Three-dimensional monitoring data time series difference compensation and dynamic threshold adaptive adjustment method

Abstract

This invention discloses a method for compensating for temporal discrepancies in three-dimensional monitoring data and for adaptively adjusting dynamic thresholds. The method involves collecting three-dimensional point cloud data and environmental sensor data; extracting environmental features using regionally adaptive partitioned PCA to address spatial heterogeneity; accurately reconstructing the environmental field distribution of the entire monitoring area from limited environmental sensor data using physical information-enhanced environmental field reconstruction technology; constructing a cognitive physics-data dual-driven compensation model, embedding the physical model into a data-driven architecture; calculating the expected displacement caused by the environment based on an environment-structure response model and deducting it from the measured displacement; and dynamically adjusting the change detection threshold. This method addresses the problem of "pseudo-changes" caused by environmental factors and improves the accuracy and reliability of three-dimensional monitoring data.

Description

Technical Field

[0001] The present invention belongs to the field of structural health monitoring, and in particular to a method for compensating for time series differences in three-dimensional monitoring data and adaptively adjusting dynamic thresholds. Background Art

[0002] Three-dimensional monitoring technology has important applications in construction engineering, historical building preservation, infrastructure management, and other fields. Point cloud data acquired through high-precision 3D laser scanners enables precise recording and change monitoring of structural geometry, providing a key basis for structural health assessment and safety early warning. However, outdoor building structures are exposed to the elements for long periods of time. Environmental factors such as temperature, humidity, and light can cause subtle displacements in materials, such as thermal expansion and contraction, and humidity-induced deformation. These "pseudo-changes" often blend in with actual structural deformations, severely impacting the accuracy and reliability of change detection. Therefore, studying mechanisms to compensate for the impact of environmental factors on 3D monitoring data is of great theoretical and practical significance.

[0003] At present, a series of technical methods have been formed in the field of three-dimensional point cloud change detection. Common point cloud-based change detection methods include point-to-point comparison method, point-to-surface distance method and feature comparison method. In order to reduce the impact of environmental factors, researchers have proposed a specific time period sampling and comparison method, that is, collecting data during time periods with similar environmental conditions for comparison; some scholars have also introduced statistical filtering technology to screen changes by setting fixed thresholds or adaptive thresholds based on statistical characteristics; in terms of point cloud registration, the iterative closest point (ICP) algorithm and its improved algorithm are widely used for accurate registration of point clouds at different times. For compensation of environmental factors, some studies have begun to try to establish a simple linear regression model to describe the relationship between a single environmental parameter and structural displacement.

[0004] However, existing technologies still face several key technical bottlenecks in practical applications. First, traditional environmental compensation methods assume a linear relationship between environmental factors and structural responses, and are unable to handle nonlinear thermal expansion of materials and multi-factor coupling effects, resulting in poor compensation effects under extreme environmental conditions. Second, existing methods ignore structural spatial heterogeneity. Due to differences in materials, orientations, and stress conditions, different parts of the same structure have significantly different response characteristics to environmental factors. Using a unified model for compensation will produce regional errors. Third, environmental sensors are arranged in discrete positions. How to accurately reconstruct the environmental parameter field distribution of the entire monitoring structure surface from limited environmental monitoring points and achieve accurate environmental compensation for each point cloud point is a difficult problem that has not yet been well solved by existing technologies. These technical problems lead to a high false positive rate in existing systems under complex structures and changing environmental conditions, affecting monitoring reliability. Summary of the Invention

[0005] The purpose of the invention is to provide a method for compensating for time series differences in three-dimensional monitoring data and adaptively adjusting dynamic thresholds, in order to solve at least one technical problem existing in the prior art.

[0006] The technical solution, a method for compensating for time series differences in three-dimensional monitoring data and adaptively adjusting dynamic thresholds, includes:

[0007] Collect and preprocess point cloud data to obtain registered point cloud data;

[0008] Based on the registered point cloud data and pre-stored material parameter data, PCA environmental features are extracted by region to obtain regional environmental features;

[0009] Using regional environmental characteristics and pre-stored environmental sensor data, perform physical information enhanced environmental field reconstruction to obtain the final environmental field and build a cognitive physical-data dual-driven compensation model based on it to obtain a training model;

[0010] When in use, the dynamic threshold adaptive adjustment and timing difference compensation are performed through the training model, and the environmental displacement field, compensated displacement field and adaptive threshold are calculated to obtain the change detection result.

[0011] Beneficial effects: The present invention enables more accurate modeling of the complex coupling relationship of environmental factors, realizes the fine reconstruction of the local environmental field, and significantly reduces the regional error caused by the overall unified model; at the same time, it not only solves the problem of insufficient sensor coverage, but also provides an accurate environmental compensation basis for each point cloud point; it solves the "pseudo-change" problem caused by environmental factors, and improves the accuracy and reliability of three-dimensional monitoring data. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A flowchart of the steps of a method for compensating for timing differences in three-dimensional monitoring data and adaptively adjusting dynamic thresholds provided in an embodiment of the present application.

[0013] Figure 2 A flowchart of the steps for extracting PCA environmental features by region provided in an embodiment of the present application.

[0014] Figure 3 A flowchart of the steps for performing response similarity evaluation provided in an embodiment of the present application.

[0015] Figure 4 A flowchart of the steps of applying time-series weighted PCA feature extraction provided in an embodiment of the present application. DETAILED DESCRIPTION

[0016] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions 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 embodiments described 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 making creative efforts should fall within the scope of protection of the present invention.

[0017] It should be noted that to clearly illustrate the steps of this application, serial numbers are assigned to each step in the specification. These serial numbers are for illustrative purposes only and do not limit the order in which the steps must be executed. In actual operation, depending on the technical requirements of the specific implementation scenario, the steps may be executed in a different order than shown in the specification, and in some cases, parallel processing between steps may be implemented.

[0018] like Figure 1 As shown, the method for compensating for time series differences in three-dimensional monitoring data and adaptively adjusting dynamic thresholds includes the following steps:

[0019] S1, collect point cloud data and preprocess it to obtain registration point cloud data;

[0020] Specifically, a 3D laser scanner is used to acquire point cloud data of the target structure’s surface, including a digital representation of its shape, position, and other information. Environmental information, such as temperature and humidity, can also be collected, and the specific time of acquisition is recorded.

[0021] S2, based on the registered point cloud data and pre-stored material parameter data, extract PCA environmental features by region to obtain regional environmental features;

[0022] Specifically, material parameter data includes physical properties such as the coefficient of thermal expansion and elastic modulus. The point cloud data is divided into several regions. Within each region, principal component analysis (PCA) is used to extract key characteristics related to environmental changes. Ultimately, each region is given a set of characteristic data that describes how it responds to environmental factors.

[0023] S3, using regional environmental characteristics and pre-stored environmental sensor data, performing physical information enhanced environmental field reconstruction to obtain the final environmental field;

[0024] Specifically, environmental sensor data refers to real-time environmental data recorded by sensors, such as temperature and humidity changes. By using physical laws (such as heat conduction and air flow), constraints are added to the model to ensure that the reconstructed environmental field conforms to physical phenomena and is not based solely on sensor data.

[0025] S4. Based on the final environmental field, a cognitive physical-data dual-driven compensation model is constructed to obtain a training model;

[0026] Specifically, the cognitive physics-data dual-driven compensation model combines physical laws with data-driven methods for compensation and optimization. That is, physical theory is used to establish the basic framework, while data analysis and learning are used to refine the model, making it more accurate and practical.

[0027] S5. When in use, the dynamic threshold adaptive adjustment and timing difference compensation are performed through the training model, and the environmental displacement field, the compensated displacement field and the adaptive threshold are calculated to obtain the change detection result.

[0028] Specifically, the threshold is dynamically adjusted based on the current situation, acting like an adjustable standard to adapt to varying environmental conditions. Then, time differences are taken into account and compensated for. This means that when comparing data across different time periods, errors caused by time shifts are eliminated to ensure accurate results.

[0029] This embodiment can accurately identify and monitor dynamic changes in the environment, effectively reducing data dimensions, thereby improving computing speed and analysis efficiency; ensuring that the model not only adheres to theoretical foundations, but can also adaptively learn from data to improve accuracy and enhance practicality; at the same time, it not only improves the overall reliability of the model, but also optimizes the accuracy of the analysis, achieving high-precision, strong robustness and high-efficiency data monitoring and change detection.

[0030] According to one aspect of the present application, the pre-processing step comprises:

[0031] S11. Multi-source data acquisition. Use a 3D laser scanner to collect point cloud data of the target structure. t , where t represents the collection time point; deploy an environmental sensor array to collect environmental parameter data E t , including environmental factors such as temperature, humidity, and light, and synchronously record the acquisition time t; obtain the material parameter data M of the structure, including physical properties such as thermal expansion coefficient and elastic modulus, and record the scanning position information L and scanning parameters S for subsequent point cloud alignment and data correction.

[0032] S12. Point cloud data preprocessing. Read the original point cloud data and perform noise reduction to obtain a noise-reduced point cloud. Downsample the noise-reduced point cloud to control the uniformity of point density to obtain a uniform point cloud. Extract the geometric features of the uniform point cloud, including normal vectors and curvature, to generate a feature point cloud. Based on the feature point cloud and the scanning position information L, register the point clouds acquired at different times to obtain a registered point cloud.

[0033] S13, environmental data preprocessing. Read environmental parameter data E t, detect outliers and obtain filtered environmental data; perform time series smoothing on the filtered environmental data to obtain smoothed environmental data; calculate the changes in environmental parameters at adjacent time points to generate environmental change data; associate the smoothed environmental data with the sensor position coordinates C to establish an environment-space mapping.

[0034] S14. Structural Segmentation and Material Labeling. Based on the feature point cloud and material parameter data M, the point cloud is segmented into regions of different materials to obtain a segmented point cloud. Corresponding material parameters are assigned to each region in the segmented point cloud to generate a material labeling point cloud. The geometric properties (area, volume, etc.) of each segmented region are calculated to obtain region characteristic data R. Adjacency relationships G between the segmented regions are established to represent the spatial connectivity between regions of different materials.

[0035] S15. Initial change detection. Select the registered point cloud at the reference time point as a reference. Compare the registered point cloud at the current time point t with the reference point cloud, calculate the point-to-point distance or point-to-surface distance, and generate an original change map. Filter the original change map (for example, by applying a traditional thresholding method) to obtain the initial change detection results.

[0036] like Figure 2 As shown, according to one aspect of the present application, the step of extracting PCA environmental features by region to obtain regional environmental features includes:

[0037] S21. Based on the registered point cloud data and the material parameter data, perform initial division of the structural response area to obtain initial partitions;

[0038] S22, evaluating the response similarity of the initial partitions, and obtaining the optimized partitions by constructing a response correlation matrix and performing spectral cluster analysis;

[0039] S23, applying time-series weighted PCA feature extraction to the optimized partitions, and obtaining a PCA model by constructing a time-decay weight function and a weighted covariance matrix;

[0040] S24. Based on the PCA model, perform robust environmental feature extraction to obtain an environmental feature vector;

[0041] S25. Based on the environmental feature vector and the PCA model, a nonlinear kernel function mapping is constructed to obtain regional environmental characteristics.

