Dam void detection method, device, equipment, medium and program product

Abstract

The invention relates to the technical field of water conservancy energy, in particular to a dam void detection method, device and equipment, a medium and a program product.The method comprises the steps that attribute data of a dam medium to be detected are collected to correspond to working parameters of scanning equipment; based on the attribute data and the working parameters, identifying void data of the dam to be tested and a corresponding risk level; and predicting predicted void data of the to-be-detected dam void and the corresponding predicted risk level by using a pre-constructed void trend prediction model. Therefore, the problems of large positioning deviation and inaccurate thickness data of the void area caused by the fact that the geological radar is easily influenced by uneven dam body media and complex structure in the related technology are solved; the impact echo method is difficult to realize full-coverage detection, has a blind area and cannot comprehensively master void distribution. Meanwhile, the problems that a multi-source data fusion mechanism is lacked, an accurate three-dimensional void map is difficult to generate, risk changes cannot be evaluated, and the repair opportunity is likely to be missed are solved.

Description

Technical Field

[0001] This application relates to the field of water conservancy and energy technology, and in particular to a method, apparatus, equipment, medium and procedure for detecting dam delamination. Background Technology

[0002] As dams age, they are susceptible to voids due to various factors, including changes in geological conditions, long-term water erosion, temperature stress cycles, and concrete aging. These voids are cavities or fissures formed between the dam body and the foundation rock or between different structural layers. If these voids are not detected and addressed promptly, they can lead to uneven stress distribution within the dam body, accelerate the formation of seepage channels, and in severe cases, cause partial dam collapse and a dramatic increase in leakage.

[0003] Among related technologies, ground-penetrating radar (GPR) can be used to scan the entire dam area. GPR transmits high-frequency electromagnetic waves into the ground through a transmitting antenna. When the electromagnetic waves encounter the interface between different electrical media during propagation, they are reflected, refracted, and absorbed. The radar profile is then generated based on the received reflected electromagnetic wave signals, thereby inferring the location, shape, and properties of underground targets. Alternatively, based on the propagation and reflection characteristics of stress waves inside concrete, low-frequency stress waves can be generated through mechanical impact. Sensors can be used to receive the reflected signals, and spectrum analysis can be performed to determine the thickness of the dam structure or the location of defects.

[0004] However, among related technologies, ground-penetrating radar is easily affected by the non-uniformity of the electrical conductivity and dielectric constant of the dam body and the complexity of the structure, which can lead to large deviations in the location of suspected voids and make it impossible to accurately obtain void thickness data. The impact echo method cannot cover the entire dam area, has blind spots, and cannot fully grasp the distribution of voids. In addition, due to the lack of an effective multi-source detection data fusion mechanism, it is difficult to generate accurate three-dimensional visualization void maps through data correction and integration, making it impossible to assess the direction of void expansion and changes in risk level, and easily missing the best repair opportunity. Improvements are urgently needed. Summary of the Invention

[0005] This application provides a method, apparatus, equipment, medium, and program product for detecting dam voids, to address the problems in related technologies, such as the susceptibility of ground-penetrating radar to the unevenness of the dam body medium and the complexity of the structure, leading to large positioning deviations and inaccurate thickness data of void areas; the inability of impact echo detection to achieve full coverage, resulting in blind spots and an inability to comprehensively grasp the distribution of voids; and the lack of a multi-source data fusion mechanism, making it difficult to generate accurate three-dimensional void maps, assess risk changes, and easily miss the opportunity for repair.

[0006] The first aspect of this application provides a method for detecting dam caving, comprising the following steps: collecting attribute data of the medium of the dam to be tested, and determining at least one operating parameter of the scanning device corresponding to the dam to be tested based on the attribute data; identifying caving data of the dam to be tested and the risk level corresponding to the caving data based on the attribute data and the at least one operating parameter; inputting the caving data and the risk level into a pre-constructed caving trend prediction model to predict the predicted caving data of the dam to be tested and the predicted risk level corresponding to the predicted caving data.

[0007] The above technical solution allows for the determination of the corresponding scanning equipment's operating parameters based on the property data of the dam's medium. This enables the identification of voiding data and corresponding risk levels within the dam. A pre-built voiding trend prediction model then predicts the predicted voiding data and corresponding risk levels. The scanning equipment's operating parameters are adaptively adjusted based on the dam's medium property data, and multi-source data fusion correction eliminates system biases, accurately presenting the voiding location, depth, and size. This provides a reliable data foundation for risk assessment. Furthermore, it visually displays the voiding distribution and risk levels, preventing misjudgments by maintenance personnel due to information ambiguity. This promotes a shift towards proactive prevention in safety management, allowing for early prediction of voiding development and risk changes. This facilitates seizing the optimal repair opportunity, reducing manual decision-making costs and repetitive testing, significantly lowering maintenance expenses, improving management efficiency, and ensuring the long-term safety of the dam. This comprehensive approach effectively delays dam aging, prevents safety accidents, and provides both economic and social benefits.

[0008] Optionally, in one embodiment of this application, identifying the de-cavitation data of the dam under test and the risk level corresponding to the de-cavitation data based on the attribute data and the at least one operating parameter includes: determining the de-cavitation region of the dam under test and the initial de-cavitation data of the de-cavitation region based on the attribute data, the at least one operating parameter, and the dam under test; obtaining the corresponding de-cavitation thickness data based on the de-cavitation region; determining the de-cavitation data based on the initial de-cavitation data and the de-cavitation thickness data; and identifying the risk level based on the de-cavitation data.

[0009] The above technical solution can first determine the voiding area and initial voiding data of the dam under test based on attribute data and working parameters, then obtain the voiding thickness data of the corresponding voiding area, thereby determining the final voiding data and identifying the corresponding risk level. The voiding problem can be handled in stages and in a refined manner, which can overcome the limitations of a single detection method and improve the positioning accuracy and the reliability of risk assessment through layered processing, providing a data-driven scientific basis for subsequent repair decisions.

