Anchor-anchored diaphragm wall measuring point anomaly identification and global deformation three-dimensional visualization method and system

Abstract

The application discloses a kind of anchor ground diaphragm wall measuring point anomaly identification and global deformation three-dimensional visualization method and system, method includes: displacement sensor is arranged on anchor ground diaphragm wall, form three-dimensional monitoring array of uniform distribution, and the anchor ground diaphragm wall monitoring system including this three-dimensional monitoring array is built;Anchor ground diaphragm wall monitoring system network time synchronization;Real-time acquisition of the data of various sensors on ground diaphragm wall and upload to cloud monitoring database;Ground diaphragm wall is divided into grid structure, and discrete monitoring data is expanded into high-density grid data by interpolation algorithm, realize the displacement simulation of global high accuracy of ground diaphragm wall;For the abnormal data that appears, automatically eliminate;Ground diaphragm wall deformation three-dimensional visualization.The application more accurately reflects the overall deformation state of anchor ground diaphragm wall, and by anomaly value detection mode, eliminate abnormal data, improve the reliability of monitoring data;Solve the problem that traditional monitoring data is difficult to intuitively reflect the spatial deformation characteristics of ground diaphragm wall.

Description

Technical Field

[0001] This invention relates to the field of civil engineering monitoring and visualization technology, and in particular to a method, system, and storage medium for anomaly identification and three-dimensional visualization of full-domain deformation of anchored diaphragm wall measuring points. Background Technology

[0002] Deep foundation pit engineering is a crucial component of bridge construction, and its scale and number are constantly increasing with the ongoing urbanization process. Diaphragm walls are the most widely used form of support structure for deep foundation pits, offering advantages such as convenient construction, excellent water-stopping effect, and high rigidity. However, diaphragm walls are also among the highest-risk components in deep foundation pit engineering, with complex stress states and deformation directly impacting the safety of the entire pit. Traditional automated monitoring methods for diaphragm walls primarily use inclinometer integration to obtain horizontal displacement. While this method can acquire deformation within the wall, the scattered distribution of monitoring points makes it difficult to comprehensively reflect the overall deformation state of the diaphragm wall. Furthermore, the monitoring data lacks intuitive visualization, hindering engineers from quickly assessing structural safety.

[0003] In recent years, with the rapid development of new-generation information technologies such as the Internet of Things, big data, and cloud computing, real-time acquisition of structural deformation data through inclinometers and subsequent data analysis for comprehensive and dynamic monitoring of diaphragm walls has become a research hotspot in the field of deep foundation pit engineering. However, traditional planar display panels of monitoring data are insufficient to intuitively reflect the spatial deformation characteristics of diaphragm walls, and data anomalies often affect decision-making during construction. There is an urgent need to develop a three-dimensional visualization method suitable for diaphragm wall structures, capable of transforming massive amounts of monitoring data into intuitive three-dimensional scenes, providing engineers with more intelligent and efficient safety management tools. This research aims to achieve key technologies such as multi-source heterogeneous data fusion, real-time performance monitoring, and three-dimensional visual presentation for diaphragm walls, providing new solutions for the safety of deep foundation pit engineering. Summary of the Invention

[0004] In view of the above-mentioned defects or improvement needs of the existing technology, the present invention aims to solve the problem that traditional monitoring data flat display boards are difficult to intuitively reflect the spatial deformation characteristics of diaphragm walls, and are difficult to comprehensively reflect the overall deformation state of diaphragm walls. At the same time, the monitoring data lacks intuitive visualization, and abnormal data states often affect decision-making during the construction process.

[0005] This invention provides a method for identifying anomalies at measuring points and visualizing three-dimensional deformation across the entire area in a diaphragm wall anchorage, comprising the following steps:

[0006] Step S1. Sensor arrangement: Displacement sensors are arranged on the anchor diaphragm wall to form a uniformly distributed three-dimensional monitoring array along the horizontal and vertical directions, and an anchor diaphragm wall monitoring system including the three-dimensional monitoring array is constructed.

