Method for identifying underwater crack behavior of concrete faced rockfill dam

Abstract

The invention discloses a concrete faced rockfill dam underwater crack behavior identification method comprising the following steps: obtaining original monitoring data and a concrete faced rockfill dam as-built drawing, and carrying out preprocessing; constructing a rock-fill penetration-mechanical coupling state model to obtain a state field and an uncertainty field; based on the state field and the as-built drawing, a panel deformation field and a stress field are obtained through panel deformation and stress analysis; the deformation field, the stress field and underwater detection data are utilized, and a crack behavior comprehensive report is obtained through crack feature extraction and visualization. According to the method, the penetration-mechanical coupling state index is introduced, the rock-fill state space partitioning is realized, the deformation field reconstruction accuracy is improved, and a scientific basis is provided for dam safety assessment.

Description

Technical Field

[0001] The invention belongs to the field of water conservancy engineering, and in particular to a method for identifying underwater crack properties of a face rockfill dam. Background Art

[0002] Concrete face rockfill dam is one of the mainstream forms of dam construction today, and its safe operation is crucial to water conservancy projects and the national economy. As a key anti-seepage structure, concrete face panels are prone to cracks under long-term water pressure and rockfill deformation, especially underwater cracks that are difficult to observe directly, posing a potential threat to the safety of the dam. Accurately identifying the location, shape and development trend of underwater cracks is of great significance for preventing leakage accidents, extending the service life of dams and formulating scientific maintenance plans.

[0003] At present, underwater crack identification mainly relies on sonar scanning, underwater video and manual diving detection. Sonar scanning can obtain the outline of underwater structures; underwater video can record surface details; and manual diving detection provides direct observation. In terms of data processing, common methods include image segmentation, contour extraction and acoustic signal processing to identify crack characteristics, and use empirical or semi-empirical models to analyze the correlation between deformation and cracks. In addition, multi-source data fusion technology has gradually been applied to the field of underwater structure detection, which has improved the comprehensiveness of information acquisition.

[0004] The most critical problem in the existing technology is the lack of a coupled modeling method that can simultaneously consider the mutual influence of the stress state and permeability of the rockfill body. The rockfill body shows significant differences in permeability under different stress states, especially in the critical stress region, where there are nonlinear changes. This permeability-mechanical coupling state will directly affect the deformation of the panel and the development of cracks. Existing studies often separate the seepage analysis from the stress analysis, or use a simple linear relationship to characterize the interaction between the two. They cannot accurately characterize the spatiotemporal evolution of the permeability-mechanical relationship of the rockfill body under complex stress fields, especially the local nonlinear behavior in areas where the stress gradient changes dramatically. This technical difficulty seriously restricts the accuracy of underwater fracture state identification, and innovative solutions are urgently needed. Summary of the invention

[0005] The purpose of the invention is to provide a method for identifying underwater crack properties of a concrete face rockfill dam, in order to solve at least one technical problem existing in the prior art.

[0006] Technical solution: a method for identifying underwater crack properties of a face rockfill dam, comprising the following steps: The original monitoring data and the completion drawings of the concrete face rockfill dam were obtained, and the standardized monitoring data set and data reliability index were obtained through preprocessing. Based on the standardized monitoring data set, data reliability index and the completion drawing of the concrete face rockfill dam, the rockfill state field and state uncertainty field are obtained through the rockfill body permeability-mechanical coupling state modeling. Using the rockfill state field, state uncertainty field and as-built drawings of the face rockfill dam, the face deformation field and face stress field are obtained through face deformation and stress analysis. Based on the panel deformation field, panel stress field and pre-stored underwater detection data, a comprehensive report on crack properties is generated through crack feature extraction and visual decision support.

[0007] Beneficial effect: The present invention realizes high-precision modeling of the permeability-mechanical coupling state of the rockfill body, provides a reliable theoretical basis for subsequent face plate deformation and stress analysis and crack feature extraction, and ultimately achieves the purpose of accurately identifying the underwater crack properties of the face plate rockfill dam. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 A flowchart of the steps of a method for identifying underwater crack properties of a face rockfill dam provided in an embodiment of the present application.

[0009] Figure 2 A flowchart of the steps for modeling the permeability-mechanical coupling state of a rockfill body provided in an embodiment of the present application.

[0010] Figure 3 A flowchart of the steps for characterizing the spatial heterogeneity of the state of a rockfill body provided in an embodiment of the present application.

[0011] Figure 4 A flowchart of the steps for obtaining a panel deformation field and a panel stress field through panel deformation and stress analysis provided in an embodiment of the present application. DETAILED DESCRIPTION

[0012] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0013] It should be noted that in order to clearly show the steps of this application, serial numbers are marked for each step in the specification. These serial numbers are only used for the convenience of explanation and do not limit the order of execution of the steps. In actual operation, according to the technical requirements of the specific implementation scenario, the steps can be executed in a different order than that shown in the specification, and in some cases, parallel processing between steps can be achieved.

[0014] like Figure 1 As shown, a method for identifying underwater crack properties of a concrete face rockfill dam comprises the following steps: S1. Obtain the original monitoring data and the completion drawing of the panel rockfill dam, and pre-process them to obtain the standardized monitoring data set and data reliability index; Specifically, the original monitoring data include: structural geometry data: 3D geometry information of the above-water part of the panel, the dam top and the downstream dam surface obtained through 3D laser scanning; underwater sonar scanning data: including the underwater dimensions and blanket morphology of the panel; deformation monitoring data: dam deformation information obtained through water tube sedimentation instrument; mechanical parameter data: including stress and strain measurement data; hydraulic parameter data: including hydraulic monitoring data such as pore water pressure and flow rate; temperature field data: temperature distribution information inside and outside the dam body; time series monitoring data: historical records of the changes of various parameters over time. The completion drawings of the panel rockfill dam are the final design and construction records formed after the completion of the project construction. These drawings describe in detail the design parameters of the dam structure and each component.

[0015] S2. Based on the standardized monitoring data set, data reliability index and the completion drawing of the concrete face rockfill dam, the rockfill state field and state uncertainty field are obtained through the rockfill body permeability-mechanical coupling state modeling; Specifically, in the model, water infiltration and the mechanical behavior of the dam structure (rockfill) are considered at the same time. In other words, the flow of water inside the dam (infiltration) and the deformation of the dam under pressure (mechanical behavior) are coupled and affect each other. Through numerical simulation, the "actual state field of the dam" can be obtained, which includes information such as stress, deformation state, internal water pressure, etc. in each area, like a "map" of the internal conditions of the dam. Since there is a certain degree of uncertainty in both monitoring data and model parameters, the model also evaluates the reliability of the prediction results in each area, which forms a state uncertainty field, which can show which areas have high credibility in the evaluation results and which areas may need to be treated more cautiously due to data or parameter problems.

[0016] S3, using the rockfill state field, state uncertainty field and the as-built drawing of the face rockfill dam, the face deformation field and face stress field are obtained through face deformation and stress analysis; Specifically, the state information of the rockfill is used as input conditions, and combined with the geometric shape and material properties of the components, numerical simulation or theoretical calculation is carried out to calculate the deformation (such as bending, displacement) and stress distribution (such as compressive stress, tensile stress) of the dam panel under the influence of internal driving force, reaction and external environment.

[0017] S4. Based on the panel deformation field, panel stress field and pre-stored underwater detection data, a comprehensive report on crack properties is generated through crack feature extraction and visual decision support.

[0018] Specifically, the crack characteristics are extracted and their development mechanism is analyzed to generate a multi-dimensional visualization of the crack state and provide targeted maintenance suggestions. In other words, the panel deformation field and stress field can be used to find out which areas have abnormalities. For example, if the deformation suddenly increases or the stress is concentrated in a certain area, it may indicate that cracks have formed or expanded in the local structure. By comparing or combining these abnormal areas with underwater detection data, the characteristics of the cracks (such as location, length, width, depth, etc.) can be further confirmed and refined. After extracting the crack-related features, data visualization technology is used to intuitively present the distribution and severity of the cracks through charts, maps or 3D models.

[0019] This embodiment achieves comprehensive and dynamic monitoring of the safety status of the dam structure through multi-source data integration, precise physical coupling modeling and intuitive visual decision support; from reducing data errors, improving model accuracy, to timely and scientific identification of potential structural problems, the entire process has improved the technical level of dam health monitoring and risk warning.

[0020] According to one aspect of the present application, the pre-processing step is specifically as follows: S11, reading 3D laser scanning data, underwater sonar scanning data, and water tube sedimentation instrument monitoring data, and calibrating them through time tags to form original monitoring data; S12, read the original monitoring data, identify and mark abnormal values ​​using statistical methods, and calculate the data quality index of each monitoring point; S13, reading the original monitoring data and data quality indicators, performing spatiotemporal coordinate conversion and alignment of multi-source data, and generating a spatiotemporal aligned data set; S14, read the spatiotemporal aligned data set, apply the adaptive wavelet denoising algorithm according to the characteristics of different sensors and environmental interference factors, and output the standardized monitoring data set and the data reliability index for comprehensive evaluation.

[0021] like Figure 2 As shown, according to one aspect of the present application, the steps of obtaining the rockfill body state field and state uncertainty field by modeling the rockfill body permeability-mechanical coupling state include: S21. Based on the as-built drawings of the concrete face rockfill dam and the structural information in the standardized monitoring data set, a physical model of the rockfill body is established, and a geometric model of the rockfill body and material partition information are generated; S22. Characterize the spatial heterogeneity of the rockfill state by combining the standardized monitoring data set, data reliability index and material partition information to form the spatial distribution characteristics of the rockfill state; S23. Based on the spatial distribution characteristics of the rockfill state and the time series data in the standardized monitoring data set, simulate the dynamic evolution of the time-varying state and construct a spatiotemporal evolution model of the rockfill state; S24. Integrate the spatiotemporal evolution model of the rockfill state and the data reliability index, analyze and quantify the uncertainty and its propagation law, and output the rockfill state field and state uncertainty field.

[0022] Specifically, the standardized monitoring data set, data reliability index and material partition information are read, and the stress state sensitive self-organizing mapping method is used to identify and characterize the spatial heterogeneity of the rockfill body's permeability-mechanical coupling characteristics, and output the spatial distribution characteristics of the rockfill body state. Based on the spatial distribution characteristics of the rockfill body state and the time series data in the standardized monitoring data set, a time-varying evolution model of the rockfill body's permeability-mechanical coupling state is constructed, and the spatiotemporal evolution model of the rockfill body state is output. According to the spatiotemporal evolution model of the rockfill body state and the data reliability index, a method combining Monte Carlo simulation and variational Bayesian inference is used to quantify the uncertainty of the rockfill body state parameters and their propagation laws, and generate the rockfill body state field and state uncertainty field.

[0023] This embodiment extracts fine structural information from static design drawings and real-time monitoring data, constructs a geometric model and material partitioning that truly reflects the complex internal structure of the dam, and ensures that subsequent calculations are based on a solid and accurate information foundation; by characterizing the heterogeneity of the rockfill state space, it reveals the local differences in internal materials, structures and stress conditions, and enhances the ability to locate risks and regional differentiated management; the model can capture the dynamic evolution trend of the dam state over time, and provide early warning and trend analysis support for fault prediction, accident prevention and maintenance decisions; it not only gives a prediction of the current state, but also clarifies the uncertainty range of the prediction results, scientifically supporting engineers in focusing on monitoring risk areas and formulating response measures; it realizes all-round monitoring and description of the dam rockfill from spatial distribution to temporal evolution.

[0024] like Figure 3 As shown, according to one aspect of the present application, the steps of characterizing the spatial heterogeneity of the rockfill state and forming the spatial distribution characteristics of the rockfill state include: Extract relevant monitoring data from the standardized monitoring data set and construct a permeability-mechanical coupling state index that considers effective stress, pore water pressure, and strain state; Based on the permeability-mechanical coupling state index and material partition information, stress state sensitive self-organizing mapping is performed to divide the rockfill state characteristic partitions; According to the state characteristic zoning of rockfill bodies, a regional mechanical characteristic dynamic model considering stress-seepage coupling is established to generate a set of local mechanical response models; Based on the local mechanical response model set and data reliability indicators, boundary adaptive fusion is implemented to achieve seamless connection of different partition models and output the spatial distribution characteristics of the rockfill state.