[0010] Optionally, in one embodiment of this application, before inputting the de-caking data and the risk level into a pre-constructed de-caking trend prediction model, the method further includes: obtaining historical de-caking data of the target dam to determine at least one operating parameter of the target dam; determining the operating weight corresponding to the at least one operating parameter based on the historical de-caking data; and constructing the de-caking trend prediction model based on the historical de-caking data, the at least one operating parameter, and the operating weight.

[0011] The above technical solution allows for the determination of the target dam's operating parameters and corresponding operating weights based on its historical detachment data before utilizing the detachment trend prediction model. This enables the construction of a corresponding detachment trend prediction model. Data-driven, precise modeling avoids the limitations of relying solely on theoretical assumptions or short-term testing. Dynamic weight optimization prevents static models from becoming rigid, adapts to complex operating conditions, and improves predictive adaptability.

[0012] Optionally, in one embodiment of this application, identifying the vacancy data of the dam under test and the risk level corresponding to the vacancy data includes: obtaining a structural threshold for the dam under test to meet preset working conditions; determining the current structural value of the dam under test in the current state based on the vacancy data; and identifying the risk level based on the structural threshold and the current structural value.

[0013] The above technical solution can first determine the structural threshold of the dam under certain preset working conditions, and then, based on the current structural value and structural threshold of the dam under the current state, identify the risk level, dynamically adapt the threshold, avoid the misjudgment of static threshold with a "one-size-fits-all" approach, improve the accuracy of the assessment, quantify the current state, realize dynamic risk tracking, and reduce the subjectivity of human judgment by establishing objective and reproducible risk level classification rules, thereby enhancing the applicability and reliability of the project.

[0014] Optionally, in one embodiment of this application, the method further includes: generating at least one maintenance instruction for the dam under test based on the predicted vacancy data and the predicted risk level; and maintaining the dam under test according to the at least one maintenance instruction to ensure that the dam under test meets preset stability conditions.

[0015] The above technical solution can generate corresponding maintenance instructions based on the predicted caving data and the predicted risk level, thereby maintaining the dam under test to meet certain stability conditions. It transforms the predicted caving data and risk level into specific maintenance instructions, avoiding the disconnect between risk information and maintenance measures, forming a feasible engineering solution. It can automatically adapt to risk evolution, avoid over-maintenance or delayed repair, achieve precise resource allocation, balance cost and benefit, and meet the usage needs of different scenarios.

[0016] A second aspect of this application provides a dam caving detection device, comprising: a first determining module, configured to collect attribute data of the medium of the dam to be tested, and determine at least one operating parameter of a scanning device corresponding to the dam to be tested based on the attribute data; an identification module, configured to identify caving data of the dam to be tested and the risk level corresponding to the caving data based on the attribute data and the at least one operating parameter; and a prediction module, configured to input the caving data and the risk level into a pre-constructed caving trend prediction model to predict predicted caving data of the dam to be tested and the predicted risk level corresponding to the predicted caving data.

[0017] The above technical solution allows for the determination of the corresponding scanning equipment's operating parameters based on the property data of the dam's medium. This enables the identification of voiding data and corresponding risk levels within the dam. A pre-built voiding trend prediction model then predicts the predicted voiding data and corresponding risk levels. The scanning equipment's operating parameters are adaptively adjusted based on the dam's medium property data, and multi-source data fusion correction eliminates system biases, accurately presenting the voiding location, depth, and size. This provides a reliable data foundation for risk assessment. Furthermore, it visually displays the voiding distribution and risk levels, preventing misjudgments by maintenance personnel due to information ambiguity. This promotes a shift towards proactive prevention in safety management, allowing for early prediction of voiding development and risk changes. This facilitates seizing the optimal repair opportunity, reducing manual decision-making costs and repetitive testing, significantly lowering maintenance expenses, improving management efficiency, and ensuring the long-term safety of the dam. This comprehensive approach effectively delays dam aging, prevents safety accidents, and provides both economic and social benefits.

[0018] Optionally, in one embodiment of this application, the identification module includes: a first determining unit, configured to determine the voided area of ​​the dam under test and the initial voided data of the voided area based on the attribute data, the at least one working parameter, and the dam under test; a first acquiring unit, configured to acquire corresponding voided thickness data based on the voided area; a second determining unit, configured to determine the voided data based on the initial voided data and the voided thickness data; and a first identifying unit, configured to identify the risk level based on the voided data.

[0019] The above technical solution can first determine the voiding area and initial voiding data of the dam under test based on attribute data and working parameters, then obtain the voiding thickness data of the corresponding voiding area, thereby determining the final voiding data and identifying the corresponding risk level. The voiding problem can be handled in stages and in a refined manner, which can overcome the limitations of a single detection method and improve the positioning accuracy and the reliability of risk assessment through layered processing, providing a data-driven scientific basis for subsequent repair decisions.

[0020] Optionally, in one embodiment of this application, it further includes: an acquisition module, configured to acquire historical detachment data of the target dam before inputting the detachment data and the risk level into a pre-constructed detachment trend prediction model, so as to determine at least one operating parameter of the target dam; a second determination module, configured to determine the operating weight corresponding to the at least one operating parameter based on the historical detachment data; and a construction module, configured to construct the detachment trend prediction model based on the historical detachment data, the at least one operating parameter, and the operating weight.

[0021] The above technical solution allows for the determination of the target dam's operating parameters and corresponding operating weights based on its historical detachment data before utilizing the detachment trend prediction model. This enables the construction of a corresponding detachment trend prediction model. Data-driven, precise modeling avoids the limitations of relying solely on theoretical assumptions or short-term testing. Dynamic weight optimization prevents static models from becoming rigid, adapts to complex operating conditions, and improves predictive adaptability.

