Dam deformation monitoring and early warning method and system based on Beidou and machine vision

Abstract

The invention relates to the technical field of dam deformation monitoring, and provides a dam deformation monitoring and early warning method and system based on Beidou and machine vision, and the method comprises the steps: collecting the original displacement data of a dam and the original image data of the surface of the dam; performing RTK differential processing and multi-point positioning data weighted average on the original displacement data to obtain dam displacement data, and performing multispectral analysis and deep learning processing on the original image data to obtain dam surface structure feature data; carrying out localization processing on the dam displacement data to obtain real-time displacement change data, and carrying out parallel processing on the dam surface structure feature data to obtain real-time deformation feature data; dynamically fusing the real-time displacement change data and the real-time deformation characteristic data to obtain comprehensive deformation data; and establishing a dam deformation trend prediction model according to the comprehensive deformation data, and pushing graded early warning information to a monitoring center when abnormal deformation is detected. According to the invention, the real-time performance of dam deformation monitoring and the early warning reliability are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of dam deformation monitoring, and in particular to a dam deformation monitoring and early warning method and system based on Beidou and machine vision. Background Art

[0002] With the continuous expansion of the scale of water conservancy project construction, the importance of dam safety monitoring has become increasingly prominent. Traditional dam deformation monitoring mainly relies on a single monitoring method, such as using displacement sensors or visual detection equipment alone for monitoring. These monitoring methods often have problems such as limited data collection accuracy and insufficient monitoring coverage.

[0003] Existing technologies usually use fixed monitoring equipment to monitor dam deformation, and analyze deformation data through simple data processing methods. A single monitoring method is difficult to fully reflect the deformation state of the dam. Various types of monitoring data are often processed separately, resulting in low correlation of monitoring information. Due to the lack of intelligent data fusion capabilities, it is difficult to effectively integrate monitoring data from different sources, affecting the accuracy of monitoring results. The monitoring and early warning mechanism is relatively fixed and cannot be dynamically optimized and adjusted according to the actual monitoring results, resulting in insufficient timeliness and accuracy of early warning. There is a lack of effective fusion methods for multi-source heterogeneous monitoring data, and it is impossible to achieve collaborative analysis of displacement monitoring data and visual monitoring data. It is difficult to accurately grasp the overall deformation trend of the dam, thereby affecting the reliability of monitoring and early warning. Summary of the invention

[0004] In view of this, the present invention proposes a dam deformation monitoring and early warning method and system based on Beidou and machine vision, which solves the problem that the prior art lacks an effective fusion method for multi-source heterogeneous monitoring data and cannot realize the collaborative analysis of displacement monitoring data and visual monitoring data.

[0005] The technical solution of the present invention is implemented as follows: In the first aspect, the present invention provides a dam deformation monitoring and early warning method based on Beidou and machine vision, comprising the following steps:

[0006] The original displacement data of the dam is collected in real time through Beidou receivers, and the original image data of the dam surface is collected using monitoring equipment;

[0007] Performing RTK differential processing and weighted averaging of multi-point positioning data on the original displacement data to obtain dam displacement data, and performing multispectral analysis and deep learning processing on the original image data to obtain dam surface structure feature data;

[0008] The dam displacement data is locally processed by edge computing to obtain real-time displacement change data, and the dam surface structure feature data is processed in parallel by distributed computing to obtain real-time deformation feature data;

[0009] Based on the Kalman filter algorithm, the real-time displacement change data and the real-time deformation feature data are dynamically integrated to obtain comprehensive deformation data;

[0010] A dam deformation trend prediction model is established based on the comprehensive deformation data, and multi-level warning thresholds are set. When abnormal deformation is detected, graded warning information is pushed to the monitoring center.

[0011] On the basis of the above technical solution, preferably, the real-time collection of the original displacement data of the dam by the Beidou receiver and the collection of the original image data of the dam surface by the monitoring equipment specifically include:

[0012] A plurality of BeiDou receivers are arranged in the monitoring area of ​​the dam to construct a BeiDou monitoring network, wherein the BeiDou monitoring network includes a reference station and a plurality of monitoring stations, wherein the reference station is arranged in a stable area outside the influence range of the dam deformation, and the plurality of monitoring stations are arranged at a plurality of key parts of the dam, wherein the plurality of key parts include a dam top, a dam body and a dam foundation, and the three-dimensional coordinate data of the dam is collected in real time through the BeiDou monitoring network as the original displacement data;

[0013] Arrange multiple cameras around the dam to build an all-round monitoring network, and collect multi-angle images of the dam surface as the original image data;

[0014] The multiple cameras include a visible light camera and an infrared camera. The visible light camera is used to collect images of the dam surface during the day, and the real-time infrared camera is used to collect thermal imaging images of the dam surface at night and under low light conditions.

[0015] On the basis of the above technical solution, preferably, the raw displacement data is subjected to RTK differential processing and weighted averaging of multi-point positioning data to obtain dam displacement data, and the raw image data is subjected to multispectral analysis and deep learning processing to obtain dam surface structure feature data, specifically including:

[0016] The original displacement data is processed by RTK differential processing using a dynamic baseline adjustment algorithm to obtain optimized displacement data, and the optimized displacement data is fused using a weighted average algorithm to obtain dam displacement data;

[0017] The infrared image data and the visible light image data are integrated through a multispectral image fusion algorithm to obtain a fused multispectral image. The fused multispectral image is trained and recognized based on a convolutional neural network model to obtain the surface structural feature data of the dam.