[0025] Specifically, the local mechanical response model set and data reliability index are read, and the boundary adaptive fusion method is used to achieve seamless connection of different partition models, and output the spatial distribution characteristics of the rockfill state; the boundary adaptive fusion algorithm: CSI(x) = Σi[Wi(x)·CSIi(x)]; Wi(x) = Ri·ρi(x) / Σj[Rj·ρj(x)]; ρi(x) = exp(-di(x) 2 / 2li 2 ); CSI(x) is the fused state indicator field; CSIi(x) is the state indicator of the ith local model; Wi(x) is the weight of the ith model at position x; Ri is the reliability score of the ith model; ρi(x) is the distance decay function; di(x) is the distance from point x to the center of the ith region; li is the characteristic length scale of the ith region; x is the spatial coordinate point; i and j are the indexes of the state characteristic partitions. The seamless connection of different regional models is achieved through the boundary adaptive fusion method, and each local model is weightedly fused according to data reliability and spatial distance, which effectively solves the spatial heterogeneity of the permeability-mechanical relationship inside the rockfill.

[0026] This embodiment comprehensively analyzes the mutual influence of stress, seepage, and deformation state of the rockfill body, accurately characterizes the spatial heterogeneity of the rockfill body; dynamically simulates the response characteristics of the rockfill body under different stress states, thereby improving the prediction and control capabilities; connects different partition models to ensure seamless connection between partitions, which helps to achieve overall optimization and coordination of spatial distribution characteristics of the rockfill body state; and enhances the credibility and accuracy of the technical results in the model generation process, ensuring that the final state distribution characteristics can accurately reflect the actual situation.

[0027] Since traditional methods usually only consider a single indicator of water content or pore water pressure to characterize the degree of wetting, the complex state of solid-liquid-gas coexistence inside the rockfill is ignored. Therefore, according to one aspect of the present application, the steps of constructing a permeability-mechanical coupling state indicator include: Extract effective stress, pore water pressure, and strain state data from standardized monitoring data sets; Establish a mathematical model that comprehensively considers effective stress, pore water pressure and strain state, and calculate the permeability-mechanical coupling state index CSI (x, t); CSI(x,t) = α·σ'(x,t) / σ'max + β·P(x,t) / Pmax + γ·ε(x,t) / εmax; Where CSI(x, t) represents the permeability-mechanical coupling state index of the spatial point x at time t; σ'(x, t) represents the effective stress; P(x, t) represents the pore water pressure; ε(x, t) represents the strain; σ'max represents the maximum effective stress; Pmax represents the maximum pore water pressure; εmax represents the maximum strain; α, β, γ represent weight coefficients, and α+β+γ=1; x represents the spatial coordinate point; t represents the time point.

[0028] This embodiment introduces a comprehensive permeability-mechanical coupling state index (CSI), and unifies the three key parameters of effective stress, pore water pressure and strain into a quantitative framework through the formula CSI(x, t) = α·σ'(x, t) / σ'max + β·P(x, t) / Pmax + γ·ε(x, t) / εmax, thereby realizing a comprehensive characterization of the complex state inside the rockfill body, overcoming the limitation of the traditional method of separating the seepage and mechanical analysis, and solving the problem that a single index cannot fully describe the wetting state.

[0029] The traditional SOM algorithm cannot effectively identify the critical point of the phase change of the wetting degree when processing the wetting zoning of the rockfill body. Therefore, according to one aspect of the present application, the steps of performing stress state sensitive self-organizing mapping and dividing the rockfill body state characteristic zoning include: Input the permeability-mechanical coupling state index and material partition information; Apply the improved self-organizing map algorithm to partition the rockfill state space and generate the rockfill state characteristic partitions; The improved self-organizing map algorithm contains the following core update formula: wij(t+1) = wij(t) + η(t)·h(i,BMU(x),t)·[x - wij(t)]·ψ(σ'(x,t)); where wij(t) is the j-th dimension weight of the ith neuron at time t; η(t) is the learning rate, η(t) = η0·exp(-t / τ1), η0 is the initial learning rate; h(i, BMU(x), t) is the neighborhood function, h(i, BMU(x), t) = exp(-||ri -rBMU(x)|| 2 / (2σ 2 (t))); ri is the position of the ith neuron in the grid; r is the spatial position; σ(t) is the neighborhood radius, σ(t) = σ0 exp(-t / τ2); τ1, τ2 are time constants; σ0 is the initial neighborhood radius; BMU(x) is the best matching unit index; ψ(σ'(x, t)) is the stress state sensitivity function, ψ(σ') = [1 + exp(-k (σ'-σ'0))] -1; σ'(x, t) is the effective stress; σ'0 is the stress critical value; k is the stress sensitivity parameter; x is the characteristic vector of the input sample, rBMU(x) is the position of the best matching unit in the grid, and t is the number of iterations.

[0030] Among them, the stress state sensitivity function ψ(σ') is used to adjust the sensitivity of the algorithm to different stress state areas and improve the recognition accuracy of the critical stress area.

[0031] This embodiment proposes a stress state sensitive self-organizing mapping algorithm, by introducing a stress sensitive function ψ(σ') = [1 + exp(-k·(σ'-σ'0))] into the traditional SOM algorithm -1 , achieving accurate identification of critical stress areas. The algorithm has differentiated response sensitivities to areas with different stress states, especially enhancing the ability to identify areas with drastic changes in stress gradients, solving the problem that traditional methods are difficult to accurately capture nonlinear change characteristics.

[0032] Traditional wetting diffusion models usually adopt homogeneous assumptions and fixed diffusion coefficients, which cannot capture the nonlinear characteristics of the wetting process inside the rockfill. Therefore, according to one aspect of the present application, the steps of establishing a regional mechanical property dynamic model include: Analyze the mechanical characteristics of the rockfill state characteristic zones; A dynamic model of regional mechanical characteristics considering stress-seepage coupling is constructed: ∏CSI(x, t) / ∏t = ▽·[D(x, σ', CSI)·▽CSI(x, t)] + Q(x, t, σ'); where ∏ is the partial derivative; D(x, σ', CSI) represents the diffusion coefficient tensor, D(x, σ', CSI) = D0 exp(-α e σ')·exp(λ·CSI)·R(θ); R(θ) represents the anisotropic rotation matrix; D0 represents the reference diffusion coefficient; α e represents the effective stress influence coefficient; λ represents the coupling state sensitivity coefficient; Q(x, t, σ') represents the source-sink term, which represents the state change rate caused by local stress change; θ represents the angle between the main diffusion direction and the reference direction; CSI(x, t) is the permeability-mechanical coupling state index of the spatial point x at time t; σ' is the effective stress; ▽ is the gradient operator; x is the spatial coordinate point; t is the time point; ▽· is the divergence operator.

[0033] This embodiment constructs a regional mechanical property dynamics model, in which the diffusion coefficient tensor considers the influence of effective stress and coupling state index at the same time, and can accurately describe the nonlinear mechanical response of the rockfill under complex stress state, solving the problem of insufficient accuracy caused by the use of fixed diffusion coefficients in traditional diffusion models.

[0034] According to one aspect of the present application, The steps to generate a comprehensive report on fracture properties through fracture feature extraction and visual decision support include: Read the panel deformation field and panel stress field, calculate the crack sensitivity index of each area of ​​the panel based on the crack mechanics theory, and obtain the crack sensitive area map; Read underwater detection data and crack sensitive area map, apply wavelet transform domain morphological decomposition and adaptive reconstruction method to identify crack location, direction and width, and obtain crack characteristic data; Read crack characteristic data, panel stress field and panel deformation field, comprehensively analyze the cause, development status and risk level of the cracks, and obtain the crack property determination results; Read the crack behavior determination results, crack characteristic data and crack sensitive area map, generate a multi-dimensional crack behavior visualization expression, provide targeted maintenance suggestions based on risk analysis, and output a comprehensive crack behavior report.

[0035] Among them, the wavelet transform domain morphological decomposition and adaptive reconstruction method includes: Perform local illumination normalization and color channel weighted fusion on the underwater detection data to obtain a fused grayscale image; Apply multi-layer wavelet decomposition to the fused grayscale image to obtain low-frequency approximation coefficients and multi-layer detail coefficients; Calculate the directional coherence measure and phase consistency of the detail coefficients to obtain a directional coherence measure set and a phase consistency map; An adaptive enhancement function is constructed based on the directional coherence measure set and the phase consistency map to selectively enhance the wavelet coefficients and obtain enhanced wavelet coefficients. Performing inverse wavelet transform and local statistical enhancement on the enhanced wavelet coefficients to obtain an enhanced crack image; Morphological sharpening and crack feature measurement are applied to the enhanced crack image to obtain crack feature data.

[0036] The calculation of the directional coherence measure includes: reading the horizontal detail coefficient and the vertical detail coefficient, and calculating the initial directional coherence measure for each scale j and spatial position (x, y): M_j(x,y) = |∑ω cH_j(x,y)·cH_j(x+ω,y) + cV_j(x,y)·cV_j(x,y+ω)| / sqrt(cH_j(x,y)) 2 + cV_j(x,y) 2); calculate the directional consistency compensation coefficient in the local area: γ_j(x,y) = max(0, 1 - var(θ(x+Δx,y+Δy)) / π), where θ represents the local gradient direction and var represents the variance; combine the initial directional coherence measure and the directional consistency compensation coefficient to calculate the compensated directional coherence measure: M'_j(x,y) = M_j(x,y)·(1 + α_j·γ_j(x,y)), where α_j is the scale adaptation coefficient; ω is the neighborhood range; cH_j(x,y) represents the horizontal detail coefficient of the spatial position (x, y) at scale j; cV_j(x,y) represents the vertical detail coefficient of the spatial position (x, y) at scale j; Δx,y is the local offset of the spatial position (x, y).

[0037] According to one aspect of the present application, the construction of the adaptive enhancement function includes: Read the directional coherence measure set and phase consistency diagram, and construct an adaptive enhancement function: f_j(M',PC') =(1 + tanh(α_j·(M'_j - β_j))) / 2·(1 + γ_j·PC'); adaptively determine the enhancement function parameters: α_j =α_0·(1 + Δ·SNR_j); β_j = β_0·(1 - ρ·SNR_j); γ_j = γ_0·(1 + ω·PC_mean), where SNR_j is the estimated j-th scale signal-to-noise ratio, PC_mean is the average phase consistency, β_j is the threshold parameter at the j-th scale; PC' is the local phase consistency value; α_0 is the initial scale adaptation coefficient; β_0 is the baseline value of the initial directional coherence measure; ρ is the adjustment coefficient related to the signal-to-noise ratio; γ_0 is the initial phase consistency compensation coefficient. Apply the enhancement function to the wavelet detail coefficients: cH'_j(x,y) = cH_j(x,y)·f_j(M'_j(x,y), PC'(x,y)); apply the amplitude limit function to prevent over-enhancement: cH''_j = sign(cH'_j)·min(|cH'_j|, λ_j·std(cH_j)), where λ_j is the scale adaptive coefficient.

[0038] According to one aspect of the present application, step S23 may also be: S231. Multi-scale state decomposition and transition point identification.

[0039] The spatial distribution characteristics S_space of the rockfill state and the time series data T_data in the standardized monitoring data set are read, and wavelet decomposition is applied to the state time series CSI(x,t) of each spatial point x. Daubechies wavelet (db4) is selected as the basis function, and a 5-layer discrete wavelet transform is performed: CSI(x,t) = ∑j∑k c_j,k(x)ψ_j,k(t) + ∑k a_J,k(x)φ_J,k(t); where j=1,2,...,J represents the scale level (J=5), k is the time displacement, ψ_j,k(t) is the wavelet function, φ_J,k(t) is the scale function, c_j,k(x) is the detail coefficient, and a_J,k(x) is the approximation coefficient. The multi-scale wavelet coefficient set W = {a_J,k(x), c_j,k(x)} is output.

