Dam anti-seepage body integrity detection method based on artificial power supply

Abstract

The invention discloses a dam anti-seepage body integrity detection method based on an artificial power supply. Comprising the following steps: injecting a broadband excitation current signal into a dam anti-seepage body through a multi-frequency program control constant current source; a modular distributed electrode array is adopted to collect and obtain voltage data of the surface of the dam anti-seepage body in real time; high signal-to-noise ratio voltage data is obtained by adopting filtering processing and a digital phase-locked amplification technology; carrying out three-dimensional inversion calculation by adopting an improved electrical impedance tomography algorithm, and reconstructing an internal conductivity distribution image of the dam anti-seepage body; analyzing, identifying and positioning defects through a deep learning model; and constructing an electro-seepage coupling inversion model, converting the internal conductivity distribution image based on the dam anti-seepage body into permeability coefficient distribution, and generating an integrity evaluation report of the dam anti-seepage body. Compared with a traditional detection method, the method is high in detection precision, wide in application range and high in detection efficiency, and a brand new technical means is provided for evaluating the health state of the dam seepage-proofing body.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of safety monitoring of hydraulic engineering, and particularly relates to a dam anti-seepage body integrity detection method based on an artificial power supply. BACKGROUND

[0002] The dam anti-seepage body is the core anti-seepage structure of the hydraulic engineering, and its integrity is directly related to the safety of the engineering, but the existing detection technology has many technical bottlenecks. In the traditional detection means, although the ground penetrating radar method is simple to operate, there is an inherent contradiction between the detection depth and the resolution, the electromagnetic wave attenuation is serious in the water-containing medium such as the clay core, the defect detection rate of the area deeper than 5 meters drops to below 60%, and the microcracks below 3 centimeters cannot be identified; although the drilling sampling method can obtain the intuitive core sample, the integrity of the dam anti-seepage body is damaged, and the detection range of a single hole is limited, and dozens of drilling holes are needed for the conventional dam body to obtain reliable data, and the detection period is as long as 3-5 working days.

[0003] In the electrical detection field, the conventional resistivity method uses a fixed frequency excitation, and it is difficult to meet the requirements of high resolution in the shallow layer and high penetration in the deep layer at the same time, and the measurement error is generally 15%-20% due to the influence of the electrode polarization effect and the contact impedance. Although the electrical impedance tomography technology can realize nondestructive detection in theory, the existing method has obvious limitations: the spatial resolution is limited by the number of electrodes and the algorithm, and only defects above 10 centimeters can be identified; in the complex electromagnetic environment in the field, the power frequency interference and random noise result in a signal-to-noise ratio generally lower than 60 decibels; more importantly, the existing technology lacks an effective multi-physical field coupling model, and the tracking accuracy of the leakage channel is less than 70%, and the permeability coefficient inversion error is more than 30%. These technical defects make it difficult for the current method to meet the requirements of major hydraulic engineering for millimeter-level defect identification and quantitative performance evaluation of the dam anti-seepage body, especially in key scenes such as high dams, large reservoirs and old dams in operation for many years, and new detection technology needs to be developed to break through the performance limitations of the existing method. SUMMARY

[0004] In view of the deficiencies of the prior art, the application provides a dam anti-seepage body integrity detection method based on an artificial power supply, which aims to reconstruct the three-dimensional electrical characteristic parameter distribution of the dam anti-seepage body based on an improved electrical impedance tomography algorithm, and realize intelligent diagnosis of the leakage channel and structural defects by combining a deep learning assisted defect identification algorithm. In order to achieve the above purpose, the application provides the following technical scheme: a dam anti-seepage body integrity detection method based on an artificial power supply, and the specific steps are as follows: Step S1, a multi-frequency controlled constant current source is used to inject a wideband excitation current signal into the dam anti-seepage body; Step S2, based on the wideband excitation current signal of step S1, a modular distributed electrode array is used to collect the voltage data of the surface of the dam anti-seepage body in real time; Step S3, based on the voltage data obtained from step S2, high signal-to-noise ratio voltage data is obtained by using filtering processing and digital phase-locked amplification technology; Step S4, based on the high signal-to-noise ratio voltage data obtained from step S3, a three-dimensional inversion calculation is performed using an improved electrical impedance tomography algorithm to reconstruct the internal conductivity distribution image of the dam seepage control body; Step S5, based on the internal conductivity distribution image of the dam seepage control body in step S4, the defects are identified and located by analyzing through a deep learning model; Step S6, an electro-osmotic coupling inversion model is constructed, the internal conductivity distribution image of the dam seepage control body based on step S4 is converted into a permeability coefficient distribution, and a dam seepage control body integrity evaluation report is generated.

[0005] Further, in step S1, a multi-frequency controlled constant current source is used to inject a wideband excitation current signal into the dam seepage control body; the specific steps are as follows: Step S11, a dam seepage control body material-frequency response database is established to pre-store the optimal excitation frequency band of different materials; Step S12, the multi-frequency controlled constant current source automatically identifies the type of dam seepage control body material through impedance spectrum rapid scanning and intelligently matches the optimal excitation frequency band; Step S13, a proportional-integral-derivative closed-loop control algorithm is used to dynamically adjust the multi-frequency controlled constant current source to inject a wideband excitation current signal of 0.1-1000 Hz into the dam seepage control body; Step S14, an overload protection module is integrated in the multi-frequency controlled constant current source, and the multi-frequency controlled constant current source automatically cuts off the output and alarms when the contact resistance is greater than 10 kΩ.

[0006] Further, in step S2, based on the wideband excitation current signal in step S1, a modular distributed electrode array is used to collect real-time voltage data on the surface of the dam seepage control body; the specific steps are as follows: Step S21, a modular distributed electrode array is used to deploy 128 high-precision silver-chloride silver electrodes at an interval of 1 meter, and a preamplifier circuit with a gain of 100 times and an impedance detection module with a contact impedance of less than 3 kΩ are integrated into the high-precision silver-chloride silver electrode; Step S22, based on the modular distributed electrode array in step S21, multi-channel time synchronization is achieved through global positioning system synchronous triggering, 24-bit sigma-delta analog-to-digital converters are used for synchronous sampling, and 0.1-1.5 kHz adaptive bandpass filtering and 40-70 Hz adjustable dynamic power trap are used to obtain the voltage data on the surface of the dam seepage control body.