[0042] Specifically, based on the material annotation point cloud and material parameter data M, the potential environmental sensitivity of each point is calculated to obtain a sensitivity map; according to the sensitivity map and regional characteristic data, the region growing algorithm is used to perform initial partitioning to obtain the initial partitioning result; the environmental response statistical characteristics of each initial partition are calculated to generate a partition characteristic matrix; based on the partition characteristic matrix and the adjacency relationship of the segmented areas, the boundaries of adjacent partitions are adjusted to obtain adjusted partitions.

[0043] Environmental change data from multiple historical time points and the corresponding registered point clouds are selected. For each adjusted partition, the correlation matrix between point displacement and environmental change is calculated to obtain a response correlation matrix. Based on the response correlation matrix, a spectral clustering algorithm is used to evaluate the response similarity of points within the partition to obtain a similarity index. Based on the similarity index, the partition boundaries are optimized, highly similar adjacent partitions are merged, and partitions with high response heterogeneity are split to generate optimized partitions.

[0044] For each optimized partition, an environment-displacement data matrix is constructed, which includes the environmental parameters and corresponding displacements at historical time points; and a time decay weight function W(t-τ) = e is designed. -λ(t-τ) Calculate the time weight vector, where t is the current time point, τ is the historical time point, λ is the time decay factor, and e is the base of the natural logarithm. Construct a weighted covariance matrix based on the time weight vector to obtain the weighted covariance. Perform eigendecomposition on the weighted covariance to extract the principal component vectors and eigenvalues, generating a PCA model.

[0045] An M-estimator is applied to the historical environmental-displacement data of each partition to identify and reduce the influence of outliers and obtain robust data. Based on the robust data and the PCA model, the projection of environmental features in the principal component space is calculated to obtain the environmental feature vector. A feature reconstruction mapping is constructed to project the environmental feature vector back to the original space to obtain reconstructed environmental data. The reconstruction error between the reconstructed environmental data and the original environmental data is calculated to generate a feature quality indicator.

[0046] Based on the environmental feature vector and the PCA model, a nonlinear kernel function mapping is constructed for each partition to obtain a kernel PCA model. According to the material properties of the partition, an appropriate kernel function (RBF kernel, polynomial kernel, etc.) is selected for each kernel PCA model. The influence weights of environmental factors are calculated, and the importance of each environmental parameter in the model is adjusted to obtain parameter weights. The kernel PCA model, parameter weights, and optimized partitions are integrated to construct a regional environmental feature library.

[0047] like Figure 3 As shown, according to one aspect of the present application, the steps of evaluating response similarity and obtaining optimized partitions include:

[0048] Extract environmental change data at historical time points and register point cloud data to establish an environment-response mapping table;

[0049] Based on the environment-response mapping table, multivariate regression analysis is performed on the point cloud within the initial partition to obtain the sensitivity coefficient matrix;

[0050] Based on the sensitivity coefficient matrix, the point-to-point response pattern similarity is calculated and the response correlation matrix is constructed;

[0051] Apply Laplace matrix transform and eigenvalue decomposition to the response correlation matrix, perform spectral clustering analysis, and obtain the subpartition consistency matrix;

[0052] Based on the sub-partition consistency matrix, the partition consistency index and the similarity between partitions are calculated, and partition merging or splitting operations are performed to obtain optimized partitions.

[0053] Specifically, read the historical environmental change data ΔE within a predetermined time window τ (τ = t-1, t-2, ..., tn), organize it into a time series matrix, and obtain the environmental change time series matrix ΔE t Extract the registered point cloud at the corresponding time points and calculate the point displacement vectors between each pair of adjacent time points to obtain the displacement vector field. Temporally concatenate the displacement vectors of each point to form a displacement time series, resulting in a point displacement time series matrix. Establish a correspondence table between the environmental change time series matrix and the point displacement time series matrix to generate an environment-response mapping table.

[0054] For each point cloud in the adjustment partition, data from the environment-response mapping table is extracted to construct a multivariate linear regression model, using the environmental change time series matrix as the independent variable and the point displacement time series matrix as the dependent variable to obtain the linear response model. The sum of squared residuals is calculated to assess the linear model's fit and generate the linear fit error. A nonlinear kernel regression model is applied, also using the environmental change time series matrix and the point displacement time series matrix as inputs, to obtain the nonlinear response model. The sum of squared residuals of the nonlinear model is calculated to generate the nonlinear fit error.

[0055] Compare the linear fitting error and nonlinear fitting error of each point to determine the best fitting model type and record it as the optimal model type; based on the optimal model type, extract the environmental factor sensitivity coefficient of each point and generate a sensitivity coefficient matrix; calculate the point-to-point response pattern similarity within the partition and construct the point-to-point similarity matrix PS z :PS z (i,j) = exp(-||S z coef (i) - S z coef (j)|| 2 / σ 2 ); where S z coef is the sensitivity coefficient matrix, i and j are point indices, and σ is the scale parameter. Based on the point pair similarity matrix PS z , construct a weighted adjacency graph and obtain the response correlation matrix R z :R z (i,j) = PS z(i, j) · W(d(i, j)), where W is the spatial distance weighting function and d(i, j) is the Euclidean distance between point i and point j.

[0056] Apply the Laplace matrix transform to each response correlation matrix and calculate the normalized Laplace matrix L z norm :L z norm = D z -1 / 2 · (D z - R z ) · D z -1 / 2 , where D z is the degree matrix, and the diagonal elements are the response correlation matrix R z The sum of each row. Calculate the eigenvalues and eigenvectors of the normalized Laplacian matrix, select the eigenvectors corresponding to the k smallest non-zero eigenvalues, and form an eigenvector matrix. Apply the K-means clustering algorithm to the row vectors of the eigenvector matrix to divide the points within the partition into several sub-partitions to obtain the spectral clustering results. Calculate the response consistency index of the points within each sub-partition and construct the sub-partition consistency matrix.

[0057] Based on the sub-partition consistency matrix SC z , calculate the internal response consistency score of each adjustment partition and generate the partition consistency index IC z :IC z = 1 - ∑ i (var(SC z (i)) / |SC z (i)|) / k; where var is the variance function, |SC z (i)| is the sub-partition consistency matrix SC z The size of the i-th sub-partition in , k is the number of sub-partitions. Calculate the response pattern similarity between adjacent partitions and construct the inter-partition similarity matrix ZS: ZS(i,j) = cos(S z coef i , S z coef j ), where cos is the cosine similarity function. Based on the partition consistency index IC z And the similarity matrix ZS between partitions, calculate the comprehensive similarity index, and get the similarity index S z :S z = α · IC z + (1-α) max jZS(z,j), where α is a balance factor used to adjust the weights of internal consistency and external similarity. z , set the merging threshold θ merge and the splitting threshold θ split , perform the following optimization operations: For S z < θ split The partition of , further subdivide by recursive bisection to obtain subdivided partitions; for adjacent partitions i and j, if ZS(i,j) > θ merge , then merge the two partitions to obtain a merged partition; integrate the subdivided partitions and the merged partition to generate the final optimized partition.

[0058] like Figure 4 As shown, according to one aspect of the present application, the steps of applying time-series weighted PCA feature extraction to obtain a PCA model include:

[0059] Based on the optimized partition and environment-response mapping table, the environment-displacement joint matrix is constructed;

[0060] Based on the preset time decay coefficient, the exponential decay function is applied to calculate the weight of the historical time point to obtain the normalized time weight;

[0061] Based on the normalized time weights, the weighted mean vector and weighted outer product of the environment-displacement joint matrix are calculated to construct the regularized covariance matrix;

[0062] Perform eigenvalue decomposition on the regularized covariance matrix, sort by contribution rate and select the main eigenvectors to obtain the principal component matrix;

[0063] Based on the principal component matrix, the projection transformation matrix and the reconstruction transformation matrix are constructed, and combined with the weighted mean vector to generate the PCA model.

[0064] Specifically, for each point in the optimized partition, historical data is extracted from the environment-response mapping table; the environmental parameters are organized in chronological order to construct a partition environment matrix, where rows represent time points and columns represent different environmental parameters; the average displacement vector of the points in the partition at each time point is calculated to construct a partition displacement matrix, which also uses time as the row index; the partition environment matrix and the partition displacement matrix are spliced together to form the environment-displacement joint matrix J z :J z = [E z T | D z T ], where E z T is the partition environment matrix, D z T is the partition displacement matrix.

[0065] Set the time decay coefficient λ, which controls the rate at which the influence of historical data decays over time; calculate the time interval Δt = t – τ from each historical time point τ to the current time t; apply the exponential decay function to calculate the weight of each time point to obtain the time weight vector W t :W t (τ) = exp(-λ·(t-τ)); for the time weight vector W t Perform normalization to ensure that the sum of weights is 1 and obtain the normalized time weight W t norm :W t norm (τ) = W t (τ) / ∑ i W t (i).

[0066] Using the normalized time weights, calculate the weighted mean vector μ of the environment-displacement joint matrix w :μ w = ∑ τ W t norm (τ) · J z (τ); environment-displacement joint matrix J z Subtract the weighted mean vector μ from each row of w , get the centralized matrix; based on the normalized time weight, calculate the weighted outer product of the centralized matrix and construct the weighted covariance matrix C z w :C z w = ∑ τ W t norm (τ) · J z c (τ) T · J z c (τ), where J z c is the centralized matrix, T Represents transpose. Regularize the weighted covariance matrix to increase numerical stability and obtain the regularized covariance matrix C z reg :C z reg = C z w + ε·I, where ε is a small positive number and I is the identity matrix.

[0067] Perform eigenvalue decomposition on the regularized covariance matrix to obtain eigenvalue vectors and eigenvector matrices; sort the eigenvalues in descending order and adjust the order of the eigenvectors accordingly to obtain sorted eigenvalues and sorted eigenvectors; calculate the cumulative variance contribution rate and determine the number of principal components k to be retained, so that the cumulative contribution rate reaches the preset threshold η (such as 95%): k = min{j |∑ i =1 j λ s i / ∑ i λ s i ≥ η}, where λ s is the sorting eigenvalue; select the first k columns from the sorting eigenvector to form the principal component matrix; calculate the variance contribution rate corresponding to each principal component and generate the contribution rate vector CR z :CR z (i) = λ s i / ∑ j λ s j , i = 1,2,...,k.

[0068] Based on the principal component matrix, a data projection transformation matrix is constructed to realize the mapping from the original space to the principal component space, and the projection matrix is obtained; a reconstruction transformation matrix from the principal component space to the original space is established to obtain the reconstruction matrix; the environment-displacement joint matrix is projected to the principal component space to obtain the principal component coefficient matrix PC z :PC z = J z c · P z , where P z is the principal component matrix, J z c is the centralization matrix; the weighted mean vector, principal component matrix, contribution rate vector, projection matrix and reconstruction matrix are integrated to build a complete PCA model.

