changes, and outputs the predicted temperature abnormality area.

[0022] Preferably, after obtaining the temperature anomaly area, the optimal scanning route is obtained with the shortest scanning time as the objective function, and the formula is: ,in is the total number of sub-regions, For the sub-regions to The moving time of each sub-area, For scanning route from Sub-area directly to the sub-regions, the scanning route traverses all sub-regions and each sub-region is only passed through once. The objective function is iteratively solved by genetic algorithm to obtain the optimal scanning route.

[0023] Preferably, the S4 neutron regional crack signal model outputs suspected microcrack points and marks the positions of the suspected microcrack points in real time, specifically:

[0024] Get in The received signal strength at the moment is , input the sub-region crack signal model to calculate the rate of change of the electrical signal , the formula is: ,in is the average electrical signal intensity in the crack-free area under normal circumstances, is the standard deviation of the electrical signal; the threshold value set ,when When there are suspected micro-crack points at the corresponding positions, the positions of the suspected micro-crack points are marked.

[0025] Preferably, the scanning of the suspected microcrack point positions, screening out non-microcrack points through an abnormal screening model, and determining the microcrack points is specifically as follows:

[0026] Obtain the modal change value of the microcrack point position signal , amplitude attenuation value and propagation time delay , construct the feature vector , screened by the abnormal screening model, the formula is: ,in is the Lagrange multiplier, is the sample label, is the kernel function, and the formula is: , is the standard deviation, is the bias term, and the multiple eigenvectors of each suspected microcrack point are obtained. , input the abnormal screening model for comparative screening, remove non-microcrack points, and determine the microcrack points.

[0027] Preferably, in S6, the overall structural information and microcrack point characteristics of the concrete cut-off wall are obtained, and the risk value of the microcracks outputted is calculated as follows: ,in is the volume of the concrete cut-off wall, is the Poisson's ratio of concrete, is the elastic modulus, is the microcrack area, is the depth of microcracks, is the vertical distance from the micro-crack point to the stress surface of the cut-off wall, It is the minimum horizontal distance from the micro-crack point to the wall edge.

[0028] Compared with the prior art, the technical solution of this application has the following technical effects:

[0029] The present invention comprehensively scans the concrete anti-seepage wall, calculates the difference between the received signal and the original transmitted signal, obtains the initial microcrack defect area through a pre-established microcrack signal model, arranges electrode layers in the area, calculates the resistivity distribution based on the potential difference, determines the edge of the target microcrack defect area, and through layer-by-layer screening and precise positioning of microcrack points, avoids the limitations of relying solely on surface observation or a single detection method, detects and analyzes microcracks from different angles, can accurately determine the position, size and depth of microcracks, improves the accuracy of microcrack defect detection, and provides a reliable basis for subsequent repair and maintenance work.

[0030] The present invention adopts a genetic algorithm to solve the optimal scanning route with the shortest scanning time as the objective function, which enables the detection equipment to quickly traverse each sub-area, reduce unnecessary movement time, and quickly scan and mark the suspected microcrack points along the optimal scanning route, and screen and determine the microcrack points. Through rapid scanning and analysis, the assessment of microcrack defects in large-area concrete anti-seepage walls can be completed in a short time, which greatly saves detection time and cost, improves the efficiency of engineering detection, and is conducive to the rapid advancement and timely maintenance of the project.

[0031] The present invention obtains the overall structural information of the concrete cut-off wall, including the volume of the wall, the Poisson's ratio of the concrete, the elastic modulus, etc., and combines the size, depth, and location characteristics of the determined microcrack points to construct a microcrack risk assessment model and output the risk value of the microcracks. Based on the specific conditions of the microcracks and the structural characteristics of the cut-off wall, the present invention can accurately assess the degree of influence of microcracks on the overall performance of the cut-off wall, and provide detailed risk information for project management personnel.

[0032] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application so that it can be implemented in accordance with the contents of the specification, and to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the following is a detailed description of the preferred embodiment of the present application in conjunction with the accompanying drawings.