[0022] Optionally, in one embodiment of this application, the identification module includes: a second acquisition unit, configured to acquire a structural threshold value of the dam under test that meets preset working conditions; a third determination unit, configured to determine the current structural value of the dam under test in the current state based on the data removed from the test; and a second identification unit, configured to identify the risk level based on the structural threshold value and the current structural value.

[0023] The above technical solution can first determine the structural threshold of the dam under certain preset working conditions, and then, based on the current structural value and structural threshold of the dam under the current state, identify the risk level, dynamically adapt the threshold, avoid the misjudgment of static threshold with a "one-size-fits-all" approach, improve the accuracy of the assessment, quantify the current state, realize dynamic risk tracking, and reduce the subjectivity of human judgment by establishing objective and reproducible risk level classification rules, thereby enhancing the applicability and reliability of the project.

[0024] Optionally, in one embodiment of this application, it further includes: a generation module, configured to generate at least one maintenance instruction for the dam under test based on the predicted off-target data and the predicted risk level; and a maintenance module, configured to maintain the dam under test according to the at least one maintenance instruction, so that the dam under test meets preset stability conditions.

[0025] The above technical solution can generate corresponding maintenance instructions based on the predicted caving data and the predicted risk level, thereby maintaining the dam under test to meet certain stability conditions. It transforms the predicted caving data and risk level into specific maintenance instructions, avoiding the disconnect between risk information and maintenance measures, forming a feasible engineering solution. It can automatically adapt to risk evolution, avoid over-maintenance or delayed repair, achieve precise resource allocation, balance cost and benefit, and meet the usage needs of different scenarios.

[0026] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the dam delamination detection method as described in the above embodiments.

[0027] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for detecting dam delamination.

[0028] A fifth aspect of this application provides a computer program product, including a computer program that, when executed, implements the above-described method for detecting dam delamination.

[0029] This application embodiment can determine the operating parameters of the corresponding scanning equipment based on the property data of the medium under test of the dam, thereby identifying the voiding data and corresponding risk level of the dam under test. It also utilizes a pre-built voiding trend prediction model to predict the predicted voiding data and corresponding predicted risk level of the dam under test. Combined with the dam medium property data, the operating parameters of the scanning equipment are adaptively adjusted, and multi-source data fusion correction is used to eliminate system biases and accurately present the voiding location, depth, and size, laying a reliable data foundation for risk assessment. Furthermore, it intuitively displays the voiding distribution and risk level, avoiding misjudgments by maintenance personnel due to ambiguous information, promoting the transformation of safety management towards proactive prevention, predicting the development direction and risk changes of voiding in advance, facilitating the grasp of the best repair opportunity, reducing manual decision-making costs and repeated testing, significantly reducing maintenance expenses, improving management efficiency, ensuring the long-term safety of the dam, and possessing comprehensive value. It effectively delays dam aging, avoids safety accidents, and has both economic and social benefits. This addresses several issues in related technologies, including the susceptibility of ground-penetrating radar to uneven dam media and complex structures, leading to large positioning errors and inaccurate thickness data in the vacuolated areas; the limitations of impact-echo methods in achieving full coverage detection with blind spots, making it impossible to comprehensively understand the distribution of vacuoles; and the lack of a multi-source data fusion mechanism, which hinders the generation of accurate three-dimensional vacuolation maps, makes it impossible to assess risk changes, and easily leads to missed opportunities for repair.

[0030] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0031] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart of a method for detecting dam cavitation according to an embodiment of this application; Figure 2 A flowchart illustrating the working principle of a dam caving detection method according to an embodiment of this application; Figure 3 This is a block diagram of a dam cavitation detection device provided according to an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application.

[0032] Figure label: Among them, 10-dam cavitation detection device; 100-first determination module, 200-identification module, 300-prediction module; 401-memory, 402-processor, 403-communication interface. Detailed Implementation

[0033] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0034] The following description, with reference to the accompanying drawings, outlines a method, apparatus, equipment, medium, and program product for detecting dam voids according to embodiments of this application. As mentioned in the background art, ground-penetrating radar is susceptible to the unevenness of the dam's medium and the complexity of its structure, leading to large positioning deviations and inaccurate thickness data in void areas; the impact-echo method is difficult to achieve full coverage detection, has blind spots, and cannot comprehensively grasp the distribution of voids. Meanwhile, the lack of a multi-source data fusion mechanism makes it difficult to generate accurate three-dimensional void maps, assess risk changes, and easily miss repair opportunities. This application provides a method for detecting dam voids. In this method, the operating parameters of the corresponding scanning equipment can be determined based on the property data of the medium of the dam under test, thereby identifying the void data and corresponding risk level of the dam under test. A pre-built void trend prediction model is used to predict the predicted void data and corresponding predicted risk level of the dam under test. The operating parameters of the scanning equipment are adaptively adjusted in combination with the dam medium property data. With multi-source data fusion correction, system bias is eliminated, and the location, depth, and size of the void are accurately presented, laying a reliable data foundation for risk assessment. In addition, the distribution and risk level of voids are displayed intuitively, avoiding misjudgments by maintenance personnel due to information ambiguity. This promotes the transformation of safety management towards proactive prevention, predicts the development direction and risk changes of voids in advance, helps to grasp the best repair time, reduces manual decision-making costs and repeated testing, significantly reduces maintenance expenses, improves management efficiency, and ensures the long-term safety of the dam. It has comprehensive value, effectively delays dam aging, avoids safety accidents, and has both economic and social benefits. This addresses several issues in related technologies, including the susceptibility of ground-penetrating radar to uneven dam media and complex structures, leading to large positioning errors and inaccurate thickness data in the vacuolated areas; the limitations of impact-echo methods in achieving full coverage detection with blind spots, making it impossible to comprehensively understand the distribution of vacuoles; and the lack of a multi-source data fusion mechanism, which hinders the generation of accurate three-dimensional vacuolation maps, makes it impossible to assess risk changes, and easily leads to missed opportunities for repair.