[0040] Read the multi-scale wavelet coefficient set W and calculate the energy distribution of each scale wavelet coefficient E_j(x,t) = ∑k |c_j,k(x)| 2 (within a window around time t); E_J(x,t) = ∑k |a_J,k(x)| 2 (within a window around time t); For each scale j, calculate the energy mutation rate R_j(x,t) = |E_j(x,t) - E_j(x,t-Δt)| / max(E_j(x,t-Δt), ε); where Δt is the time step and ε is a small constant to prevent division by zero. To enhance meaningful mutations, introduce energy density modulation R'_j(x,t) = R_j(x,t)·(1 + Δ·log(E_j(x,t) / E_mean)); where E_mean is the average energy and Δ=0.3 is the modulation coefficient. Output the modulated energy mutation rate set {R'_j(x,t)}. Read the modulated energy mutation rate set {R'_j(x,t)} and the physical parameters P_data in the standardized monitoring data set to extract key physical quantities: effective stress σ'(x,t) and pore water pressure p(x,t). Calculate the rate of change of physical parameters: Rσ(x,t) = |σ'(x,t) - σ'(x,t-Δt)| / σ'_max; Rp(x,t) = |p(x,t) - p(x,t-Δt)| / p_max; Construct the physical trigger correlation function C_j(x,t) = max(corr(R'_j(x,t±τ), Rσ(x,t)), corr(R'_j(x,t±τ), Rp(x,t))); where corr represents the sliding window correlation coefficient and τ is the time lag / advance range (±10 time steps). It can capture the time lag relationship between state changes and physical trigger conditions. Output the physical trigger correlation set {C_j(x,t)}.

[0041] Read the set of modulation energy mutation rates {R'_j(x,t)} and the set of physical trigger correlations {C_j(x,t)}, and design an adaptive threshold function τ_j(x,t) = μ_j(x) + α·σ_j(x,t)·(1 + β·exp(-γ·t_s(x)))·(1 -ω·C_j(x,t)); where μ_j(x) is the basic threshold (local average mutation rate), σ_j(x,t) is the local standard deviation, t_s(x) is the time since the last detected transition point, and α=2.5, β=1.0, γ=0.1, and ω=0.3 are control parameters. A physical correlation modulation term (1-ω·C_j(x,t)) is introduced to make mutations with high physical correlation easier to detect as transition points. Identify the transition point set TP_j(x) = {t | R'_j(x,t)> τ_j(x,t) and local maximum}; perform multi-scale transition point fusion to eliminate redundancy and false positives: TP(x) = Filter({TP_j(x)}, d_min, n_min); where Filter filters the transition points according to the minimum time interval d_min and the minimum number of supported scales n_min to retain the most significant true transition points. Output the state transition point set TP(x) and the transition point feature set T_char.

[0042] S232. Multiscale hierarchical physical modeling.

[0043] Read the multi-scale wavelet coefficient set W and the spatial distribution characteristics of the rockfill state S_space, and extract the low-frequency approximate coefficients a_J, k(x). Construct the physical diffusion model da_J(x,t) / dt = ▽·[D_L(x,φ(x,t))·▽a_J(x,t)] + S_L(φ(x,t)); d is the symbol of the partial derivative; D_L is the low-frequency diffusion coefficient tensor, φ(x,t) is the physical state vector (including stress, pore pressure, etc.), and S_L is the source and sink term. Diffusion coefficient D_L(x,φ) = D_0·exp(-α_e·σ'(x,t))·exp(λ·a_J(x,t))·R(θ(x)); where D_0 is the reference diffusion coefficient, α_e is the effective stress influence coefficient, λ is the coupling state sensitivity coefficient, R(θ) is the anisotropic rotation matrix, and θ is the main diffusion direction. The source-sink term S_L represents the equilibrium state drive, S_L(φ) = r_L·(a_J,eq(φ) - a_J); where r_L is the relaxation rate and a_J,eq(φ) is the equilibrium value under a given physical state φ. The finite difference method is used for discrete solution, and the low-frequency state evolution model M_L is output.

[0044] Read the multi-scale wavelet coefficient set W, the state transition point set TP(x) and the transition point characteristic set T_char, and build a scale adaptive model dc_j(x,t) / dt = D_j·▽ for each detail scale j 2 c_j(x,t) + v_j ▽c_j(x,t) +S_j(φ,a_J,t); the source term S_j is decomposed into three parts: S_j(φ,a_J,t) = S_j,eq(φ,a_J) + S_j,trans(t) + S_j,noise; the equilibrium term S_j,eq represents the drive towards the equilibrium state, S_j,eq(φ,a_J) = r_j·(c_j,eq(φ,a_J) - c_j); the transformation term S_j,trans is activated near the detected transformation point, S_j,trans(t) = ∑_{t_c∈TP} A_j(t_c)·h_j(t-t_c); where h_j is the transformation function, h_j(t) = (1-exp(-ρ_j·t)) / (1+exp(-ρ_j·t)); A_j(t_c) is the conversion amplitude, which is related to the strength of the physical trigger condition. The noise term S_j,noise is a random disturbance that simulates small-scale random fluctuations. Output the multi-scale detail evolution model set {M_j}.

[0045] Read the low-frequency state evolution model M_L and the multi-scale detail evolution model set {M_j}, and construct a cross-scale coupling mechanism. First, establish the inter-scale influence matrix I_{i,j} = influence intensity (from scale i to scale j); estimate the influence intensity through wavelet partial causal analysis based on historical data. Secondly, design the cross-scale feedback term F_j(t) = ∑_i I_{i,j}·∫ K_{i,j}(t-τ)·c_i(τ)dτ; where K_{i,j} is the inter-scale influence kernel function, representing the time delay effect. Finally, update the evolution model dc_j(x,t) / dt = ... + F_j(t); at the same time, modify the equilibrium value a_J,eq(φ) in the low-frequency model to a_J,eq(φ,{c_j}) to make it dependent on the detail coefficient to form a bidirectional coupling. Output the cross-scale coupling coefficient set C_cross and the updated multi-scale evolution model set M = {M_L, {M_j}}.

[0046] S233, Physical constraint reconstruction and uncertainty quantification.

[0047] Read the multi-scale evolution model set M and the deformation physical constraint condition set C_phys, and construct the physical consistency constraint L[CSI] - f(φ) = 0; where L is the mechanical differential operator and f(φ) is the volume force term. Transform into the optimization problem min_{a',c'} ||a'-a|| 2+ ∑_j||c'_j-c_j|| 2 + λ||L[CSI'] - f(φ)|| 2 ; where a' and c'_j are the optimized wavelet coefficients, and CSI' is the corresponding reconstructed state field. Constraint weight λ(x) = λ_0·(1 + κ·Ξ(x)); where Ξ(x) is a physical importance index, which takes a high value in stress concentration areas and areas with large pore pressure gradients. The optimization problem is solved using the alternating direction multiplier method (ADMM) and the physically consistent optimization coefficients {a'_opt, c'_j,opt} are output.

[0048] Read the physical consistency optimization coefficients {a'_opt, c'_j,opt} and the multi-scale evolution model set M, and perform state evolution prediction. Introduce Bayesian posterior analysis p(θ|D) ∝ p(D|θ)p(θ); where θ is the model parameter vector and D is the historical observation data. Use the Markov Chain Monte Carlo (MCMC) method to sample the posterior distribution and generate the parameter sample set {θ i}. Perform model prediction on each sample to obtain the state evolution sample set {CSI i (x,t)}. Calculate the predicted mean and variance: CSI_mean(x,t) = (1 / N)·∑_i CSI i (x,t);CSI_var(x,t) = (1 / N)·∑_i (CSI i (x,t) - CSI_mean(x,t)) 2 ; Output state prediction field CSI_pred and prediction uncertainty field U_pred.

[0049] Read the state prediction field CSI_pred, the prediction uncertainty field U_pred, and the time series data T_data in the standardized monitoring data set, and perform sensitivity analysis and model verification. First, calculate the relative sensitivity index S_θj = (θj / CSI)·(dCSI / dθj); determine the degree of influence of key parameters on the prediction results. Second, perform historical data verification RMSE = sqrt((1 / N)·∑ (CSI_pred - CSI_obs) 2 );R 2 = 1 - ∑(CSI_pred - CSI_obs) 2 / ∑(CSI_obs- mean(CSI_obs)) 2; Finally, calculate the prediction reliability index RI(x,t) = (1 - U_pred(x,t) / CSI_pred(x,t))·(1 - RMSE / CSI_range); output the model validation report R_validation and the prediction reliability field RI.

[0050] S234, spatiotemporal evolution model integration.

[0051] Read the physical consistency optimization coefficients {a'_opt, c'_j,opt} and the multi-scale evolution model set M, and perform multi-scale spatiotemporal reconstruction. First, initialize the current state: a_cur = a'_opt; c_j,cur = c'_j,opt; then, step by step according to the evolution model, the time step Δt: a_new = a_cur + Δt·F_L(a_cur, {c_j,cur}, φ); c_j,new = c_j,cur + Δt·F_j(a_cur, {c_i,cur}, φ); where F_L and F_j are the corresponding evolution functions. At each time step, physical constraint adjustment is performed: {a_new, {c_j,new}} = PhysicalAdjust(a_new,{c_j,new}, C_phys); finally, the state field is reconstructed by inverse wavelet transform: CSI(x,t) = IDWT(a_new, {c_j,new}); the spatiotemporal evolution prediction field CSI_evol is output.

[0052] Read the spatiotemporal evolution prediction field CSI_evol and the state transition point set TP(x), and perform dynamic reshaping of state partitions. Introduce the impact of state transitions on partitions. First, calculate the local transition significance index TS(x) = ∑_{t_c∈TP(x)} w(t-t_c)·Magnitude(t_c); where w is the time weight function and Magnitude is the transition strength. Then, adjust the state partition boundary and use the adaptive level set method: dΓ / dt = V_n·N; where Γ represents the partition boundary and V_n is the normal velocity, which depends on TS(x) and the state gradient. Output dynamic state partitions D_zones.

[0053] Read the spatiotemporal evolution prediction field CSI_evol, prediction uncertainty field U_pred and dynamic state partition D_zones to generate the final rockfill state field and uncertainty field. Perform partition boundary smoothing CSI_smooth(x,t) = ∑_zw_z(x)·CSI_z(x,t); where w_z(x) is the weight of partition z at position x, and smooth transition is achieved in the partition boundary area. Calculate the comprehensive uncertainty field U_total(x,t) = sqrt(U_pred(x,t) 2 + U_model(x,t) 2 + U_bound(x,t) 2 ); U_model is the model structure uncertainty, and U_bound is the partition boundary uncertainty. Output the rockfill state field CSI_field and the state uncertainty field U_field.

[0054] A framework for modeling the separation of low-frequency components and detail coefficients was established, and the organic integration of dynamic characteristics of different time scales was achieved through the cross-scale coupling mechanism, which is particularly suitable for the characteristics of rockfill state evolution that include both slow trends and rapid transitions. By constructing the physical consistency optimization problem of wavelet coefficients, a deep integration of the state evolution model and physical laws was achieved, ensuring that the prediction results not only conform to the historical data trend, but also meet the physical constraints.

[0055] like Figure 4 As shown, according to one aspect of the present application, the steps of obtaining the panel deformation field and the panel stress field through panel deformation and stress analysis include: S31, reading deformation monitoring data and rockfill state field in the standardized monitoring data set, reconstructing discrete monitoring point data through a multi-scale physical constraint kernel function interpolation method, and generating a continuous distribution of the deformation field; S32. Based on the rockfill state field, continuous distribution of deformation field and completion drawing of the face rockfill dam, a face plate-rockfill contact mechanical model considering the influence of wetting is constructed, the contact surface stress distribution is calculated, and the contact stress distribution is output; S33, based on the contact stress distribution, the continuous distribution of the deformation field and the panel structure information in the completion drawing of the face rockfill dam, the stress state of the panel under the action of complex loads is analyzed, and the panel stress field is calculated; S34. Integrate the continuous distribution of the rockfill state field, state uncertainty field and historical deformation field, establish a deformation prediction model and verify it with the measured data, and output a verified panel deformation field and prediction accuracy evaluation report.