[0033] Based on the detailed description of the specific embodiments of the present application in conjunction with the accompanying drawings below, those skilled in the art will become more aware of the above and other objects, advantages and features of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings required for the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without inventive work. In all drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0035] Figure 1 This is a flow chart of a method for rapid assessment of micro-crack defects in concrete anti-seepage walls according to the present invention;

[0036] Figure 2 Surface scan comparison diagram of the concrete cut-off wall area;

[0037] Figure 3 is the surface map of the initial microcrack defect area;

[0038] Figure 4 is the surface map of the target microcrack defect area;

[0039] Figure 5 This is the temperature anomaly map of the target microcrack defect sub-region A;

[0040] Figure 6 This is the crack classification and identification map of the target microcrack defect sub-region A. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. In the following description, specific details such as specific configurations and components are provided only to help fully understand the embodiments of the present application. Therefore, it should be clear to those skilled in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. In addition, for clarity and brevity, the description of known functions and structures has been omitted in the embodiments.

[0042] It should be understood that references throughout this specification to "one embodiment" or "this embodiment" mean that a particular feature, structure, or characteristic associated with the embodiment is included in at least one embodiment of the present application. Therefore, the appearance of "one embodiment" or "this embodiment" throughout this specification does not necessarily refer to the same embodiment. Furthermore, these particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0043] In addition, the present application may repeat reference numerals and / or letters in different examples. This repetition is for the purpose of simplicity and clarity and does not in itself indicate the relationship between the various embodiments and / or settings discussed.

[0044] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, B exists alone, and A and B exist at the same time. The term " / and" in this article describes another type of association object relationship, indicating that two relationships can exist. For example, A / and B can mean: A exists alone, and A and B exist alone. In addition, the character " / " in this article generally indicates that the previous and subsequent associated objects are in an "or" relationship.

[0045] The term "at least one" in this article is merely a description of the association relationship between associated objects, indicating that three relationships may exist. For example, at least one of A and B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0046] It should also be noted that, in this document, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include," "comprises," or any other variations thereof are intended to cover non-exclusive inclusion.

[0047] Example 1

[0048] This embodiment mainly describes a method for quickly assessing micro crack defects in concrete anti-seepage walls. Figure 1 Shown, including:

[0049] S1. Perform a comprehensive scan of the concrete anti-seepage wall to obtain a received signal, calculate the difference between the received signal and the original transmitted signal, input the pre-established micro-crack signal model, and obtain the initial micro-crack defect area on the concrete anti-seepage wall;

[0050] S2. Arranging an electrode layer on the surface of the initial microcrack defect area, measuring the potential difference between different electrodes, calculating the resistivity distribution of the microcrack defect area, obtaining the edge of the target microcrack defect area, forming a target microcrack defect area, and dividing the defect area into sub-areas according to the resistivity change gradient;

[0051] S3, applying thermal excitation to each divided sub-region, collecting thermal images of the sub-region, obtaining temperature anomalies in the sub-region, and obtaining the optimal scanning route through a genetic algorithm;

[0052] S4. Scan along the optimal scanning route to obtain sub-region optical signals, convert the optical signals into electrical signals, input the electrical signals into the sub-region crack signal model for monitoring, output suspected micro-crack points and mark the locations of the suspected micro-crack points in real time;

[0053] S5. Scan the suspected microcrack point location to obtain the modal change value, amplitude attenuation value, and propagation time delay of the signal, and use the signal processing algorithm to filter out non-microcrack points to determine the microcrack point;

[0054] S6. Obtain the overall structural information of the concrete cut-off wall, combine the size, depth, and location characteristics of the microcrack points, build a microcrack risk assessment model, and output the risk value of the microcracks.