[0035] Specifically, Figure 1 This is a flowchart of a method for detecting dam cavitation according to an embodiment of this application.

[0036] like Figure 1 As shown, the detection method for dam caving includes the following steps: In step S101, the property data of the medium of the dam to be tested is collected, and at least one operating parameter of the scanning device corresponding to the dam to be tested is determined based on the property data.

[0037] It is understood that, in the embodiments of this application, the attribute data may include, but is not limited to, conductivity data, and its measurement range can be... The following parameters are not specifically limited in this application: S / m, dielectric constant, etc., the measurement range can be 1-10, etc., and this application does not impose specific limitations; non-uniformity data, the measurement accuracy can be ±5%, etc., and this application does not impose specific limitations; complexity data, such as the coefficient of variation of dielectric composition, etc., can be specifically set by those skilled in the art according to the actual situation, and this application does not impose specific limitations.

[0038] Additionally, it should be noted that the scanning equipment in this application embodiment can be ground-penetrating radar, ultrasonic defect detector, laser scanner, etc., and this application does not impose any specific limitations.

[0039] Furthermore, the embodiments of this application can determine the operating parameters of the ground-penetrating radar, such as the transmission frequency band, power, sampling rate, and scanning speed; the operating parameters of the ultrasonic defect detector, such as the excitation frequency, spacing, and acquisition rate; and the operating parameters of the laser scanner, such as the accuracy, ranging range, and speed. This application does not impose specific limitations on these parameters.

[0040] For example, in the embodiments of this application, the range of the transmission frequency band of the ground-penetrating radar can be adjusted from 100MHz to 2GHz, the range of the power can be adjusted from 10 to 50W, and the range of the sampling rate can be adjusted from 100MS / s to 1GS / s. This application does not impose any specific limitations.

[0041] In some embodiments, the present application can first collect property data of the medium of the dam to be tested, such as conductivity data, dielectric constant data, non-uniformity data and complexity data, and then adjust the working parameters of the scanning equipment, such as the transmission frequency band, power, sampling rate and scanning speed of the ground-penetrating radar, according to different property data, so as to realize the full-area scanning of the dam to be tested and determine the corresponding void area and void thickness data.

[0042] This can be understood as meaning that the embodiments of this application can dynamically adjust the working parameters of the scanning equipment according to the medium property data of the dam to be tested.

[0043] For example, in some embodiments, the embodiments of this application can delineate the entire detection range based on the structural drawings of the dam of the hydropower unit to be tested (such as dam thickness, concrete strength grade markings, etc., which are not specifically limited in this application), prioritizing coverage of areas with frequent water scouring and areas prone to voiding such as dam joints. Simultaneously, the detection system is debugged to ensure that the conductivity sensor for measuring medium properties (range) is properly configured. The S / m and dielectric constant testers (range 1-10) were calibrated to the error range. The probe positioning unit for ground-penetrating radar detection (transmitting frequency band 100MHz-2GHz) and shock echo detection (laser positioning accuracy ±1mm) was powered on and performed a normal self-test.

[0044] Therefore, in this embodiment, a grid-based sampling method (sampling distance 2m×2m) can be used to sample and measure the designated area to be measured. A conductivity sensor is inserted into a pre-set measurement hole (5cm deep) on the dam surface, and the conductivity data at each measuring point is recorded (e.g., the conductivity of a certain area is measured to be 0.05S / m). A dielectric constant meter is attached to the dam surface to collect the dielectric constant at each measuring point (e.g., the dielectric constant is measured to be 6.2). Image recognition technology is used to analyze the dam surface texture and internal structure image, calculate the medium inhomogeneity, and represent the complexity using the coefficient of variation of the medium composition. All measurement data is uploaded to the system control terminal to generate a dam medium property distribution table and determine the corresponding attribute data. Furthermore, in this embodiment of the application, the operating parameters of the ground-penetrating radar are dynamically adjusted according to the corresponding attribute data. For example, for a region with a conductivity of 0.05 S / m and a dielectric constant of 6.2, this embodiment of the application can adjust the transmission frequency band of the ground-penetrating radar to 500 MHz, the power to 30 W, the sampling rate to 500 MS / s, and the scanning speed to 1 m / s, adjusting the response time to within 80 ms, thereby ensuring that the scanning is not interrupted.

[0045] In step S102, based on attribute data and at least one working parameter, the de-cavitation data of the dam under test and the risk level corresponding to the de-cavitation data are identified.

[0046] In this application, the risk level can be divided into three levels: low risk, medium risk and high risk. The specific level can be set by those skilled in the art according to the actual situation, and this application does not impose any specific restrictions.

[0047] In some embodiments, the corresponding scanning equipment can be adjusted according to the obtained working parameters to perform a full-area scan of the dam under test, thereby identifying the corresponding void data and risk level.

[0048] In this application embodiment, the data on voiding and risk levels can be corrected and integrated to generate a three-dimensional visualization map containing the voiding location, depth, thickness and size.

[0049] Optionally, in one embodiment of this application, identifying the voiding data of the dam under test and the risk level corresponding to the voiding data based on attribute data and at least one operating parameter includes: determining the voiding region of the dam under test and the initial voiding data of the voiding region based on attribute data, at least one operating parameter and the dam under test; obtaining the corresponding voiding thickness data based on the voiding region; determining the voiding data based on the initial voiding data and the voiding thickness data; and identifying the risk level based on the voiding data.