[0018] On the basis of the above technical solution, preferably, the dam displacement data is locally processed by edge computing to obtain real-time displacement change data, and the dam surface structure feature data is processed in parallel by distributed computing to obtain real-time deformation feature data, specifically including:

[0019] A dynamic data screening method based on a model predictive control algorithm is used to filter and optimize the dam displacement data in real time to obtain optimized dam displacement data, and an adaptive threshold detection algorithm is used to perform real-time anomaly detection on the optimized dam displacement data to obtain the real-time displacement change data;

[0020] A regional growing algorithm is used to extract the characteristic data of the dam surface structure to obtain characteristic regional change data. A spatiotemporal correlation analysis method based on a graph neural network is used to comprehensively analyze the characteristic regional change data to generate real-time deformation characteristic data.

[0021] On the basis of the above technical solution, preferably, the calculation formula for optimizing the dam displacement data is:

[0022] D 优 (t) = α2·D 实 (t)+(1-α2)·D 预 (t);

[0023] Among them, D 优 (t) is the optimized dam displacement data at time t, D 实 (t) is the dam displacement data at time t, D 预 (t) is the displacement data at time t predicted based on historical data, and α2 is the dynamic data adjustment coefficient;

[0024] The calculation formula of the real-time displacement change data is:

[0025]

[0026] Δd threshold =μ1+β2·σ1;

[0027] Among them, D 变 (t) is the real-time displacement change data at time t, D 优 (t) is the optimized dam displacement data at time t, D 优 (t-1) is the optimized dam displacement data at time t-1, Δd threshold is the adaptive threshold, μ1 is the sliding mean of the optimized dam displacement data, σ1 is the sliding standard deviation of the optimized dam displacement data, and β2 is the sensitivity adjustment coefficient;

[0028] The calculation formula of the characteristic area change data is:

[0029] S(p)=w1·ΔI(p)+w2·ΔT(p)+w3·C(p);

[0030]

[0031] Among them, S(p) is the growth score of pixel p in the dam surface structure feature data, ΔI(p) is the grayscale difference of pixel p, ΔT(p) is the texture feature difference of pixel p, C(p) is the spatial continuity constraint of pixel p, w1, w2, w3 are the weight coefficients of grayscale, texture feature and spatial continuity constraint respectively, ΔF 区域 is the feature area change data, R is the set of pixels in the feature area;

[0032] The calculation formula of the real-time deformation feature data is:

[0033]

[0034] Among them, FeatureFusion i is the fusion feature matrix of node i, N(i) is the set of nodes adjacent to node i, W j is the weight matrix of node j, Feature j is the feature matrix of node j, b2 is the neighbor node bias term, ReLU(·) is the ReLU activation function, F 形变 is the real-time deformation feature data, and N1 is the total number of feature nodes.

[0035] On the basis of the above technical solution, preferably, the real-time displacement change data and the real-time deformation feature data are dynamically fused based on the Kalman filter algorithm to obtain comprehensive deformation data, which specifically includes:

[0036] The real-time displacement change data and the real-time deformation feature data are respectively dynamically optimized by using a Kalman filter algorithm, including: constructing a state space model, mapping the real-time displacement change data and the real-time deformation feature data to a state vector space, respectively, dynamically optimizing the state vector through a prediction-update iterative process, wherein the prediction step performs state prediction based on historical data, and the update iterative step corrects the prediction result in combination with the observed data, introduces an adaptive factor, and dynamically adjusts the system noise covariance matrix and the observation noise covariance matrix according to the time-varying characteristics of the data to obtain optimized displacement change data and optimized deformation feature data;

[0037] The calculation formula of the Kalman filter algorithm is:

[0038]

[0039] in, is the estimated value of the state at time m, is the estimated value of the state at time m-1, α m is the adaptive factor, z m is the observed value at time m, u m is the control input, A1 is the state transfer matrix, B1 is the control matrix, K1 is the Kalman gain, v m is the innovation sequence, R m is the observation noise covariance matrix, P m is the prediction error covariance matrix, tr(·) is the trace of the matrix;

[0040] A sliding time window is established based on the data timestamp, and the optimized displacement change data and the optimized deformation feature data are time-aligned within the window. The correlation coefficient and confidence of the time-aligned data are calculated as the weight parameters of dynamic weighted fusion. A multi-scale weighted fusion method is used to combine local and global features to generate comprehensive deformation data.

[0041] The calculation formula for the time alignment is:

[0042] Δt sync =min(Δt pos ,Δt def )·exp(-β3Δt pos -Δt def |);

[0043] Among them, Δt sync is the time synchronization window size, Δt pos is the displacement data time interval, Δt def is the deformation data time interval, β3 is the time attenuation coefficient;

[0044] The calculation formula of the dynamic weighted fusion is:

[0045]

[0046] Among them, F 综 For comprehensive deformation data, To optimize the displacement change data, To optimize the deformation feature data, and They are and The weight coefficient of is the dynamic weight of the nth data source, is the correlation coefficient between the nth data source and historical data, is the correlation coefficient between the qth data source and historical data, is the data confidence of the nth data source, is the data confidence of the qth data source, q=1, 2 are the optimized displacement change data and optimized deformation feature data respectively.