[0007] Further, in step S3, based on the voltage data of the dam seepage prevention body surface obtained in step S2, high signal-to-noise ratio voltage data is obtained by filtering and digital lock-in amplification technology; the specific steps are as follows: Step S31, the voltage data on the surface of the dam seepage prevention body is preliminarily suppressed by a hardware band-pass filter; Step S32, using an adaptive notch filter based on the least mean square algorithm to track and eliminate 50 Hz power frequency and harmonic interference of 50 Hz power frequency in real time, the convergence time is less than 100 milliseconds; Step S33, combined with the digital lock-in amplification technology, the wideband excitation current signal in step S1 is used as the reference frequency for coherent detection, the in-phase and quadrature components are extracted by orthogonal vector decomposition, the output signal-to-noise ratio is monitored in real time, and the passband width and stopband attenuation parameters of the 16-order finite-length unit impulse response filter are dynamically adjusted, which can stably maintain a signal-to-noise ratio of more than 90 decibels under complex working conditions, and high signal-to-noise ratio voltage data is obtained.

[0008] Further, in step S4, based on the high signal-to-noise ratio voltage data obtained in step S3, a three-dimensional inversion calculation is performed using an improved electrical impedance tomography algorithm to reconstruct the internal conductivity distribution image of the dam seepage prevention body; wherein the improved electrical impedance tomography algorithm consists of four links of accurate forward problem modeling, inverse problem construction and improvement, efficient iterative solution, and image post-optimization; the specific steps are as follows: Step S41, accurate forward problem modeling, a complete electrode model including contact impedance effect is established; Step S42, inverse problem construction and improvement, the sensitivity matrix is calculated by the admittance method, and the objective function is constructed by combining the improved Tikhonov regularization and the regularization matrix based on the discrete Laplace operator to constrain the smoothness of the solution; Step S43, efficient iterative solution, the conjugate gradient method is used to solve the iterative process of the conductivity correction, which specifically includes iterative solution update, conjugate direction solution, and target function gradient calculation; Step S44, image post-optimization, a pre-trained deep residual network is used for image optimization to restore details and suppress noise, as shown in the formula: ; Wherein, represents the internal conductivity distribution image of the dam seepage prevention body, represents the convolutional neural network, and θ represents the parameter set of the convolutional neural network.

[0009] Further, in step S41, accurate forward problem modeling, a complete electrode model including contact impedance effect is established; the specific steps are as follows: Step S411, the control equation of the complete electrode model, the Poisson equation is used to describe the potential distribution under the steady-state electric field, as shown in the formula: ; in, Denotes divergence, Indicates electrical conductivity. Represents the gradient. Represents electric potential; Step S412, Boundary conditions for the complete electrode model, considering the contact impedance at the electrode-dielectric interface, as shown in the formula: ; in, This represents the voltage measured on the l-th electrode. Indicates the first One electrode, Represents electric potential The directional derivative in the direction n normal to the boundary. Indicates injection of the first Current of each electrode Indicates the first The contact resistance between an electrode and the dielectric surface.

[0010] Further, in step S42, the inverse problem is constructed and improved by calculating the sensitivity matrix using the admittance method and constructing the objective function using the improved Tikhonov regularization, along with a regularization matrix based on the discrete Laplace operator, to constrain the smoothness of the solution; the specific steps are as follows: Step S421: Calculate the sensitivity matrix using the admittance method. The elements of the sensitivity matrix are shown in the formula: ; in, Let represent the element in the m-th row and p-th column of the sensitivity matrix J, and Ω represent the integration domain of the entire solution region. This represents the electric field distribution calculated under the i-th current excitation mode. dΩ represents the electric field distribution calculated under the j-th current excitation mode, where i ≠ j, and dΩ represents a volume element. Step S422: Construct the objective function using improved Tikhonov regularization; as shown in the formula: ; Where min represents minimizing, i.e. finding the minimum solution of the objective function value, Δσ represents the conductivity correction amount, ΔV represents the voltage change measured on the boundary electrode, λ represents the regularization parameter, and L represents the regularization matrix; Step S423: The regularization parameter is obtained by using an adaptive decay strategy that decreases with the number of iterations; as shown in the formula: ; wherein, a represents a proportionality coefficient, β represents an attenuation coefficient, k represents an iteration number, exp(-βk) represents an exponential attenuation function, F-norm of a matrix ; In step S424, the regularization matrix L is constructed based on a discrete Laplace operator to constrain the smoothness of the solution; the elements of the regularization matrix L are shown in the formula: ; wherein, represents the element of the rth row and sth column of the regularization matrix L, represents the element of the rth row and tth column of the regularization matrix L.

[0011] Further, in step S43, an efficient iterative solution is obtained by using a conjugate gradient method to solve the iteration process of the conductivity correction amount, which specifically includes iteration solution updating, conjugate direction solving, and target function gradient calculation; the specific steps are as follows: In step S431, the conjugate gradient method is used to obtain the conductivity correction amount, as shown in the formula: ; wherein, represents the conductivity correction amount of the k+1th iteration, represents the conductivity correction amount of the kth iteration, represents the step size of the kth iteration, represents the conjugate direction of the kth iteration; In step S432, the conjugate direction is solved, as shown in the formula: ; wherein, represents the target function gradient of the kth iteration, represents the transpose of the target function gradient of the kth iteration, represents the transpose of the target function gradient of the k-1th iteration, represents the conjugate direction of the k-1th iteration; In step S433, the target function gradient is calculated to know the descending trend of the target function, as shown in the formula: ; wherein, represents the transpose of the sensitivity matrix J, represents the transpose of the regularization matrix L; In step S434, during the iteration process of steps S431 to S433, the convergence condition is set: the change amount of the target function value is less than a threshold value or the maximum iteration number is reached; when the iteration process is terminated by satisfying the convergence condition, the final conductivity correction amount Δσ finalAdding this to the initial conductivity distribution σ0 yields the preliminary conductivity distribution image σ reconstructed by the improved electrical impedance tomography algorithm. EIT .