[0050] In some embodiments, the present application can initially determine the voided area of ​​the dam to be tested and the corresponding initial voided data, and perform precise detection on the voided area to obtain the corresponding voided thickness data. Then, the initial voided data and voided thickness data are corrected and fused to identify the corresponding risk level.

[0051] In this application embodiment, the data fusion can employ a multi-source data correction algorithm, which includes at least error compensation based on the dam medium properties to eliminate systematic biases in the initial void separation data and void separation thickness data.

[0052] For example, in this embodiment of the application, a ground-penetrating radar with adjusted operating parameters can be used to perform a full-area scan of the dam. The ground-penetrating radar is driven to scan at a constant speed along a designated route, and the radar antenna moves close to the dam surface to collect reflected wave signals in real time. The system automatically performs preliminary processing on the signals, removes interference noise, and generates a two-dimensional cross-sectional view of the internal structure of the dam. Based on areas with abnormal wave velocity changes, three suspected voiding areas are initially identified, and their depth ranges are marked as 2-3m below the dam surface, 5-6m in the middle of the dam, and 8-9m deep within the dam. The coordinates of the suspected areas are marked on the dam plan drawing to determine the initial voiding data.

[0053] Furthermore, this embodiment of the application conducts precise point-to-point detection on three identified suspected voiding areas. The probe positioning unit for impact echo detection is activated, employing laser positioning technology to deploy a 0.5m × 0.5m detection grid within each suspected voiding area, precisely aligning the impact probe with the grid nodes. The probe's impact energy is adjusted according to the depth of the suspected voiding area, and impact tests are performed on each node. Simultaneously, the signal amplification unit is activated to enhance the weak reflected echo signal. The system records the round-trip time of the reflected wave and, combined with the wave velocity of the dam medium (calculated based on the previous dielectric constant), automatically calculates the voiding thickness. For example, the measured voiding thickness for the first suspected area is 0.8m, the second is 1.2m, and the third is 1.5m, generating a thickness distribution heatmap for each suspected voiding area to obtain the corresponding voiding thickness data.

[0054] It can be understood that, in the embodiments of this application, the shock echo detection includes a probe positioning unit and a signal amplification unit. The probe positioning unit adopts laser positioning technology, which can achieve fixed-point coverage of the grid in the suspected void area. The amplification factor of the signal amplification unit is adjustable, which is used to enhance the weak reflection echo signal and ensure the effectiveness of void thickness data acquisition.

[0055] Furthermore, embodiments of this application can employ a multi-source data correction algorithm. Based on previously measured attribute data (such as conductivity data, inhomogeneity data, etc., this application does not impose specific limitations), error compensation is used to eliminate systematic deviations between the initial void data and the void thickness data. For example, the 2-3m depth marked by ground-penetrating radar is corrected to 2.2-3.1m, and matched with the 0.8m thickness measured by shock echo. The system integrates the corrected void location (coordinates), depth (2.2-3.1m, 5.1-6.2m, 8.2-9.1m), thickness (0.8m, 1.2m, 1.5m), and size (calculated from thickness and planar range) data to obtain void data and construct a three-dimensional visualization map. Different colors are used to distinguish void areas in the map, intuitively presenting the void distribution status. Furthermore, embodiments of this application can generate a color three-dimensional risk distribution map based on the void size in the three-dimensional visualization map, such as green representing low risk level, yellow representing medium risk level, and red representing high risk level, this application does not impose specific limitations.

[0056] Optionally, in one embodiment of this application, identifying the void data of the dam under test and the risk level corresponding to the void data includes: obtaining the structural threshold of the dam under test to meet the preset working conditions; determining the current structural value of the dam under test in the current state based on the void data; and identifying the risk level based on the structural threshold and the current structural value.

[0057] It is understood that the structural thresholds meeting certain working conditions in the embodiments of this application can be interpreted as critical parameter values ​​set for the dam under normal operation, extreme working conditions, or sudden events to ensure structural safety, normal function, and the safety of downstream protected objects, i.e., the dam structural safety threshold. These certain working conditions can be set by those skilled in the art according to actual circumstances, and this application does not impose specific limitations.

[0058] In some embodiments, this application can identify the corresponding risk level based on the relationship between the current structural value of the dam under test in its current state and the dam structural safety threshold. For example, this application can identify the risk level as low risk when the void size corresponding to the current structural value is less than 30% of the dam structural safety threshold; as medium risk when the void size corresponding to the current structural value is between 30% and 70% of the dam structural safety threshold; and as high risk when the void size corresponding to the current structural value is greater than 70% of the dam structural safety threshold.

[0059] It should be noted that, in the embodiments of this application, the safety threshold of the dam structure can be dynamically adjusted according to the dam design parameters (including concrete strength grade, dam thickness, etc., which are not specifically limited in this application) and service life (such as lowering the threshold by 5%-8% for every 5 years, which is not specifically limited in this application). The specific settings can be made by those skilled in the art according to the actual situation, and are not specifically limited in this application.

[0060] Optionally, in one embodiment of this application, before inputting the de-causing data and risk level into the pre-built de-causing trend prediction model, the method further includes: obtaining historical de-causing data of the target dam to determine at least one operating parameter of the target dam; determining the operating weight corresponding to the at least one operating parameter based on the historical de-causing data; and constructing the de-causing trend prediction model based on the historical de-causing data, at least one operating parameter, and operating weight.

[0061] It is understood that the embodiments of this application can construct historical voiding data based on the dam commissioning time, water flow leakage, dam structural characteristics, water storage height parameters, and historical voiding detection results, and then construct a voiding trend prediction model to assess the future voiding expansion direction and risk level changes.