[0056] This embodiment can generate a high-precision continuous distribution of the deformation field, improve the integrity and spatial resolution of the data; more realistically reflect the dynamic changes of the stress distribution of the contact surface, thereby enhancing the analysis capability of the panel structural behavior under the action of wetting; conduct a comprehensive analysis of the stress state under the action of complex loads, accurately obtain the panel stress field, optimize the structural design and construction planning; improve the prediction accuracy, and provide a reliable judgment on the dynamic change trend of the panel deformation.

[0057] According to one aspect of the present application, the steps of reconstructing discrete monitoring point data by a multi-scale physical constraint kernel function interpolation method to generate a continuous distribution of the deformation field include: Analyze the completion drawings of the panel rockfill dam and the state field of the rockfill body, extract the deformation physical constraints based on the principle of mechanical equilibrium, and form a set of deformation physical constraints; Perform variational mode decomposition on the deformation monitoring data in the standardized monitoring data set to identify the multi-level characteristic scales of the deformation field and generate a multi-scale characteristic spectrum; Combining the deformation physical constraint condition set and the multi-scale characteristic spectrum, a multi-scale kernel function that satisfies the physical constraint is constructed, and a physical response kernel function set is established; The physical response kernel function set is used to process the deformation monitoring data in the standardized monitoring data set, and multi-scale kernel function interpolation calculation is performed to achieve high-precision reconstruction of discrete monitoring point data into a continuous deformation field, and output a high-precision continuous distribution of the deformation field.

[0058] Among them, the physical response kernel function set ensures that the interpolation results meet both the data fitting requirements and the physical constraints, effectively solving the shortcomings of traditional pure mathematical interpolation methods in terms of physical rationality.

[0059] Specifically, the completion drawing of the panel rockfill dam and the state field of the rockfill body are read, and the physical constraints of the deformation field are extracted based on the principle of mechanical equilibrium to generate a set of physical constraints for deformation. The mathematical expression of the physical constraints is: L[u(x)] = f(x, MI(x)); B[u(x)] = g(x) on ∏Ω; L is the differential operator of elastic mechanics, L = μ▽ 2 (·) + (λ+μ)▽(▽·(·)); u(x) is the displacement field; f(x, MI(x)) is the body force, which is related to the wetting index MI(x); B is the boundary operator; g(x) is the boundary condition; λ and μ are the Lame constants, which are related to the material properties; ∏Ω is the boundary of the computational domain; ▽ is the gradient operator; ▽· is the divergence operator; ▽ 2 is the Laplace operator; x is the spatial coordinate point, and on represents the scope of application of the mathematical conditions or the area of ​​action of the constraints.

[0060] This embodiment successfully converts discrete monitoring point data into a high-precision continuous distribution of deformation field, effectively improving spatial resolution and data integrity; the generated multi-scale characteristic spectrum can fully reflect the complex behavior of the deformation field, providing a refined multi-level data basis for subsequent analysis; ensuring physical consistency in the deformation reconstruction process, enhancing the scientific nature and reliability of the results; achieving high-precision conversion from discrete points to continuous fields, and improving the ability to describe the distribution characteristics of the deformation field; providing an important reference for deformation analysis, engineering monitoring and structural optimization design of rockfill dams, and having high practical engineering application value.

[0061] Traditional interpolation methods are usually based on pure mathematical models and lack physical constraints. Therefore, according to one aspect of the present application, the steps of performing variational mode decomposition, generating multi-scale characteristic spectra and constructing multi-scale kernel functions, and establishing a physical response kernel function set specifically include: The variational modal decomposition algorithm is applied to the deformation monitoring data in the standardized monitoring data set to decompose the deformation field signal into modal components with different frequency characteristics, identify multi-level characteristic scales, and generate multi-scale characteristic spectra; The variational mode decomposition algorithm is: min{uk,ωk}{Σk||∏t[(Δ(t)+j / πt)*uk(t)]·e -jωkt || 2 2}; st Σk uk(t) = u(t); where uk(t) represents the modal component of the kth scale; ωk represents the center frequency of the kth mode; Δ(t) represents the Dirac function; j represents the imaginary unit; * represents the convolution operator; u(t) represents the original signal; ∏ is the partial derivative; t is the time variable; e -jωkt is a complex exponential function; ||·|| 2 2 is the square of the L2 norm; k is the modal index; ∏t is the time partial derivative operator; According to the characteristic functions of mechanical differential operators in the set of deformation physical constraints, a set of physical response kernel functions that satisfy the mechanical equilibrium equations is constructed; The construction method of the physical response kernel function set is: K(x, y) = Σn[Ξn(x)·Ξn(y) / λn]; where Ξn(x) represents the nth eigenfunction of the mechanical differential operator L, satisfying L[Ξn(x)]= λn·Ξn(x); λn represents the corresponding eigenvalue; K(x, y) represents the physical response kernel function; x and y represent the spatial coordinate points; n represents the characteristic mode index. The combination of variational mode decomposition and physical response kernel function realizes the organic integration of the multi-scale characteristics of the signal and the physical constraints, and improves the physical rationality of the deformation field reconstruction.

[0062] According to one aspect of the present application, the steps of performing multi-scale kernel function interpolation calculation and outputting a high-precision continuous distribution of the deformation field include: Apply the physical response kernel function set to the deformation monitoring data in the standardized monitoring data set, establish an interpolation equation system, and output a high-precision continuous distribution of the deformation field; Establish an interpolation equation system: u(x) = Σi[αi·K(x,xi)] + p(x); Σi[αi·p(xi)]= 0 forall p∈P; where the coefficient αi to be solved must satisfy: Σj[αj·K(xi,xj)] + p(xi) = ui for i=1,2,...,N; u(x) represents the deformation field reconstructed by interpolation; xi represents the position of the i-th monitoring point; ui represents the monitoring value of the i-th monitoring point; K(x,y) represents the physical response kernel function; αi represents the undetermined coefficient; p(x) represents the polynomial function to ensure the completeness of the interpolation; P represents the polynomial space of a given order; N represents the total number of monitoring points; i and j are monitoring point indexes; x is an arbitrary spatial point; for different spatial regions, the kernel function parameters are adaptively adjusted to optimize the interpolation accuracy; the cross-validation method is used to evaluate the accuracy of the interpolation results to form a continuous distribution of the deformation field with a confidence index; This embodiment ensures that the deformation field satisfies the mechanical equilibrium condition while ensuring the data fitting accuracy, thereby improving the accuracy and physical rationality of the deformation field reconstruction.

[0063] According to one aspect of the present application, the steps of reconstructing discrete monitoring point data by a multi-scale physical constraint kernel function interpolation method to generate a continuous distribution of the deformation field include: Read deformation monitoring data and rockfill state field, build a multi-resolution hierarchical structure, perform spectral decomposition and harmonic residual calculation, and obtain anomaly point set and anomaly credibility index; read anomaly point set, deformation monitoring data and multi-scale spectral residual set, estimate the preliminary repair value of the anomaly point, establish a physical constrained optimization problem, and obtain a constrained optimization problem; read the constrained optimization problem, apply the iterative harmonic solution to solve it, and perform uncertainty assessment and verification to obtain repaired deformation monitoring data and repair uncertainty index; read and repair deformation monitoring data, apply physical response kernel function interpolation calculation, and obtain a high-precision continuous distribution of the deformation field.

[0064] Among them, the construction of multi-resolution hierarchical structure includes: Read the deformation monitoring data, standardize it to get the standardized measurement matrix and correlation index; perform quadtree decomposition based on the spatial distribution of monitoring points: initialize the quadtree root node, which contains all monitoring points; if the number of points contained in the node is greater than the threshold and the area size is greater than the minimum size, it is divided into four child nodes; recursively perform the above steps until the termination condition is met; define the resolution level according to the quadtree structure: H1= {the center point of each node in the first layer of the tree}, H2= {the center point of each node in the second layer of the tree}, ..., H m= {the center point of each node in the deepest level of the tree}, where the center point is defined by the weighted average of the monitoring points in the region, with the weights based on the measurement reliability.

[0065] Among them, spectral decomposition and residual calculation include: Read the normalized measurement matrix and the multi-resolution hierarchy, perform singular value decomposition for each resolution level; determine the optimal truncation dimension k_i = argmin_k {k | ∑_{j=1} by energy preservation threshold k σ_j 2 / ∑_{j=1} n σ_j 2 > τ_i}, where τ_i = τ_base + Δτ·(i-1) / (m-1) - ε·PC_i, τ_base is the base threshold, PC_i is the physical constraint satisfaction score of the i-th layer; construct the reconstruction matrix and calculate the spectral residual U_i k = V_i(:,1:k_i) Σ_i(1:k_i,1:k_i) W_i(:,1:k_i) T , SR_i = |U_i - U_i k |. / σ_E_i; calculate the comprehensive anomaly score AS(p) =∑_i w_i·SR_i(p)·(1 + λ·TS(p)), where TS(p) is the time stability index and w_i is the hierarchical weight; apply the adaptive threshold to identify the anomaly point τ_AS = μ_AS + η·σ_AS·(1 + γ·D(p)), where D(p) is the isolation index of point p.

[0066] The construction and solution of physical constraint optimization problems include: Read the set of outliers and the set of preliminary repair values, and construct a physical constraint optimization problem: min_{u*} ||u* - u''|| 2 + μ||L[u*] - f|| 2 + ρ·∑_{q∉O}(u*(q)-u(q)) 2 , where u* is the final repair value vector, L is the mechanical differential operator, and f is the volume force term; the adaptive regularization parameter μ(p)=μ0·exp(-λ·CI(p)) is designed, where CI(p) is the abnormal credibility index; the variational multi-grid acceleration strategy is applied to solve: construct the nested space V1 ∽ V2 ∽ ... ∽ V n ; where ∽ represents the true inclusion relation of the set; solve the initial solution on the coarsest grid V1; progressively refine, at each layer V kThe initial value is obtained and improved through the previous layer solution and interpolation operator; finally, the repaired deformation monitoring data is obtained; uncertainty assessment is performed, including calculating the residual with physical constraints: r = ||L[u*] - f||; evaluating the repaired spectral residual SR*; and constructing the uncertainty index: U(p) = ω1·r(p) + ω2·SR*(p) + ω3·CI(p).

[0067] According to one aspect of the present application, step S31 is specifically: Step S311: read the deformation monitoring raw data D_raw, including the monitoring point coordinates {xi, yi, zi} and the corresponding measurement values ​​ui. Perform data format verification, check coordinate consistency, mark obvious over-limit values, and generate preliminary cleaning data D_clean and data integrity report R_integrity.

[0068] Read the completion diagram G of the concrete rockfill dam and the rockfill state field CSI, and extract the elastic differential operator L = μ▽ 2 (·) + (λ+μ)▽(▽·(·)); where λ and μ are Lame constants, determined according to the material partition information. Construct physical constraints: L[u(x)] = f(x, CSI(x)); B[u(x)]= g(x) on dΩ; where f(x, CSI(x)) is the volume force term, which is related to the permeability-mechanical coupling state indicator CSI(x); B is the boundary operator; g(x) is the boundary condition; dΩ is the computational domain boundary. Output the deformation physical constraint set C_phys.

[0069] S312, read the preliminary cleaning data D_clean, and construct the deformation measurement matrix U: the rows represent time points, and the columns represent monitoring points. Standardization processing U_norm = (U - μ) / σ; where μ and σ are the mean and standard deviation vectors, respectively. Calculate the time correlation R_time and space correlation R_space of the measurement matrix. Output the standardized measurement matrix U_norm and correlation index {R_time, R_space}.

[0070] Read the preliminary cleaning data D_clean and construct a multi-resolution hierarchy H = {H1, H2,..., H m First, perform quadtree decomposition: initialize the quadtree root node, which contains all monitoring points; if the number of points contained in the node is greater than the threshold T_split and the region size is greater than the minimum size S_min, it is divided into four child nodes; recursively execute until the termination condition is met; then define the resolution level according to the tree structure: H1={the center point of each node in the first layer of the tree}; H2={the center point of each node in the second layer of the tree}; H m={the center point of each node in the deepest layer of the tree}; where the center point is defined by the weighted average of all monitoring points in the region, with the weights based on the measurement reliability. Output multi-resolution hierarchy H.