[0007] Step S2. Network time synchronization of the anchorage diaphragm wall monitoring system: Time synchronization of each node of the anchorage diaphragm wall monitoring system in step S1;

[0008] Step S3. Data Acquisition and Upload: Collect data from various sensors on the ground-mounted wall in real time and upload it to the cloud monitoring database;

[0009] Step S4. Global Displacement Simulation of the Diaphragm Wall: (Global displacement means the entire diaphragm wall): The Thin Plate Spline (TPS) interpolation method is used to fit the discrete monitoring data by minimizing the energy functional, and the observed value r(x) is obtained. i ,y i ,z i The corresponding estimation function f is used to divide the diaphragm wall into a grid structure. The discrete monitoring data is expanded into high-density grid data of the entire area through the estimation function f, so as to realize virtual sensing on the surface of the diaphragm wall.

[0010] Step S5. Abnormal Sensor Data Removal: Perform residual analysis on the high-density grid data in Step S4 to identify and remove abnormal sensor data. If there are abnormalities, remove the abnormal data; otherwise, proceed directly to the next step.

[0011] Step S6. 3D visualization of diaphragm wall deformation: Render the data processed in step S5 into an interactive 3D heat map with overlaid color markers, and perform various operations and information queries.

[0012] Furthermore, the specific method of step S2 includes: establishing a unified time reference and synchronizing the system clocks of each displacement sensor node, the aggregation node, and the database server through the NTP (Network Time Protocol) to achieve time synchronization of the distributed monitoring network.

[0013] Furthermore, the specific method of step S3 includes: collecting data from various sensors on the ground-mounted wall in real time, using wireless sensor network technology based on the ZigBee protocol to encapsulate the monitoring data into a unified data frame format, and uploading it to the cloud monitoring database in real time.

[0014] Furthermore, step S3 also includes dynamically adjusting the sampling frequency of each sensor based on the data change rate and signal characteristics, so as to reduce data redundancy and energy consumption while ensuring information integrity.

[0015] Furthermore, step S3 also includes attaching a timestamp tag to the data frame to record the data acquisition time. An adaptive data acquisition strategy is designed to address the differences in sampling frequencies among different sensors.

[0016] Furthermore, the method of using Thin Plate Spline (TPS) interpolation in step S4 to fit discrete monitoring data by minimizing the energy functional includes:

[0017] (1) At a certain point in time, suppose there are n sensor observations r(x) on the diaphragm wall. i ,y i ,z i ):

[0018] r(x i ,y i ,z i )=f(x i ,y i ,z i )+ε(x i ,y i ,z i ), i = 1, 2, ..., n (1)

[0019] In the formula, f is the observed value r(x) i ,y i ,z i The corresponding estimation function is ε, which is the estimation error, a zero-mean, uncorrelated random error; (x) i ,y i ,z i () represents Euclidean coordinates;

[0020] (2) To make the estimated function f as close as possible to the observed value, the energy function ξ(f) should be as small as possible:

[0021] ξ(f)=E d (f)+λE(f) (2)

[0022]

[0023] In the formula, λ is a smoothing parameter that can balance and control the deformation stiffness E. d (f) and the smoothness E(f) of the fitted surface.

[0024] Further, the method in step S4 of dividing the diaphragm wall into a grid structure and expanding the discrete monitoring data into high-density grid data using the estimation function f includes: dividing the diaphragm wall into a grid structure in a virtual coordinate system, and using the estimation function f... f The displacement value of each grid point is calculated, and the grid data is uploaded to the cloud database of the anchor diaphragm wall monitoring system for archiving in a timely manner; thus realizing high-density virtual sensing on the surface of the diaphragm wall.