[0062] For example, in this application embodiment, the dam's commissioning time (such as service life, etc., which are not specifically limited in this application), water flow leakage monitoring data (historical maximum and average leakage), water storage height change curves, and previous void detection results (such as no void was found 5 years ago, and the first suspected area was found 3 years ago) can be retrieved from the dam operation and maintenance management system to form historical void data. Combined with the dam design parameters, the structural safety threshold of the dam is initially estimated (for example, a concrete gravity dam is designed with a dam body thickness of 50m and a concrete strength grade of C30, and the initial safety threshold is set at 10m), providing a benchmark for subsequent risk level classification.

[0063] In some embodiments, when constructing the caving trend prediction model, this application employs a historical data association analysis algorithm. This involves establishing a database of historical caving data according to time series and matching the operational weights of dam operating parameters based on the time-series variation patterns. The operational weights may include, but are not limited to, the contribution rate of water storage height to caving expansion, the correlation coefficient between water seepage and caving size changes, such as a water storage height coefficient of 0.45 and a seepage correlation coefficient of 0.55. This application does not impose specific limitations, thereby constructing the caving trend prediction model.

[0064] In step S103, the de-cavitation data and risk level are input into the pre-built de-cavitation trend prediction model to predict the predicted de-cavitation data of the dam to be tested and the predicted risk level corresponding to the predicted de-cavitation data.

[0065] In some embodiments, the present application can use a pre-built de-venting trend prediction model to predict the predicted de-venting data and corresponding predicted risk level of the dam to be tested.

[0066] For example, embodiments of this application can utilize a voiding trend prediction model to output predicted voiding data. Based on the proportion of voiding size over the next three years, the corresponding predicted risk level can be determined. For instance, if the first voiding size indicates a voiding area that may extend 0.3-0.5m deeper into the dam body, the predicted risk level for the first voiding area can be determined as low risk. Similarly, if the second voiding size indicates a voiding area that may extend 0.3-0.5m deeper into the dam body, the predicted risk level for the second voiding area can be determined as low risk. Likewise, if the third voiding size indicates a voiding area that may extend 0.3-0.5m deeper into the dam body, the predicted risk level for the third voiding area can be determined as low risk, but enhanced monitoring is required. Furthermore, embodiments of this application can generate a color three-dimensional risk distribution map.

[0067] Optionally, in one embodiment of this application, the method further includes: generating at least one maintenance instruction for the dam under test based on the predicted de-empty data and the predicted risk level; and maintaining the dam under test in accordance with the at least one maintenance instruction so that the dam under test meets the preset stability conditions.

[0068] In some embodiments, this application can formulate targeted countermeasures (such as selection of repair materials, construction process parameters, and operation and maintenance cycle suggestions, etc., based on predicted voiding data and predicted risk levels; this application does not impose specific limitations) to obtain different maintenance instructions. Then, the dam under test is maintained according to the corresponding maintenance instructions, so that the dam under test meets certain stability conditions. These certain stability conditions can be set by those skilled in the art according to actual conditions; this application does not impose specific limitations.

[0069] For example, in the embodiments of this application, for low-risk levels, the generated maintenance instructions can be periodic monitoring and surface protection strategies (wherein, the monitoring cycle can be 3-6 months, and this application does not impose specific limitations); for medium-risk levels, the generated maintenance instructions can be local grouting repair and enhanced monitoring strategies; for high-risk levels, the generated maintenance instructions can be emergency reinforcement treatment and real-time monitoring strategies, and the parameters of the strategies can be fine-tuned according to the specific operating environment of the dam (such as high water level, strong water flow area), which can be set by those skilled in the art according to the actual situation, and this application does not impose specific limitations.

[0070] For example, this application embodiment targets three predicted low-risk voiding areas and employs a strategy of regular monitoring and surface protection. Ground-penetrating radar re-surveys are conducted every four months, and a penetrating protective coating is applied to the surface of the voiding areas to prevent water infiltration and accelerated voiding expansion. Furthermore, this application embodiment can establish a dedicated monitoring archive, storing the three-dimensional visualization maps, risk distribution maps, thickness data, and prediction results obtained from each detection in a corresponding database, facilitating maintenance personnel to track voiding changes. The detection system is calibrated and maintained every six months, focusing on checking the accuracy of the sensors measuring media properties and the positioning accuracy of the impact echo probe to ensure the reliability of the next detection data.

[0071] The working principle of the dam caving detection method proposed in this application will be introduced below with reference to a specific embodiment.

[0072] in, Figure 2 This is a flowchart illustrating the working principle of a dam cavitation detection method according to an embodiment of this application.

[0073] Step S201: Measure the property data of the medium of the dam to be tested, and select the working parameters of the ground-penetrating radar based on the property data.

[0074] Step S202: The address radar completes a full-area scan of the dam and uses impact echo detection to perform precise point detection in the voided areas.

[0075] In this embodiment, the ground-penetrating radar with adjusted working parameters can be used to perform a full-area scan of the dam, initially identifying the suspected void area (void area) and the initial void data of the area. Then, for the suspected void area, impact echo detection is used for precise point detection to obtain the void thickness data of the suspected void area.

[0076] Step S203: Use a multi-source data correction algorithm to determine the corresponding missing data.

[0077] In this application embodiment, a multi-source data correction algorithm can be used to correct and integrate the void thickness data and depth data to generate void data containing void location, depth, thickness and size, and to construct a three-dimensional visualization map using the void data.

[0078] Step S204: Divide the risk levels and generate a color three-dimensional risk distribution map.

[0079] In this embodiment, a color three-dimensional risk distribution map can be generated based on the risk level division in the three-dimensional visualization map, such as green representing low risk level, yellow representing medium risk level, and red representing high risk level, thereby realizing the visual differentiation of risks.

[0080] Step S205: Use the pre-built de-venting trend prediction model to predict the predicted de-venting data and the predicted risk level of the dam to be tested.