[0047] On the basis of the above technical solution, preferably, the dam deformation trend prediction model is established according to the comprehensive deformation data, and a multi-level warning threshold is set. When abnormal deformation is detected, the graded warning information is pushed to the monitoring center, specifically including:

[0048] Based on the comprehensive deformation data, a dam deformation trend prediction model is constructed, and a trend prediction of the dam deformation data is performed using a time series analysis method to generate a future deformation trend curve;

[0049] Performing time series decomposition on the comprehensive deformation data, decomposing the comprehensive deformation data into trend items, period items and random items, using a long short-term memory network model to perform trend prediction based on the trend items, period items and random items, performing error evaluation on the prediction results, using a sliding window method to correct the prediction error, and generating a future deformation trend curve;

[0050] According to the historical monitoring data and the structural characteristics of the dam, a multi-level warning threshold is set, which includes normal, safety warning, risk warning and emergency warning. The deviation between the predicted trend curve and the warning threshold is calculated. When any point of the predicted trend curve exceeds the safety warning threshold, the corresponding level of warning information is triggered. The graded warning information is pushed to the monitoring center using the preset communication network, and a detailed deformation trend report is attached according to the warning level.

[0051] In a second aspect, the present invention further provides a dam deformation monitoring and early warning system based on Beidou and machine vision, the system comprising:

[0052] The data acquisition module is used to collect the original displacement data of the dam in real time through the Beidou receiver and to collect the original image data of the dam surface using the monitoring equipment;

[0053] A data processing module is used to perform RTK differential processing and weighted averaging of multi-point positioning data on the original displacement data to obtain dam displacement data, and to perform multispectral analysis and deep learning processing on the original image data to obtain dam surface structure feature data;

[0054] A deformation analysis module is used to perform local processing on the dam displacement data using an edge computing algorithm to obtain real-time displacement change data, and to perform parallel processing on the dam surface structure feature data using a distributed computing method to obtain real-time deformation feature data;

[0055] A data fusion module, used for dynamically fusing the real-time displacement change data and the real-time deformation feature data based on a Kalman filter algorithm to obtain comprehensive deformation data;

[0056] The monitoring and early warning module is used to establish a dam deformation trend prediction model based on the comprehensive deformation data, set multi-level early warning thresholds, and push graded early warning information to the monitoring center when abnormal deformation is detected.

[0057] In a third aspect, the present invention further provides an electronic device, comprising: at least one processor, at least one memory, a communication interface and a bus;

[0058] Among them, the processor, memory, and communication interface communicate with each other through the bus, the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to implement steps such as a dam deformation monitoring and early warning method based on Beidou and machine vision.

[0059] In a fourth aspect, the present invention also provides a computer-readable storage medium, which stores computer instructions, and the computer instructions enable a computer to implement steps such as a dam deformation monitoring and early warning method based on Beidou and machine vision.

[0060] The dam deformation monitoring and early warning method and system based on Beidou and machine vision of the present invention have the following beneficial effects compared with the prior art:

[0061] (1) By combining Beidou positioning and machine vision, RTK differential processing, deep learning processing, edge computing and distributed computing are used to process dam monitoring data in real time, and the Kalman filter algorithm is used to realize the dynamic fusion of multi-source data. A prediction model is established based on the fused comprehensive deformation data and a graded early warning is realized, which significantly improves the real-time performance of dam deformation monitoring and the reliability of early warning.

[0062] (2) By optimizing the dam displacement data and real-time displacement change data, combining historical data prediction, adaptive threshold and sliding statistical methods, dynamically adjusting data processing parameters, effectively reducing noise interference and random errors, and improving the sensitivity of displacement change detection, real-time monitoring of dam deformation is achieved;

[0063] (3) The real-time displacement change data and real-time deformation feature data are dynamically optimized through the Kalman filtering algorithm. The state space model and the prediction-update iterative process are combined to eliminate noise interference, dynamically adjust the system noise and observation noise covariance matrix, improve the stability of data optimization, and realize real-time dynamic analysis of dam deformation. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0065] Figure 1 A flow chart of a dam deformation monitoring and early warning method based on Beidou and machine vision of the present invention;

[0066] Figure 2 This is a structural diagram of a dam deformation monitoring and early warning system based on Beidou and machine vision of the present invention. DETAILED DESCRIPTION

[0067] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0068] See also Figure 1 The present invention provides a dam deformation monitoring and early warning method based on Beidou and machine vision, comprising the following steps:

[0069] The original displacement data of the dam is collected in real time by Beidou receivers installed at key locations of the dam, and the original image data of the dam surface is collected by monitoring equipment;

[0070] Performing RTK differential processing and weighted averaging of multi-point positioning data on the original displacement data to obtain dam displacement data, and performing multispectral analysis and deep learning processing on the original image data to obtain dam surface structure feature data;

[0071] The dam displacement data is locally processed by edge computing to obtain real-time displacement change data, and the dam surface structure feature data is processed in parallel by distributed computing to obtain real-time deformation feature data;

[0072] Based on the Kalman filter algorithm, the real-time displacement change data and the real-time deformation feature data are dynamically fused, a unified time synchronization mechanism is established to ensure the timeliness of data fusion, and comprehensive deformation data is obtained;

[0073] A dam deformation trend prediction model is established based on the comprehensive deformation data, and a multi-level warning threshold is set. When abnormal deformation is detected, graded warning information is pushed to the monitoring center through a preset communication network.

[0074] Specifically, this embodiment combines Beidou positioning and machine vision, and adopts RTK differential processing, deep learning processing, edge computing and distributed computing to process dam monitoring data in real time, and uses the Kalman filter algorithm to realize dynamic fusion of multi-source data. A prediction model is established based on the fused comprehensive deformation data and graded early warning is implemented, which significantly improves the real-time performance of dam deformation monitoring and the reliability of early warning.