[0025] Furthermore, the method for removing abnormal sensor data in step S5 includes:

[0026] (1) Estimate the values ​​of all monitoring points based on the thin plate spline interpolation function f established in step S3;

[0027] (2) Compare the estimated value with the measured value point by point and calculate the residual at each monitoring point;

[0028] (3) The mean μ and standard deviation σ of the statistical residuals;

[0029] (4) Monitoring points with residual absolute values ​​exceeding μ+2σ are marked as suspected anomalies;

[0030] (5) Remove the identified abnormal sensor data, record the abnormal sensors, and reconstruct the thin plate spline interpolation function f;

[0031] (6) Repeat (1)-(5) until no new anomalies appear, and finally confirm the interpolation function and the list of abnormal sensors.

[0032] Furthermore, the three-dimensional visualization method for diaphragm wall deformation in step S6 includes:

[0033] (1) Return the obtained data to the front end in JSON format;

[0034] (2) The front end sends a request via AJAX or Fetch.API to obtain the (x, y, z) coordinates of the monitoring point and its corresponding deformation value;

[0035] (3) Use Plotly.js to render a 3D heatmap;

[0036] (4) On the heat map, a red mark is superimposed at each monitoring point to indicate the location of the sensor;

[0037] (5) Use scatter3d layers to render sensor points separately, clearly mark the sensor positions, and support mouse interaction;

[0038] (6) Customize the content displayed when hovering using hoverinfo and hovertemplate so that detailed information about each sensor can be queried.

[0039] As another aspect of the present invention, it also relates to an anchor diaphragm wall anomaly identification and three-dimensional visualization device, including an anchor diaphragm wall monitoring system network time synchronization unit, a data acquisition and uploading unit, a discrete monitoring data expansion unit, an anomaly sensor data rejection unit, and a diaphragm wall deformation three-dimensional visualization unit.

[0040] The network time synchronization unit of the anchorage-connected wall monitoring system is used to synchronize the time of each node of the anchorage-connected wall monitoring system.

[0041] The data acquisition and uploading unit is used to collect, process, and store the raw sensor data of the anchorage diaphragm wall monitoring system;

[0042] The discrete monitoring data extension unit is used to fit the discrete monitoring data by minimizing the energy functional using the Thin Plate Spline (TPS) method to obtain the observed value r(x). i ,y i ,z i The corresponding estimation function f is used to divide the diaphragm wall into a grid structure. The discrete monitoring data is expanded into high-density grid data through the estimation function f, thereby realizing virtual sensing on the surface of the diaphragm wall.

[0043] The abnormal sensor data removal unit is used to perform residual analysis on the high-density grid data of the anchorage wall monitoring system, and to identify and remove abnormal sensor data.

[0044] The 3D visualization unit for diaphragm wall deformation is used to construct a 3D visualization model of the anchored diaphragm wall monitoring system.

[0045] As another aspect of the present invention, a computer-readable storage medium is also disclosed, on which a computer program is stored, which is executed by a processor as a method for monitoring and three-dimensional visualization of diaphragm wall deformation in large-scale foundation pit engineering.

[0046] In summary, compared with the prior art, the above-described technical solutions conceived by this invention can achieve the following beneficial effects:

[0047] (1) The method for identifying anomalies at measuring points and three-dimensional visualization of overall deformation of anchored diaphragm walls of the present invention provides a comprehensive monitoring method for the three-dimensional detection array method for anchored diaphragm wall structures, compared with the traditional method of using inclinometer tube integration to obtain horizontal displacement in automated monitoring of anchored diaphragm walls. This method can more accurately reflect the overall deformation state of the anchored diaphragm wall.

[0048] (2) The anchor diaphragm wall measuring point anomaly identification and full-domain deformation three-dimensional visualization method of the present invention is designed for the massive data collected from the structure of the anchor diaphragm wall. During the collection and processing process, the sampling frequency is dynamically adjusted to optimize the data collection process and reduce energy consumption. Abnormal data is eliminated through two abnormal value detection methods, which improves the reliability of monitoring data and avoids the problem that abnormal data status often affects decision-making during the construction process.