[0069] According to one aspect of the present application, the steps of performing robust environmental feature extraction to obtain an environmental feature vector include:

[0070] Based on the environment-displacement joint matrix, the Huber loss function is used as a robust M-estimator to obtain the weight function;

[0071] Use the weight function to calculate the weight of the data points, identify outliers and make corrections to obtain a robust data matrix;

[0072] Project the robust data matrix through the projection matrix of the PCA model to generate a robust coefficient matrix;

[0073] The corresponding relationship between environmental parameters and principal components is analyzed based on the robust coefficient matrix, key environmental features are extracted, and the environmental feature vector is obtained.

[0074] Specifically, based on the environment-displacement joint matrix, the Mahalanobis distance of each data point to its temporal neighbor is calculated to obtain a distance matrix; a robust loss function ρ(x) is designed, such as the Huber loss or the Tukey double-weight loss function: ρ Huber (x) = {x 2 / 2, if |x| ≤ c; c·|x| - c 2 / 2, if |x| > c}, where c is a tuning parameter that controls sensitivity to outliers. Based on outliers in historical data, optimize the M-estimator parameters, such as the parameter c of the Huber loss, to obtain the optimized M-estimator. Design a corresponding weight function w(x) = ρ'(x) / x to weight the data points, obtaining the weight function. x is a data point, and ρ'(x) is the derivative of the loss function ρ(x) with respect to x.

[0075] For each data point in the environment-displacement joint matrix, the distance matrix and weight function are applied to calculate the weight to obtain the data point weight matrix; the outlier identification threshold is set, and the data points with weights lower than the threshold are identified as outliers to generate the outlier labeling matrix; the identified outliers are corrected by local smoothing or interpolation methods to obtain corrected data points; the original data points and the corrected data points are merged according to the weights to form the robust data matrix J z rob :J z rob = W z point Θ J z + (1- W z point ) Θ J z corr , where Θ represents the element-wise multiplication operation, W z point is the data point weight matrix, J z is the environment-displacement joint matrix, J z corr Corrected data points.

[0076] The robust principal component coefficients are calculated using the robust data matrix and the projection matrix in the PCA model to obtain a robust coefficient matrix. The statistical properties of the robust coefficient matrix, such as mean, variance, and distribution shape, are analyzed to generate coefficient statistical characteristics. The correspondence between environmental parameters and principal components is identified, the physical meaning captured by each principal component is determined, and a principal component interpretation table is generated. Based on the principal component interpretation table, the main environmental-related features are extracted from the robust coefficient matrix to form an environmental feature vector.

[0077] Use the environmental feature vector and the reconstruction matrix in the PCA model to reconstruct the environmental parameters and obtain the reconstructed environmental data; calculate the mean square error between the reconstructed environmental data and the original environmental data to generate the reconstruction error; use the leave-one-out cross-validation method to evaluate the generalization ability of the feature extraction model and obtain the cross-validation error; combine the reconstruction error and cross-validation error to calculate the comprehensive feature quality score and generate the feature quality index Q z :Q z = β · (1 - norm(MSE z )) + (1-β) · (1 -norm(CVE z )), where norm is the normalization function, β is the trade-off parameter, and MSE z is the reconstruction error, CVE z is the cross validation error.

[0078] Based on the statistical characteristics of the robust data matrix, an adaptive anomaly detection model is constructed to obtain an anomaly detector; the spatiotemporal distribution characteristics of anomaly patterns in historical data are analyzed to build an anomaly pattern library; an adaptive threshold adjustment strategy is designed to dynamically adjust the threshold according to the current environmental conditions and historical anomaly patterns to obtain the adaptive threshold function AT z :AT z (x) = θ b ase ·(1 + γ · sim(x, AM z )), where θ b ase is the basic threshold, γ is the adjustment parameter, sim is the similarity function, AM z It is an abnormal pattern library; the anomaly detector and adaptive threshold function are integrated to form a complete robust feature extraction system.

[0079] In one embodiment of the present application, robust environmental features are extracted. The Mahalanobis distance is calculated for the joint environment-displacement matrix J to identify outliers: Mahalanobis distance formula: d(J(τ)) = sqrt((J(τ)-μ) T ·C -1(J(τ)-μ), for example: d(J(t-5)) = 3.82 > c(=1.345); w(J(t-5)) = 1.345 / 3.82 = 0.352, identifying 4 outliers and constructing the robust data matrix J z rob :J z rob (t-5) = 0.352×J(t-5) + 0.648×J corr (t-5), where J corr (t-5) is calculated by weighted average of the 5 adjacent points; the robust data matrix is projected through the PCA model: PC z = (J z rob - μ w )×Projection Matrix= (J z rob - μ w )×P T , and obtain the robust coefficient matrix, where μ w is the weighted mean vector.

[0080] Select radial basis function (RBF) to construct nonlinear kernel function mapping: k(x,y) = exp(-γ||xy|| 2 ), where γ = 0.1 is the kernel parameter. Example of calculating the kernel matrix K: K(1,2) = exp(-0.1×||PC z (1)-PC z (2)|| 2 ); Apply kernel PCA to calculate the new feature projection: α = kernel principal component eigenvector; kernel space projection = K×α, integrate to obtain regional environmental characteristics: regional environmental characteristics (region 1A) = {v env , PCA model , kernel function parameter, α}, PCA model The PCA model is used. Through the above steps, the environmental feature extraction of region 1A is completed. The same process is repeated for the other six regions to obtain a complete set of regional environmental features.

[0081] According to one aspect of the present application, the steps of performing physical information enhanced environment field reconstruction to obtain a final environment field include:

[0082] S31. Based on regional environmental characteristics, registered point cloud data, and material parameter data, a three-dimensional computational domain geometric model and physical boundary conditions are constructed to obtain a computational domain model and boundary condition function.

[0083] S32. Calculate the spatial gradient of the environmental parameters based on the computational domain model and generate a multi-resolution grid; wherein a fine grid is used in areas where the spatial gradient of the environmental parameters exceeds a preset threshold;

[0084] S33. For the temperature field, humidity field, and light field, a heterogeneous physical model is constructed in combination with material parameter data, including the heat conduction equation, convection-diffusion equation, and radiation transfer equation, to obtain an environmental field physical model set;

[0085] S34, fusing the environmental field physical model set with the environmental sensor data through the observation operator and the ensemble Kalman filter, performing data assimilation, and obtaining the posterior environmental field;

[0086] S35. Calculate the theoretical structural response based on the posterior environmental field, compare it with the measured displacement, and adjust the environmental field parameters through feedback optimization to obtain the final environmental field.

[0087] Specifically, based on the registration point cloud and the segmentation point cloud, a three-dimensional computational domain geometric model is constructed to obtain the computational domain model; the boundary surface of the computational domain model is identified to generate the boundary condition area; according to the location and environmental characteristics of the boundary condition area, the physical boundary conditions (such as temperature and humidity boundary values) are set to obtain the boundary condition function; according to the material annotation point cloud, the material physical parameters are assigned to different areas in the computational domain to generate the regional physical parameters.

[0088] Based on the computational domain model, an initial uniform grid is constructed to obtain an initial grid; the spatial gradient of the environmental parameters is calculated, and the areas with large gradients are identified to generate a gradient map; the gradient map and the sensitivity map are combined to construct a grid refinement index to obtain a refinement index; based on the refinement index, the initial grid is adaptively refined to generate a multi-resolution grid; a fine grid is used in areas where the spatial gradient of the environmental parameters is large and exceeds a preset threshold.

[0089] A heterogeneous heat conduction equation is constructed for the temperature field, and the position-related heat conduction coefficient is set based on the regional physical parameters to obtain the temperature field model. A convection-diffusion equation considering air flow is constructed for the humidity field to obtain the humidity field model. A model combining radiation transfer and ray tracing is constructed for the illumination field to obtain the illumination field model. The temperature field model, humidity field model and illumination field model are integrated to construct an environmental field physical model set.

[0090] Construct an observation operator to associate the state variables of the environmental field physical model set with the smoothed environmental data; initialize the model state variables and use the physical model for forward calculation to obtain the initial prediction field; calculate the difference between the initial prediction field and the smoothed environmental data to generate the observation residual; apply the ensemble Kalman filter algorithm and update the model state in combination with the observation residual to obtain the posterior environmental field.

[0091] Based on material parameter data and the posterior environmental field, the theoretical structural response is calculated to obtain the theoretical response; the displacement difference between the theoretical response and the actual measurement is compared to generate a response residual; based on the response residual, the environmental field parameters are adjusted, and the posterior environmental field is updated using a feedback optimization algorithm; global consistency constraints are applied to ensure that the updated posterior environmental field conforms to physical laws to obtain the final environmental field.

[0092] According to one aspect of the present application, the step of obtaining an environmental field physical model set includes:

[0093] Based on the material parameter data, the position-dependent heat conductivity field and heat source function are used to establish the heterogeneous heat conduction equation and obtain the temperature field model.

[0094] Based on the material parameter data and pre-stored spatial geometric characteristics, the humidity convection-diffusion equation is established through the humidity diffusion coefficient field and the air flow field to obtain the humidity field model;

[0095] Based on the optical characteristic parameters in the material parameter data, the radiation transfer equation is constructed through the bidirectional reflectance distribution function to obtain the illumination field model;

[0096] Based on multi-resolution grids, design spatial and temporal discretization formats suitable for the characteristics of each physical process and build a numerical solution framework;

[0097] Analyze the coupling relationship between physical fields, construct coupling solution strategies and calculation scheduling algorithms, integrate temperature field, humidity field and light field models, and obtain the environmental field physical model set.

[0098] Specifically, the material annotation point cloud and material parameter data are read, the heat conduction related parameters of different materials are extracted, and the heat conduction parameter mapping is constructed; based on the material distribution in the regional physical parameters, the position-dependent heat conduction coefficient field is constructed to obtain the heat conduction coefficient field κ t :κ t (x) = H_κ(material(x)), where material(x) is the material type at position x and H_κ is the heat conduction parameter mapping; design the heat source function s(x,t), considering external heat sources (such as sunlight radiation) and internal heat sources (such as equipment heat generation), and obtain the heat source function S t ; Construct a complete heterogeneous heat conduction equation, define the temperature field evolution law, and form a temperature field model T_m: ΨT / Ψt - ▽·(κ t (x)▽T) = S t (x,t) in Ω; T = g t (x,t) on ΨΩ D κ t (x)ΨT / Ψn = h t (x,t) on ΨΩN , where g t and h t are the Dirichlet and Neumann boundary condition functions, Ω is the computational domain model, Ψ is the partial derivative symbol, T is the temperature field variable, ▽ is the gradient operator, and S t (x, t) is the heat source function, which represents the external or internal heat source at position x and time t; ΨΩ D is the Dirichlet boundary region, n is the unit normal vector, ΨΩ N is the Neumann boundary region.