[0012] Furthermore, in step S5, based on the conductivity distribution image inside the dam seepage barrier obtained in step S4, a deep learning model is used to analyze and identify defects; the specific steps are as follows: Step S51: Construct a simulation training database; establish a parametric geometric model library containing various dam structures, dam seepage prevention materials, and foundation types; embed typical defects with adjustable parameters, including seepage channels, cracks, and cavities, into the model base of the geometric model library; for each parametric model, perform forward problem calculations of electrical impedance tomography to simulate the excitation and measurement processes of steps S1 to S3, generating simulated voltage data; subsequently, input the simulated voltage data into the improved electrical impedance tomography algorithm in step S4 for inversion, generating the corresponding three-dimensional conductivity distribution image as input data for training samples; finally, generate a simulation training database containing more than 100,000 sets of samples. Step S52: Design and construct a 3D defect recognition model; adopt a U-shaped network as the basic architecture; replace the encoder of the U-shaped network with a residual network-50 as the backbone feature extraction network; embed a spatial attention module at the jump connection between the encoder and the decoder; use a normalized exponential function at the end of the decoder to achieve pixel-level defect classification. Step S53: Train the end-to-end 3D defect recognition model from step S52; use a hybrid loss function of Dess loss and cross-entropy loss to train the 3D defect recognition model and obtain the trained 3D defect recognition model. In step S54, the conductivity distribution image inside the dam seepage prevention body obtained in step S4 is input into the trained three-dimensional defect recognition model. The encoder is used to downsample the image to 1 / 32 resolution and extract feature maps at different levels. Subsequently, the feature maps are upsampled by the decoder and fused with the same-scale encoder features weighted by skip connections and spatial attention modules. Finally, a defect classification probability map of the same size as the input image is output. Step S55: For the defect classification probability map output in step S54, a three-dimensional connected component analysis algorithm is used to identify each independent defect; a sub-pixel localization algorithm is used to calculate the three-dimensional coordinates of the geometric center of each independent defect; finally, the category, three-dimensional coordinates of the geometric center, and equivalent size information of all defects are integrated to generate and output a three-dimensional defect distribution map with spatial coordinates.

[0013] Further, in step S6, an electro-seepage coupled inversion model is constructed to convert the conductivity distribution image inside the dam seepage barrier obtained in step S4 into a permeability coefficient distribution, and a dam seepage barrier integrity evaluation report is generated; the specific steps are as follows: Step S601: Based on the inherent physical relationship between electrical conductivity and permeability in soil and rock media, and using the traditional Alzer's law as a foundation, an electro-permeability coupled inversion model is established, as shown in the formula: ; Where K represents the permeability coefficient, with units of centimeters per second or meters per day. Volume conductivity is expressed in Siemens per meter (S / m). The empirical coefficients of the model are represented by u, which depend on the mineral composition, pore structure and cementation of the dam seepage prevention material, and u = 1, 2, 3, 4. Step S602: Accurately calibrate the empirical coefficients of the model through indoor geotechnical tests; prepare a series of dam seepage prevention material samples with different mix ratios, including different moisture contents, densities, and clay contents; for each dam seepage prevention material sample, use a permeameter to measure the permeability coefficient and a resistivity meter to measure the volumetric conductivity. Step S603: Substitute the measured volumetric conductivity and permeability coefficient into the electro-seepage coupling inversion model, and use the nonlinear least squares method to perform regression analysis to solve for the specific coefficients of the dam seepage prevention material, i.e., the empirical coefficients of the model. Step S604: Using the conductivity distribution image inside the dam seepage barrier from step S4 as input, and using the empirical coefficients of the model from step S603, the initial permeability coefficient distribution of the entire dam seepage barrier region is initially calculated through the electro-seepage coupling inversion model. Step S605: Based on the initial permeability coefficient distribution of the entire dam seepage prevention area, construct the governing equations for the steady-state seepage field, as shown in the formula: ; Where K represents the permeability coefficient distribution and h represents the total head, which drives seepage. Step S606: Discretize the three-dimensional structure of the dam seepage barrier into a finite element mesh; apply the corresponding head boundary or flow boundary to the finite element mesh according to the actual operating conditions of the dam seepage barrier; solve the control equation of the steady-state seepage field using the finite element method to obtain the head distribution within the entire dam seepage barrier area. Step S607: Define the objective function, which is to minimize the difference between the head distribution and the measured head distribution; starting from the initial permeability coefficient distribution, use the gradient descent method or Gauss-Newton method to repeatedly adjust the permeability coefficient distribution, and return to step S606 to solve the control equation of the steady-state seepage field until the objective function value is less than the preset threshold, and finally obtain the high-precision permeability coefficient distribution. Step S608: Perform spatial analysis on the obtained high-precision permeability coefficient distribution; set a critical permeability coefficient value K. critAutomatically identify and mark all permeability coefficient distribution values ​​K that are greater than or equal to the critical permeability coefficient value K. crit The spatial area is marked as the weak zone in seepage prevention, and its three-dimensional spatial coordinates and volume are recorded. Step S609: Based on the results of steps S607 and S608, calculate the structural integrity score S of the dam's seepage prevention structure; as shown in the formula: ; Among them, V total V represents the total volume of the dam's seepage prevention structure. weak This indicates the total volume of the identified weak points in the seepage prevention system. This represents the average permeability coefficient across all weak zones. Step S610: Based on the results of steps S608 and S609, generate a dam seepage prevention integrity evaluation report that includes a permeability coefficient distribution map, a weak zone location map, and a structural integrity score.

[0014] Beneficial effects of this invention: This invention innovatively proposes a signal enhancement technique that combines multi-frequency excitation with adaptive filtering, effectively solving the signal interference problem in complex environments.