[0075] The real-time collection of the original displacement data of the dam by the Beidou receiver and the collection of the original image data of the dam surface by the monitoring equipment specifically include:

[0076] A plurality of Beidou receivers are arranged in the monitoring area of ​​the dam to construct a Beidou monitoring network, wherein the Beidou monitoring network includes a reference station and a plurality of monitoring stations, wherein the reference station is arranged in a stable area outside the influence range of the dam deformation, and the plurality of monitoring stations are arranged at a plurality of key parts of the dam, wherein the plurality of key parts include the dam top, the dam body and the dam foundation, and high-precision positioning monitoring is realized through the cooperation between the reference station and the monitoring station, and the three-dimensional coordinate data of the dam is collected in real time through the Beidou monitoring network as the original displacement data;

[0077] Arrange multiple cameras around the dam to build an all-round monitoring network, and collect multi-angle images of the dam surface as the original image data;

[0078] The multiple cameras include visible light cameras and infrared cameras. The visible light cameras are used to collect images of the dam surface during the day, and the real-time infrared cameras are used to collect thermal imaging images of the dam surface at night and under low light conditions to achieve all-weather monitoring.

[0079] Specifically, this embodiment deploys multiple Beidou receivers at key locations of the dam, including the dam top, dam body and dam foundation, and combines the base station with the monitoring station to achieve high-precision three-dimensional coordinate data collection, thereby improving the collection accuracy of the dam displacement data, and providing stable and reliable displacement monitoring data, especially under complex terrain conditions.

[0080] Multiple cameras, including visible light cameras and infrared cameras, are deployed around the dam to build an all-weather, multi-angle monitoring network. Visible light cameras are used to collect images of the dam surface during the day, and infrared cameras are used to collect thermal imaging images at night or under low light conditions, thereby achieving all-weather monitoring capabilities. This multi-modal image acquisition method can fully cover the dam surface and ensure the integrity of the monitoring data.

[0081] The introduction of infrared cameras enables normal operation at night or in low-light conditions, overcoming the limitations of traditional monitoring equipment in low-light conditions and significantly enhancing the adaptability in complex environments.

[0082] The RTK differential processing and weighted averaging of multi-point positioning data are performed on the original displacement data to obtain the dam displacement data, and the multi-spectral analysis and deep learning processing are performed on the original image data to obtain the dam surface structure feature data, which specifically includes:

[0083] The dynamic baseline adjustment algorithm is used to perform RTK differential processing on the original displacement data to improve the positioning accuracy under complex terrain conditions and obtain optimized displacement data. The weighted average algorithm is used to fuse the optimized displacement data to reduce the random error of single-point data and obtain the dam displacement data.

[0084] The calculation formula of the dynamic baseline adjustment algorithm is:

[0085] B new =B current +α1·(D observed -D predicted );

[0086] Among them, B new is the new baseline value, B current is the current baseline value, α1 is the adjustment coefficient, D observed is the observed displacement data, D predicted To predict displacement data;

[0087] The infrared image data and the visible light image data are integrated by a multispectral image fusion algorithm to obtain a fused multispectral image, and the fused multispectral image is trained and recognized based on a convolutional neural network model to achieve high-precision detection of cracks and micro-deformations on the dam surface and obtain surface structural feature data of the dam;

[0088] The calculation formula of the convolutional neural network model is:

[0089]

[0090] Among them, FeatureMap l+1 is the feature map of the l+1th layer, FeatureMap l is the feature map of the lth layer, σ(·) is the activation function, W k is the kth convolution kernel, * is the convolution operation, b1 is the convolution layer bias, β1 is the attention adjustment coefficient, AttentionMap l is the attention map of the lth layer.

[0091] Specifically, this embodiment performs RTK differential processing through a dynamic baseline adjustment algorithm, dynamically adjusts the baseline value according to the difference between real-time observation data and predicted data, thereby improving the positioning accuracy under complex terrain conditions, and uses a weighted average algorithm to fuse the optimized displacement data, thereby effectively reducing the random error of single-point data.

[0092] Through the multispectral image fusion algorithm, infrared images and visible light images are effectively integrated, fully utilizing the advantages of the two imaging methods, improving the information richness of the image, and enabling stable monitoring effects to be maintained under different lighting and weather conditions.

[0093] Based on the improved convolutional neural network model, the attention mechanism is introduced for feature extraction and recognition, which improves the detection accuracy of small cracks and deformations on the dam surface. The introduction of the attention mechanism enables the model to adaptively focus on important feature areas, improving the accuracy of recognition. By combining traditional image processing methods with deep learning, intelligent processing of monitoring data is achieved, greatly improving the ability to extract and analyze the surface structural features of the dam.

[0094] The dam displacement data is processed locally by edge computing to obtain real-time displacement change data, and the dam surface structure feature data is processed in parallel by distributed computing to obtain real-time deformation feature data, specifically including:

[0095] A dynamic data screening method based on a model predictive control algorithm is used to filter and optimize the dam displacement data in real time, eliminate the influence of environmental noise on the displacement data, and obtain optimized dam displacement data. An adaptive threshold detection algorithm is used to perform real-time anomaly detection on the optimized dam displacement data, timely discover and respond to small displacement changes of the dam, and obtain the real-time displacement change data.

[0096] A regional growing algorithm is used to extract the feature data of the dam surface structure, accurately identify the characteristic areas such as cracks and deformations on the dam surface, and obtain the characteristic area change data. The spatiotemporal correlation analysis method based on graph neural network is used to comprehensively analyze the characteristic area change data to generate real-time deformation feature data.

