Digital twin and GIS fusion system

Abstract

The invention discloses a digital twinning and GIS fusion system. The system comprises a data acquisition module, a coordinate conversion module, a data fusion module, a visualization and analysis module and a user interaction module. The data acquisition module acquires GIS spatial data, the coordinate conversion module performs coordinate conversion on the acquired data, the data fusion module is used for fusing digital twin data after coordinate conversion and the GIS spatial data, and the visualization and analysis module is used for analyzing the fused data. And the user interaction module receives the data processed by the visualization and analysis module. According to the invention, through the coordinate conversion module, the consistency of the digital twin model and the GIS spatial data is ensured. And the data fusion module can integrate the digital twin data and the GIS data, so that the availability of the data is improved. The visualization and analysis module can analyze fused data in real time, provide accurate and timely information, and help a user to quickly identify potential problems.

Description

Technical Field

[0001] The present invention belongs to the fields of digital twin technology and geographic information technology, and specifically relates to a digital twin and GIS integration system. Background Art

[0002] In recent years, with the rapid development of Internet of Things (IoT), big data, and cloud computing technologies, digital twin technology has gradually become an important tool in various industries. Digital twin refers to creating a virtual model of a real-world object or system through digital means to achieve real-time monitoring and analysis of its state, behavior, and performance. In this context, more and more research and practices have begun to attempt to combine digital twin with Geographic Information System (GIS) technology to improve the intelligent level of urban management and services.

[0003] In the prior art, for example, the technical solution described in the patent with the publication number CN118424315A: A system and method for intelligent path guidance in a park based on digital twin, including a data acquisition module that acquires monitoring information of a set area and road information of the set area, preprocesses and cleans the acquired road information, a model construction module that converts the obtained geographic information data and building information data into a three-dimensional digital twin model; an object positioning module that acquires the three-dimensional position information of an object in the set area; and a path planning module that performs path planning for the set area based on the monitoring information of the set area and the converted three-dimensional digital twin model and outputs a path planning route.

[0004] In the prior art, when digital twin and GIS systems perform coordinate transformation, errors are likely to occur, affecting the accuracy of data and the reliability of the model. Especially in a large-scale geographic area, the error accumulation will be more obvious. Although digital twin and GIS respectively process spatial and physical data, there is a lack of effective integration between the two, resulting in limitations in the analysis results of data. Summary of the Invention

[0005] The purpose of the present invention is to provide a digital twin and GIS integration system to solve the problem in the prior art described in the background art that when digital twin and GIS systems perform coordinate transformation, errors are likely to occur, affecting the accuracy of data and the reliability of the model.

[0006] To solve the above technical problems, the technical solution adopted by the present invention is: A digital twin and GIS integration system includes a data acquisition module, a coordinate conversion module, a data fusion module, a visualization and analysis module, and a user interaction module; among them, the data acquisition module collects GIS spatial data and transfers the GIS spatial data to the coordinate conversion module, and the coordinate conversion module performs coordinate conversion on the collected data to ensure the matching of the digital twin model and the GIS spatial data; the data fusion module is used to fuse the digital twin data and the GIS spatial data after coordinate conversion, and optimize the data to unify the format. The visualization and analysis module is used to analyze the fused data and use the analysis results of the data for further processing and visualization; the user interaction module receives the data processed by the visualization and analysis module and displays the data to the user for real-time interaction feedback and decision support.

[0007] According to the above technical solution, the coordinate conversion module converts between the digital twin model and the GIS geographic data, including the following steps: First, the coordinate conversion module uses a conversion function to convert the spherical coordinates of the earth into UTM plane coordinates. Specifically, by calculating the east-west plane coordinates and the north-south plane coordinates respectively, the spherical coordinates are converted into UTM plane coordinates. Then, based on the earth ellipsoid parameters, the conversion is performed to complete the conversion operation from longitude and latitude to the corresponding UTM plane coordinates: by combining the curvature radius corresponding to different latitudes and the change of the meridian arc length, the geographical spatial position represented by the longitude and latitude is converted into the accurate position corresponding to the plane coordinates, thus completing the conversion.

[0008] According to the above technical solution, the data fusion module fuses the spatial data of the digital twin and GIS, and the fusion adopts the intelligent weighted average method. Specifically: Among them, is the result after fusion, is the measurement value of the th data source, is the weight of the th data source, is the number of data sources.

[0009] According to the above technical solution, to optimize the fused data, a support vector machine is used to optimize the data, including the objective function for the linearly separable problem and the objective function for the non-linearly separable problem: For the linearly separable problem, the objective function: such that: Among them, is the normal vector of the hyperplane, is the bias; is the th input data; is the th data label.

[0010] According to the above technical solution, for the non-linearly separable problem, by introducing a kernel function, the data is mapped to a high-dimensional space for processing, and the following optimization problem is obtained: such that: wherein, is the normal vector of the hyperplane, is the regularization parameter, is the slack variable, used to handle misclassified data, is the kernel function, is the bias, is the th input data.

[0011] According to the above technical solution, the visualization and analysis module realizes the display and intelligent analysis of multi-dimensional data by integrating data analysis and visualization tools; the data analysis is realized through principal component analysis, specifically: Calculate the covariance matrix of the data set: wherein, is the data sample, is the sample mean, is the covariance matrix; perform eigenvalue decomposition on the covariance matrix to obtain eigenvectors and eigenvalues: , wherein, is the eigenvector, is the eigenvalue.