[0099] Based on the material parameter data M, the humidity diffusion coefficient and moisture absorption performance parameters of different materials are extracted to construct a humidity diffusion parameter mapping. Based on the spatial geometric characteristics and material distribution, a position-dependent humidity diffusion coefficient field is constructed to obtain a humidity diffusion coefficient field. Based on the building opening position and ambient wind speed data, an air flow field is constructed to obtain a wind field model. The humidity source function is designed, taking into account humidity sources such as humidification equipment and human breathing to obtain a humidity source function. A complete humidity convection-diffusion equation is constructed to form a humidity field model: ΨH / Ψt + V t ·▽H - ▽·(D t (x)▽H) = S H (x,t) in Ω; H =g H (x,t) on ΨΩ D ;D t (x)ΨH / Ψn = h H (x,t) on ΨΩ N , where g H and h H is the boundary condition function of the humidity field, D t is the humidity diffusion coefficient field, V t is the wind field model; S H (x, t) is the humidity source function, and H is the humidity field variable.

[0100] Based on the material parameter data M, the optical characteristic parameters of different materials, such as reflectivity and absorptivity, are extracted to construct an optical parameter mapping, determine the position and characteristics of the light source, including natural light sources (sun) and artificial light sources, and build a light source model; define a bidirectional reflectance distribution function (BRDF) for each surface material to describe the interaction between light and the surface, and obtain a BRDF set; construct a physics-based radiation transfer equation to simulate the propagation of light in the environment and form a light field model: L(x,ω) = L e (x,ω) + ∫ Ω f r (x,ω',ω)L i(x,ω')(n·ω')dω', where L represents the radiance, L e is the self-luminous term, f r is the BRDF, ω and ω' are the outgoing and incident directions respectively, and n is the surface normal vector.

[0101] Based on multi-resolution grids, the physical model is spatially discretized to construct a spatial discrete operator. A time discrete format suitable for the characteristics of each physical process is designed, such as the implicit Euler, Crank-Nicolson, or WENO format, to obtain a time discrete operator. For nonlinear terms, a suitable linearization strategy or iterative solution scheme is designed to obtain a nonlinear processing operator. The spatial discrete operator, time discrete operator, and nonlinear processing operator are integrated to construct a complete numerical solution framework.

[0102] Analyze the coupling relationship between physical fields, such as how temperature affects humidity diffusion and how light affects temperature distribution, and construct a physical field coupling matrix. Design numerical processing strategies for coupling terms, such as explicit / implicit coupling, separate solution, or overall solution, to obtain a coupling solution strategy. Design a scheduling algorithm for multi-physical field calculations, determine the order and iteration method of calculations for different physical fields, and obtain a calculation scheduling algorithm. Integrate the temperature field model, humidity field model, and light field model, consider the physical field coupling matrix, and construct a complete set of environmental field physical models.

[0103] According to one aspect of the present application, the step of obtaining the posterior environmental field includes:

[0104] Determine the location of environmental sensors in a multi-resolution grid, design an observation operator for each environmental parameter, and obtain a unified observation operator through an observation error model;

[0105] The unified observation operator is combined with the environmental sensor data to construct the initial state vector, which is then forward-time-integrated through the environmental field physical model set to obtain the model prediction state and observation residual.

[0106] Based on the model prediction state, a predetermined set of members is generated to represent different possible states, and the prior mean and covariance matrix are calculated to construct the state-observation cross covariance matrix;

[0107] Combine the state-observation cross-covariance matrix and the observation residual to calculate the Kalman gain, update the model prediction state and set members, and obtain the posterior set;

[0108] The global state vector of the posterior set is decomposed into local region state vectors, and the ensemble Kalman filter algorithm is applied independently to each local region. The posterior environmental field is obtained by fusing the overlapping region information.

[0109] Specifically, for each environmental sensor, its position in the multi-resolution grid is determined, and a spatial mapping between the sensor and the grid nodes is established to obtain the sensor position mapping; a corresponding observation operator is designed for each environmental parameter (temperature, humidity, and light), and the model state variables are mapped to physical quantities measurable by the sensor to obtain the parameter observation operator; based on the sensor characteristics (such as response time and measurement error), an observation error model is constructed to obtain the observation error distribution; the parameter observation operators are integrated to construct a complete observation system equation to form a unified observation operator H, y = H(x) + ε; where y is the sensor observation value vector, x is the model state vector, and ε is the observation error vector, which obeys the observation error distribution.

[0110] Based on the smoothed environmental data and sensor position mapping, an initial estimate of the environmental field is constructed to obtain the initial state vector; the physical equations in the environmental field physical model set are applied, and the forward time integration is performed using the numerical solution framework to obtain the model prediction state; the model prediction state is mapped to the observation space using a unified observation operator to obtain the model prediction observation y f :y f =H(x f ), where H is the unified observation operator, x f is the model prediction state; compare the model prediction observation with the actual smoothed environmental data, calculate the observation residual, and generate the observation residual O t :O t = E t s -y f , where E t s This is the actual smoothing environment data.

[0111] Based on the model prediction state, N set members are generated to represent different possible states, forming the state set X f :X f = {x f 1, x f 2, ..., x f N Perturb the observation error distribution to generate N groups of observation samples and obtain an observation set; calculate the mean and covariance matrix of the state set to obtain the prior mean and prior covariance; apply the unified observation operator H to the state set to obtain the predicted observation set and calculate the state-observation cross covariance matrix.

[0112] Based on the prior covariance, cross covariance and observation error distribution, calculate the Kalman gain matrix K: K = P xy ·(H·P f ·H T + R) -1 , where P fis the prior covariance, P xy is the cross covariance, R is the observation error covariance matrix; using the observation residual and Kalman gain K, the model state is updated to obtain the posterior state x a :x a = x f + K·(E t s -y f ); Update each set member to generate the posterior set X a :x a i = x f i + K·(E t s + ε i - H(x f i )), where ε i is the perturbation observation error; calculate the mean and covariance of the posterior set to obtain the posterior mean and posterior covariance.

[0113] Decompose the global state vector into local region state vectors and construct the local state set {x l 1, x l 2, ..., x l _M}; for each local area, determine the observation data within its influence range and establish a local observation mapping; independently apply the ensemble Kalman filter algorithm to each local area to obtain the local posterior state set {x a,l 1, x a,l 2, ..., x a,l _M}; Using overlapping area information fusion technology, local posterior states are combined into a global posterior state to generate an integrated posterior environment field.

[0114] According to one aspect of the present application, the step of obtaining a training model includes:

[0115] S41. Based on the environmental field physical model set, construct the physically constrained neural ordinary differential equation in the form of dx / dt =f θ (x,t) + g(x,t), we get the mixed model; where f θ is the parameterized part of the neural network, and g is the physical residual term;

[0116] S42. Construct environmental field reconstruction, structural response prediction and physical consistency loss functions to form a multi-task loss function;

[0117] S43, converting the hybrid model into a Bayesian model, calculating the posterior distribution of the parameters (e.g., by using a variational inference method), generating environmental field samples based on the final environmental field, and constructing a displacement distribution;

[0118] S44. Based on the displacement distribution, a multi-scale model from the material microscopic to the structural macroscopic is constructed, and a cross-scale fusion model is obtained through scale bridging;

[0119] S45. Integrate the hybrid model, Bayesian model and cross-scale fusion model, optimize the parameters through the multi-task loss function, and obtain the training model.

[0120] Specifically, based on the set of physical models of the environmental field, a model architecture with physical constraints is designed to obtain a physical framework; the physical framework is embedded in the neural network architecture, and a neural ordinary differential equation with physical constraints is constructed to generate a hybrid model; a set of feature extraction functions based on physical principles is designed to generate a physical feature extractor; the physical feature extractor is applied to process the final environmental field to extract features with clear physical meanings to obtain physical features.

[0121] An environmental field reconstruction loss function is designed to measure the difference between the predicted environmental field and the measured environmental data to obtain the environmental reconstruction loss. A structural response prediction loss function is designed to evaluate the difference between the predicted displacement and the measured displacement to obtain the response prediction loss. A physical consistency loss function is constructed to ensure that the model prediction conforms to physical laws to obtain the physical consistency loss. A multi-task loss function is constructed by combining the environmental reconstruction loss, response prediction loss, and physical consistency loss. Based on the hybrid model, a Bayesian neural network is constructed to model the distribution of model parameters to obtain a Bayesian model. A variational inference method is used to approximate the posterior distribution of the parameters to obtain the parameter distribution. Based on the parameter distribution and the final environmental field, multiple environmental field samples are generated to obtain the environmental field distribution. The uncertainty of the environmental field is propagated to the structural response, and the uncertainty of the structural displacement is calculated to obtain the displacement distribution.

[0122] Construct a multiscale physical model, from the microscopic response of materials to the macroscopic behavior of structures, to obtain a multiscale model set. Design a scale bridging method to enable information transfer between models of different scales, to obtain a scale bridging operator. Develop a scale adaptive selection algorithm to select the appropriate model scale based on computational needs and accuracy requirements, to obtain a scale selection strategy. Integrate the multiscale model set, scale bridging operator, and scale selection strategy to construct a cross-scale fusion model. Combine hybrid models, Bayesian models, and cross-scale fusion models to construct a comprehensive model for predicting environmental-structural responses, to obtain a comprehensive prediction model. Use historical data to train the comprehensive prediction model and optimize model parameters to obtain a training model. Design a model self-assessment mechanism to continuously monitor model performance, to obtain a performance evaluation function. Build an anomaly detection and response system to handle extreme environmental conditions, to obtain an anomaly handling strategy.

[0123] According to one aspect of the present application, the step of constructing a displacement distribution includes:

[0124] The deterministic network parameters of the hybrid model are converted into random variables, and appropriate prior distributions are constructed for different types of parameters to obtain a Bayesian model.

[0125] Construct the evidence lower bound objective function, and obtain the ELBO function and SGVI optimizer through stochastic gradient variational inference and reparameterization;

[0126] Use the SGVI optimizer to maximize the ELBO function, obtain the optimized variational parameters, construct the parameter distribution and extract the parameter sample set;

[0127] For each set of parameter samples, a hybrid model is used to perform forward prediction, generate an environmental field sample set, calculate statistical moments, and construct the environmental field distribution;

[0128] Based on the environmental field sample set, the corresponding structural response is calculated, the displacement sample set and its probability distribution are constructed, and the displacement distribution is obtained.

[0129] Specifically, based on the hybrid model, the deterministic network parameters are converted into random variables, and the parameter prior distribution is constructed to obtain the parameter prior; suitable prior distributions are designed for different types of parameters, such as Gaussian priors for weights and inverse gamma priors for variance parameters, to construct a hierarchical prior structure; the posterior distribution form of the parameters is designed, such as the mean field Gaussian distribution family, to construct a posterior distribution family; the hybrid model, parameter prior and posterior distribution family are integrated to construct a complete Bayesian model.