[0097] Specifically, this embodiment uses a dynamic data screening method based on a model predictive control algorithm to filter and optimize the dam displacement data in real time, eliminate the interference of environmental noise, and adopts an adaptive threshold detection algorithm to dynamically adjust the detection threshold according to actual monitoring data, timely discover and respond to small displacement changes of the dam, improve the sensitivity of abnormal detection, and extract features from the dam surface structure feature data through a regional growing algorithm, which can accurately identify characteristic areas such as cracks and deformations on the dam surface. Using a spatiotemporal correlation analysis method based on a graph neural network, it is possible to comprehensively analyze the characteristic area change data, and realize intelligent identification and correlation analysis of deformation features.

[0098] The calculation formula for optimizing the dam displacement data is:

[0099] D 优 (t) = α2·D 实 (t)+(1-α2)·D 预 (t);

[0100] Among them, D 优 (t) is the optimized dam displacement data at time t, D 实 (t) is the dam displacement data at time t, D 预 (t) is the displacement data at time t predicted based on historical data, and α2 is the dynamic data adjustment coefficient;

[0101] The calculation formula of the real-time displacement change data is:

[0102]

[0103] Δd threshold =μ1+β2·σ1;

[0104] Among them, D 变 (t) is the real-time displacement change data at time t, D 优 (t) is the optimized dam displacement data at time t, D 优 (t-1) is the optimized dam displacement data at time t-1, Δd threshold is the adaptive threshold, μ1 is the sliding mean of the optimized dam displacement data, σ1 is the sliding standard deviation of the optimized dam displacement data, and β2 is the sensitivity adjustment coefficient;

[0105] The calculation formula of the characteristic area change data is:

[0106] S(p)=w1·ΔI(p)+w2·ΔT(p)+w3·C(p);

[0107]

[0108] Among them, S(p) is the growth score of pixel p in the dam surface structure feature data, ΔI(p) is the grayscale difference of pixel p, ΔT(p) is the texture feature difference of pixel p, C(p) is the spatial continuity constraint of pixel p, w1, w2, w3 are the weight coefficients of grayscale, texture feature and spatial continuity constraint respectively, ΔF 区域 is the feature area change data, R is the set of pixels in the feature area;

[0109] The calculation formula of the real-time deformation feature data is:

[0110]

[0111] Among them, FeatureFusion i is the fusion feature matrix of node i, N(i) is the set of nodes adjacent to node i, W j is the weight matrix of node j, Feature j is the feature matrix of node j, b2 is the neighbor node bias term, ReLU(·) is the ReLU activation function, F 形变 is the real-time deformation feature data, and N1 is the total number of feature nodes.

[0112] Specifically, this embodiment optimizes the original displacement data by optimizing the dam displacement data, combining historical data prediction and dynamic adjustment coefficients, effectively improving the reliability of the data, and introducing predicted data as a reference, making the optimization process more forward-looking.

[0113] The calculation of real-time displacement change data adopts the adaptive threshold method. Through the dynamic calculation of the sliding mean and standard deviation, the detection sensitivity is automatically adjusted according to the data characteristics, which improves the detection ability of small displacement changes. The calculation of feature area change data comprehensively considers the three key factors of grayscale difference, texture characteristics and spatial continuity constraints. Through the reasonable configuration of weight coefficients, accurate identification and change analysis of the feature area of ​​the dam surface are achieved. The calculation of real-time deformation feature data adopts a feature fusion method based on graph structure. Through the weight matrix between nodes and ReLU activation function, intelligent extraction and analysis of features are realized.

[0114] The Kalman filter algorithm is used to dynamically fuse the real-time displacement change data and the real-time deformation feature data to obtain comprehensive deformation data, which specifically includes:

[0115] The real-time displacement change data and the real-time deformation feature data are respectively dynamically optimized by using a Kalman filter algorithm, including: constructing a state space model, mapping the real-time displacement change data and the real-time deformation feature data to a state vector space, respectively, dynamically optimizing the state vector through a prediction-update iterative process, wherein the prediction step performs state prediction based on historical data, and the update iterative step corrects the prediction result in combination with the observed data, introduces an adaptive factor, and dynamically adjusts the system noise covariance matrix and the observation noise covariance matrix according to the time-varying characteristics of the data, thereby improving the optimization effect and obtaining optimized displacement change data and optimized deformation feature data;

[0116] The calculation formula of the Kalman filter algorithm is:

[0117]

[0118] in, is the estimated value of the state at time m, is the estimated value of the state at time m-1, α m is the adaptive factor, z m is the observed value at time m, u m is the control input, A1 is the state transfer matrix, B1 is the control matrix, K1 is the Kalman gain, v m is the innovation sequence, R m is the observation noise covariance matrix, P m is the prediction error covariance matrix, tr(·) is the trace of the matrix;

[0119] A sliding time window is established based on the data timestamp, and the optimized displacement change data and the optimized deformation feature data are time-aligned within the window. The correlation coefficient and confidence of the time-aligned data are calculated as the weight parameters of dynamic weighted fusion. A multi-scale weighted fusion method is used to combine local and global features to generate comprehensive deformation data.

[0120] The calculation formula for the time alignment is:

[0121] Δt sync =min(Δt pos ,Δt def )·exp(-β3Δt pos -Δt def |);

[0122] Among them, Δt sync is the time synchronization window size, Δt pos is the time interval of displacement data, Δt def is the deformation data time interval, β3 is the time attenuation coefficient;

[0123] The calculation formula of the dynamic weighted fusion is:

[0124]

[0125] Among them, F 综 For comprehensive deformation data, To optimize the displacement change data, To optimize the deformation feature data, and They are and The weight coefficient of is the dynamic weight of the nth data source, is the correlation coefficient between the nth data source and historical data, is the correlation coefficient between the qth data source and historical data, is the data confidence of the nth data source, is the data confidence of the qth data source, q=1, 2 are the optimized displacement change data and optimized deformation feature data respectively.