[0055] Furthermore, in S1, a low-frequency ultrasonic wave is used to comprehensively scan the concrete anti-seepage wall, and the received signal and the original transmitted signal of the anti-seepage wall area are obtained, and the difference value is calculated. The formula is: ,in, is the original transmitted signal, To receive the signal, is the signal acquisition time, is the time delay, according to the minimum value value, get the time delay when the difference is the largest ,calculate The difference between the time , the formula is: ,Will The difference between the time Input pre-established microcrack signal model , obtain the initial microcrack defect area.

[0056] Furthermore, the pre-established microcrack signal model is constructed through a convolutional neural network, specifically:

[0057] For a large number of different microcrack conditions, the difference values and signal data Preprocess the difference Arranged into a two-dimensional matrix according to time series Input convolutional neural network for feature extraction, the formula is: ,in The output feature map of the first convolutional layer is The value of the position, It is The convolution kernel in the layer The weight of the position, It is a bias term. After multi-layer convolution and pooling operations, the signal features are extracted and the probability value of microcrack defects is output through the fully connected layer. , according to the pre-set threshold When judging, if , is the initial microcrack defect area.

[0058] Furthermore, a regular grid-like electrode layer is arranged on the surface of the initial microcrack defect area in S2. The electrodes are made of highly conductive and corrosion-resistant materials and are slender and cylindrical. They penetrate a certain depth into the concrete to achieve good contact with the internal medium. The electrodes are evenly spaced, with equal spacing between rows and columns, to avoid signal interference caused by overcrowding. They are vertically implanted into the concrete surface using drilling equipment and filled and fixed with an adhesive colloid, which enhances the connection stability between the electrodes and the concrete and prevents interference from external moisture and impurities, forming a criss-crossing grid-like electrode layer with a stable structure and reliable performance.

[0059] By constructing a grid-like electrode layer, the adjacent potential difference is measured, the resistivity distribution of the microcrack defect area is calculated, and the edge of the target microcrack defect area is obtained. Specifically:

[0060] By measuring the potential difference between adjacent electrodes, the electrode and electrodes The potential difference between , injecting a steady current into the electrode , calculate the resistivity between adjacent electrodes , the formula is ,in is the electrode spacing, is the correction coefficient; when obtaining the edge of the target microcrack defect area by calculating the resistivity change rate, the resistivity change rate is defined as , the formula is: ,in is the resistivity between electrodes at adjacent positions, when Greater than the preset edge judgment threshold When the electrode is at the edge of the microcrack defect area, the edge contour of the target microcrack defect area is determined by traversing the resistivity change rate between all electrode pairs to form the target microcrack defect area.

[0061] Further, the target microcrack defect area is obtained and divided into sub-areas according to the resistivity change gradient of the defect area, specifically;

[0062] Calculate the points within the target microcrack defect area Resistivity gradient , the formula is: ,in and for and The resistivity change rate in the direction is: ,in and For and Small displacement in direction; setting gradient threshold , two adjacent points and satisfy When the target microcrack defect area is reached, it is divided into the same sub-area, and the sub-area division is completed by traversing all points in the target microcrack defect area.

[0063] Furthermore, in S3, after scanning each divided sub-region and applying thermal excitation, the theoretical temperature distribution in the sub-region is obtained through the sub-region heat conduction model, and the infrared thermal imager is used to collect thermal images to obtain actual temperature data. The theoretical temperature data and the actual temperature data are matched pixel by pixel to form a temperature difference matrix. The temperature difference matrix is used as the input of the deep learning model. Through the convolutional autoencoder and the addition of the attention mechanism module, it automatically focuses on the area with significant temperature difference changes and outputs the predicted temperature abnormality area.

[0064] Furthermore, after obtaining the temperature anomaly area, the optimal scanning route is obtained with the shortest scanning time as the objective function. The formula is: ,in is the total number of sub-regions, For the sub-regions to The moving time of each sub-area, For scanning route from Sub-area directly to the sub-regions, the scanning route traverses all sub-regions and each sub-region is only passed through once. The objective function is iteratively solved by genetic algorithm to obtain the optimal scanning route.