[0015] This invention achieves non-destructive evaluation of the permeability coefficient of impermeable bodies by constructing an electro-permeation coupled inversion model. Attached Figure Description

[0016] Figure 1 This is a flowchart of the present invention. Detailed Implementation

[0017] This invention provides a technical solution: a method for detecting the integrity of dam seepage prevention structures based on artificial power sources, such as... Figure 1 As shown, it includes the following steps: Step S1: Inject a wideband excitation current signal into the seepage prevention body of the dam using a multi-frequency programmable constant current source; Step S2: Based on the wideband excitation current signal from step S1, the voltage data on the surface of the dam seepage barrier is acquired in real time using a modular distributed electrode array. Step S3: Based on the voltage data of the dam seepage prevention body surface obtained in step S2, high signal-to-noise ratio voltage data is obtained by filtering and digital phase-locked amplification technology. Step S4: Based on the high signal-to-noise ratio voltage data obtained in step S3, a three-dimensional inversion calculation is performed using an improved electrical impedance tomography algorithm to reconstruct the conductivity distribution image inside the dam seepage barrier. Step S5: Based on the image of the electrical conductivity distribution inside the dam seepage barrier obtained in Step S4, analyze it using a deep learning model to identify and locate defects. Step S6: Construct an electro-seepage coupled inversion model, convert the electrical conductivity distribution image inside the dam seepage barrier based on step S4 into a permeability coefficient distribution, and generate a dam seepage barrier integrity evaluation report.

[0018] Furthermore, in step S1, a wideband excitation current signal is injected into the dam's seepage prevention body through a multi-frequency programmable constant current source; the specific steps are as follows: Step S11: Establish a database of frequency response for dam seepage prevention materials, and pre-store the optimal excitation frequency bands for different materials; Step S12: The multi-frequency programmable constant current source automatically identifies the type of dam seepage prevention material by rapidly scanning the impedance spectrum and intelligently matches the optimal excitation frequency band. Step S13: The proportional-integral-derivative closed-loop control algorithm is used to dynamically adjust the multi-frequency programmable constant current source to inject a wideband excitation current signal of 0.1-1000 Hz into the seepage prevention body of the dam. Step S14: The multi-frequency programmable constant current source integrates an overload protection module. When the multi-frequency programmable constant current source detects a contact resistance > 10 kΩ, it automatically cuts off the output and alarms.

[0019] Furthermore, in step S2, based on the broadband excitation current signal from step S1, a modular distributed electrode array is used to acquire the voltage data on the surface of the dam's seepage prevention body in real time; the specific steps are as follows: Step S21: Modular distributed electrode array, deploying 128 high-precision silver-silver chloride electrodes with a 1-meter spacing, integrating a preamplifier circuit with a gain of 100 times and an impedance detection module with a contact impedance of <3 kΩ from the high-precision silver-silver chloride electrodes; Step S22: Based on the modular distributed electrode array in step S21, multi-channel time synchronization is achieved through synchronous triggering via the Global Positioning System. A 24-bit sigma-delta analog-to-digital converter is used for synchronous sampling, and voltage data of the dam seepage prevention body surface is obtained in conjunction with 0.1-1.5 kHz adaptive bandpass filtering and 40-70 Hz adjustable dynamic power frequency notch filtering.

[0020] Furthermore, in step S3, the voltage data on the surface of the dam seepage barrier obtained in step S2 is processed using filtering and digital phase-locked loop amplification techniques to obtain high signal-to-noise ratio voltage data; the specific steps are as follows: Step S31: Perform primary noise suppression on the voltage data of the dam seepage prevention body surface using a hardware bandpass filter; Step S32: An adaptive notch filter based on the least mean square algorithm is used to track and eliminate the 50 Hz power frequency and 50 Hz power frequency harmonic interference in real time, with a convergence time of <100 milliseconds. Step S33: Combining digital lock-in amplification technology, coherent detection is performed using the wideband excitation current signal from step S1 as the reference frequency. In-phase and quadrature components are extracted through orthogonal vector decomposition. The output signal-to-noise ratio is monitored in real time. The passband width and stopband attenuation parameters of the 16th-order finite-length unit impulse response filter are dynamically adjusted. The signal-to-noise ratio can be stably maintained at >90 dB under complex working conditions, resulting in high signal-to-noise ratio voltage data.

[0021] Furthermore, in step S4, based on the high signal-to-noise ratio voltage data obtained in step S3, a three-dimensional inversion calculation is performed using an improved electrical impedance tomography algorithm to reconstruct the conductivity distribution image inside the dam's seepage barrier. The improved electrical impedance tomography algorithm consists of four steps: accurate forward problem modeling, inverse problem construction and improvement, efficient iterative solution, and post-image optimization. The specific steps are as follows: Step S41: Accurate forward problem modeling, establishing a complete electrode model that includes contact resistance effects; Step S42, Inverse problem construction and improvement: The sensitivity matrix is ​​calculated by admittance method and the objective function is constructed by combining improved Tikhonov regularization with a regularization matrix based on discrete Laplace operator to constrain the smoothness of the solution; Step S43, Efficient Iterative Solution: The iterative process of solving the conductivity correction using the conjugate gradient method includes iterative solution updating, conjugate direction solving, and calculation of the objective function gradient. Step S44, post-image optimization: A pre-trained deep residual network is used to optimize the image to restore details and suppress noise, as shown in the formula: ; in, Image showing the electrical conductivity distribution inside the seepage barrier of the dam. Let θ represent a convolutional neural network, and let θ represent the set of parameters of the convolutional neural network.

[0022] Further, in step S41, precise forward problem modeling is performed to establish a complete electrode model that includes the contact resistance effect; the specific steps are as follows: Step S411: The governing equations for the complete electrode model are described using the Poisson equation to depict the potential distribution under the steady-state electric field, as shown in the formula: ; in, Denotes divergence, Indicates electrical conductivity. Represents the gradient. Represents electric potential; Step S412, Boundary conditions for the complete electrode model, considering the contact impedance at the electrode-dielectric interface, as shown in the formula: ; in, This represents the voltage measured on the l-th electrode. Indicates the first One electrode, Represents electric potential The directional derivative in the direction n, which is the outer normal to the boundary. Indicates injection of the first Current of each electrode Indicates the first The contact resistance between an electrode and the dielectric surface.