[0126] Specifically, this embodiment uses the Kalman filter algorithm to dynamically optimize the real-time displacement change data and the real-time deformation feature data, and combines the state space model and the prediction-update iterative process to eliminate data noise and improve data quality. The adaptive factor is introduced to dynamically adjust the system noise covariance matrix and the observation noise covariance matrix to make the optimization process more adaptive. By establishing a sliding time window mechanism based on the data timestamp, accurate time alignment of data from different sources is achieved, which solves the problem of time asynchrony of multi-source data. The time alignment calculation formula takes into account the time attenuation factor. The multi-scale weighted fusion method is adopted, and the data correlation coefficient and confidence are calculated as weight parameters to achieve an effective combination of local and global features.

[0127] The dam deformation trend prediction model is established based on the comprehensive deformation data, and a multi-level warning threshold is set. When abnormal deformation is detected, the graded warning information is pushed to the monitoring center, specifically including:

[0128] Based on the comprehensive deformation data, a dam deformation trend prediction model is constructed, and a trend prediction of the dam deformation data is performed using a time series analysis method to generate a future deformation trend curve;

[0129] Performing time series decomposition on the comprehensive deformation data, decomposing the comprehensive deformation data into trend items, period items and random items, and using a long short-term memory network model to perform trend prediction based on the trend items, period items and random items. The long short-term memory network model includes introducing an attention mechanism to improve prediction accuracy; performing error evaluation on the prediction results, using a sliding window method to correct the prediction error, and generating a future deformation trend curve;

[0130] The calculation formula for the time series decomposition is:

[0131]

[0132] Among them, F 综 For comprehensive deformation data, is a trend item, reflecting the long-term change trend of deformation data. is a periodic term, reflecting the periodic fluctuation of deformation data, is a random term, reflecting random fluctuations in the deformation data;

[0133] The calculation formula for the error assessment is:

[0134]

[0135] in, is the prediction error, is the real deformation data, To predict deformation data, is the corrected prediction data, N2 is the sliding window size, is the current moment, s is the time step index;

[0136] According to historical monitoring data and dam structural characteristics, multi-level warning thresholds are set, including normal, safety warning, risk warning and emergency warning, and the deviation between the predicted trend curve and the warning threshold is calculated. When any point of the predicted trend curve exceeds the safety warning threshold, the corresponding level of warning information is triggered. The graded warning information is pushed to the monitoring center using the preset communication network, and a detailed deformation trend report is attached according to the warning level;

[0137] The judgment formula for multi-level warning is:

[0138]

[0139] in, is the deviation between the predicted value and the warning threshold, for The predicted value at time, for The warning threshold at the moment, Δ1 is the first warning threshold, and Δ2 is the second warning threshold.

[0140] Specifically, this embodiment decomposes the comprehensive deformation data into trend items, periodic items and random items through time series decomposition, adopts a long short-term memory network model and introduces an attention mechanism, thereby improving the ability to capture long-term dependencies.

[0141] The prediction results are corrected in real time through the sliding window method, which effectively reduces the prediction error. The error evaluation calculation is used to achieve dynamic optimization of the prediction results and improve the stability of deformation trend prediction.

[0142] Based on historical monitoring data and dam structural characteristics, a multi-level warning mechanism including normal, safety alert, risk warning and emergency warning has been established. Through the setting of warning thresholds, accurate identification of deformation risks of different degrees can be achieved, so that warning information of corresponding levels can be issued in time, and detailed deformation trend reports can be automatically generated. The warning information includes a detailed analysis report of the deformation trend, providing a comprehensive decision-making basis for managers, and timely push of warning information is achieved through the preset communication network, ensuring the timeliness of information transmission.

[0143] See also Figure 2 The present invention also provides a dam deformation monitoring and early warning system based on Beidou and machine vision, the system comprising:

[0144] The data acquisition module is used to collect the original displacement data of the dam in real time through the Beidou receiver and to collect the original image data of the dam surface using the monitoring equipment;

[0145] A data processing module is used to perform RTK differential processing and weighted averaging of multi-point positioning data on the original displacement data to obtain dam displacement data, and to perform multispectral analysis and deep learning processing on the original image data to obtain dam surface structure feature data;

[0146] A deformation analysis module is used to perform local processing on the dam displacement data using an edge computing algorithm to obtain real-time displacement change data, and to perform parallel processing on the dam surface structure feature data using a distributed computing method to obtain real-time deformation feature data;

[0147] A data fusion module, used for dynamically fusing the real-time displacement change data and the real-time deformation feature data based on a Kalman filter algorithm to obtain comprehensive deformation data;

[0148] The monitoring and early warning module is used to establish a dam deformation trend prediction model based on the comprehensive deformation data, set multi-level early warning thresholds, and push graded early warning information to the monitoring center when abnormal deformation is detected.

[0149] Specifically, a dam deformation monitoring and early warning system based on Beidou and machine vision in this embodiment realizes full-process intelligent processing of dam deformation monitoring through the collaborative work of five functional modules: the data acquisition module realizes all-weather, multi-angle data acquisition through Beidou receivers and monitoring equipment; the data processing module adopts RTK differential and deep learning technology to improve data quality; the deformation analysis module uses edge computing and distributed computing to achieve real-time processing; the data fusion module realizes dynamic fusion of multi-source data based on the Kalman filtering algorithm; the monitoring and early warning module timely detects potential risks through trend prediction and multi-level early warning mechanism, thereby improving the real-time and reliability of deformation monitoring.