[0071] Read the standardized measurement matrix U_norm and the multi-resolution hierarchy H, for each resolution level H i Perform the following steps: Extract the corresponding measurement sub-matrix U_i; Perform singular value decomposition: U_i = V_i Σ_i W_i T ; Determine the optimal truncation dimension k_i = argmin_k {k | ∑_{j=1} k σ_j 2 / ∑_{j=1} n σ_j 2 > τ_i}; where σ_j is a singular value, τ_i is the energy retention threshold, which increases with i; construct the reconstruction matrix U_i k = V_i(:,1:k_i) Σ_i(1:k_i,1:k_i) W_i(:,1:k_i) T ; Calculate the reconstruction error E_i = U_i - U_i k ; Calculate the spectral residual SR_i = |E_i| . / σ_E_i; τ_i = τ_base + Δτ·(i-1) / (m-1) - ε·PC_i; τ_base=0.85 is the base threshold, Δτ=0.1 is the level interval, PC_i is the physical constraint satisfaction score of the i-th layer, and ε=0.05 is the physical compensation coefficient. Output the multi-scale spectral residual set {SR_i}.

[0072] Read the multi-scale spectral residual set {SR_i}, and calculate the comprehensive anomaly score AS(p) = ∑_i w_i·SR_i(p) for each monitoring point p; where w_i is the hierarchical weight, which decreases with the increase of resolution. Introduce recursive stability analysis AS'(p) = AS(p)·(1 + λ·TS(p)); TS(p) is the temporal stability index, TS(p) = std(AS_t(p)) / mean(AS_t(p)); AS_t(p) is the anomaly score at time t in the past. Anomaly point identification uses an adaptive threshold: τ_AS = μ_AS + η·σ_AS·(1 + γ·D(p)); where D(p) is the isolation index of point p, indicating the average distance from neighboring points, η=2.5, γ=0.3. Finally, the anomaly point set O and the anomaly credibility index CI are output.

[0073] S313, read the abnormal point set O, the standardized measurement matrix U_norm and the multi-scale spectral residual set {SR_i}, for each abnormal point p∈O, estimate the preliminary repair value u'(p) = ∑_i v_i·u_i based on the multi-scale reconstruction matrix k (p); where u_i k (p) is the value of point p in the i-th layer reconstruction matrix, vi is the confidence weight, which is inversely proportional to the spectral residual SR_i, vi = exp(-α·SR_i(p)) / ∑_j exp(-α·SR_i(p)); α=2.0 is the sensitivity parameter. To enhance temporal consistency, the time window smoothing u''(p) = β·u'(p) + (1-β)·∑_t w_t·u'_t(p) is introduced; where u'_t(p) is the preliminary repair value at time t in the past, w_t is the time weight, and β=0.6 is the weight at the current moment. Output the preliminary repair value set u''.

[0074] Read the abnormal point set O, the preliminary repair value set u'' and the deformation physical constraint condition set C_phys, and construct the physical constraint optimization problem: min_{u*} ||u* - u''|| 2 + μ||L[u*] - f|| 2 ;st u*(q) = u(q) for all q belongs to O; where u* is the final repair value vector, u represents the original measurement value, L is the mechanical differential operator, and f is the body force term. In order to improve the computational efficiency, the penalty function method is used to convert it into an unconstrained optimization problem: min_{u*} ||u* - u''|| 2 + μ||L[u*] - f|| 2 + ρ·∑_{q∉O}(u*(q) - u(q)) 2 ; Adaptive regularization parameter μ(p) = μ0·exp(-λ·CI(p)); where CI(p) is the anomaly credibility index, μ0=0.5 is the basic parameter, and λ=2.0 is the attenuation coefficient. This makes the algorithm rely more on physical constraints rather than preliminary repair values ​​for highly abnormal points. Output constrained optimization problem P_opt.

[0075] Read the constrained optimization problem P_opt and apply the iterative harmonic solution to solve it. First, discretize the problem and construct a linear system: (I + μA T A + ρB T B)u* = (u'' + μA T f + ρB Tu); A is the discrete matrix of the mechanical operator L, and B is the selection matrix (extracting non-abnormal points). The conjugate gradient method is used to solve the problem, and the variational multi-grid acceleration strategy is introduced: construct a nested space V1 contained in V2 contained in... contained in V n ; Solve the initial solution on the coarsest grid V1; progressively refine, at each layer V k On the top, through the previous layer solution u*_{k-1} and the interpolation operator I k _{k-1} obtains the initial value; performs N times of conjugate gradient iteration to improve the solution; obtains the final solution u*, and outputs the repaired deformation monitoring data D_fixed.

[0076] Read the repair deformation monitoring data D_fixed and the deformation physical constraint condition set C_phys, and perform uncertainty assessment: calculate the residual with physical constraints: r = ||L[u*] - f||; evaluate the spectral residual SR* after repair; construct the uncertainty index: U(p) = ω1·r(p) + ω2·SR*(p) + ω3·CI(p); where ω1=0.4, ω2=0.3, ω3=0.3 are weight coefficients. Perform cross-validation to evaluate the repair quality: randomly select 50% of non-abnormal points as pseudo-abnormal points; apply the repair algorithm; calculate the recovery error; repeat 20 times to obtain statistical indicators; output the repair uncertainty index U and the repair quality assessment report R_quality. In the anomaly detection stage, physical constraints are introduced to assist in the evaluation of spectral truncation, and in the repair stage, the preliminary statistical repair and physical constraint optimization are unified into one framework.

[0077] According to one aspect of the present application, the steps of generating a comprehensive report on fracture properties through fracture feature extraction and visual decision support include: S41, reading the panel stress field and panel deformation field, calculating the crack sensitivity index of each area of ​​the panel based on the crack mechanics theory, and outputting a crack sensitive area map; S42, reading underwater detection data and crack sensitive area map, applying image enhancement technology and feature extraction algorithm for underwater environment, identifying crack location, direction and width, and outputting crack feature data; S43, reading crack characteristic data, panel stress field and panel deformation field, comprehensively analyzing the cause, development status and risk level of the cracks, and outputting the crack property determination result; S44, read the crack property determination results, crack characteristic data and crack sensitive area map, generate a multi-dimensional crack property visualization expression, provide targeted maintenance suggestions based on risk analysis, and output a comprehensive crack property report.

[0078] According to one aspect of the present application, physical trigger condition association analysis and adaptive threshold transition point identification include: Read the physical parameters in the standardized monitoring data set, extract the effective stress and pore water pressure, and calculate the change rate of the physical parameters: Rσ(x,t) = |σ'(x,t) - σ'(x,t-Δt)| / σ'_max, Rp(x,t) = |p(x,t) - p(x,t-Δt)| / p_max; construct the physical trigger correlation function C_j(x,t) = max(corr(R'_j(x,t±τ), Rσ(x,t)), corr(R'_j(x,t±τ), Rp(x,t))), where corr represents the sliding window correlation coefficient and τ is the time lag / lead range; design the adaptive threshold function τ_j(x,t) = μ_j(x) + α·σ_j(x,t)·(1 + β·exp(-γ·t_s(x)))·(1 - ω·C_j(x,t)), where μ_j(x) is the base threshold, σ_j(x,t) is the local standard deviation, and t_s(x) is the time since the last transition point; identify the set of transition points and perform multi-scale fusion TP_j(x) = {t | R'_j(x,t)>τ_j(x,t) and local maximum}, TP(x) = Filter({TP_j(x)}, d_min, n_min).

[0079] Among them, multi-scale hierarchical physical modeling includes: Construct a low-frequency physical diffusion model: da_J(x,t) / dt = ▽·[D_L(x,φ(x,t))·▽a_J(x,t)]+ S_L(φ(x,t)), where D_L(x,φ) = D_0·exp(-α_e·σ'(x,t))·exp(λ·a_J(x,t))·R(θ(x)), S_L(φ) = r_L·(a_J,eq(φ) - a_J); construct a detail scale adaptive model: dc_j(x,t) / dt =D_j·▽ 2c_j(x,t) + v_j·▽c_j(x,t) + S_j(φ,a_J,t), where S_j(φ,a_J,t) = S_j,eq(φ,a_J) + S_j,trans(t) + S_j,noise, S_j,trans(t) = ∑_{t_c∈TP} A_j(t_c)·h_j(t-t_c), h_j(t) = (1-exp(-ρ_j·t)) / (1+exp(-ρ_j·t)); establish a cross-scale coupling mechanism: F_j(t) = ∑_i I_{i,j}·∫ K_{i,j}(t-τ)·c_i(τ)dτ, dc_j(x,t) / dt = ... + F_j(t), and at the same time modify a_J,eq(φ) to a_J,eq(φ,{c_j}) to form a bidirectional coupling.

[0080] Among them, consistency optimization based on physical constraints and Bayesian posterior analysis include: Construct the physical consistency constraint optimization problem min_{a',c'} ||a'-a|| 2 + ∑_j||c'_j-c_j|| 2 + λ||L[CSI'] - f(φ)|| 2 , where λ(x) = λ_0·(1 + κ·Ξ(x)), Ξ(x) is a physical importance indicator; apply Bayesian posterior analysis p(θ|D) ∝ p(D|θ)p(θ), where θ is the model parameter vector and D is the historical observation data; use the Markov chain Monte Carlo method to sample the posterior distribution and generate the parameter sample set {θ i}; Perform model prediction for each sample and calculate the prediction mean and variance: CSI_mean(x,t) = (1 / N)·∑_i CSI i (x,t), CSI_var(x,t) = (1 / N)·∑_i (CSI i (x,t) - CSI_mean(x,t)) 2 ; Calculate the prediction reliability index RI(x,t) = (1 - U_pred(x,t) / CSI_pred(x,t))·(1 - RMSE / CSI_range).

[0081] According to one aspect of the present application, step S42 may be: S421. Read the original image I of the underwater cracks, and calculate the mean μW(x,y) and standard deviation σW(x,y) of the local window W(x,y) centered on each pixel (x,y), with the window size being 15×15 pixels. Apply the local illumination normalization formula I_norm(x,y) = (I(x,y) - μW(x,y)) / σW(x,y) to obtain the illumination normalized image I_norm.

[0082] Read the illumination normalized image I_norm and separate the three RGB channels IR, IG, and IB. Apply channel characteristic analysis to calculate the contrast scores CR, CG, and CB and the signal-to-noise ratio scores SR, SG, and SB of each channel. Construct the crack enhancement weight vector w = [wR, wG, wB]: wR = 0.2 + 0.4·CR + 0.4·SR; wG = 0.3 + 0.4·CG + 0.3·SG; wB = 0.5 + 0.3·CB + 0.2·SB; normalize the weight vector and perform weighted fusion: I_fused = wR·IR + wG·IG + wB·IB, and obtain the fused grayscale image I_fused.

[0083] S422, read the fused grayscale image I_fused, apply four-layer discrete wavelet transform, select the sym4 wavelet basis function, and calculate the wavelet coefficients of four scales: low-frequency approximation coefficient cA_4 and detail coefficients {cH_j, cV_j, cD_j}, j=1,2,3,4, representing horizontal, vertical and diagonal details respectively.

[0084] Read the horizontal detail coefficients cH_j and vertical detail coefficients cV_j, and for each scale j and spatial position (x, y), calculate the directional coherence measure M_j: M_j(x, y) = |∑ω cH_j(x, y)·cH_j(x+ω, y) + cV_j(x, y)·cV_j(x, y+ω)| / sqrt(cH_j(x, y) 2 + cV_j(x,y) 2 ); where ω∈[-3,3] represents the local neighborhood range. In order to improve the sensitivity to small cracks, the directional consistency compensation γ_j(x,y) = max(0, 1 - var(θ(x+Δx,y+Δy)) / π) is introduced; where θ represents the local gradient direction and var represents the variance. Finally, the compensated directional coherence measure M'_j(x,y) = M_j(x,y)·(1 + α_j·γ_j(x,y)) is obtained; where α_j is the scale adaptation coefficient, α_1=0.8, α_2=0.6, α_3=0.4, α_4=0.2. Output the directional coherence measure set {M'_j}.