[0023] Further, in step S42, the inverse problem is constructed and improved by calculating the sensitivity matrix using the admittance method and constructing the objective function using the improved Tikhonov regularization, along with a regularization matrix based on the discrete Laplace operator, to constrain the smoothness of the solution; the specific steps are as follows: Step S421: Calculate the sensitivity matrix using the admittance method. The elements of the sensitivity matrix are shown in the formula: ; in, Let represent the element in the m-th row and p-th column of the sensitivity matrix J, and Ω represent the integration domain of the entire solution region. This represents the electric field distribution calculated under the i-th current excitation mode. dΩ represents the electric field distribution calculated under the j-th current excitation mode, where i ≠ j, and dΩ represents a volume element. Step S422: Construct the objective function using improved Tikhonov regularization; as shown in the formula: ; Where min represents minimizing, i.e. finding the minimum solution of the objective function value, Δσ represents the conductivity correction amount, ΔV represents the voltage change measured on the boundary electrode, λ represents the regularization parameter, and L represents the regularization matrix; Step S423: The regularization parameter is obtained by using an adaptive decay strategy that decreases with the number of iterations; as shown in the formula: ; Where α represents the proportionality coefficient, β represents the decay coefficient, k represents the number of iterations, and exp(-βk) represents the exponential decay function. Representation matrix The F-norm; Step S424: The regularization matrix L is constructed based on the discrete Laplace operator to constrain the smoothness of the solution; the elements of the regularization matrix are shown in the formula: ; in, This represents the element in the r-th row and s-th column of the regularization matrix L. Let represent the element in the r-th row and t-th column of the regularization matrix L.

[0024] Further, step S43 involves efficient iterative solution, achieved through an iterative process of solving for the conductivity correction using the conjugate gradient method. This process specifically includes updating the iterative solution, determining the conjugate direction, and calculating the gradient of the objective function. The specific steps are as follows: Step S431: The conductivity correction is obtained using the conjugate gradient method, as shown in the formula: ; in, This represents the conductivity correction amount in the (k+1)th iteration. This represents the conductivity correction amount in the k-th iteration. This represents the step size of the k-th iteration. This indicates the conjugate direction of the k-th iteration; Step S432, solve for the conjugate direction, as shown in the formula: ; in, This represents the gradient of the objective function in the k-th iteration. This represents the transpose of the gradient of the objective function in the k-th iteration. This represents the transpose of the gradient of the objective function in the (k-1)th iteration. This indicates the conjugate direction of the (k-1)th iteration; Step S433: Calculate the gradient of the objective function to understand its descent trend, as shown in the formula: ; in, This represents the transpose of the sensitivity matrix J. This represents the transpose of the regularization matrix L; Step S434: During the iteration process of steps S431 to S433, a convergence condition is set: the change in the objective function value is less than a threshold or the maximum number of iterations is reached; when the iteration process terminates after satisfying the convergence condition, the final conductivity correction amount Δσ is obtained. final Adding this to the initial conductivity distribution σ0 yields the preliminary conductivity distribution image σ reconstructed by the improved electrical impedance tomography algorithm. EIT .

[0025] Furthermore, in step S5, based on the conductivity distribution image inside the dam seepage barrier obtained in step S4, a deep learning model is used to analyze and identify defects; the specific steps are as follows: Step S51: Construct a simulation training database; establish a parametric geometric model library containing various dam structures, dam seepage prevention materials, and foundation types; embed typical defects with adjustable parameters, including seepage channels, cracks, and cavities, into the model base of the geometric model library; for each parametric model, perform forward problem calculations of electrical impedance tomography to simulate the excitation and measurement processes of steps S1 to S3, generating simulated voltage data; subsequently, input the simulated voltage data into the improved electrical impedance tomography algorithm in step S4 for inversion, generating the corresponding three-dimensional conductivity distribution image as input data for training samples; finally, generate a simulation training database containing more than 100,000 sets of samples. Step S52: Design and construct a 3D defect recognition model; adopt a U-shaped network as the basic architecture; replace the encoder of the U-shaped network with a residual network-50 as the backbone feature extraction network; embed a spatial attention module at the jump connection between the encoder and the decoder; use a normalized exponential function at the end of the decoder to achieve pixel-level defect classification. Step S53: Train the end-to-end 3D defect recognition model from step S52; use a hybrid loss function of Dess loss and cross-entropy loss to train the 3D defect recognition model and obtain the trained 3D defect recognition model. In step S54, the conductivity distribution image inside the dam seepage prevention body obtained in step S4 is input into the trained three-dimensional defect recognition model. The encoder is used to downsample the image to 1 / 32 resolution and extract feature maps at different levels. Subsequently, the feature maps are upsampled by the decoder and fused with the same-scale encoder features weighted by skip connections and spatial attention modules. Finally, a defect classification probability map of the same size as the input image is output. Step S55: For the defect classification probability map output in step S54, a three-dimensional connected component analysis algorithm is used to identify each independent defect; a sub-pixel localization algorithm is used to calculate the three-dimensional coordinates of the geometric center of each independent defect; finally, the category, three-dimensional coordinates of the geometric center, and equivalent size information of all defects are integrated to generate and output a three-dimensional defect distribution map with spatial coordinates.