[0049] (3) The anchored diaphragm wall measuring point anomaly identification and full-domain deformation three-dimensional visualization method of the present invention, by constructing a three-dimensional visualization method for anchored diaphragm wall structure deformation, can transform massive monitoring data into intuitive and vivid three-dimensional scenes, providing engineers with more intelligent and efficient safety management methods. It solves the problem that traditional monitoring data planar display boards cannot intuitively reflect the spatial deformation characteristics of diaphragm walls. Attached Figure Description

[0050] Figure 1 This is a schematic diagram of the overall process of a preferred embodiment of the present invention;

[0051] Figure 2 This is a top view schematic diagram of the three-dimensional monitoring array of the anchored ground-connected wall according to a preferred embodiment of the present invention;

[0052] Figure 3 This is a schematic diagram of the inclinometer tube side of a preferred embodiment of the present invention;

[0053] Figure 4 This is a schematic diagram comparing the presence or absence of outliers in the data during outlier detection in a preferred embodiment of the present invention.

[0054] Figure 5 A comparative schematic diagram showing the change of three-dimensional behavior of the diaphragm wall horizontal displacement structure over time in a preferred embodiment of the present invention; Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. Furthermore, the technical features involved in the various embodiments of this invention described below can be combined with each other as long as they do not conflict with each other.

[0056] Please refer to Figures 1-3 The present invention provides a method for identifying anomalies at measuring points and visualizing three-dimensional deformation across the entire area of ​​a diaphragm wall anchorage, comprising:

[0057] (1) Deployment of multi-source heterogeneous sensors:

[0058] Various types of displacement sensors (such as fiber optic grating sensors can also be used to improve monitoring accuracy and stability, and to achieve distributed monitoring for more comprehensive deformation information) are rationally arranged on the diaphragm wall to form a uniformly distributed three-dimensional monitoring array along the horizontal and vertical directions. In this embodiment, taking a circular foundation pit as an example, at least 12-20 holes (e.g., 16 holes, P1 to P16) are evenly spaced on the diaphragm wall of the circular foundation pit. An inclinometer tube is placed in each hole, with the depth of the inclinometer tube consistent with the diaphragm wall structure. The guide groove of the inclinometer tube is perpendicular to the edge of the foundation pit and points towards the center of the pit. The sensor acquisition frequency is 1 time / hour.

[0059] (2) Data acquisition, uploading, and spatiotemporal data interpolation extension:

[0060] A unified time reference is established, and the system clocks of each sensor node, aggregation node, and database server are synchronized through the NTP (Network Time Protocol) to achieve time synchronization of the distributed network. In some other embodiments, high-precision satellite time synchronization technology can also be used to ensure that the time error of each sensor node is controlled within a smaller range.

[0061] The system collects data in real time from various sensors attached to the wall. Utilizing ZigBee-based wireless sensor network technology, the monitoring data is encapsulated into a unified data frame format and uploaded to a cloud-based monitoring database in real time. In some embodiments, an automatic backup module can be configured during data acquisition and upload. This module monitors the data transmission status in real time. When a network failure or other situation that may lead to data loss is detected, local caching is immediately initiated. The collected data is stored in a reliable local storage device with a specific format and timestamp, while also recording relevant acquisition node information and original path information. After the network returns to normal, the locally cached data is re-uploaded to the cloud-based monitoring database according to time sequence and data integrity verification mechanisms. Data comparison and fusion are then performed to ensure data continuity and integrity.

[0062] A timestamp is appended to the data frame to record the data acquisition time. An adaptive data acquisition strategy is designed to address the differences in sampling frequencies among different sensors. Based on the data change rate and signal characteristics, the sampling frequency of each sensor is dynamically adjusted to reduce data redundancy and energy consumption while ensuring information integrity.