[0085] Read the detail coefficients of each scale {cH_j, cV_j, cD_j} and convert them into amplitude and phase representation: A_j(x,y) =sqrt(cH_j(x,y) 2 + cV_j(x,y) 2 + cD_j(x,y) 2 );Ξ_j(x,y) = atan2(cV_j(x,y), cH_j(x,y));Calculate cross-scale phase consistency: PC(x,y) = |∑j e_j·A_j(x,y)·cos(Ξ_j(x,y) – Ξ*(x,y))| / ∑j A_j(x,y); Where e_j is the scale weight, e_1=0.4, e_2=0.3, e_3=0.2, e_4=0.1, Ξ*(x,y) is the weighted average phase. In order to improve the adaptability to the underwater environment, the brightness compensation function η(x,y) = 1 / (1 +exp(-k·(cA_4(x,y) - cA_th))) is introduced; Where k=5, cA_th is the adaptive threshold, which is determined from cA_4 by the Otsu method. Finally, the adjusted phase consistency is obtained: PC'(x,y) = PC(x,y)·η(x,y), and the phase consistency diagram PC' is output.

[0086] S423. Read the directional coherence measure set {M'_j} and the phase consistency diagram PC', and construct the adaptive enhancement function f_j(M',PC') = (1 + tanh(α_j·(M'_j - β_j))) / 2 · (1 + γ_j·PC'); where α_j is the sensitivity parameter, β_j is the threshold parameter, and γ_j is the phase enhancement coefficient. Adaptive determination of parameters: α_j = α_0·(1 +Δ·SNR_j); β_j = β_0·(1 - ρ·SNR_j); γ_j = γ_0·(1 + ω·PC_mean); where SNR_j is the estimated j-th scale signal-to-noise ratio, PC_mean is the average phase consistency, α_0=3.5, β_0=0.45, γ_0=0.6, Δ=0.3, ρ=0.2, ω=0.5. Output enhancement function set {f_j}. Read wavelet coefficients {cH_j, cV_j, cD_j} and enhancement function set {f_j}, and perform selective enhancement: cH'_j(x,y) = cH_j(x,y)·f_j(M'_j(x,y), PC'(x,y)); cV'_j(x,y) = cV_j(x,y)·f_j(M'_j(x,y), PC'(x,y)); cD'_j(x,y) = cD_j(x,y)·f_j(M'_j(x,y), PC'(x,y)); To prevent over-enhancement, an amplitude limiting function cH''_j = sign(cH'_j)·min(|cH'_j|, λ_j·std(cH_j)) is introduced; where λ_j is the scale adaptive coefficient, and the values ​​of j=1,2,3,4 are 4.0, 3.5, 3.0, 2.5 respectively. The vertical and diagonal coefficients cV''_j and cD''_j are processed in the same way. The low-frequency coefficient remains unchanged: cA'_4 = cA_4. Output enhanced wavelet coefficients {cA'_4, cH''_j, cV''_j, cD''_j}. Read the enhanced wavelet coefficients {cA'_4, cH''_j,cV''_j, cD''_j}, and perform inverse wavelet transform to reconstruct the image I_rec. To further optimize the crack details, local statistical enhancement is applied to the reconstructed image: I_enh(x,y) = I_rec(x,y) + λ·(I_rec(x,y) - μ_L(x,y))·(σ_G / σ_L(x,y)); where μ_L and σ_L are the local mean and standard deviation, σ_G is the global standard deviation, and λ=0.7 is the enhancement coefficient. The enhanced crack image I_enh is output.

[0087] S424. Read the enhanced crack image I_enh, and apply adaptive threshold segmentation to obtain the preliminary crack binary image B_init. Construct a directional linear structural element SE_θ, where θ ∈ {0°, 45°, 90°, 135°} and the length is 7 pixels. Perform morphological opening operations for each direction, and then take the minimum response B_open(x, y) = min_θ{(B_init O SE_θ)(x, y)}; where O represents the morphological opening operation. Then apply conditional dilation operation B_dilate = Δ_I_enh(B_open, T); where Δ_I_enh represents the dilation operation conditional on I_enh, and T is the termination condition. Output the crack binary image B_dilate.

[0088] Read the crack binary image B_dilate and the enhanced crack image I_enh, and apply a skeleton extraction algorithm to obtain the crack centerline S. For each point p on the centerline S, calculate the crack width W(p) perpendicular to the direction θ(p) as W(p) = argmin_d{I_enh(p + d·n(p)) < T_edge and I_enh(p - d·n(p)) < T_edge}; where n(p) is the normal vector at point p, and T_edge is the edge threshold. Calculate the crack length L as the total length of the centerline S. Integrate to obtain the crack feature dataset F = {S, W, L, θ}, which includes the centerline, width distribution, total length, and direction distribution. Read the crack feature dataset F and the enhanced crack image I_enh, and construct a false color enhancement display. Map the crack width W to the color space C(p) = ColorMap(W(p) / W_max); where ColorMap is a color mapping from blue (thin) to red (wide). Generate the enhanced visualization image I_vis = α·I_enh + (1 - α)·Rasterize(S, C); where Rasterize represents rendering the centerline S as a raster image according to the color C, and α = 0.4 is the mixing coefficient. Output the crack visualization image I_vis.

[0089] In this embodiment, a parameter adaptive adjustment method based on local signal-to-noise ratio and phase characteristics is established, enabling the system to adapt to the imaging condition differences in different underwater regions. Nonlinear selective enhancement based on crack morphological features is realized in the wavelet domain, solving the traditional contradiction between "over-smoothing" and "noise retention".

[0090] In a specific embodiment of the present application, a method for identifying underwater crack properties of a panel rockfill dam is applicable to the safety monitoring and maintenance of large panel rockfill dams. The overall process includes four main steps: multi-source data acquisition and preprocessing, rockfill body permeability-mechanical coupling state modeling, panel deformation and stress analysis, and crack feature extraction and visualization decision support. The implementation process of this method will be described in detail below in conjunction with actual monitoring data of a large panel rockfill dam. It should be noted that non-innovative points such as knowledge or skills known to technical personnel in this field are briefly described.

[0091] Step 1: Multi-source data collection and preprocessing.

[0092] 1.1. Acquisition of multi-source monitoring data.

[0093] In this embodiment, the original monitoring data of the panel rockfill dam are first obtained, including: three-dimensional geometric data of the above-water part, dam top and downstream dam surface of the panel obtained by three-dimensional laser scanning, with a spatial resolution of 5mm; underwater sonar scanning data, including underwater dimensions and blanket morphology information of the panel, with a resolution of 10mm; dam body deformation data obtained by water tube sedimentation meter, with a measurement accuracy of 0.1mm; stress and strain monitoring data, including stress and strain time series data of 25 monitoring points; pore water pressure monitoring data, from 32 monitoring points inside the dam body.

[0094] 1.2. Data quality assessment and anomaly detection.

[0095] Statistical methods were used to identify and mark outliers: the 3σ standard was calculated for each monitoring point data, and data outside the mean ±3σ range were marked as potential outliers; the Grubbs test method was used for further verification, and the statistic G = |outlier-mean| / standard deviation was calculated; the data quality index DQI = (1-outlier ratio) × (1-missing value ratio) × (1-standard deviation / mean) was calculated for each monitoring point. Through this step, a total of 57 outliers and 12 monitoring points with data quality below 0.75 were identified.

[0096] 1.3. Spatiotemporal alignment and fusion preprocessing.

[0097] To address the spatiotemporal inconsistency issues of multi-source data: establish a unified coordinate system based on high-precision GPS coordinates and measurement control networks; apply Helmert seven-parameter transformation to convert data from different sources into a unified coordinate system; perform data time alignment based on timestamps, and use linear interpolation to handle different sampling frequencies; generate spatiotemporal aligned data sets to achieve consistent expression of multi-source data.

[0098] 1.4. Adaptive noise reduction and data enhancement.

[0099] According to different sensor characteristics and environmental interference: wavelet denoising algorithm is used to process noise data, and db4 wavelet basis function is selected; for stress monitoring data, threshold coefficient λ = 3.5×sqrt(2logN), N is the data length; for underwater sonar data, adaptive Bayesian shrinkage (BayesShrink) threshold method is applied, and the threshold is calculated as λj = σ 2 / σj,σ 2 is the noise variance, σj is the signal variance; calculate the comprehensive data reliability index: RI = w1×DQI + w2×SNR + w3×TC, where DQI is the data quality index, SNR is the signal-to-noise ratio, TC is the time consistency, and the weights are w1=0.5, w2=0.3, w3=0.2 respectively; through this link, the noise level is reduced by 85% and the data reliability is improved by 32%, laying the foundation for subsequent analysis.

[0100] This embodiment combines the spatiotemporal alignment of multi-source data with adaptive noise reduction, solving the problem that multi-source heterogeneous data is difficult to process uniformly in traditional methods. In particular, the adaptive wavelet noise reduction algorithm dynamically adjusts the threshold according to the characteristics of different sensors, which improves the noise reduction efficiency by about 30% compared with the traditional fixed threshold method and effectively retains important feature information. The introduction of comprehensive data reliability indicators provides a data quality reference for subsequent analysis, making the credibility of the analysis results quantifiable and assessable, which is a significant breakthrough in the field of underwater structure detection.

[0101] Step 2: Modeling of the rockfill permeability-mechanical coupling state.

[0102] 2.1. Construction of physical model of rockfill.

[0103] Based on the completion drawings and monitoring data of the concrete face rockfill dam: establish a three-dimensional geometric model including the structural layers of the rockfill body; generate a grid model with unit size varying with depth, 5m in the surface area and 10m in the deep area; determine the material partitioning according to the completion data, including the transition material area, the main rockfill area and the cushion layer area; output the rockfill body geometric model (including 10,245 nodes and 45,368 units) and material partitioning information.

[0104] 2.2. Construction of permeability-mechanical coupling state index.

[0105] Construct the permeability-mechanical coupling state index CSI: extract effective stress σ'(x, t), pore water pressure P(x, t) and strain ε(x, t) data from the standardized monitoring data set; calculate the permeability-mechanical coupling state index: CSI(x, t) = α·σ'(x, t) / σ'max + β·P(x, t) / Pmax + γ·ε(x, t) / εmax; where α=0.45, β=0.35, and γ=0.20 are weight coefficients, indicating the relative importance of each factor; σ'max=2.5MPa is the maximum effective stress; Pmax=0.8MPa is the maximum pore water pressure; εmax=0.004 is the maximum strain; x is the spatial coordinate point; and t is the time point.

[0106] Traditional methods usually consider stress state or permeability state separately, and it is difficult to characterize the interaction between the two. This embodiment proposes a permeability-mechanical coupling state index CSI, which unifies the three key parameters of effective stress, pore water pressure and strain into a quantitative framework. By setting different weight coefficients to reflect the contribution of each factor to the coupling state, the problem that traditional methods cannot comprehensively characterize the complex state inside the rockfill body is solved. Practical applications have shown that this indicator can accurately reflect the comprehensive state of the rockfill body, and the recognition accuracy of the wetting area and the stress concentration area has been improved by 42%, providing more reliable basic data for subsequent analysis.

[0107] 2.3. Stress state sensitive self-organizing map.

[0108] Based on the permeability-mechanical coupling state index, a stress state sensitive self-organizing map is implemented: the input data is the permeability-mechanical coupling state index CSI and material partition information; the SOM network parameters are set as follows: 10×10 neuron grid, initial learning rate η0=0.1, time constant τ1=1000, initial neighborhood radius σ0=5.0, time constant τ2=500; the core update formula of the improved self-organizing map algorithm is applied: wij(t+1) = wij(t) + η(t)·h(i, BMU(x),t)·[x - wij(t)]·ψ(σ'(x, t)); where wij(t) is the j-th dimension weight of the ith neuron at time t; η(t) = η0·exp(-t / τ1) is the learning rate; h(i, BMU(x),t) = exp(-||ri - rBMU(x)|| 2 / (2σ 2 (t))) is the neighborhood function; σ(t) = σ0·exp(-t / τ2) is the neighborhood radius; ψ(σ'(x,t)) = [1 + exp(-k·(σ'-σ'0))] -1is the stress state sensitivity function; σ'0 = 1.2 MPa is the stress critical value; k = 5.0 is the stress sensitivity parameter. After 5000 iterations, the rockfill state characteristic partition is generated.