[0026] Further, in step S6, an electro-seepage coupled inversion model is constructed to convert the conductivity distribution image inside the dam seepage barrier obtained in step S4 into a permeability coefficient distribution, and a dam seepage barrier integrity evaluation report is generated; the specific steps are as follows: Step S601: Based on the inherent physical relationship between electrical conductivity and permeability in soil and rock media, and using the traditional Alzer's law as a foundation, an electro-permeability coupled inversion model is established, as shown in the formula: ; Where K represents the permeability coefficient, with units of centimeters per second or meters per day. Volume conductivity is expressed in Siemens per meter (S / m). The empirical coefficients of the model are represented by u, which depend on the mineral composition, pore structure and cementation of the dam seepage prevention material, and u = 1, 2, 3, 4. Step S602: Accurately calibrate the empirical coefficients of the model through indoor geotechnical tests; prepare a series of dam seepage prevention material samples with different mix ratios, including different moisture contents, densities, and clay contents; for each dam seepage prevention material sample, use a permeameter to measure the permeability coefficient and a resistivity meter to measure the volumetric conductivity. Step S603: Substitute the measured volumetric conductivity and permeability coefficient into the electro-seepage coupling inversion model, and use the nonlinear least squares method to perform regression analysis to solve for the specific coefficients of the dam seepage prevention material, i.e., the empirical coefficients of the model. Step S604: Using the conductivity distribution image inside the dam seepage barrier from step S4 as input, and using the empirical coefficients of the model from step S603, the initial permeability coefficient distribution of the entire dam seepage barrier region is initially calculated through the electro-seepage coupling inversion model. Step S605: Based on the initial permeability coefficient distribution of the entire dam seepage prevention area, construct the governing equations for the steady-state seepage field, as shown in the formula: ; Where K represents the permeability coefficient distribution and h represents the total head, which drives seepage. Step S606: Discretize the three-dimensional structure of the dam seepage barrier into a finite element mesh; apply the corresponding head boundary or flow boundary to the finite element mesh according to the actual operating conditions of the dam seepage barrier; solve the control equation of the steady-state seepage field using the finite element method to obtain the head distribution within the entire dam seepage barrier area. Step S607: Define the objective function, which is to minimize the difference between the head distribution and the measured head distribution; starting from the initial permeability coefficient distribution, use the gradient descent method or Gauss-Newton method to repeatedly adjust the permeability coefficient distribution, and return to step S606 to solve the control equation of the steady-state seepage field until the objective function value is less than the preset threshold, and finally obtain the high-precision permeability coefficient distribution. Step S608: Perform spatial analysis on the obtained high-precision permeability coefficient distribution; set a critical permeability coefficient value K. crit Automatically identify and mark all permeability coefficient distribution values ​​K that are greater than or equal to the critical permeability coefficient value K. crit The spatial area is marked as the weak zone in seepage prevention, and its three-dimensional spatial coordinates and volume are recorded. Step S609: Based on the results of steps S607 and S608, calculate the structural integrity score S of the dam's seepage prevention structure; as shown in the formula: ; Among them, V total V represents the total volume of the dam's seepage prevention structure. weak This indicates the total volume of the identified weak points in the seepage prevention system. This represents the average permeability coefficient across all weak zones. Step S610: Based on the results of steps S608 and S609, generate a dam seepage prevention integrity evaluation report that includes a permeability coefficient distribution map, a weak zone location map, and a structural integrity score.

[0027] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for detecting the integrity of an artificial power-based dike cutoff, characterized in that, The method comprises the following steps: Step S1, injecting a wideband excitation current signal into the dam seepage prevention body through a multi-frequency constant current source; Step S2, based on the wideband excitation current signal of step S1, using a modular distributed electrode array to collect voltage data on the surface of the dam seepage prevention body in real time; Step S3, based on the voltage data on the surface of the dam seepage prevention body obtained in step S2, using filtering processing and digital lock-in amplification technology to obtain high signal-to-noise ratio voltage data; Step S4, based on the high signal-to-noise ratio voltage data obtained in step S3, using an improved electrical impedance tomography algorithm for three-dimensional inversion calculation to reconstruct the internal conductivity distribution image of the dam seepage prevention body; Step S5, based on the internal conductivity distribution image of the dam seepage prevention body of step S4, analyzing, identifying and positioning defects through a deep learning model; Step S6, constructing an electro-osmotic coupling inversion model, converting the internal conductivity distribution image of the dam seepage prevention body based on step S4 into a permeability coefficient distribution, and generating a dam seepage prevention body integrity evaluation report.

2. The method for detecting the integrity of a dam anti-seepage body based on an artificial power source according to claim 1, characterized in that, In step S1, the wideband excitation current signal is injected into the dam seepage prevention body through a multi-frequency constant current source; the specific steps are as follows: Step S11, establishing a dam seepage prevention body material-frequency response database to pre-store the optimal excitation frequency band of different materials; Step S12, the multi-frequency constant current source automatically identifies the type of dam seepage prevention body material through impedance spectrum rapid scanning and intelligently matches the optimal excitation frequency band; Step S13, using a proportional-integral-derivative closed-loop control algorithm to dynamically adjust the multi-frequency constant current source to inject a wideband excitation current signal of 0.1-1000 Hz into the dam seepage prevention body; Step S14, integrating an overload protection module in the multi-frequency constant current source, and the multi-frequency constant current source automatically cuts off the output and alarms when the contact resistance is greater than 10 kΩ.

3. The method for detecting the integrity of a dam anti-seepage body based on an artificial power supply according to claim 2, characterized in that, In step S2, based on the wideband excitation current signal of step S1, a modular distributed electrode array is used to collect voltage data on the surface of the dam seepage prevention body in real time; the specific steps are as follows: Step S21, the modular distributed electrode array is deployed with 128 high-precision silver-silver chloride electrodes at an interval of 1 meter, and a preamplifier circuit with a gain of 100 times and an impedance detection module with a contact impedance of less than 3 kΩ are integrated with the high-precision silver-silver chloride electrodes; Step S22, based on the modular distributed electrode array in step S21, multi-channel time synchronization is achieved through global positioning system synchronous triggering, 24-bit sigma-delta analog-to-digital converters are used for synchronous sampling, and 0.1-1.5 kHz adaptive bandpass filtering and 40-70 Hz adjustable dynamic power trap are used to obtain voltage data on the surface of the dam seepage prevention body.