[0130] Construct the Evidence Lower Bound (ELBO) objective function as an approximation of the KL divergence between the posterior distribution and the true posterior, and obtain the ELBO function L eLBO :L eLBO = E_q[log P(D|θ)] - KL[q(θ)||p(θ)], where q(θ) is the approximate posterior, p(θ) is the prior, P(D|θ) is the likelihood function, and E_q represents the expectation function; a stochastic gradient variational inference (SGVI) algorithm is designed, the ELBO is optimized to obtain the best approximate posterior, and an SGVI optimizer is constructed; the reparameterization technique is implemented to reduce the variance of the gradient estimate and improve the optimization stability, resulting in a reparameterization module; an inference convergence criterion is designed to determine when to stop the variational inference iteration, and a convergence detector is constructed.

[0131] Use the SGVI optimizer to maximize the ELBO function to obtain the optimized variational parameters and construct the optimized variational parameters; construct an approximate posterior distribution based on the optimized variational parameters to obtain the parameter distribution; extract multiple groups of parameter samples from the parameter distribution to form a parameter set and obtain a parameter sample set; analyze the statistical characteristics of the parameter sample set, such as mean, variance, distribution shape, etc., and generate a parameter statistical report.

[0132] For each set of parameter samples in the parameter statistical report, a hybrid model is used for forward prediction to generate environmental field samples and obtain an environmental field sample set; the statistical moments of the environmental field sample set, such as the mean field, variance field, etc., are calculated to construct the environmental field distribution; a visualization method is designed to display the uncertainty distribution of the environmental field, such as uncertainty heat maps, confidence intervals, etc., to obtain an uncertainty visualization tool; based on the predicted uncertainty of the environmental field, high uncertainty areas and locations that require additional attention or sampling are identified to generate uncertainty hotspot maps.

[0133] Based on the environmental field sample set, the corresponding structural response is calculated to generate a displacement sample set; the statistical characteristics of the displacement sample set are calculated, the probability distribution of the displacement is constructed, and the displacement distribution is obtained; the spatial distribution of displacement uncertainty is analyzed, the structural areas with high uncertainty are identified, and a displacement uncertainty map is generated; the probability distribution of the change detection results is calculated, the reliability of the detection results is evaluated, and a detection reliability assessment is obtained.

[0134] According to one aspect of the present application, the step of obtaining a change detection result includes:

[0135] S51. Input the final environment field into the training model, predict the displacement field caused by the environment, extract the displacement vector corresponding to each point cloud point, and obtain the environment displacement field and point cloud environment displacement;

[0136] S52, calculating the measured displacement field between the registration point cloud data and the reference point cloud, subtracting the point cloud environment displacement therefrom, and obtaining the compensated displacement field and compensation uncertainty;

[0137] S53, calculating a basic threshold for each region based on regional response statistics and compensation uncertainty, building an adaptive threshold calculation model in combination with measurement uncertainty, and obtaining an adaptive threshold;

[0138] S54, applying an adaptive threshold to screen the compensated displacement field, calculating the change confidence by constraining spatial continuity and temporal consistency, and obtaining a change detection result;

[0139] S55. Record the corresponding relationship between the detection threshold and the result, establish a threshold history database, optimize the threshold adjustment strategy through reinforcement learning, and obtain an optimized threshold system.

[0140] Specifically, the current final environmental field is input into the training model to predict the structural displacement field caused by the environment and obtain the environmental displacement field; the uncertainty of the predicted displacement is calculated in combination with the displacement distribution to obtain the displacement uncertainty; the expected displacement vector corresponding to each point cloud point is extracted from the environmental displacement field to obtain the point cloud environmental displacement; the environmental response statistical characteristics of different material areas are calculated to generate regional response statistics.

[0141] The current registration point cloud and the registration point cloud at the reference time point are read, the actual displacement field is calculated, and the measured displacement field is obtained; the point cloud environmental displacement is subtracted from the measured displacement field to obtain the compensated displacement field; based on the displacement uncertainty, the uncertainty propagation of the compensation process is calculated to obtain the compensated uncertainty; the compensated displacement field is applied to the registration point cloud to generate a point cloud after environmental impact compensation, and thus obtain the compensated point cloud.

[0142] Based on regional response statistics and compensation uncertainty, a basic threshold is calculated for each optimized partition to obtain the basic threshold; considering factors such as point cloud acquisition accuracy and registration error, the measurement uncertainty is calculated to obtain the measurement uncertainty; combining the basic threshold and measurement uncertainty, an adaptive threshold calculation model is constructed to obtain the regional threshold model; according to the historical change detection performance, the threshold coefficient is dynamically adjusted to generate the final adaptive threshold.

[0143] An adaptive threshold is applied to the compensated displacement field to obtain the initial screening changes. The initial screening changes are further screened using spatial continuity and temporal consistency constraints to obtain the screening changes. The confidence of each detected change is calculated, and the change confidence is generated based on the compensation uncertainty and detection indicators. The screening changes and change confidence are combined to generate the final change detection results.

[0144] Record the change detection results and the corresponding adaptive thresholds, establish a historical threshold database, and obtain the threshold history; based on the threshold history and actual detection results, use the reinforcement learning method to optimize the threshold adjustment strategy and obtain the threshold learning model; for areas with poor detection performance, analyze the failure causes and adjust the corresponding threshold calculation parameters to obtain the parameter adjustment strategy; integrate the threshold learning model and parameter adjustment strategy into the threshold calculation process to obtain an optimized threshold system.

[0145] According to one aspect of the present application, the step of obtaining an optimized threshold system includes:

[0146] Record adaptive thresholds and corresponding change detection results, calculate detection performance indicators, and build a threshold history database;

[0147] Threshold adjustment is modeled as a reinforcement learning task, with the state defined as the current threshold and historical performance, the action as the direction and magnitude of the threshold adjustment, and the reward as the degree of improvement in detection performance. A threshold learning model is constructed.

[0148] Analyze the spatial distribution of change detection results, identify areas with poor detection performance, study their characteristics, and obtain defect factor analysis;

[0149] Based on defect factor analysis, parameter adjustment rules are designed, automatic adjustment modules and expert intervention interfaces are implemented, and parameter adjustment strategies are constructed;

[0150] By integrating the threshold learning model and parameter adjustment strategy, a unified threshold optimization framework and status monitoring mechanism are constructed to obtain an optimized threshold system.

[0151] Specifically, the adaptive threshold used for each change detection and its corresponding detection result change detection result are recorded; the performance indicators of each detection, such as precision, recall rate, F1 score, etc., are calculated to build a performance record; the detection threshold, detection results and performance indicators are associated to establish a complete historical data item and obtain a historical item set; the historical items are stored by time index to build a complete threshold history.

[0152] The threshold adjustment problem is modeled as a reinforcement learning task, defining the state, action, and reward functions to construct an RL problem definition: State: current threshold and historical performance; Action: direction and magnitude of threshold adjustment; Reward: degree of improvement in detection performance. Design RL algorithms suitable for threshold optimization, such as Q-learning and policy gradient, and build an RL algorithm implementation. Train the RL model based on the threshold history to learn the optimal threshold adjustment policy, resulting in a threshold policy model. Implement an online learning mechanism to enable the model to continuously learn and optimize from new detection results, and construct an online learning module. Integrate the RL problem definition, RL algorithm implementation, threshold policy model, and online learning module to construct a complete threshold learning model.

[0153] Analyze the spatial distribution of change detection results, identify areas with poor detection performance, and construct a performance defect map; study the characteristics of performance defect areas, such as material properties, environmental conditions, etc., identify influencing factors, and obtain a defect factor analysis; design corresponding improvement strategies for different types of performance defects and construct an improvement strategy map; develop an automated performance evaluation tool to regularly evaluate detection performance and identify problem areas to obtain an automatic evaluation tool.

[0154] Based on defect factor analysis and improved strategy mapping, customized parameter adjustment strategies were designed for different regions, resulting in parameter adjustment rules. An automated parameter adjustment mechanism was implemented to automatically update threshold parameters based on detection feedback, building an automatic adjustment module. A manual intervention interface was designed to allow experts to manually adjust threshold parameters based on their experience, resulting in an expert intervention interface. An audit tracking system for parameter adjustment was established to record all parameter changes and their effects, building an adjustment audit system. The parameter adjustment rules, automatic adjustment module, expert intervention interface, and adjustment audit system were integrated to construct a complete parameter adjustment strategy. The threshold learning model and parameter adjustment strategy were integrated to build a unified threshold optimization framework, resulting in an optimization framework.

[0155] In a specific embodiment of the present application, 3D point cloud data containing 5,000 points was collected in a historical building monitoring scenario. The building is composed of three different materials: masonry (area 1), wood (area 2), and metal components (area 3). Environmental monitoring includes three parameters: temperature, humidity, and light. Data was collected once a day for the past 30 days. The steps of the method for compensating for time series differences in 3D monitoring data and adaptively adjusting dynamic thresholds are as follows:

[0156] Step 1: Region-adaptive partitioning PCA environment feature extraction.

[0157] 1.1. Initial division of structural response area.

[0158] First, the initial division is performed based on the material parameter data: Material parameter data M: masonry structure: thermal expansion coefficient α = 8×10 -6 / °C, elastic modulus E = 10 GPa; wooden structure: thermal expansion coefficient α = 5×10 -6 / °C(radial), 50×10 -6 / °C (tangential), elastic modulus E = 12 GPa; metal components: thermal expansion coefficient α = 23×10 -6 / °C, elastic modulus E = 200 GPa. Three initial partitions are formed based on material properties, each containing 2500 points in the point cloud: Region 1 (masonry): 1800 points; Region 3 (metal): 700 points.

[0159] 1.2. Response similarity evaluation and optimized partitioning.

[0160] Method for constructing environment-response mapping table: mapping relationship between environmental factor changes and displacement t = [ΔT t , ΔH t , ΔL t ]; displacement vector D t = [Δx t , Δy t , Δz t ]; where ΔT t is the temperature change (°C); ΔH t is the humidity change (%); ΔL t is the illumination change (lux); Δx t , Δy t , Δz twhere t is the displacement in the x, y, and z directions (mm), respectively; t is the time index. The sensitivity coefficient for a point in region 1 is calculated using the data from the last five days (t = 1 to 5): Environmental change data: Date 1: ΔT = 5.2°C, ΔH = 12%, ΔL = 1500 lux; Date 2: ΔT = -3.1°C, ΔH = 5%, ΔL = -800 lux; Date 3: ΔT = 1.8°C, ΔH = -7%, ΔL = 500 lux; Date 4: ΔT = 0.5°C, ΔH = 3%, ΔL = 1200 lux; Date 5: ΔT = -2.3°C, ΔH = -8%, ΔL = -1300 lux. Corresponding displacement data: Date 1: Δx = 0.12mm, Δy = 0.08mm, Δz = 0.15mm; Date 2: Δx = -0.07mm, Δy = -0.05mm, Δz = -0.09mm; Date 3: Δx = 0.04mm, Δy = -0.02mm, Δz = 0.05mm; Date 4: Δx = 0.01mm, Δy = 0.03mm, Δz = 0.03mm; Date 5: Δx = -0.06mm, Δy = -0.07mm, Δz =-0.08mm.