[0065] Furthermore, the S4 neutron regional crack signal model outputs suspected microcrack points and annotates the locations of suspected microcrack points in real time, specifically:

[0066] Get in The received signal strength at the moment is , input the sub-region crack signal model to calculate the rate of change of the electrical signal , the formula is: ,in is the average electrical signal intensity in the crack-free area under normal circumstances, is the standard deviation of the electrical signal; the threshold value set ,when When there are suspected micro-crack points at the corresponding positions, the positions of the suspected micro-crack points are marked.

[0067] Furthermore, the suspected microcrack points are scanned, and non-microcrack points are screened out through the abnormal screening model to determine the microcrack points. Specifically:

[0068] Obtain the modal change value of the microcrack point position signal , amplitude attenuation value and propagation time delay , construct the feature vector , screened by the abnormal screening model, the formula is: ,in is the Lagrange multiplier, is the sample label, is the kernel function, and the formula is: , is the standard deviation, is the bias term, and the multiple eigenvectors of each suspected microcrack point are obtained. , input the abnormal screening model for comparative screening, remove non-microcrack points, and determine the microcrack points.

[0069] Furthermore, in S6, the overall structural information of the concrete cut-off wall is obtained, including the geometric parameters and physical and mechanical parameters of the concrete cut-off wall; the geometric parameters include the length, height and thickness of the cut-off wall; the physical and mechanical parameters include the elastic modulus and Poisson's ratio; the microcrack points are determined and detailed characteristic information is obtained, including size, depth and location characteristics; the risk value of the microcracks is output based on the obtained overall structural information of the concrete cut-off wall and the characteristic information of the microcrack points, and the formula is: ,in is the volume of the concrete cut-off wall, is the Poisson's ratio of concrete, is the elastic modulus, is the microcrack area, is the depth of microcracks, is the vertical distance from the micro-crack point to the stress surface of the cut-off wall, It is the minimum horizontal distance from the micro-crack point to the wall edge.

[0070] This embodiment describes in detail how to accurately locate microcracks by integrating multiple detection technologies. Microcracks are quickly identified by establishing a signal model, measuring resistivity, and performing thermal imaging scanning. Scanning routes are planned using an optimization algorithm, greatly improving detection efficiency. The constructed risk assessment model can comprehensively assess microcrack risks, provide a scientific basis for maintenance decisions, improve detection accuracy and efficiency, and ensure the safe and stable operation of concrete cut-off walls.

[0071] Based on Example 1, this example describes in detail the implementation process and technical effects of the present application, specifically:

[0072] The concrete anti-seepage wall of a reservoir was selected as the experimental object. The anti-seepage wall has been in service for several years. After preliminary investigation, there are many potential micro-crack areas. The anti-seepage wall is scanned in all directions, and ultrasonic signals are emitted into the interior of the anti-seepage wall. The signals propagate in the concrete medium in the form of fluctuations, and the reflected received signals are obtained. The received signals are compared with the original signals without defects. From the amplitude point of view, if there are micro-cracks, the amplitude of the received signals will be significantly weakened compared with the original signals due to energy loss during the signal propagation process; in terms of frequency, the uneven propagation medium caused by micro-cracks will cause the frequency of the received signals to shift; and in terms of phase, due to the change in the signal propagation path, the phase of the received signal will also differ from the original signal, and the initial micro-crack defect area is obtained, such as Figure 2-3 As shown;

[0073] Electrode layer arrangement was performed on the surface of the initial microcrack defect area. An electrode array with a spacing of 0.2 meters was arranged on the surface of the initial microcrack defect area. 26 electrodes (including boundary electrodes) were arranged horizontally and 16 electrodes (including boundary electrodes) were arranged vertically, forming a total of 25 × 15 electrode pairs for measurement.