[0150] The present invention also discloses an electronic device, comprising: at least one processor, at least one memory communication interface and a bus: wherein the processor, memory and communication interface communicate with each other through the bus; the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to implement a dam deformation monitoring and early warning method based on Beidou and machine vision.

[0151] The present invention also discloses a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, wherein the computer instructions enable the computer to implement all or part of the steps of a dam deformation monitoring and early warning method based on Beidou and machine vision described in an embodiment of the present invention. The storage medium includes: a U disk, a mobile hard disk, a read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk, and other media that can store program codes.

[0152] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A dam deformation monitoring and early warning method based on Beidou and machine vision, characterized in that: The following steps are involved: The original displacement data of the dam is collected in real time through Beidou receivers, and the original image data of the dam surface is collected using monitoring equipment; Performing RTK differential processing and weighted averaging of multi-point positioning data on the original displacement data to obtain dam displacement data, and performing multispectral analysis and deep learning processing on the original image data to obtain dam surface structure feature data; The dam displacement data is locally processed by edge computing to obtain real-time displacement change data, and the dam surface structure feature data is processed in parallel by distributed computing to obtain real-time deformation feature data; Based on the Kalman filter algorithm, the real-time displacement change data and the real-time deformation feature data are dynamically integrated to obtain comprehensive deformation data; A dam deformation trend prediction model is established based on the comprehensive deformation data, and multi-level warning thresholds are set. When abnormal deformation is detected, graded warning information is pushed to the monitoring center.

2. A dam deformation monitoring and early warning method based on Beidou and machine vision as claimed in claim 1, characterized in that: The real-time collection of the original displacement data of the dam by the Beidou receiver and the collection of the original image data of the dam surface by the monitoring equipment specifically include: A plurality of BeiDou receivers are arranged in the monitoring area of ​​the dam to construct a BeiDou monitoring network, wherein the BeiDou monitoring network includes a reference station and a plurality of monitoring stations, wherein the reference station is arranged in a stable area outside the influence range of the dam deformation, and the plurality of monitoring stations are arranged at a plurality of key parts of the dam, wherein the plurality of key parts include a dam top, a dam body and a dam foundation, and the three-dimensional coordinate data of the dam is collected in real time through the BeiDou monitoring network as the original displacement data; Arrange multiple cameras around the dam to build an all-round monitoring network, and collect multi-angle images of the dam surface as the original image data; The multiple cameras include a visible light camera and an infrared camera. The visible light camera is used to collect images of the dam surface during the day, and the real-time infrared camera is used to collect thermal imaging images of the dam surface at night and under low light conditions.

3. A dam deformation monitoring and early warning method based on Beidou and machine vision as claimed in claim 2, characterized in that: The RTK differential processing and weighted averaging of multi-point positioning data are performed on the original displacement data to obtain the dam displacement data, and the multi-spectral analysis and deep learning processing are performed on the original image data to obtain the dam surface structure feature data, which specifically includes: The original displacement data is processed by RTK differential processing using a dynamic baseline adjustment algorithm to obtain optimized displacement data, and the optimized displacement data is fused using a weighted average algorithm to obtain dam displacement data; The infrared image data and the visible light image data are integrated through a multispectral image fusion algorithm to obtain a fused multispectral image. The fused multispectral image is trained and recognized based on a convolutional neural network model to obtain the surface structural feature data of the dam.

4. The method for monitoring and early warning of dam deformation based on Beidou and machine vision as claimed in claim 1, characterized in that: The dam displacement data is processed locally by edge computing to obtain real-time displacement change data, and the dam surface structure feature data is processed in parallel by distributed computing to obtain real-time deformation feature data, specifically including: A dynamic data screening method based on a model predictive control algorithm is used to filter and optimize the dam displacement data in real time to obtain optimized dam displacement data, and an adaptive threshold detection algorithm is used to perform real-time anomaly detection on the optimized dam displacement data to obtain the real-time displacement change data; A regional growing algorithm is used to extract the characteristic data of the dam surface structure to obtain characteristic regional change data. A spatiotemporal correlation analysis method based on a graph neural network is used to comprehensively analyze the characteristic regional change data to generate real-time deformation characteristic data.

5. The method for monitoring and early warning of dam deformation based on Beidou and machine vision as claimed in claim 4, characterized in that: The calculation formula for optimizing the dam displacement data is: D 优 (t)=α2·D 实 (t)+(1-α2)·D 预 (t); Among them, D 优 (t) is the optimized dam displacement data at time t, D 实 (t) is the dam displacement data at time t, D 预 (t) is the displacement data at time t predicted based on historical data, and α2 is the dynamic data adjustment coefficient; The calculation formula of the real-time displacement change data is: Δd threshold =μ1+β2·σ1; Among them, D 变 (t) is the real-time displacement change data at time t, D 优 (t) is the optimized dam displacement data at time t, D 优 (t-1) is the optimized dam displacement data at time t-1, Δd threshold is the adaptive threshold, μ1 is the sliding mean of the optimized dam displacement data, σ1 is the sliding standard deviation of the optimized dam displacement data, and β2 is the sensitivity adjustment coefficient; The calculation formula of the characteristic area change data is: S(p)=w1·ΔI(p)+w2·ΔT(p)+w3·C(p); Among them, S(p) is the growth score of pixel p in the dam surface structure feature data, ΔI(p) is the grayscale difference of pixel p, ΔT(p) is the texture feature difference of pixel p, C(p) is the spatial continuity constraint of pixel p, w1, w2, w3 are the weight coefficients of grayscale, texture feature and spatial continuity constraint respectively, ΔF 区域 is the feature area change data, R is the set of pixels in the feature area; The calculation formula of the real-time deformation feature data is: Among them, FeatureFusion i is the fusion feature matrix of node i, N(i) is the set of nodes adjacent to node i, W j is the weight matrix of node j, Feature j is the feature matrix of node j, b2 is the neighbor node bias term, ReLU(·) is the ReLU activation function, F 形变 is the real-time deformation feature data, and N1 is the total number of feature nodes.