[0161] Multivariate regression analysis method: Δd = β t ·ΔT + β H ·ΔH + β_L·ΔL + ε; where Δd is the displacement component (mm); β t , β H , β_L is the environmental factor sensitivity coefficient; ΔT is the temperature change (°C); ΔH is the humidity change (%); ΔL is the light change (lux); ε is the residual term. Through multivariate regression analysis, the sensitivity coefficient matrix S of this point is obtained: S = [β t x, β H x, β_Lx;β t y, β H y, β_Ly;β t z, β H z, β_Lz]= [0.0223, 0.0031, 0.00005; 0.0157, 0.0042, 0.00002; 0.0278, 0.0026, 0.00004].

[0162] Point-to-point response pattern similarity calculation method: point-to-point similarity PS z (i,j) = exp(-||S z (i)-Sz (j)|| 2 / σ 2 ); where S z (i) S z (j) is the sensitivity coefficient matrix of point i and point j; ||·|| is the matrix Frobenius norm; σ is the scale parameter, which is 0.05; i and j are the point indices in the point cloud. Calculate the response similarity of two adjacent points (i=15, j=16) in region 1: S(15) = [0.0223, 0.0031, 0.00005;0.0157, 0.0042, 0.00002;0.0278,0.0026, 0.00004]; S(16) = [0.0235, 0.0029, 0.00006;0.0149, 0.0045, 0.00002;0.0283, 0.0024, 0.00005]; ||S(15)-S(16)|| 2 = 0.0000267;PS z (15,16) = exp(-0.0000267 / 0.05 2 ) = 0.9989, indicating that the environmental response patterns of these two points are very similar.

[0163] Construct the response correlation matrix R z , R z =PS z (i,j)× W(d), where W(d) is the spatial distance weighting function; W(d) = exp(-d 2 / 0.1 2 ) is the spatial distance weighting function, d is the distance between two points; the Laplace matrix is calculated for the response correlation matrix: the diagonal matrix element D z (i,i) = Σj R z (i,j); Laplace matrix L z norm (i,j) = -R z (i,j) / sqrt(D z (i,i)×D z (j,j)); calculate L z normThe eigenvalues of the eigenvalues were calculated, and the first three eigenvectors were used to construct a spectral embedding. K-means (k=2) clustering was then applied to obtain sub-regions. Spectral clustering analysis of Region 1 revealed differences in point response patterns within the region, leading to further subdivision into two sub-regions: Region 1A (south-facing masonry): 1400 points; Region 1B (north-facing masonry): 1100 points. The final optimized sub-regions were: Region 1A (south-facing masonry): 1400 points; Region 1B (north-facing masonry): 1100 points; Region 2 (wooden structure): 1800 points; and Region 3 (metal structure): 700 points.

[0164] 1.3. Time series weighted PCA feature extraction.

[0165] Time decay weight function calculation method: W t (τ) = exp(-λ·(t-τ)); where t is the current time point; τ is a historical time point; λ is the time decay factor, which is 0.2; and exp is the base of the natural logarithm. Using the data from the past 10 days (τ = t-10 to t-1), setting the time decay factor λ = 0.2, calculate the weight of each historical time point: W t (t-1) = exp(-0.2×1)= 0.8187; W t (t-2) = exp(-0.2×2) = 0.6703;...;W t (t-10) = exp(-0.2×10) = 0.1353. Normalized weight: sum = 0.8187 + 0.6703 + ... + 0.1353 = 4.311; W t norm (t-1) =0.8187 / 4.311 = 0.1899; W t norm (t-2) = 0.6703 / 4.311 = 0.1555;...;W t norm (t-10) =0.1353 / 4.311 = 0.0314.

[0166] Weighted covariance matrix construction method: C z w = ∑ τ W t norm (τ)·(X τ -μ w ) T ·(X τ -μ w ); where X τ is the environment-displacement joint matrix at time point τ; μ wis the weighted mean vector; W t norm (τ) is the normalized time weight; τ is the historical time point. Construct the joint environment-displacement matrix J for region 1A, where each row represents a time point and the columns include temperature, humidity, light, and displacement in the x, y, and z directions: J = [T, H, L, Δx, Δy, Δz]. An example of data at a certain time point is: J(t-1) = [25.3, 65, 5200, 0.12, 0.08, 0.15]. Calculate the weighted mean vector μ w :μ w = ∑ τ W t norm (τ)·J(τ)=0.1899×[25.3, 65, 5200, 0.12, 0.08, 0.15] + ... = [23.7, 63.2, 4850, 0.08,0.06, 0.11]; calculate the centering matrix J c :J c (t-1) = J(t-1) - μ w = [1.6, 1.8, 350, 0.04, 0.02, 0.04]; Construct the weighted covariance matrix C z w , the example only gives part of the calculation: C z w (1,1) = 0.1899×1.6 2 +0.1555×(-1.2) 2 + ... = 3.24; C z w (1,4) = 0.1899×1.6×0.04 + 0.1555×(-1.2)×(-0.03) + ... = 0.062; .... Through eigenvalue decomposition, the sorted eigenvalues and corresponding eigenvectors are obtained: eigenvalues: λ= [15.6, 8.2, 3.5, 0.9, 0.4, 0.1]; cumulative contribution rate: [54.2%, 82.8%, 95.0%, 98.1%, 99.5%, 100%]; the first three principal components are selected, and the contribution rate reaches 95%, and the principal component matrix is constructed: P = [e1, e2, e3]=[0.15, 0.42, 0.31;0.22, 0.38, -0.53;0.82, -0.29, 0.06;0.31, 0.45, 0.52;0.28,0.51, -0.33;0.29, 0.38, 0.48].

[0167] 1.4. Robust environmental feature extraction.

[0168] Huber loss function method: ρ Huber (x) = {x 2 / 2, |x| ≤ c; c·|x| - c 2 / 2, |x| > c}; the weight function w(x) = {1, |x| ≤ c; c / |x|, |x| > c}; where x is the residual; c is the threshold parameter, set to 1.345; and |x| is the absolute value. The Huber loss function is applied to identify and reduce the influence of outliers. The Mahalanobis distance is calculated for the joint environment-displacement matrix, and a weighting function is applied: the Mahalanobis distance of a data point is d = 2.6; since d > 1.345, the weight w = 1.345 / 2.6 = 0.517. Five outliers are identified in region 1A, and after weight correction, a robust data matrix is obtained. The robust coefficient matrix is projected through the PCA model. Analysis of the physical meaning of the principal components: the first principal component (54.2%) primarily captures illumination changes and the resulting displacement; the second principal component (28.6%) primarily reflects temperature changes and the resulting displacement; and the third principal component (12.2%) primarily reflects the influence of humidity changes. Environmental characteristic vector (region 1A): v env = [0.82, 0.31, 0.28, 0.29], indicating that light has the greatest impact on this area, followed by temperature.

[0169] Step 2: Reconstruction of the environmental field enhanced by physical information.

[0170] Using physical information-enhanced environmental field reconstruction technology, the environmental field distribution of the entire monitoring area is accurately reconstructed from limited environmental sensor data. Five environmental sensors are deployed in the monitoring area to measure temperature, humidity, and light. The sensor locations are as follows: Sensor 1: South exterior of the building (25.4°C, 58%, 6200 lux); Sensor 2: North exterior of the building (22.1°C, 62%, 1800 lux); Sensor 3: Center of the room (23.8°C, 55%, 850 lux); Sensor 4: East interior (24.2°C, 54%, 1200 lux); Sensor 5: West interior (23.5°C, 56%, 750 lux).

[0171] 2.1. Construction of three-dimensional computational domain geometric model.

[0172] The computational domain geometry model is constructed based on the point cloud data. The building dimensions are 20m×15m×8m, and the wall thickness is approximately 0.5m. Boundary conditions are set: South wall outer surface: T = ambient temperature (sensor 1), convection heat dissipation coefficient h = 25 W / (m2 ·K); North wall outer surface: T = ambient temperature (sensor 2), convection heat dissipation coefficient h = 20 W / (m 2 ·K); Internal space: Initial temperature is set to 23.5°C.

[0173] 2.2. Multi-resolution mesh generation.

[0174] The grid refinement index is calculated as: CI(x) = α·|▽T(x)| + β·|▽H(x)| + γ·|▽L(x)|; where CI(x) is the refinement index at position x; ▽T(x), ▽H(x), and ▽L(x) are the gradients of temperature, humidity, and light, respectively; α, β, and γ are weight coefficients, taking values of 1.0, 0.6, and 0.8, respectively; and |·| is the gradient norm. To calculate the gradient of environmental parameters, using temperature as an example: the initial uniform grid point spacing is 0.5m; the temperature gradient between the north and south walls is: |▽T| = |25.4-22.1| / 20 = 0.165°C / m; the temperature gradient in the window area is: |▽T| = |25.4-23.8| / 0.5 = 3.2°C / m. Based on the gradient calculation, refine the index: window area: CI = 1.0×3.2 + 0.6×8 + 0.8×670 = 540.4; wall area: CI = 1.0×0.62 + 0.6×1.5 + 0.8×5 = 5.42. Set the threshold CI t hreshold = 10. A finer mesh is used in areas with large environmental gradients, such as windows and doors: normal areas: mesh size 0.5m; high-gradient areas: mesh size 0.1m. The resulting multi-resolution mesh contains approximately 85,000 nodes.

[0175] 2.3. Construction of heterogeneous physical model.

[0176] Heterogeneous heat conduction equation: ΨT / Ψt = ▽·(κ t (x)▽T) + S t (x,t); where: T is the temperature field (°C); t is the time (s); κ t (x) is the thermal conductivity at position x (W / (m·K)); S t (x,t) is the heat source function (W / m 3 ); ▽ is the gradient operator; Ψ represents the partial derivative. Set the thermal conductivity coefficient for different material areas: masonry structure: κ = 0.6-1.0 W / (m·K); wooden structure: κ = 0.12-0.04 W / (m·K); metal structure: κ = 45-55 W / (m·K). Light heat source function (south window area): S t(x,t) = η·I(x,t)·(1-ρ(x)), where η is the photothermal conversion efficiency (0.3), I is the incident light intensity (W / m 2 ), ρ is the reflectivity (0.2).

[0177] Humidity convection-diffusion equation: ΨH / Ψt + V t ·▽H = ▽·(D t (x)▽H) + S H (x, t); where H is the humidity field (%); t is time (s); V t is the wind field (m / s); D t (x) is the humidity diffusion coefficient (m 2 / s); S H (x, t) is the humidity source function (% / s); ▽ is the gradient operator; Ψ represents the partial derivative. The humidity diffusion coefficient is related to the material and temperature: For porous materials: D t (x) = D_0·exp(b·T(x)), where D_0 is the reference diffusion coefficient (2.5×10 -6 m 2 / s), b is the temperature coefficient (0.025 / °C).