[0081] In this embodiment, historical voiding data can be constructed based on the dam commissioning time, water seepage, dam structural characteristics, water storage height parameters, and historical voiding detection results, and then a voiding trend prediction model can be constructed.

[0082] Furthermore, in this embodiment of the application, a pre-built de-cavitation trend prediction model is used to assess the future de-cavitation expansion direction and risk level changes of the dam under test, thereby obtaining the corresponding predicted de-cavitation data and predicted risk level.

[0083] Step S206: Obtain the corresponding maintenance instructions based on the predicted risk level to provide scientific support for the safe operation of the dam.

[0084] In this application, for low-risk levels, the generated maintenance instructions can be periodic monitoring and surface protection strategies (the monitoring cycle can be 3-6 months, and this application does not impose a specific limitation); for medium-risk levels, the generated maintenance instructions can be local grouting repair and enhanced monitoring strategies; for high-risk levels, the generated maintenance instructions can be emergency reinforcement treatment and real-time monitoring strategies, and the strategy parameters can be fine-tuned according to the specific operating environment of the dam (such as high water level, strong water flow area).

[0085] The dam void detection method proposed in this application can determine the operating parameters of the corresponding scanning equipment based on the property data of the medium under test of the dam, thereby identifying the void data and corresponding risk level of the dam under test. It also uses a pre-built void trend prediction model to predict the predicted void data and corresponding predicted risk level of the dam under test. The operating parameters of the scanning equipment are adaptively adjusted in conjunction with the dam medium property data, and multi-source data fusion correction is used to eliminate system bias and accurately present the void location, depth, and size, laying a reliable data foundation for risk assessment. Furthermore, it intuitively displays the void distribution and risk level, avoiding misjudgments by maintenance personnel due to information ambiguity, promoting the transformation of safety management towards proactive prevention, predicting the development direction and risk changes of void in advance, facilitating the grasp of the best repair opportunity, reducing manual decision-making costs and repeated testing, significantly reducing maintenance expenses, improving management efficiency, ensuring the long-term safety of the dam, and possessing comprehensive value. It effectively delays dam aging, avoids safety accidents, and has both economic and social benefits. This addresses several issues in related technologies, including the susceptibility of ground-penetrating radar to uneven dam media and complex structures, leading to large positioning errors and inaccurate thickness data in the vacuolated areas; the limitations of impact-echo methods in achieving full coverage detection with blind spots, making it impossible to comprehensively understand the distribution of vacuoles; and the lack of a multi-source data fusion mechanism, which hinders the generation of accurate three-dimensional vacuolation maps, makes it impossible to assess risk changes, and easily leads to missed opportunities for repair.

[0086] Next, referring to the accompanying drawings, a dam caving detection device according to an embodiment of this application is described.

[0087] Figure 3 This is a block diagram of a dam cavitation detection device provided according to an embodiment of this application.

[0088] like Figure 3 As shown, the dam caving detection device 10 includes: a first determination module 100, an identification module 200, and a prediction module 300.

[0089] The first determining module 100 is used to collect the attribute data of the medium of the dam to be tested, and determine at least one working parameter of the scanning device corresponding to the dam to be tested based on the attribute data.

[0090] The identification module 200 is used to identify the de-cavitation data of the dam under test and the risk level corresponding to the de-cavitation data based on attribute data and at least one working parameter.

[0091] The prediction module 300 is used to input the de-cavitation data and risk level into a pre-built de-cavitation trend prediction model to predict the predicted de-cavitation data and the predicted risk level corresponding to the predicted de-cavitation data of the dam to be tested.

[0092] Optionally, in one embodiment of this application, the identification module 200 includes: a first determining unit, a first acquiring unit, and a second determining unit.

[0093] The first determining unit is used to determine the voiding region of the dam under test and the initial voiding data of the voiding region based on attribute data, at least one working parameter and the dam under test.

[0094] The first acquisition unit is used to acquire the corresponding void thickness data based on the voided area.

[0095] The second determining unit is used to determine the voiding data based on the initial voiding data and voiding thickness data.

[0096] The first identification unit is used to identify the risk level based on the data removed from the database.

[0097] Optionally, in one embodiment of this application, it further includes: an acquisition module, a second determination module, and a construction module.

[0098] The acquisition module is used to acquire historical detachment data of the target dam before inputting detachment data and risk levels into a pre-built detachment trend prediction model, so as to determine at least one operating parameter of the target dam.

[0099] The second determination module is used to determine the operating weight corresponding to at least one operating parameter based on historical data.

[0100] The module is used to build a short-selling trend prediction model based on historical short-selling data, at least one operating parameter, and operating weights.

[0101] Optionally, in one embodiment of this application, the identification module 200 includes: a second acquisition unit, a third determination unit, and a second identification unit.

[0102] The second acquisition unit is used to acquire the structural threshold of the dam under test to meet the preset working conditions.

[0103] The third determining unit is used to determine the current structural value of the dam under test in its current state based on the data detached from the test.

[0104] The second identification unit is used to identify the risk level based on the structural threshold and the current structural value.

[0105] Optionally, in one embodiment of this application, it further includes a generation module and a maintenance module.

[0106] The generation module is used to generate at least one maintenance instruction for the dam under test based on the predicted de-empty data and the predicted risk level.

[0107] The maintenance module is used to maintain the dam under test according to at least one maintenance instruction so that the dam under test meets the preset stability conditions.

[0108] It should be noted that the explanation of the aforementioned method for detecting dam cavitation also applies to the dam cavitation detection device of this embodiment, and will not be repeated here.