[0063] Please refer to Figure 4 The raw data uploaded to the monitoring database may contain outliers and noise, requiring preliminary processing to improve data quality. The statistically based 3σ principle is used for outlier detection. For each monitoring indicator, the mean μ and standard deviation σ of its time series data are calculated. Data points exceeding the range of μ ± 3σ are marked as outliers and replaced with linear interpolation using the normal values ​​at the preceding and following time points. The 3σ principle, based on the assumption that the data follows a normal distribution, can identify the vast majority of random anomalies.

[0064] For a small number of deterministic anomalies (such as continuous anomalies caused by sensor failure), the correlation and constraint relationships between monitored quantities can be utilized in the next step to further improve the accuracy of anomaly identification. The Thin Plate Spline (TPS) interpolation method is introduced to fit discrete monitoring data by minimizing the energy functional, generating virtual sensing data. Compared to other interpolation methods, TPS can reflect the physical characteristics of surface changes, exhibiting smooth and continuous characteristics, making it suitable for discrete point interpolation.

[0065] Assume that at a certain point in time, the diaphragm wall has n sensor observations r(x) i ,y i ,z i This can be expressed as follows:

[0066] r(x i ,y i ,z i )=f(x i ,y i ,z i )+ε(x i ,y i ,z i ), i = 1, 2, ..., n (1)

[0067] In the formula, f is the observed value r(x) i ,y i ,z i The corresponding estimation function is ε, which is the estimation error, a zero-mean, uncorrelated random error; (x) i ,y i ,z i ) is a Euclidean coordinate system.

[0068] To make the estimated function f as close as possible to the observed value, the energy function ξ(f) should be as small as possible:

[0069] ξ(f)=E d (f)+λE(f) (2)

[0070]

[0071] In the formula, λ is a smoothing parameter that can balance and control the deformation stiffness E. d (f) and the smoothness E(f) of the fitted surface.

[0072] Please refer to Figure 5In this embodiment, the diaphragm wall can be divided into multiple parts vertically and circumferentially, for example, 25 parts vertically and 180 parts circumferentially, with a grid size of approximately 2.5m × 2.5m. Using the estimation function f, the displacement values ​​of 24 * 179 = 4296 grid points can be calculated, realizing high-density virtual sensing on the surface of the diaphragm wall. The grid data is uploaded to the database for archiving in a timely manner after calculation. Figure 5 After implementing the expansion of discrete monitoring data into high-density grid data across the entire area (left side is before implementation, right side is after implementation), the color distribution of displacement changes spreads across the entire ground diaphragm wall.

[0073] (3) Abnormal sensor data removal

[0074] The values ​​at all monitoring points are estimated using the estimation function f, and the estimated values ​​are compared with the measured values ​​point by point. The residual ε(x) at each monitoring point is then calculated. i ,y i ,z i ).

[0075] The mean μ and standard deviation σ of the statistical residuals are distributed. Monitoring points with an absolute residual value exceeding μ+2σ are marked as suspected anomalies. Data from the identified abnormal sensors are removed. The estimation function f (thin plate spline interpolation function) is reconstructed, and the residual distribution of all monitoring points is recalculated until no new anomalies appear. Finally, the interpolation function and the list of abnormal sensors are determined.

[0076] In some other embodiments, multi-dimensional statistical analysis can also be performed on the collected sensor data. First, statistical measures such as the mean, median, and mode of each data point are calculated to obtain the central tendency characteristics of the data. Second, the variance and standard deviation of the data are analyzed to assess the dispersion of the data. Then, for data from different time periods, data distribution histograms or frequency distribution curves are constructed to observe the data distribution pattern. By setting a reasonable threshold range, based on statistical measures and distribution characteristics, data points exceeding the normal range are identified. Combined with residual analysis and other methods, anomalies in the sensor data are comprehensively judged, improving the accuracy and reliability of anomaly identification.

[0077] (4) Three-dimensional interactive operation

[0078] To achieve 3D web visualization of diaphragm wall deformation, predicted grid point data and measured data from monitoring points are retrieved from the database, and the query results are returned to the front end in JSON format. The front end then sends a request via AJAX or the Fetch API to obtain the (x, y, z) coordinates of the monitoring points and their corresponding deformation values, and finally uses Plotly.js to render a 3D heatmap.