[0178] Radiative transfer equation: L(x,ω) = L e (x,ω) + ∫ Ω f r (x,ω',ω)L i (x,ω')(n·ω')dω'; where L is the radiance (W / (m 2 ·sr));L e is the self-luminous item; f r is the bidirectional reflectance distribution function; ω and ω' are the outgoing and incident directions respectively; n is the surface normal vector; Ω is the hemispherical space; sr is the solid angle unit. The south window uses an anisotropic BRDF model: f r (ω i ,ω_o) = k D / π + (n+2) / (2π)·k_s·(ω r ·ω_o) n , where k D is the diffuse reflection coefficient (0.3), k_s is the specular reflection coefficient (0.7), and n is the glossiness parameter (10).

[0179] 2.4. Environmental field data assimilation.

[0180] Ensemble Kalman filter update equation: x a = x f + K·(y - H(x f)); K = P xy ·(H·P f ·H T +R) -1 ; where: x a is the posterior state vector; x f is the prior state vector; K is the Kalman gain matrix; y is the observation vector; H is the observation operator; P xy is the state-observation cross covariance matrix; P f is the prior error covariance matrix; R is the observation error covariance matrix. Initialize the state vector x based on the physical model f , containing the temperature, humidity and light values of all grid points: x f = [T1,T2, ..., T N , H1, H2, ..., H N , L1, L2, ..., L N ] T The observation vector y contains the measurements of 5 sensors: y = [25.4, 22.1, 23.8, 24.2, 23.5, 58, 62, 55, 54, 56, 6200, 1800, 850, 1200,750] T , generate 50 set members, perturb the initial state to build the prior set: x f i = x f + ε i , i=1,2,...,50; where ε i The perturbations are random, with a standard deviation of 0.5°C for temperature, 2% for humidity, and 100 lux for illumination. After calculating the prior ensemble mean and covariance matrix, the ensemble Kalman filter is applied to update the posterior state: observation error: temperature ±0.3°C, humidity ±2%, illumination ±50 lux; Kalman gain matrix K: dimension (3N × 15); the posterior state x a : Dimension (3N×1). Decompose the global state into 5 sub-regions and apply filters independently. Fusion is performed on the overlapping regions to finally obtain the complete posterior environment field.

[0181] 2.5. Environmental field feedback optimization.

[0182] Environmental field parameter adjustment method: α N ew = α old ·(1 + η·e r ); where α N ew, α old are the model parameters before and after the update; η is the learning rate (0.1); e ris the response residual, defined as (d meas -d pred ) / d meas ;d meas is the measured displacement; d pred To predict displacement. Calculate the difference between the theoretical structural response and the measured displacement: Theoretical temperature response at a point in area 1A: 0.107mm; measured displacement: 0.127mm; response residual: e r = (0.127-0.107) / 0.127 = 0.157. Adjusted thermal conductivity: Before adjustment: κ old = 0.8 W / (m·K); after adjustment: κ New = 0.8×(1+0.1×0.157) = 0.813W / (m·K). After feedback optimization and adjustment, the final environmental field can accurately reflect the temperature, humidity, and light distribution of the entire building.

[0183] Step 3: Cognitive physics-data dual-driven compensation model. By building a cognitive physics-data dual-driven compensation model, the physical model is embedded in the data-driven architecture while taking the uncertainty of the model into account.

[0184] 3.1. Construction of Neural Ordinary Differential Equations with Physical Constraints.

[0185] Physical Constraints God Ordinary Differential Equation: dx / dt = f θ (x,t) + g(x,t); where x is the state vector; t is time; f θ is a parameterized neural network; θ is a network parameter; g is a physical constraint. The physical model of the environmental field is transformed into a neural ordinary differential equation: For the temperature field: dT / dt = f θt (T,t) + ▽·(κ(x)▽T); neural network f θt A three-layer structure is adopted (4 input nodes, 16 hidden nodes, and 1 output node), and the physical constraints are discretized using the finite difference method.

[0186] 3.2. Construction of multi-task loss function.

[0187] Multi-task loss function: L_mt = α·L e + β·L r + γ·L_p; where L e Reconstruction of losses for the environment; L r is the response prediction loss; L_p is the physical consistency loss; α, β, and γ are weight coefficients, which are 0.4, 0.4, and 0.2 respectively. Environment reconstruction loss (MSE): L e = 1 / N·∑ i=1 N(E predi -E measi ) 2 ; Among them E predi is the predicted environmental variable value of the i-th sample; E measi is the true measured environmental variable value of the i-th sample, N is the number of samples used to calculate the environmental reconstruction loss; response prediction loss (MAE): L r = 1 / M·∑ j=1 M |D predj -D measj |; where D predj is the predicted response variable value of the jth sample; D measj is the true measured response variable value of the jth sample, M is the number of samples used to calculate the response prediction loss; physical consistency loss (energy conservation): L_p = |∫ Ω (ΨT / Ψt - ▽·(κ▽T) - S) 2 dΩ|; Loss value of a batch in model training: L e = 0.052; L r = 0.018; L_p = 0.031; L_mt = 0.4×0.052 + 0.4×0.018 + 0.2×0.031 = 0.034.

[0188] 3.3. Bayesian model and displacement distribution.

[0189] ELBO function: L e LBO = E_q[log P(D|θ)] - KL[q(θ)||p(θ)]; where E_q represents the expectation about q(θ); log P(D|θ) is the log likelihood; KL[q(θ)||p(θ)] is the KL divergence; q(θ) is the approximate posterior distribution; p(θ) is the parameter prior distribution. Convert the mixed model to a Bayesian neural network and set the prior distribution for the network weights: weight w ~ N(0, σ 2 ); bias b ~ N(0, 0.1). Using mean-field variational inference, approximate the posterior distribution: q(w) ~ N(μ w , σ w 2 );q(b) ~ N(μ b , σ b 2 ); Maximize the ELBO function to optimize the variational parameters. The ELBO value after 500 iterations is: L eLBO = 256.3. 100 parameter samples were drawn from the posterior distribution to predict the temperature change in region 1A: the expected displacement for a 10°C temperature rise was: mean: 0.241mm; standard deviation: 0.032mm; 95% confidence interval: [0.178mm, 0.304mm].

[0190] 3.4. Multi-scale model construction.

[0191] Establish a multi-scale model from the microscopic material to the macroscopic structure: Microscopic level (10 -6 m): Crystal thermal vibration model; mesoscopic level (10 -3 m): Material volume thermal expansion model; macroscopic level (10 0 m): Overall structural deformation model. Example of cross-scale parameter relationships: Mesoscopic-macroscopic bridging: The thermal expansion coefficient α affects the macroscopic displacement d: d = α·ΔT·L.

[0192] 3.5. Training model integration.

[0193] Integrate hybrid model, Bayesian model and cross-scale fusion model: Comprehensive prediction model: C_m = {H_m, B_m, F_ms}; Use 30 days of historical data to train the model, and the performance indicators on the validation set are: Environmental field reconstruction RMSE: temperature 0.38°C, humidity 1.7%, light 86lux; Displacement prediction MAE: 0.023mm; Displacement prediction R 2 : 0.924.

[0194] Step 4: Dynamic threshold adaptive adjustment: Dynamic threshold adaptive adjustment based on the environment-structure response model is implemented to improve the accuracy of change detection.

[0195] 4.1. Environmental displacement field prediction.

[0196] Environmental displacement prediction method: D t env (x) = C_m train (E t final (x)); where D t env (x) is the predicted environmental displacement field at position x; C_m train is the trained comprehensive model; E t final(x) is the final environmental field at position x. The current environmental field data is input to the training model: the middle point of the south wall (x0): temperature: 27.3°C; humidity: 52%; illumination: 5800 lux. Predicted displacements due to the environment: x-direction: 0.145mm; y-direction: 0.063mm; z-direction: 0.118mm; total displacement: 0.197mm; displacement uncertainty: ±0.032mm.

[0197] 4.2. Timing difference compensation.

[0198] Timing difference compensation method: D t comp (x) = D t meas (x) - D t env (x); where D t comp (x) is the displacement field after compensation; D t meas (x) is the measured displacement field; D t env (x) represents the environmental displacement field. Calculate the difference between the measured displacement and the reference point cloud: Measured displacement of the center point (x0) of the south wall: 0.183 mm in the x-direction; 0.071 mm in the y-direction; 0.157 mm in the z-direction; total displacement: 0.250 mm. Applying environmental displacement compensation: After compensation, the x-direction is 0.183 - 0.145 = 0.038 mm; the y-direction is 0.071 - 0.063 = 0.008 mm; the z-direction is 0.157 - 0.118 = 0.039 mm; total displacement after compensation: 0.055 mm; compensation uncertainty: ±0.045 mm.

[0199] 4.3. Regional adaptive threshold calculation.

[0200] Adaptive threshold function: T a (x) = T b ·(1 + γ·U t comp (x) / σ r ef); where T a (x) is the adaptive threshold at position x; T b is the basic threshold (0.05mm); γ is the adjustment coefficient (0.8); U t comp (x) is the compensation uncertainty at position x; σ refThe reference standard deviation is 0.03mm. The basic threshold value is calculated for area 1A based on historical response statistics: displacement residual standard deviation: 0.032mm; point cloud measurement error: 0.018mm; basic threshold value T b = 0.05mm. Calculate the adaptive threshold at the middle point of the south wall (x0): Compensate for the uncertainty U t comp = 0.045mm; adaptive threshold T a = 0.05×(1 + 0.8×0.045 / 0.03) = 0.06mm. Compared to the fixed threshold method: under the fixed threshold (0.1mm), 0.055mm < 0.1mm is considered unchanged; under the adaptive threshold, 0.055mm < 0.06mm is considered unchanged but close to the threshold.

[0201] 4.4. Change detection and result screening.

[0202] Change confidence calculation method: V t (x) = (D t comp (x) - T a (x)) / (2·U t comp (x)); if V t (x) > 0, then normalize to the interval [0,1]; where V t (x) is the confidence level of the change at position x; D t comp (x) is the displacement field after compensation; T a (x) is the adaptive threshold; U t comp (x) is the compensation uncertainty. A set of potential change points (exceeding the adaptive threshold) are detected on the west side of the building: position y0 displacement after compensation: 0.078mm; adaptive threshold: 0.058mm; compensation uncertainty: 0.042mm. Change confidence V t = (0.078-0.058) / (2×0.042) = 0.238; after normalization: 0.643; after applying the spatial continuity constraint, a continuous change area (10cm 2 ), contains 27 points.

[0203] 4.5. Dynamic threshold learning and optimization.