4. The method for detecting the integrity of a dam anti-seepage body based on an artificial power source according to claim 3, characterized in that, In step S3, based on the voltage data on the surface of the dam seepage prevention body obtained in step S2, high signal-to-noise ratio voltage data is obtained by using filtering processing and digital lock-in amplification technology; the specific steps are as follows: Step S31, performing primary noise suppression on the voltage data on the surface of the dam seepage prevention body through a hardware bandpass filter; Step S32, using an adaptive notch filter based on the least mean square algorithm to track and eliminate 50 Hz power frequency and harmonic interference of 50 Hz power frequency in real time, with a convergence time of less than 100 milliseconds; Step S33, combined with digital lock-in amplification technology, the wideband excitation current signal in step S1 is used as the reference frequency for coherent detection, the in-phase and quadrature components are extracted through quadrature vector decomposition, the output signal-to-noise ratio is monitored in real time, the passband width and stopband attenuation parameters of the 16-order finite-length unit impulse response filter are dynamically adjusted, the signal-to-noise ratio can be stably maintained at >90 decibels under complex working conditions, and high signal-to-noise ratio voltage data is obtained.

5. The method for detecting integrity of a dam anti-seepage body based on an artificial power source according to claim 4, characterized in that, In step S4, based on the high signal-to-noise ratio voltage data obtained in step S3, an improved electrical impedance tomography algorithm is used for three-dimensional inversion calculation to reconstruct the internal conductivity distribution image of the dam anti-seepage body; wherein the improved electrical impedance tomography algorithm consists of four links of accurate forward problem modeling, inverse problem construction and improvement, efficient iterative solution, and image post-optimization; the specific steps are as follows: Step S41, accurate forward problem modeling, a complete electrode model containing contact impedance effect is established; Step S42, inverse problem construction and improvement, the sensitivity matrix is calculated by the admittance method, and the objective function is constructed by combining the improved Tikhonov regularization and the regularization matrix based on the discrete Laplace operator to constrain the smoothness of the solution; Step S43, efficient iterative solution, the iterative process of the conductivity correction amount is solved by using the conjugate gradient method, which specifically includes iterative solution updating, conjugate direction solving, and target function gradient calculation; Step S44, image post-optimization, a pre-trained deep residual network is used for image optimization to restore details and suppress noise as shown in the formula: ； wherein, represents an internal electrical conductivity distribution image of the dam impervious body, represents a convolutional neural network, and θ represents a parameter set of the convolutional neural network.

6. The method for detecting integrity of a dam anti-seepage body based on an artificial power source according to claim 5, characterized in that, Step S41, accurate forward problem modeling, a complete electrode model containing contact impedance effect is established; the specific steps are as follows: Step S411, control equation of complete electrode model, Poisson equation is used to describe the potential distribution under steady-state electric field, as shown in the formula: ； wherein, denotes divergence, denotes conductivity, denotes gradient, denotes electric potential; Step S412, boundary condition of complete electrode model, considering the contact impedance of electrode-dielectric interface, as shown in the formula: ； wherein Vl denotes the voltage measured at the lth electrode, Vl denotes the voltage measured at the lth electrode, Vl denotes the voltage measured at the lth electrode, Vl denotes the voltage measured at the lth electrode, Vl denotes the voltage measured at the lth electrode, Vl denotes the voltage measured at the lth electrode, Vl denotes the voltage measured at the lth electrode, Vl denotes the voltage measured at the lth electrode, Vl denotes the voltage measured at the lth electrode, 7. The method for detecting integrity of a dam anti-seepage body based on an artificial power source according to claim 6, characterized in that, Step S42, inverse problem construction and improvement, the sensitivity matrix is calculated by the admittance method, and the objective function is constructed by combining the improved Tikhonov regularization and the regularization matrix based on the discrete Laplace operator to constrain the smoothness of the solution; the specific steps are as follows: Step S421, the sensitivity matrix is calculated by the admittance method, the elements of the sensitivity matrix are as shown in the formula: ； wherein, represents the element of the sensitivity matrix J in the mth row and the pth column, Ω represents the integral domain of the entire solving region, represents the electric field distribution calculated in the ith current excitation mode, represents the electric field distribution calculated in the jth current excitation mode, i≠j, dΩ represents a volume element; Step S422, the objective function is constructed by the improved Tikhonov regularization; as shown in the formula: ； Wherein, min represents the minimum of the objective function value, Δσ represents the conductivity correction amount, ΔV represents the voltage change measured on the boundary electrode, λ represents the regularization parameter, and L represents the regularization matrix; Step S423, the regularization parameter is obtained by using the adaptive attenuation strategy with the number of iterations; as shown in the formula: ； wherein a denotes a proportional coefficient, β denotes an attenuation coefficient, k denotes an iteration number, exp(-βk) denotes an exponential attenuation function, denotes the F-norm of the matrix ​ Step S424, the regularization matrix L is constructed based on the discrete Laplace operator to constrain the smoothness of the solution; the elements of the regularization matrix are as shown in the formula: ； wherein denotes the element of the regularization matrix L in the rth row and sth column, denotes the element of the regularization matrix L in the rth row and tth column.

8. The method for detecting integrity of a dam anti-seepage body based on an artificial power source according to claim 7, characterized in that, Step S43, efficient iterative solution, the iterative process of the conductivity correction amount is solved by using the conjugate gradient method, which specifically includes iterative solution updating, conjugate direction solving, and target function gradient calculation; the specific steps are as follows: Step S431, the conductivity correction amount is obtained by using the conjugate gradient method, as shown in the formula: ； wherein, denotes the conductivity correction of the k+1 iteration, denotes the conductivity correction of the k iteration, denotes the step size of the k iteration, denotes the conjugate direction of the k iteration; Step S432, the conjugate direction is solved, as shown in the formula: ； wherein, denotes the gradient of the objective function at the kth iteration, denotes the transpose of the gradient of the objective function at the kth iteration, denotes the transpose of the gradient of the objective function at the k-1th iteration, denotes the conjugate direction at the k-1th iteration; Step S433, the gradient of the objective function is calculated to know the downward trend of the objective function, as shown in the formula: ； wherein, denotes the transpose of the sensitivity matrix J, denotes the transpose of the regularization matrix L; Step S434, in the iterative process of executing steps S431 to S433, a convergence condition is set: the change amount of the objective function value is less than a threshold value or the maximum iteration number is reached; when the iterative process is terminated when the convergence condition is met, the final obtained conductivity correction amount Δσ final is added to the initial conductivity distribution σ0, to obtain the preliminary conductivity distribution image σ reconstructed by the improved electrical impedance tomography algorithm EIT .