[0109] The dam caving detection device proposed in this application can determine the operating parameters of the corresponding scanning equipment based on the property data of the medium under test of the dam, thereby identifying the caving data and corresponding risk level of the dam under test. It also uses a pre-built caving trend prediction model to predict the predicted caving data and corresponding predicted risk level of the dam under test. The operating parameters of the scanning equipment are adaptively adjusted in conjunction with the dam medium property data, and multi-source data fusion correction is used to eliminate system bias and accurately present the location, depth, and size of the caving, laying a reliable data foundation for risk assessment. Furthermore, it intuitively displays the caving distribution and risk level, avoiding misjudgments by maintenance personnel due to unclear information, promoting the transformation of safety management towards proactive prevention, predicting the development direction and risk changes of caving in advance, facilitating the grasp of the best repair opportunity, reducing manual decision-making costs and repeated testing, significantly reducing maintenance expenses, improving management efficiency, ensuring the long-term safety of the dam, and possessing comprehensive value. It effectively delays dam aging, avoids safety accidents, and has both economic and social benefits. This addresses several issues in related technologies, including the susceptibility of ground-penetrating radar to uneven dam media and complex structures, leading to large positioning errors and inaccurate thickness data in the vacuolated areas; the limitations of impact-echo methods in achieving full coverage detection with blind spots, making it impossible to comprehensively understand the distribution of vacuoles; and the lack of a multi-source data fusion mechanism, which hinders the generation of accurate three-dimensional vacuolation maps, makes it impossible to assess risk changes, and easily leads to missed opportunities for repair.

[0110] Figure 4 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. The electronic device may include: The memory 401, the processor 402, and the computer program stored on the memory 401 and capable of running on the processor 402.

[0111] When the processor 402 executes the program, it implements the dam delamination detection method provided in the above embodiments.

[0112] Furthermore, electronic devices also include: Communication interface 403 is used for communication between memory 401 and processor 402.

[0113] The memory 401 is used to store computer programs that can run on the processor 402.

[0114] Memory 401 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0115] If the memory 401, processor 402, and communication interface 403 are implemented independently, then the communication interface 403, memory 401, and processor 402 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized into address buses, data buses, control buses, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0116] Optionally, in a specific implementation, if the memory 401, processor 402, and communication interface 403 are integrated on a single chip, then the memory 401, processor 402, and communication interface 403 can communicate with each other through an internal interface.

[0117] Processor 402 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0118] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described method for detecting dam delamination.

[0119] This application also provides a computer program product, including a computer program that, when executed, implements the above-described method for detecting dam delamination.

[0120] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0121] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0122] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0123] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). In addition, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically by optically scanning paper or other media, then editing, interpreting or otherwise processing them as necessary, and then storing them in computer memory.

[0124] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0125] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0126] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0127] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A method for detecting dam caving, characterized in that, The method comprises the following steps: Collect attribute data of a to-be-tested dam medium, and determine at least one working parameter of a scanning device corresponding to the to-be-tested dam according to the attribute data; Based on the attribute data and the at least one working parameter, identify the void data of the to-be-tested dam and the risk level corresponding to the void data; Input the void data and the risk level into a pre-constructed void trend prediction model to predict the predicted void data of the to-be-tested dam and the predicted risk level corresponding to the predicted void data.

2. The method of claim 1, wherein, The identification of the void data of the to-be-tested dam and the risk level corresponding to the void data based on the attribute data and the at least one working parameter comprises: Based on the attribute data, the at least one working parameter and the to-be-tested dam, determine the void area of the to-be-tested dam and the initial void data of the void area; Based on the void area, obtain the corresponding void thickness data; Based on the initial void data and the void thickness data, determine the void data; Based on the void data, identify the risk level.

3. The method of claim 1, wherein, Before inputting the void data and the risk level into the pre-constructed void trend prediction model, further comprising: Obtain the historical void data of a target dam to determine at least one running parameter of the target dam; Based on the historical void data, determine the running weight corresponding to the at least one running parameter; Based on the historical void data, the at least one running parameter and the running weight, construct the void trend prediction model.

4. The method of claim 1, wherein, The identification of the void data of the to-be-tested dam and the risk level corresponding to the void data comprises: Obtain the structure threshold value of the to-be-tested dam meeting the preset working condition; Based on the void data, determine the current structure value of the to-be-tested dam in the current state; Based on the structure threshold value and the current structure value, identify the risk level.

5. The method of claim 1, wherein, Further comprising: Based on the predicted void data and the predicted risk level, generate at least one maintenance instruction of the to-be-tested dam; Maintain the to-be-tested dam according to the at least one maintenance instruction, so that the to-be-tested dam meets the preset stable condition.

6. A device for detecting voids in a dam, characterized in that Comprise: A determination module is configured to collect attribute data of a to-be-tested dam medium, and determine at least one working parameter of a scanning device corresponding to the to-be-tested dam according to the attribute data; An identification module is configured to identify the void data of the to-be-tested dam and the risk level corresponding to the void data based on the attribute data and the at least one working parameter; A prediction module is configured to input the void data and the risk level into a pre-constructed void trend prediction model to predict the predicted void data of the to-be-tested dam and the predicted risk level corresponding to the predicted void data.

7. The apparatus of claim 6, wherein, The identification module comprises: A first determination unit is configured to determine the void area of the to-be-tested dam and the initial void data of the void area based on the attribute data, the at least one working parameter and the to-be-tested dam; A first acquisition unit is configured to obtain the corresponding void thickness data based on the void area; The second determining unit is configured to determine the void data based on the initial void data and the void thickness data. The first identifying unit is configured to identify the risk level based on the void data.

8. An electronic device, comprising: The computer program is executed by the processor to implement the method for detecting the dam void according to any one of claims 1-5. The computer program is executed by the processor to implement the method for detecting the dam void according to any one of claims 1-5.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the method for detecting the dam void according to any one of claims 1-5.

10. A computer program product, characterised in that, ​

Images