[0079] Specifically, the 3D model is rendered using a mesh3d layer in Plotly.js, and the deformation value of each monitoring point is mapped to a color using the intensity property, with rendering performed using a continuous color spectrum (Viridis). Users can view different angles of the 3D model by rotating, scaling, and panning. The system also provides interactive functionality, allowing users to hover over or click on a point to display its specific displacement data.

[0080] Building upon the heatmap, the system can further overlay red markers at each monitoring point to indicate the sensor's location. By using a scatter3d layer to render these sensor points individually, the red dots not only clearly mark the sensor's location but also support mouse interaction. When the user moves the mouse over a red dot, a pop-up displaying the sensor's number and corresponding monitoring point information will appear. To enhance the interactive experience, the system allows customization of the content displayed on hover using hoverinfo and hovertemplate, enabling users to quickly query detailed information for each sensor.

[0081] Those skilled in the art will readily understand that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for identifying anomalies at measuring points and performing three-dimensional visualization of full-domain deformation in diaphragm anchorage walls, characterized in that: Includes the following steps: Step S1. Displacement sensors are arranged on the anchor diaphragm wall to form a uniformly distributed three-dimensional monitoring array along the horizontal and vertical directions, and an anchor diaphragm wall monitoring system including the three-dimensional monitoring array is constructed. Step S2. Synchronize the time of each node in the anchorage diaphragm wall monitoring system from step S1; Step S3. Collect data from various sensors on the ground-mounted wall in real time and upload it to the cloud monitoring database; Step S4. Using the thin-plate spline interpolation method, the discrete monitoring data are fitted by minimizing the energy functional to obtain the observed values. Corresponding estimation function The diaphragm wall is divided into a grid structure, and the function is estimated. Expand discrete monitoring data into high-density grid data to achieve virtual sensing of the diaphragm wall surface; Step S5. Perform residual analysis on the high-density grid data from step S4 to identify and remove abnormal sensor data; Step S6. Render the data processed in step S5 into an interactive 3D heatmap with overlaid color markers, and perform various operations and information queries. Step S4 employs a thin-plate spline interpolation method, which involves minimizing the energy functional to fit the discrete monitoring data. This method includes: S41: At a certain point in time, suppose there are n sensor observations on the diaphragm wall. : (1) In the formula Observed values The corresponding estimation function; It is the estimation error, which is a zero-mean, uncorrelated random error; It is a Euclidean coordinate system; S42: Makes the estimated function The energy function is the closest it can get to the observed value. It should be: (2) (3) (4) In the formula To smooth the parameters, the deformation stiffness can be controlled in a balanced manner. Smoothness of the fitted surface .

2. The method for identifying anomalies at anchorage diaphragm wall measuring points and for three-dimensional visualization of full-domain deformation according to claim 1, characterized in that: The specific methods for step S2 include: A unified time reference is established, and the system clocks of each displacement sensor node, the aggregation node, and the database server are synchronized through the NTP protocol to achieve time synchronization of the distributed monitoring network.

3. The method for identifying anomalies at anchorage diaphragm wall measuring points and for three-dimensional visualization of full-domain deformation according to claim 1, characterized in that: The specific methods for step S3 include: Data from various sensors on the ground-mounted wall is collected in real time. Using wireless sensor network technology based on the ZigBee protocol, the monitoring data is encapsulated into a unified data frame format and uploaded to the cloud monitoring database in real time.

4. The method for identifying anomalies at anchorage diaphragm wall measuring points and for three-dimensional visualization of full-domain deformation according to claim 3, characterized in that: Step S3 also includes attaching a timestamp label to the data frame to record the data acquisition time, and designing an adaptive data acquisition strategy to address the differences in sampling frequencies of different sensors.