[0109] The traditional SOM algorithm has limitations when processing data with nonlinear distribution characteristics. This embodiment introduces the stress state sensitivity function ψ(σ'), which makes the algorithm have differentiated response sensitivity to different stress state areas, especially enhancing the ability to identify critical stress areas. Experimental verification shows that compared with the traditional SOM, the classification accuracy of the improved algorithm in the critical stress area (0.9MPa-1.5MPa) is improved by 38%, and the boundary recognition accuracy is improved by 25%. This improvement is of great significance for accurately identifying the sudden change area of ​​stress state inside the rockfill body, and provides a more accurate spatial partition basis for subsequent crack risk assessment.

[0110] 2.4. Dynamic modeling of regional mechanical properties.

[0111] Based on the state characteristics zoning of the rockfill body, a regional mechanical characteristics dynamic model considering stress-seepage coupling is established: the dynamic differential equation is constructed: ∏CSI(x, t) / ∏t = ▽·[D(x, σ', CSI)·▽CSI(x, t)] + Q(x, t, σ'); where D(x, σ', CSI) = D0·exp(-α e σ')·exp(λ·CSI)·R(θ) is the diffusion coefficient tensor; D0=1.5×10 -6 m 2 / s is the reference diffusion coefficient; α e =0.8 MPa -1 is the effective stress influence coefficient; λ=2.5 is the coupling state sensitivity coefficient; R(θ) is the anisotropic rotation matrix, and the angle between the principal axis and the dam axis is θ=15°; Q(x, t, σ') is the source-sink term, which represents the state change rate caused by local stress change, Q(x, t, σ') = β1·∏σ' / ∏t·[1-exp(-β2·σ')], where β1=0.01, β2=1.2 MPa -1 The finite element method was used to solve the dynamic equations with a time step of 1 day to generate a set of local mechanical response models.

[0112] Traditional seepage-mechanical analysis usually uses a fixed diffusion coefficient, which cannot reflect the complex nonlinear characteristics inside the rockfill. This embodiment expresses the diffusion coefficient as a function of effective stress and coupled state index D(x, σ', CSI), and introduces a source-sink term Q(x, t, σ') to characterize local state changes. This expression can accurately describe the nonlinear mechanical response of the rockfill under complex stress states, especially capturing the impact of stress changes on permeability characteristics. Measured data verification shows that compared with the traditional fixed coefficient model, the dynamic model has a 45% improvement in the prediction accuracy of the internal state changes of the dam body, and a 57% improvement in the recognition sensitivity of local abnormal areas, providing a reliable basis for accurately assessing crack risk areas.

[0113] 2.5. Boundary adaptive fusion.

[0114] The boundary adaptive fusion method is used to achieve seamless connection of different partition models: Boundary adaptive fusion algorithm: CSI(x) = Σ i [W i (x) CSI i (x)] W i (x) = R i ·ρ i (x) / Σ j [R j ·ρ j (x)]ρ i (x) = exp(-d i (x) 2 / 2l i 2 ), where CSI(x) is the fused state indicator field; CSI i (x) is the state index of the i-th local model; W i (x) is the weight of the i-th model at position x; R i is the reliability score of the i-th model, ranging from [0.75-0.95], determined based on the data reliability index; ρ i (x) is the distance decay function; d i (x) is the distance from point x to the center of the ith region; l i is the characteristic length scale of the ith region, which is determined adaptively according to the partition size and ranges from [10m-30m]. i , achieving smooth transition of boundary areas; outputting spatial distribution characteristics of rockfill state, including global CSI field and regional boundary transition characteristics.

[0115] Traditional regional models often have discontinuities at the boundaries, resulting in jumps in the calculation results. The boundary adaptive fusion method proposed in this embodiment achieves seamless connection of different partition models by introducing a weight function based on data reliability and spatial distance. In particular, by adaptively adjusting the feature length scale l i , so that the model can automatically optimize the width of the boundary transition area according to local characteristics. Practical application has proved that this embodiment eliminates the discontinuity of the model boundary, makes the state field transition smoother and more natural, and improves the state prediction accuracy of the boundary area by 36%, providing high-quality state space distribution characteristics for subsequent deformation field and stress field calculations.

[0116] 2.6. Simulation of dynamic evolution of time-varying states and quantification of uncertainty.

[0117] Based on the spatial distribution characteristics of the rockfill state, the dynamic evolution of the time-varying state is simulated: the time-varying differential equations are solved through prediction-correction iterations with a time step of 1 day; the model parameters are calibrated using historical monitoring data to optimize the evolution prediction accuracy; the uncertainty of the state field is quantified through Monte Carlo simulation and variational Bayesian inference: 1000 Monte Carlo simulations are performed, and the input parameters are randomly perturbed by ±10%; the standard deviation distribution of the state field is calculated to generate the state uncertainty field; high uncertainty areas are identified to provide a reference for risk assessment; the rockfill state field (with a resolution of 1m×1m×1m) and the state uncertainty field are output.

[0118] Traditional state evolution analysis usually ignores the impact of parameter uncertainty, resulting in incomplete risk assessment. This embodiment combines Monte Carlo simulation and variational Bayesian inference to not only predict the evolution of the state field, but also quantify the uncertainty distribution of the prediction results. It can identify high-risk areas and provide more comprehensive information support for decision makers. Practical applications show that the average relative error of state evolution prediction is reduced to 6.3%, which is 42% lower than the traditional method; at the same time, uncertainty quantification increases the early identification rate of high-risk areas by 65%, enhancing risk warning capabilities.

[0119] Step 3: Panel deformation and stress analysis.

[0120] 3.1. Interpolation and reconstruction of discrete monitoring point data.

[0121] 3.1.1. Physical constraint extraction.

[0122] Based on the completion drawing of the concrete face rockfill dam and the state field of the rockfill body: extract the deformation physical constraint conditions based on the principle of mechanical equilibrium: L[u(x)] = f(x, CSI(x)) B[u(x)]= g(x) on ∏Ω; where L = μ▽ 2(·) + (λ+μ)▽(▽·(·)) is the elastic differential operator; u(x) is the displacement field; f(x, CSI(x)) is the volume force, which is related to the permeability-mechanical coupling state indicator CSI(x); B is the boundary operator; g(x) is the boundary condition; λ=25GPa, μ=12GPa are the Lame constants, which are determined according to the material properties; ∏Ω is the computational domain boundary. Generate a set of deformation physical constraint conditions, including equilibrium equations and boundary conditions.

[0123] 3.1.2. Hierarchical feature scale analysis.

[0124] Apply variational mode decomposition to deformation monitoring data: Variational mode decomposition algorithm: min{uk,ωk}{Σk||∏t[(Δ(t)+j / πt)*uk(t)]·e -jωkt || 2 2}; st Σk uk(t) = u(t); where uk(t) is the modal component of the kth scale; ωk is the center frequency of the kth mode; Δ(t) is the Dirac function; j is the imaginary unit; * is the convolution operator; e -jωkt is a complex exponential function; ||·|| 2 2 is the square of the L2 norm; u(t) is the original signal; t is the time variable; k is the modal index; ∏t is the time partial derivative operator. The deformation field is decomposed into 6 main modes, covering deformation characteristics of different time scales; and a multi-scale characteristic spectrum is output, including frequency and energy distribution information.

[0125] Traditional deformation analysis usually regards deformation as a single-scale phenomenon, and it is difficult to distinguish deformation characteristics at different time scales. This embodiment introduces variational modal decomposition technology to decompose the deformation field signal into modal components with different frequency characteristics, thereby realizing multi-scale feature extraction. Experimental results show that this embodiment successfully identifies seasonal changes (low-frequency modes), water level change responses (medium-frequency modes) and local structural responses (high-frequency modes) in dam body deformation. Compared with traditional Fourier analysis, the feature recognition accuracy is improved by 53%, providing a scientific basis for subsequent kernel function construction.

[0126] 3.1.3. Construction of physical response kernel function.

[0127] Combined with the deformation physical constraint set and multi-scale characteristic spectrum: Physical response kernel function construction method: K(x, y) =Σn[Ξn(x)·Ξn(y) / λn]; where Ξn(x) is the nth characteristic function of the mechanical differential operator L, satisfying L[Ξn(x)]= λn·Ξn(x); λn is the corresponding eigenvalue; K(x, y) is the physical response kernel function; x and y are spatial coordinate points; n is the characteristic mode index, taking the first 50 main modes. Solve the differential operator characteristic function system based on the finite element method; construct the corresponding multi-scale physical response kernel function for different scale characteristics; output the physical response kernel function set, including kernel functions of 6 scales.

[0128] Traditional kernel function interpolation methods are usually based on pure mathematical models (such as radial basis functions) and lack physical constraints. This embodiment constructs a physical response kernel function that satisfies the mechanical equilibrium equation, and ensures that the interpolation result conforms to the physical law by solving the characteristic function system of the mechanical differential operator. It has been verified in practice that the physical response kernel function improves the physical rationality of the interpolation result by 78% while ensuring the accuracy of data fitting, especially in sparse monitoring point areas, the prediction accuracy is improved by 65%, providing a theoretical guarantee for the accurate reconstruction of the panel deformation field.

[0129] 3.1.4. Multi-scale kernel function interpolation calculation.

[0130] The physical response kernel function set is used to process the deformation monitoring data: the multi-scale kernel function interpolation equation system: u(x) =Σi[αi·K(x,xi)] + p(x);Σi[αi·p(xi)]= 0 for all p∈P; where u(x) is the deformation field reconstructed by interpolation; xi is the position of the i-th monitoring point; K(x,y) is the physical response kernel function; αi is the unknown coefficient, which is determined by solving the equation system: Σj[αj·K(xi,xj)] + p(xi) = ui for i=1,2,...,N; ui is the monitoring value of the i-th monitoring point; p(x) is a second-order polynomial function to ensure the completeness of the interpolation; P is the polynomial space of a given order; N is the total number of monitoring points, which is 168 in this case. The kernel function parameters are adaptively adjusted for different spatial regions. The interpolation accuracy is evaluated using 10-fold cross validation, and the root mean square error (RMSE) and consistency index (CI) are calculated. The deformation field is output as a continuous distribution with a spatial resolution of 0.5 m.

[0131] Traditional interpolation methods often have the problem of insufficient local accuracy when processing data from non-uniformly distributed monitoring points. The multi-scale kernel function interpolation method proposed in this embodiment achieves high-precision reconstruction of the deformation field by combining physical response kernel functions of different scales. In particular, by adaptively adjusting the kernel function parameters, the algorithm can automatically optimize the interpolation strategy according to the local data density. Practical applications show that the interpolation accuracy (RMSE) of this embodiment is 0.86mm, which is 47% higher than that of the traditional radial basis function method; in sparse areas of monitoring points, the prediction accuracy is improved by 62%, enhancing the reliability of deformation field reconstruction.

[0132] 3.2. Mechanical simulation and stress analysis of panel-rockfill contact.

[0133] Based on the reconstructed deformation field and rockfill state field: a panel-rockfill contact mechanical model is constructed, and the augmented Lagrangian method is used to deal with contact constraints; the influence of the permeability-mechanical coupling state on the contact characteristics is considered, and the contact stiffness and friction coefficient are corrected; the stress distribution of the contact surface, including normal stress and tangential stress, is calculated; based on the contact stress distribution and panel structure information, the stress state of the panel under complex loads is analyzed; the finite element method is used to solve the panel stress field, with a grid size of 0.5m and a total number of 12,568 units; the panel stress field is output, including principal stress, shear stress and equivalent stress.