[0074] The potential difference between different electrodes was measured, and the potential difference value was 0.012mV; the potential difference between adjacent electrode pairs in the longitudinal direction was 0.015mV. Combined with the electrode spacing, the area corresponding to each electrode pair was regarded as a small unit. Based on the measured potential difference and electrode spacing information, the resistivity of the small unit was calculated to obtain the resistivity distribution of the initial microcrack defect area. Based on the calculated resistivity distribution, the edge of the target microcrack defect area was obtained. Since the presence of microcracks will cause the resistivity around them to change, the boundary position where the resistivity change is obvious was determined by analyzing the change trend of the resistivity data. According to the resistivity change gradient of the defect area, it was divided into sub-areas, namely sub-area A and sub-area B, as shown in the figure. Figure 4 shown.

[0075] Taking sub-region A as an example, thermal excitation is applied to uniformly heat the surface of sub-region A, so that the temperature of sub-region A increases as a whole. A high-resolution thermal imager is used to collect the thermal image of sub-region A, as shown in FIG. Figure 5 As shown in the figure, five temperature anomaly points were found in the thermal image of sub-area A. The temperatures of anomaly points 1, 2, 3, 4, and 5 were 25.5°C, 27.2°C, 26.3°C, 31.2°C, and 30.8°C, respectively, while the average temperature of the surrounding pixels was 19.2°C, exceeding the set threshold.

[0076] A genetic algorithm was used to obtain the optimal scanning route for the five temperature anomaly points. Sub-area A was divided into 25 equidistant small squares, with each small square regarded as a search node. The goal was to traverse all temperature anomaly points with the shortest total distance. The genetic algorithm was used for multiple iterative calculations. After 15 iterations, the optimal scanning route was obtained. Following the optimal scanning route of sub-area A obtained by the genetic algorithm, this route covered the three temperature anomaly points in sub-area A. During the scanning process, optical signal acquisition equipment was used to collect optical signals every 1 cm along the route. These optical signals were converted one by one into electrical signals through a high-precision photoelectric conversion device. Each group of optical signals was converted into an electrical signal with a specific voltage value. These electrical signals were input into the pre-established sub-area crack signal model for monitoring, accurately identifying the signal characteristics related to microcracks and marking the locations of suspected microcrack points A1-A9.

[0077] Scan the suspected microcrack points A1-A9, such as Figure 6 As shown in the figure, irregular cracks in the internal aggregate and cement paste distribution were screened out, and bifurcated cracks and unidirectional cracks were obtained, and microcrack points A1, A3-A5, A7, and A8 were obtained. Based on the overall structural information of the concrete cut-off wall, combined with the size, depth, and location characteristics of the microcrack points A1, A3-A5, A7, and A8, the microcrack risk assessment model was used to output the risk value of the microcracks, as shown in the following table:

[0078] Microcrack point number Size (length × width, mm) Depth (m) Location characteristics (horizontal distance from the edge of the cut-off wall / m, vertical distance from the main load-bearing surface / m) Value at Risk A1 2.5×0.04 0.18 （3.26，0.31） 0.52 A3 1.8×0.03 0.12 （3.45，0.25） 0.43 A4 2.1×0.035 0.15 （3.16，0.28） 0.48 A5 1.6×0.025 0.1 （3.28，0.22） 0.38 A7 2.3×0.04 0.16 （3.45，0.32） 0.50 A8 1.9×0.03 0.13 （3.48，0.26） 0.45

[0079] According to the risk values output by the microcrack risk assessment model, the microcrack points A1, A3-A5, A7, and A8 are ranked from high to low: A1 (risk value 0.52), A7 (risk value 0.5), A4 (risk value 0.48), A8 (risk value 0.45), A3 (risk value 0.43), and A5 (risk value 0.38). Given that the higher the risk value, the greater the potential threat of microcracks to the structural safety and anti-seepage performance of the concrete cut-off wall, the A1 microcrack point is addressed first, and targeted repair measures such as pressure grouting and surface sealing are taken to prevent its further development and affect the overall performance of the cut-off wall; then the A7 microcrack point is addressed; and so on, until all microcrack points are treated to ensure the safe and stable operation of the concrete cut-off wall.