5. The method for identifying anomalies at anchorage diaphragm wall measuring points and performing three-dimensional visualization of full-domain deformation according to claim 1, characterized in that, In step S4, the diaphragm wall is divided into a mesh structure, and the estimation function is used to... Methods for expanding discrete monitoring data into high-density grid data include: dividing the diaphragm wall into a grid structure in a virtual coordinate system, and using an estimation function. The displacement value of each grid point is calculated, and the grid data is uploaded to the cloud database of the anchor diaphragm wall monitoring system for archiving in a timely manner; thus realizing high-density virtual sensing on the surface of the diaphragm wall.

6. The method for identifying anomalies at measuring points and performing three-dimensional visualization of full-domain deformation in diaphragm walls according to any one of claims 1-4, characterized in that, The method for removing abnormal sensor data in step S5 includes: (1) Based on the estimation function established in step S3 Estimate the values ​​of all monitoring points; (2) Compare the estimated value with the measured value point by point, and calculate the residual for each monitoring point; (3) The mean μ and standard deviation σ of the statistical residuals; (4) Monitoring points with residual absolute values ​​exceeding μ+2σ are marked as suspected anomalies; (5) Remove the identified abnormal sensor data, record the abnormal sensors, and reconstruct the estimation function. ; (6) Repeat (1)-(5) until no new anomalies appear, and finally confirm the interpolation function and the list of abnormal sensors.

7. The method for identifying anomalies at measuring points and performing three-dimensional visualization of full-domain deformation in diaphragm walls according to any one of claims 1-4, characterized in that, The three-dimensional visualization method for diaphragm wall deformation in step S6 includes: (1) Return the obtained data to the front end in JSON format; (2) The front end sends a request via AJAX or Fetch.API to obtain the (x, y, z) coordinates of the monitoring point and its corresponding deformation value; (3) Render a 3D heatmap using Plotly.js; (4) On the heat map, a red marker is superimposed at each monitoring point to indicate the location of the sensor; (5) Use scatter3d layers to render sensor points separately, clearly mark the sensor positions, and support mouse interaction; (6) Customize the content displayed when hovering through hoverinfo and hovertemplate so that detailed information about each sensor can be queried.

8. A system for identifying and visualizing anomalies in diaphragm anchorage walls in three dimensions, characterized in that: The network time synchronization unit is used to synchronize the time of each node in the anchorage diaphragm wall monitoring system. The data acquisition and uploading unit is used to collect, process, and store the raw sensor data of the anchorage diaphragm wall monitoring system. Discrete monitoring data extension unit, used to fit discrete monitoring data and obtain observation values ​​by minimizing the energy functional using the thin-plate spline interpolation method. Corresponding estimation function The diaphragm wall is divided into a grid structure, and the function is estimated. Expand discrete monitoring data into high-density grid data to achieve virtual sensing of the diaphragm wall surface; The abnormal sensor data removal unit is used to perform residual analysis on the high-density grid data of the anchorage diaphragm wall monitoring system, and to identify and remove abnormal sensor data. The 3D visualization unit for diaphragm wall deformation is used to construct a 3D visualization model of the anchored diaphragm wall monitoring system. The thin-plate spline interpolation method is used in the discrete monitoring data extension unit. Methods for fitting discrete monitoring data by minimizing the energy functional include: S41: At a certain point in time, suppose there are n sensor observations on the diaphragm wall. : (1) In the formula Observed values The corresponding estimation function; It is the estimation error, which is a zero-mean, uncorrelated random error; It is a Euclidean coordinate system; S42: Makes the estimated function The energy function is the closest it can get to the observed value. It should be: (2) (3) (4) In the formula To smooth the parameters, the deformation stiffness can be controlled in a balanced manner. Smoothness of the fitted surface .

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer program is executed by a processor using the method for anomaly identification and three-dimensional visualization of global deformation of anchored diaphragm wall measuring points as described in any one of claims 1-7.

Images