[0134] Traditional contact analysis usually uses fixed contact parameters, which makes it difficult to reflect the impact of rockfill state on contact characteristics. This embodiment introduces the permeability-mechanical coupling state into the contact model, and achieves a more accurate contact mechanics simulation by correcting the contact stiffness and friction coefficient. Comparative analysis shows that the contact model considering the coupling state has a 39% higher prediction accuracy than the traditional model, especially in the stress concentration area, the stress prediction error is reduced by 56%, providing more reliable stress field data for crack risk assessment.

[0135] 3.3. Deformation prediction and verification.

[0136] Combining the rockfill state field, state uncertainty field and historical deformation data: construct a deformation prediction model based on the long short-term memory network (LSTM); the model input includes factors such as the permeability-mechanical coupling state index CSI, water level changes, and temperature; the model is trained using a historical data set, which includes 5 years of monitoring data, of which 70% is used for training and 30% is used for verification; the prediction uncertainty is evaluated through Monte Carlo random sampling; the verified panel deformation field and prediction accuracy evaluation report are output, with an average relative error of 4.2%.

[0137] Step 4: Crack feature extraction and visualization decision support.

[0138] 4.1. Identification of crack sensitive areas.

[0139] Based on the panel stress field and deformation field: Calculate the crack sensitivity index CFI according to the panel stress state: CFI = (σ1 / ft) α1 + (τmax / fs) α2 + (ε / εc) α3 ; Among them, σ1 is the maximum principal stress; τmax is the maximum shear stress; ε is the maximum principal strain; ft=3.5MPa is the tensile strength of concrete; fs=2.8MPa is the shear strength; εc=0.0002 is the critical strain; α1=2.0, α2=1.5, α3=1.0 are weight indexes. Fuzzy comprehensive evaluation is used to determine the crack risk level, which is divided into low risk, medium risk and high risk; the crack sensitive area map is output to identify the potential crack development area.

[0140] 4.2. Underwater crack image enhancement and feature extraction.

[0141] Process underwater detection data: Apply adaptive histogram equalization and bilateral filtering to enhance underwater image quality; use an improved U-Net deep learning network for crack segmentation; extract crack centerline and width through morphological processing; apply Hough transform to identify the main direction of cracks; output crack feature data, including location, direction, length and width.

[0142] 4.3. Comprehensive determination of crack properties and visual decision support.

[0143] Comprehensive analysis of crack characteristics: Combine stress field analysis to determine the cause of cracks: stress type, temperature type or mixed type; evaluate crack development trends based on stress field, deformation field and crack characteristics; provide targeted maintenance recommendations based on risk assessment; generate three-dimensional visualization to display the spatial distribution of cracks and risk levels; output a comprehensive report on crack properties, including cause analysis, risk rating and maintenance recommendations.

[0144] Traditional crack analysis is usually limited to surface feature extraction and lacks correlation analysis with internal stress states. This embodiment combines crack characteristics with the permeability-mechanical coupling state, stress field and deformation field to achieve a comprehensive analysis of crack causes and development trends. In particular, the introduced crack sensitivity index CFI comprehensively considers factors such as stress, strain and material strength, thereby improving the accuracy of crack risk assessment. Practical applications have shown that this embodiment has increased the early identification rate of cracks by 58% and the accuracy of risk assessment by 46%, providing a scientific basis and decision-making support for dam safety maintenance.

[0145] This embodiment achieves high-precision identification of underwater crack properties of face rockfill dams through the organic combination of multiple steps. Compared with traditional methods, it has the following advantages: permeability-mechanical coupling state modeling improves the prediction accuracy of the internal state of the rockfill body by 45%; multi-scale physical constraint kernel function interpolation improves the accuracy of deformation field reconstruction by 47%; the contact model considering the coupling state improves the stress prediction accuracy by 39%. The present invention achieves high-precision modeling of the permeability-mechanical coupling state of the rockfill body, provides a reliable theoretical basis for subsequent panel deformation and stress analysis and crack feature extraction, and ultimately achieves the purpose of accurately identifying the underwater crack properties of face rockfill dams.

[0146] The preferred embodiments of the present invention are described in detail above; however, the present invention is not limited to the specific details in the above embodiments. Within the technical concept of the present invention, various equivalent transformations can be made to the technical solutions of the present invention, and these equivalent transformations all belong to the protection scope of the present invention.

Claims

1. A method for identifying underwater crack properties of a concrete face rockfill dam, characterized in that: The following steps are involved: The original monitoring data and the completion drawings of the concrete face rockfill dam were obtained, and the standardized monitoring data set and data reliability index were obtained through preprocessing. Based on the standardized monitoring data set, data reliability index and the completion drawing of the concrete face rockfill dam, the rockfill state field and state uncertainty field are obtained through the rockfill body permeability-mechanical coupling state modeling. Using the rockfill state field, state uncertainty field and as-built drawings of the face rockfill dam, the face deformation field and face stress field are obtained through face deformation and stress analysis. Based on the panel deformation field, panel stress field and pre-stored underwater detection data, a comprehensive report on crack properties is generated through crack feature extraction and visual decision support.

2. The method according to claim 1, characterized in that The steps of obtaining the rockfill state field and state uncertainty field by modeling the rockfill permeability-mechanical coupling state include: Based on the as-built drawings of the concrete face rockfill dam and the structural information in the standardized monitoring data set, a physical model of the rockfill body is established to generate material partition information; Combining standardized monitoring data sets, data reliability indicators and material partition information, the spatial heterogeneity of rockfill states is characterized and the spatial distribution characteristics of rockfill states are formed; Based on the spatial distribution characteristics of the rockfill state and the time series data in the standardized monitoring data set, the dynamic evolution of the time-varying state is simulated and a spatiotemporal evolution model of the rockfill state is constructed; Integrate the spatiotemporal evolution model of rockfill state and data reliability indicators, analyze and quantify uncertainty and its propagation law, and output the rockfill state field and state uncertainty field.

3. The method according to claim 2, characterized in that The steps of characterizing the spatial heterogeneity of the rockfill state and forming the spatial distribution characteristics of the rockfill state include: Extract relevant monitoring data from the standardized monitoring data set and construct a permeability-mechanical coupling state index that considers effective stress, pore water pressure, and strain state; Based on the permeability-mechanical coupling state index and material partition information, stress state sensitive self-organizing mapping is performed to divide the rockfill state characteristic partitions; According to the state characteristic zoning of rockfill bodies, a regional mechanical characteristic dynamic model considering stress-seepage coupling is established to generate a set of local mechanical response models; Based on the local mechanical response model set and data reliability indicators, boundary adaptive fusion is implemented to achieve seamless connection of different partition models and output the spatial distribution characteristics of the rockfill state.

4. The method according to claim 3, characterized in that The steps to construct the permeability-mechanical coupling state index include: Extract effective stress, pore water pressure, and strain state data from standardized monitoring data sets; Establish a mathematical model that comprehensively considers effective stress, pore water pressure and strain state, and calculate the permeability-mechanical coupling state index CSI (x, t); CSI(x,t) = α·σ'(x,t) / σ'max + β·P(x,t) / Pmax + γ·ε(x,t) / εmax; Where CSI(x, t) represents the permeability-mechanical coupling state index of the spatial point x at time t; σ'(x, t) represents the effective stress; P(x, t) represents the pore water pressure; ε(x, t) represents the strain; σ'max represents the maximum effective stress; Pmax represents the maximum pore water pressure; εmax represents the maximum strain; α, β, γ represent weight coefficients, and α+β+γ=1; x represents the spatial coordinate point; t represents the time point.

5. The method according to claim 1, characterized in that The steps of obtaining the panel deformation field and panel stress field through panel deformation and stress analysis include: Read the deformation monitoring data and rockfill state field in the standardized monitoring data set, reconstruct the discrete monitoring point data through the multi-scale physical constraint kernel function interpolation method, and generate a continuous distribution of the deformation field; Based on the rockfill state field, continuous distribution of deformation field and completion drawing of the concrete face rockfill dam, a slab-rockfill contact mechanical model is constructed to calculate the contact stress distribution. According to the contact stress distribution, continuous distribution of deformation field and the panel structure information in the completion drawing of the face rockfill dam, the stress state of the panel under complex loads is analyzed and the panel stress field is calculated. The rockfill state field, state uncertainty field and historical deformation field are continuously distributed, a deformation prediction model is established and verified with measured data, and a verified panel deformation field is output.

6. The method according to claim 5, characterized in that The steps to generate a continuous distribution of the deformation field include: Analyze the completion drawings of the panel rockfill dam and the state field of the rockfill body, extract the deformation physical constraints based on the principle of mechanical equilibrium, and form a set of deformation physical constraints; Perform variational mode decomposition on the deformation monitoring data in the standardized monitoring data set to identify the multi-level characteristic scales of the deformation field and generate a multi-scale characteristic spectrum; Combining the deformation physical constraint condition set and the multi-scale characteristic spectrum, a multi-scale kernel function that satisfies the physical constraint is constructed, and a physical response kernel function set is established; The physical response kernel function set is used to process the deformation monitoring data in the standardized monitoring data set, and multi-scale kernel function interpolation calculation is performed to output a high-precision continuous distribution of the deformation field.

7. The method according to claim 1, characterized in that The steps of crack feature extraction include: Perform local illumination normalization and color channel weighted fusion on the underwater detection data to obtain a fused grayscale image; Apply multi-layer wavelet decomposition to the fused grayscale image to obtain low-frequency approximation coefficients and multi-layer detail coefficients; Calculate the directional coherence measure and phase consistency of the detail coefficients to obtain a directional coherence measure set and a phase consistency map, and construct an adaptive enhancement function based on the directional coherence measure set and phase consistency map to perform selective enhancement on the wavelet coefficients to obtain enhanced wavelet coefficients. The enhanced wavelet coefficients are subjected to inverse wavelet transform and local statistical enhancement to obtain an enhanced crack image, which is then subjected to morphological sharpening and crack feature measurement to obtain crack feature data.

8. The method according to claim 5, characterized in that The steps for generating a continuous distribution of the deformation field may also be: Read deformation monitoring data and rockfill state field, build a multi-resolution hierarchical structure, perform spectral decomposition and residual calculation, and obtain anomaly point sets and multi-scale spectral residual sets; Read the abnormal point set, deformation monitoring data and multi-scale spectral residual set, estimate the initial repair value of the abnormal point, establish a physical constraint optimization problem, and obtain a constrained optimization problem; Read the constrained optimization problem, apply iterative harmonic solution to solve it, perform uncertainty assessment and verification, and obtain the repair deformation monitoring data; Read and repair deformation monitoring data, apply physical response kernel function interpolation calculation, and obtain high-precision continuous distribution of deformation field.

9. The method according to claim 8, characterized in that The construction of a multi-resolution hierarchy includes: Read the deformation monitoring data and perform standardization processing to obtain a standardized measurement matrix; Perform quadtree decomposition based on the spatial distribution of monitoring points in the standardized measurement matrix, including: Initialize the quadtree root node, which contains all monitoring points; If the number of points contained in the quadtree root node is greater than the threshold and the region size is greater than the minimum size, it is divided into four child nodes; Recursively perform quadtree decomposition until the termination condition is met; Define the resolution hierarchy based on the quadtree structure: H i = {the center point of each node in the i-th level of the tree}, ..., H m = {the center point of each node in the deepest layer of the tree}, 1≤i≤m; m is the number of levels of quadtree decomposition; The center point is defined by the weighted average of the monitoring points in the area, with the weights based on the measurement reliability.

10. The method according to claim 2, characterized in that The steps of simulating the dynamic evolution of time-varying state and constructing the spatiotemporal evolution model of rockfill state include: Read the spatial distribution characteristics of the rockfill state and the time series data in the standardized monitoring data set, perform wavelet multi-scale time decomposition, calculate energy analysis and physical trigger condition correlation analysis, and generate a multi-scale wavelet coefficient set and a state transition point set; The multi-scale wavelet coefficient set and state transition point set are read, the physical diffusion model of the low-frequency component and the dynamic model of the medium- and high-frequency detail coefficients are constructed, and a cross-scale dynamic coupling mechanism is established to obtain a multi-scale evolution model set, namely, the spatiotemporal evolution model of the rockfill state.

Images