[0080] This embodiment achieves efficient detection and classification of microcracks through specific implementation methods, quickly screens out non-crack interference, accurately identifies bifurcated and unidirectional cracks, and can also scientifically sort them according to risk values, giving priority to high-risk cracks, greatly improving the efficiency of anti-seepage wall disease treatment and engineering safety.

[0081] The above are only preferred embodiments of the present invention, which do not limit the scope of protection of the present invention. For those skilled in the art, the present invention can be modified and varied in various ways. Any changes, modifications, replacements, integrations and parameter changes to these embodiments through conventional substitutions or that can achieve the same functions without departing from the principles and spirit of the present invention fall within the scope of protection of the present invention.

Claims

1. A method for rapid assessment of micro-crack defects in concrete anti-seepage walls, characterized in that: include: S1. Perform a comprehensive scan of the concrete anti-seepage wall to obtain a received signal, calculate the difference between the received signal and the original transmitted signal, input the pre-established micro-crack signal model, and obtain the initial micro-crack defect area on the concrete anti-seepage wall; S2. Arranging an electrode layer on the surface of the initial microcrack defect area, measuring the potential difference between different electrodes, calculating the resistivity distribution of the microcrack defect area, obtaining the edge of the target microcrack defect area, forming a target microcrack defect area, and dividing the defect area into sub-areas according to the resistivity change gradient; S3, applying thermal excitation to each divided sub-region, collecting thermal images of the sub-region, obtaining temperature anomalies in the sub-region, and obtaining the optimal scanning route through a genetic algorithm; S4. Scan along the optimal scanning route to obtain sub-region optical signals, convert the optical signals into electrical signals, input the electrical signals into the sub-region crack signal model for monitoring, output suspected micro-crack points and mark the locations of the suspected micro-crack points in real time; S5. Scan the suspected microcrack point location to obtain the modal change value, amplitude attenuation value, and propagation time delay of the signal, and use the signal processing algorithm to filter out non-microcrack points to determine the microcrack point; S6. Obtain the overall structural information of the concrete cut-off wall, combine the size, depth, and location characteristics of the microcrack points, build a microcrack risk assessment model, and output the risk value of the microcracks.

2. A method for rapid assessment of microcrack defects in concrete cut-off walls according to claim 1, characterized in that: In S1, the received signal and the original transmitted signal of the anti-seepage wall area are obtained and the difference value is calculated. The formula is: ,in, is the original transmitted signal, To receive the signal, is the signal acquisition time, is the time delay, according to the minimum value value, get the time delay when the difference is the largest ,calculate The difference between the time , the formula is: ,Will The difference between the time Input pre-established microcrack signal model , obtain the initial microcrack defect area.

3. A method for rapid assessment of microcrack defects in concrete cut-off walls according to claim 2, characterized in that: The pre-established microcrack signal model is constructed through a convolutional neural network, specifically: For a large number of different microcrack conditions, the difference values and signal data Preprocess the difference Arranged into a two-dimensional matrix according to time series Input convolutional neural network for feature extraction, the formula is: ,in The output feature map of the first convolutional layer is The value of the position, It is The convolution kernel in the layer The weight of the position, It is a bias term. After multi-layer convolution and pooling operations, the signal features are extracted and the probability value of microcrack defects is output through the fully connected layer. , according to the pre-set threshold When judging, if , is the initial microcrack defect area.

4. A method for rapid assessment of microcrack defects in concrete cut-off walls according to claim 1, characterized in that: In the S2, a regular grid-like electrode layer is arranged on the surface of the initial microcrack defect area, and the adjacent potential difference is measured to calculate the resistivity distribution of the microcrack defect area and obtain the edge of the target microcrack defect area, specifically: By measuring the potential difference between adjacent electrodes, the electrode and electrodes The potential difference between , injecting a steady current into the electrode , calculate the resistivity between adjacent electrodes , the formula is ,in is the electrode spacing, is the correction coefficient; when obtaining the edge of the target microcrack defect area by calculating the resistivity change rate, the resistivity change rate is defined as , the formula is: ,in is the resistivity between electrodes at adjacent positions, when Greater than the preset edge judgment threshold When the electrode is at the edge of the microcrack defect area, the edge contour of the target microcrack defect area is determined by traversing the resistivity change rate between all electrode pairs to form the target microcrack defect area.