6. The method for monitoring and early warning of dam deformation based on Beidou and machine vision as claimed in claim 1, characterized in that: The Kalman filter algorithm is used to dynamically fuse the real-time displacement change data and the real-time deformation feature data to obtain comprehensive deformation data, which specifically includes: The real-time displacement change data and the real-time deformation feature data are respectively dynamically optimized by using a Kalman filter algorithm, including: constructing a state space model, mapping the real-time displacement change data and the real-time deformation feature data to a state vector space, respectively, dynamically optimizing the state vector through a prediction-update iterative process, wherein the prediction step performs state prediction based on historical data, and the update iterative step corrects the prediction result in combination with the observed data, introduces an adaptive factor, and dynamically adjusts the system noise covariance matrix and the observation noise covariance matrix according to the time-varying characteristics of the data to obtain optimized displacement change data and optimized deformation feature data; The calculation formula of the Kalman filter algorithm is: in, is the estimated value of the state at time m, is the estimated value of the state at time m-1, α m is the adaptive factor, z m is the observed value at time m, u m is the control input, A1 is the state transfer matrix, B1 is the control matrix, K1 is the Kalman gain, v m is the innovation sequence, R m is the observation noise covariance matrix, P m is the prediction error covariance matrix, tr(·) is the trace of the matrix; A sliding time window is established based on the data timestamp, and the optimized displacement change data and the optimized deformation feature data are time-aligned within the window. The correlation coefficient and confidence of the time-aligned data are calculated as the weight parameters of dynamic weighted fusion. A multi-scale weighted fusion method is used to combine local and global features to generate comprehensive deformation data. The calculation formula for the time alignment is: Δt sync =min(Δt pos ,Δt def )·exp(-β3Δt pos -Δt def |); Among them, Δt sync is the time synchronization window size, Δt pos is the displacement data time interval, Δt def is the deformation data time interval, β3 is the time attenuation coefficient; The calculation formula of the dynamic weighted fusion is: Among them, F 综 For comprehensive deformation data, To optimize the displacement change data, To optimize the deformation feature data, and They are and The weight coefficient of is the dynamic weight of the nth data source, is the correlation coefficient between the nth data source and historical data, is the correlation coefficient between the qth data source and historical data, is the data confidence of the nth data source, is the data confidence of the qth data source, q=1, 2 are the optimized displacement change data and optimized deformation feature data respectively.

7. The method for monitoring and early warning of dam deformation based on Beidou and machine vision as claimed in claim 6, characterized in that: The dam deformation trend prediction model is established based on the comprehensive deformation data, and a multi-level warning threshold is set. When abnormal deformation is detected, the graded warning information is pushed to the monitoring center, specifically including: Based on the comprehensive deformation data, a dam deformation trend prediction model is constructed, and a trend prediction of the dam deformation data is performed using a time series analysis method to generate a future deformation trend curve; Performing time series decomposition on the comprehensive deformation data, decomposing the comprehensive deformation data into trend items, period items and random items, using a long short-term memory network model to perform trend prediction based on the trend items, period items and random items, performing error evaluation on the prediction results, using a sliding window method to correct the prediction error, and generating a future deformation trend curve; According to the historical monitoring data and the structural characteristics of the dam, a multi-level warning threshold is set, which includes normal, safety warning, risk warning and emergency warning. The deviation between the predicted trend curve and the warning threshold is calculated. When any point of the predicted trend curve exceeds the safety warning threshold, the corresponding level of warning information is triggered. The graded warning information is pushed to the monitoring center using the preset communication network, and a detailed deformation trend report is attached according to the warning level.

8. A dam deformation monitoring and early warning system based on Beidou and machine vision, characterized in that: The system comprises: The data acquisition module is used to collect the original displacement data of the dam in real time through the Beidou receiver and to collect the original image data of the dam surface using the monitoring equipment; A data processing module is used to perform RTK differential processing and weighted averaging of multi-point positioning data on the original displacement data to obtain dam displacement data, and to perform multispectral analysis and deep learning processing on the original image data to obtain dam surface structure feature data; A deformation analysis module is used to perform local processing on the dam displacement data using an edge computing algorithm to obtain real-time displacement change data, and to perform parallel processing on the dam surface structure feature data using a distributed computing method to obtain real-time deformation feature data; A data fusion module, used for dynamically fusing the real-time displacement change data and the real-time deformation feature data based on a Kalman filter algorithm to obtain comprehensive deformation data; The monitoring and early warning module is used to establish a dam deformation trend prediction model based on the comprehensive deformation data, set multi-level early warning thresholds, and push graded early warning information to the monitoring center when abnormal deformation is detected.

9. An electronic device, characterized in that: include: at least one processor, at least one memory, a communication interface, and a bus; The processor, memory, and communication interface communicate with each other via the bus, the memory stores program instructions executable by the processor, and the processor calls the program instructions to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions enable a computer to implement the method according to any one of claims 1 to 7.

Images