[0204] Reinforcement learning was used to optimize the threshold adjustment strategy: State: Current threshold, historical detection performance; Action: Threshold adjustment amount (-0.01mm, 0, +0.01mm); Reward: Improved detection accuracy. After 100 monitoring cycles, the threshold system reached a stable state: Region 1A: 0.058mm±0.012mm; Region 1B: 0.062mm±0.015mm; Region 2: 0.072mm±0.018mm; Region 3: 0.045mm±0.010mm.

[0205] In the test scenario, the false positive rate of the traditional fixed threshold method was 18.7%, which was reduced to 3.2% in this embodiment, and the true positive rate was increased from 85.3% to 94.8%. Through regional adaptive partitioning PCA, structural areas with different materials, orientations and stress conditions were correctly processed, so that the compensation model could achieve the best effect in each area. The displacement prediction errors of areas 1A and 1B were reduced from 0.085mm and 0.092mm to 0.021mm and 0.026mm respectively. From the limited data of only 5 environmental sensors, the environmental field distribution of the entire building was accurately reconstructed, and the RMSE of the temperature field reconstruction was 0.38°C, which was better than the 1.25°C of the interpolation method. The cognitive compensation model of this embodiment combines physical and data-driven methods, and the generalization performance of the simple data-driven method under extreme environmental conditions (temperature change >15°C) is improved by 45%. Compared with the fixed threshold method, the adaptive threshold of this embodiment improves the F1 score of change detection under variable environmental conditions by 18.3%, especially during seasonal transitions.

[0206] This invention effectively addresses the nonlinearity, multi-factor coupling, spatial heterogeneity, and sensor sparsity issues encountered in traditional environmental compensation. Its technical benefits are primarily reflected in the following aspects: By introducing nonlinear kernel function mapping and regional PCA feature extraction, the complex coupling relationships of environmental factors can be more accurately modeled, enabling accurate reconstruction of environmental parameter fields even under extreme environmental conditions and providing targeted structural response compensation. Through initial partitioning, response correlation matrix construction, spectral clustering analysis, and optimized partitioning algorithms, subregions with high response similarity are identified. Subsequently, within each subregion, time-weighted PCA and robust M-estimation are used to extract environmental features, achieving a detailed reconstruction of the local environmental field and significantly reducing the regional errors caused by the overall unified model. By combining discrete environmental sensor data with registered point cloud data and material parameter data, a three-dimensional computational domain geometric model and multi-resolution grid are constructed. Through data assimilation and physical information enhancement, the limited sensor information is expanded into an environmental parameter field for the entire structural surface. This not only addresses the problem of insufficient sensor coverage but also provides a precise basis for environmental compensation for each point cloud point. The deterministic network parameters are converted into random variables. By setting prior distributions for weights and biases and calculating the ELBO within the framework of mean-field variational inference, the posterior distribution of the parameters is optimized. Bayesian inference is used to probabilistically describe the model parameters, quantifying the uncertainty of the parameters and predictions. Furthermore, by extracting parameter samples for forward prediction, the distribution of the structural response (displacement) is constructed, providing a reliable statistical basis for subsequent dynamic threshold adaptive adjustment. A combination of three task losses—environmental reconstruction, response prediction, and physical consistency—is employed, with appropriate weight allocation to ensure full utilization of historical and sensor data while maintaining the model's internal consistency under physical constraints. The dynamic threshold adaptive adjustment mechanism allows the model to automatically calibrate the detection threshold based on the discrepancy between real-time predictions and monitored data, thereby reducing the false positive rate and improving the reliability and stability of the monitoring system. It not only completes environmental field reconstruction and displacement prediction at a single scale, but also realizes the bridging of cross-scale data by integrating multi-scale information of the material micro, local structure and the whole structure; it uses the time series weighting mechanism to capture the changing trend and timeliness in the historical data, and further improves the effect of time series difference compensation, so that the monitoring not only accurately reflects the instantaneous state, but also takes into account the continuity of dynamic changes. The present invention improves the adaptability and accuracy of the monitoring system under complex structures and changing environmental conditions. By organically combining physical models, data-driven methods and Bayesian statistics, it achieves a precise description of environmental compensation and structural response matching, reduces the risk of false alarms and missed detections, and provides a highly robust and reliable technical solution for structural health monitoring.

[0207] 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 fall within the scope of protection of the present invention.

Claims

1. A method for compensating for time series differences in three-dimensional monitoring data and adaptively adjusting dynamic thresholds, characterized in that: include: Collect and pre-process the three-dimensional point cloud data of the building structure to obtain the registered point cloud data; Based on the registered point cloud data and pre-stored material parameter data, PCA environmental features are extracted by region to obtain regional environmental features; Using regional environmental characteristics and pre-stored environmental sensor data, perform physical information enhanced environmental field reconstruction to obtain the final environmental field and build a cognitive physical-data dual-driven compensation model based on it to obtain a training model; When in use, the training model is used to perform dynamic threshold adaptive adjustment and time series difference compensation, calculate the environmental displacement field, the compensated displacement field and the adaptive threshold, and obtain the change detection result; The steps of performing physical information enhanced environment field reconstruction to obtain the final environment field include: Based on regional environmental characteristics, registered point cloud data and material parameter data, a 3D computational domain geometric model is constructed, the spatial gradient of environmental parameters is calculated, and a multi-resolution grid is generated; For the temperature field, humidity field, and light field, a heterogeneous physical model is constructed in combination with material parameter data, including the heat conduction equation, convection-diffusion equation, and radiation transfer equation, to obtain the environmental field physical model set. This model is then integrated with the environmental sensor data and data assimilation is performed to obtain the posterior environmental field. The theoretical structural response is calculated based on the posterior environmental field and compared with the measured displacement. The environmental field parameters are adjusted through feedback optimization to obtain the final environmental field.

2. The method according to claim 1, characterized in that The steps of extracting PCA environmental features by region and obtaining regional environmental features include: Based on the registered point cloud data and material parameter data, the initial structural response area is divided into initial partitions. The response similarity is evaluated and the optimized partitions are obtained by constructing a response correlation matrix and performing spectral cluster analysis. Apply time-weighted PCA feature extraction to the optimized partitions, construct a time-decay weight function and a weighted covariance matrix, obtain a PCA model and perform robust environmental feature extraction to obtain the environmental feature vector; Based on the environmental feature vector and PCA model, a nonlinear kernel function mapping is constructed to obtain the regional environmental characteristics.

3. The method according to claim 2, characterized in that The steps for evaluating response similarity and obtaining optimized partitions include: Extract environmental change data at historical time points and register point cloud data to establish an environment-response mapping table; Based on the environment-response mapping table, multivariate regression analysis is performed on the point cloud within the initial partition to obtain a sensitivity coefficient matrix. Based on this, the point-to-point response pattern similarity is calculated and a response correlation matrix is constructed. Laplace matrix transformation and eigenvalue decomposition are applied to the response correlation matrix, and spectral clustering analysis is performed to obtain the sub-partition consistency matrix; based on this, the partition consistency index and the similarity between partitions are calculated, and partition merging or splitting operations are performed to obtain the optimized partitions.

4. The method according to claim 3, characterized in that The steps of applying time-series weighted PCA feature extraction to obtain the PCA model include: Based on the optimized partition and environment-response mapping table, the environment-displacement joint matrix is constructed; Based on the preset time decay coefficient, the exponential decay function is applied to calculate the weight of the historical time point to obtain the normalized time weight; based on this, the weighted mean vector and weighted outer product of the environment-displacement joint matrix are calculated to construct the regularized covariance matrix; Perform eigenvalue decomposition on the regularized covariance matrix, sort it by contribution rate and select the main eigenvectors to obtain the principal component matrix. Based on this, the projection transformation matrix and reconstruction transformation matrix are constructed, and combined with the weighted mean vector to generate the PCA model.

5. The method according to claim 4, characterized in that The steps of extracting robust environmental features and obtaining environmental feature vectors include: Based on the environment-displacement joint matrix, the Huber loss function is used as a robust M-estimator to obtain the weight function; Use the weight function to calculate the weight of the data points, identify outliers and make corrections to obtain a robust data matrix; Project the robust data matrix through the projection matrix of the PCA model to generate a robust coefficient matrix; The corresponding relationship between environmental parameters and principal components is analyzed based on the robust coefficient matrix, key environmental features are extracted, and the environmental feature vector is obtained.

6. The method according to claim 1, wherein The steps to obtain the environmental field physical model set include: Based on the material parameter data, the position-dependent heat conductivity field and heat source function are used to establish the heterogeneous heat conduction equation and obtain the temperature field model. Based on the material parameter data and pre-stored spatial geometric characteristics, the humidity convection-diffusion equation is established through the humidity diffusion coefficient field and the air flow field to obtain the humidity field model; Based on the optical characteristic parameters in the material parameter data, the radiation transfer equation is constructed through the bidirectional reflectance distribution function to obtain the illumination field model; Based on multi-resolution grids, a numerical solution framework is constructed to analyze the coupling relationship between physical fields, integrate the temperature field, humidity field and light field models, and obtain a set of environmental field physical models.

7. The method according to claim 1, characterized in that The steps to obtain the posterior environment field include: Determine the location of environmental sensors in a multi-resolution grid and construct a unified observation operator using the observation error model. Combine this with the environmental sensor data to construct an initial state vector, which is then forward-time-integrated through the environmental field physical model set to obtain the model predicted state and observation residuals. Based on the model prediction state, a predetermined set of members is generated and the prior mean and covariance matrix are calculated to construct the state-observation cross-covariance matrix; the Kalman gain is calculated in combination with the observation residual, and the set members are updated to obtain the posterior set; The global state vector of the posterior set is decomposed into local region state vectors, and the posterior environment field is obtained through collective Kalman filtering and overlapping region information fusion.

8. The method according to claim 1, characterized in that The steps to obtain the training model include: Based on the set of environmental field physical models, a physical-constrained neural ordinary differential equation is constructed to obtain a hybrid model; Construct environmental field reconstruction, structural response prediction and physical consistency loss functions to form a multi-task loss function; The hybrid model is converted into a Bayesian model, the posterior distribution of the parameters is calculated, and the displacement distribution is constructed by combining the final environmental field. Based on this, a multi-scale model from the microscopic material to the macroscopic structure is constructed, and a cross-scale fusion model is obtained through scale bridging. The hybrid model, Bayesian model and cross-scale fusion model are integrated, and the parameters are optimized through the multi-task loss function to obtain the training model.

9. The method according to claim 8, characterized in that The steps to construct the displacement distribution include: The deterministic network parameters of the hybrid model are converted into random variables, and appropriate prior distributions are constructed for different types of parameters to obtain a Bayesian model. Construct the evidence lower bound objective function, and obtain the ELBO function and SGVI optimizer through stochastic gradient variational inference and reparameterization; Use the SGVI optimizer to maximize the ELBO function, obtain the optimized variational parameters, construct the parameter distribution and extract the parameter sample set; For each set of parameter samples, a hybrid model is used for forward prediction to generate an environmental field sample set; based on this, the corresponding structural response is calculated, a displacement sample set and its probability distribution are constructed, and the displacement distribution is obtained.

Images