9. The method of claim 8, wherein the artificial power source is a battery. In step S5, the internal conductivity distribution image of the dam impervious body based on step S4 is analyzed by a deep learning model to identify and locate defects; the specific steps are as follows: Step S51, construct a simulated training database; a parameterized geometric model library containing various dam structures, dam impervious body materials and foundation types is established; typical defects including leakage channels, cracks and cavities are embedded in the models in the geometric model library; For each parameterized model, perform the forward problem calculation of electrical impedance tomography, simulate the excitation and measurement process of steps S1 to S3, and generate simulated voltage data; then, input the simulated voltage data into the improved electrical impedance tomography algorithm of step S4 for inversion to generate the corresponding three-dimensional conductivity distribution image as the input data of the training sample; finally, a simulated training database containing more than 100,000 samples is generated; Step S52, design and build a three-dimensional defect recognition model; use a U-shaped network as the basic architecture; replace the encoder of the U-shaped network with a residual network-50 as the backbone feature extraction network; At the jump connection of the encoder and the decoder, a spatial attention module is embedded; the end of the decoder uses a normalized exponential function to realize pixel-level defect classification; Step S53, train the three-dimensional defect recognition model of step S52 in an end-to-end manner; use a hybrid loss function of Dice loss and cross-entropy loss to train the three-dimensional defect recognition model to obtain a trained three-dimensional defect recognition model; Step S54, input the internal conductivity distribution image of the dam impervious body of step S4 into the trained three-dimensional defect recognition model, and gradually downsample to 1 / 32 resolution through the encoder to extract feature maps at different levels; Then, the feature maps are gradually upsampled through the decoder, and the same scale encoder features weighted through the jump connection and the spatial attention module are fused, and finally a defect classification probability map with the same size as the input image is output; Step S55, use a three-dimensional connected component analysis algorithm to identify each independent defect based on the defect classification probability map output in step S54; use a sub-pixel positioning algorithm to calculate the three-dimensional coordinates of the geometric center of each independent defect; finally, integrate the class, three-dimensional coordinates of the geometric center, and equivalent size information of all defects to generate and output a three-dimensional defect distribution map with spatial coordinates.

10. The method for detecting integrity of a dam anti-seepage body based on an artificial power source according to claim 9, characterized in that, In step S6, an electro-osmotic coupling inversion model is constructed to convert the internal conductivity distribution image of the dam impervious body based on step S4 into a permeability coefficient distribution, and generate a dam impervious body integrity evaluation report; the specific steps are as follows: Step S601, based on the internal physical correlation between conductivity and permeability in rock-soil media, use the traditional Archie law as the basis to establish an electro-osmotic coupling inversion model, as shown in the formula: ； where K represents the permeability coefficient, in centimeters per second or meters per day, represents the volume conductivity, in siemens per meter, represents the empirical coefficient of the model, whose value depends on the mineral composition, the pore structure and the cementation of the dam impervious body material, u = 1, 2, 3, 4; Step S602, accurately calibrate the empirical coefficient of the model through indoor geotechnical test; prepare a series of dam seepage prevention material samples with different mix proportions, including different water contents, densities, and clay contents; for each dam seepage prevention material sample, measure the permeability coefficient using a permeameter, and measure the volume conductivity using a resistivity meter; Step S603, substitute the measured volume conductivity and permeability coefficient into the electro-osmotic coupling inversion model, and perform regression analysis using the nonlinear least squares method to solve the specific coefficient of the dam seepage prevention material, i.e., the empirical coefficient of the model; Step S604, input the internal conductivity distribution image of the dam seepage prevention body obtained in step S4, and use the empirical coefficient of the model obtained in step S603 to preliminarily calculate the initial permeability coefficient distribution of the entire dam seepage prevention body region through the electro-osmotic coupling inversion model; Step S605, based on the initial permeability coefficient distribution of the entire dam seepage prevention body region, construct the control equation of the steady seepage field, as shown in the formula: ； Where K represents the permeability coefficient distribution, and h represents the total water head driving seepage to occur; Step S606, discretize the three-dimensional structure of the dam seepage prevention body into finite element grids; according to the actual operating conditions of the dam seepage prevention body, apply corresponding water head boundaries or flow boundaries on the finite element grids; solve the control equation of the steady seepage field through the finite element method to obtain the water head distribution in the entire dam seepage prevention body region; Step S607, define the objective function, i.e., minimize the difference between the water head distribution and the measured water head distribution; starting from the initial permeability coefficient distribution, repeatedly adjust the permeability coefficient distribution using the gradient descent method or Gauss-Newton method algorithm, and return to solve the control equation of the steady seepage field in step S606 until the objective function value is less than the preset threshold, and finally obtain the high-precision permeability coefficient distribution; Step S608, spatial analysis is performed on the obtained high-precision permeability coefficient distribution; a critical permeability coefficient value K crit is set, and all spatial regions with a permeability coefficient distribution value K crit greater than or equal to the critical permeability coefficient value K crit are automatically identified and marked, the marked spatial regions are weak anti-seepage zones, and the three-dimensional spatial coordinates and volume thereof are recorded. Step S609, based on the results of steps S607 and S608, calculate the structural integrity score S of the dam seepage prevention body; as shown in the formula: ； where V total represents the total volume of the dam impervious body, V weak represents the total volume of the identified impervious weak zone, represents the average value of the permeability coefficient within all weak zones; Step S610, generate a dam seepage prevention body integrity evaluation report containing the permeability coefficient distribution map, weak area positioning map, and structural integrity score based on the results of steps S608 and S609.

Images