5. A method for rapid assessment of micro-crack defects in concrete cut-off walls according to claim 4, characterized in that: The target microcrack defect area is obtained and divided into sub-areas according to the resistivity change gradient of the defect area, specifically; Calculate the points within the target microcrack defect area Resistivity gradient , the formula is: ,in and for and The resistivity change rate in the direction is: ,in and For and Small displacement in direction; setting gradient threshold , two adjacent points and satisfy When the target microcrack defect area is reached, it is divided into the same sub-area, and the sub-area division is completed by traversing all points in the target microcrack defect area.

6. A method for rapid assessment of microcrack defects in concrete cut-off walls according to claim 1, characterized in that: In the above S3, after scanning each divided sub-region and applying thermal excitation, the theoretical temperature distribution in the sub-region is obtained through the sub-region heat conduction model, and the actual temperature data is obtained by collecting thermal images using an infrared thermal imager. The theoretical temperature data and the actual temperature data are matched on a pixel basis to form a temperature difference matrix. The temperature difference matrix is used as the input of the deep learning model. Through the convolutional autoencoder and the addition of the attention mechanism module, the model automatically focuses on the area with significant temperature difference changes and outputs the predicted temperature abnormality area.

7. A method for rapid assessment of microcrack defects in concrete cut-off walls according to claim 1, characterized in that: After obtaining the temperature anomaly area, the optimal scanning route is obtained with the shortest scanning time as the objective function. The formula is: ,in is the total number of sub-regions, For the sub-regions to The moving time of each sub-area, For scanning route from Sub-area directly to the sub-regions, the scanning route traverses all sub-regions and each sub-region is only passed through once. The objective function is iteratively solved by genetic algorithm to obtain the optimal scanning route.

8. A method for rapid assessment of micro-crack defects in concrete cut-off walls according to claim 1, characterized in that: The S4 neutron regional crack signal model outputs suspected microcrack points and marks the locations of the suspected microcrack points in real time, specifically: Get in The received signal strength at that moment is , input the sub-region crack signal model to calculate the rate of change of the electrical signal , the formula is: ,in is the average electrical signal intensity in the crack-free area under normal circumstances, is the standard deviation of the electrical signal; the threshold value set ,when When there are suspected micro-crack points at the corresponding positions, the positions of the suspected micro-crack points are marked.

9. A method for rapid assessment of microcrack defects in concrete cut-off walls according to claim 1, characterized in that: The suspected microcrack points are scanned, non-microcrack points are screened out using an abnormal screening model, and microcrack points are determined, specifically: Obtain the modal change value of the microcrack point position signal , amplitude attenuation value and propagation time delay , construct the feature vector , screened by the abnormal screening model, the formula is: ,in is the Lagrange multiplier, is the sample label, is the kernel function, and the formula is: , is the standard deviation, is the bias term, and the multiple eigenvectors of each suspected microcrack point are obtained , input the abnormal screening model for comparative screening, remove non-microcrack points, and determine the microcrack points.

10. A method for rapid assessment of micro-crack defects in concrete cut-off walls according to claim 1, characterized in that: In S6, the overall structural information of the concrete cut-off wall and the characteristics of the micro-crack points are obtained, and the risk value of the micro-cracks is outputted, and the formula is: ,in is the volume of the concrete cut-off wall, is the Poisson's ratio of concrete, is the elastic modulus, is the microcrack area, is the depth of microcracks, is the vertical distance from the micro-crack point to the stress surface of the cut-off wall, It is the minimum horizontal distance from the micro-crack point to the wall edge.

Images