[0012] According to the above technical solution, the visualization is presented through a heat map, and the heat map shows the magnitude or distribution of values through different color codings. The depth of the color represents the high or low of the value, indicating the intensity, trend or correlation of the data.

[0013] According to the above technical solution, the user interaction module is used to provide an interface that supports user interaction. The user can interact with the digital twin model and GIS geographic data through operations such as dragging and zooming, view the device and environmental status in real time, and generate an analysis report as needed.

[0014] According to the above technical solution, the system further includes a real-time data update module, which is used to collect data from the data source in real time and perform noise suppression and data update through the Kalman filtering algorithm to ensure that the data of the digital twin model and the GIS system are always consistent.

[0015] According to the above technical solution, the Kalman filtering algorithm is specifically as follows: State equation: Where, represents the system state, and represents the state vector of the system at time; This term represents the influence of the system control input on the state; is the state transition matrix, which describes the state change law of the system from time to time ; Observation equation: represents the observation vector at time , is the observation matrix; is the observation noise vector, represents the system state.

[0016] Compared with the prior art, the present invention has the following beneficial effects: In the present invention, through the coordinate conversion module, the consistency between the digital twin model and the GIS spatial data is ensured. The accurate matching of the data in the present invention can effectively reduce decision-making errors caused by data inconsistency. The data fusion module can integrate the digital twin data and the GIS data together and optimize the format to improve the usability of the data. This enables data from different sources to be analyzed on the same platform, enhancing the overall value of the data. The visualization and analysis module can analyze the fused data in real time, provide accurate and timely information, help users quickly identify potential problems or opportunities, and support immediate decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a schematic diagram of the fusion of the digital twin and GIS of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0018] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0019] Embodiment 1 As Figure 1 shown, a digital twin and GIS fusion system includes a data acquisition module, a coordinate conversion module, a data fusion module, a visualization and analysis module, and a user interaction module; wherein, the data acquisition module collects GIS spatial data and transmits the GIS spatial data to the coordinate conversion module, and the coordinate conversion module performs coordinate conversion on the collected data to ensure the matching of the digital twin model and the GIS spatial data; the data fusion module is used to fuse the digital twin data and the GIS spatial data after coordinate conversion, and optimize the data to unify the format. The visualization and analysis module is used to analyze the fused data and use the analysis results of the data for further processing and visualization; the user interaction module receives the data processed by the visualization and analysis module and displays the data to the user for real-time interaction feedback and decision support.

[0020] In the present invention, through the coordinate conversion module, the consistency between the digital twin model and the GIS spatial data is ensured. The accurate matching of the data in the present invention can effectively reduce decision-making errors caused by data inconsistency. The data fusion module can integrate the digital twin data and the GIS data together and optimize the format to improve the usability of the data. This enables data from different sources to be analyzed on the same platform, enhancing the overall value of the data. The visualization and analysis module can analyze the fused data in real time, provide accurate and timely information, help users quickly identify potential problems or opportunities, and support immediate decision-making.

[0021] In the present invention, the user interaction module displays the analysis results through an intuitive interface, allowing users to perform real-time interaction and feedback. This highly interactive design can enhance user participation and satisfaction, enabling users to better understand and utilize the data. Through real-time data analysis and visualization, managers and decision-makers can better plan and manage, improve resource utilization efficiency, reduce risks, and optimize operation strategies.

[0022] Since the system can integrate data from different departments, cross-departmental collaboration and communication become smoother, contributing to the formation of an overall solution.

[0023] Embodiment 2 This embodiment provides a specific implementation method.

[0024] The coordinate conversion module converts between the digital twin model and GIS geographic data, including the following steps: In such a fusion system, the coordinate conversion module plays a key bridging role. It is responsible for converting the coordinate system used by the digital twin model to the coordinate system of GIS geographic data, so that the two can achieve seamless fusion under a unified coordinate framework. The process of converting from longitude and latitude to plane coordinates is as follows: The conversion from longitude and latitude to plane coordinates includes the following steps: Step 1: Define the representation of geographic coordinates: First, set the geographic coordinates to be represented by , where represents latitude represents longitude. This is the starting data basis for the entire conversion, and all subsequent calculations and conversion operations are carried out around these two basic geographic coordinate parameters.

[0025] Step 2: Use the conversion function to generate UTM plane coordinates: The principle is to realize the transformation from the spherical coordinate form of longitude and latitude to the plane coordinate form based on the relevant geometric characteristics of the earth and pre-set projection rules, etc. In the process of converting from longitude and latitude to UTM plane coordinates, the conversion formula: Let the geographic coordinates be , where represents latitude, represents longitude. The UTM plane coordinates to be converted are represented by .

[0026] Step 201, calculate the east-west coordinate (based on the relevant principles of the Universal Transverse Mercator projection UTM): Among them, is the scale factor, which is used to reasonably scale and adjust the coordinate values to meet specific projection accuracy and range requirements, etc. Since different application scenarios have different requirements for the accuracy and range of map projections, for example, in the detailed analysis of a local area at a large scale, a smaller value may be required to ensure coordinate accuracy so that it can accurately reflect the relative position relationship of geographic features on the plane; while in the display of a large area at a small scale, a suitable value can ensure the reasonable presentation of the overall area on the plane, and will not cause problems such as too large or too small coordinate values that are not conducive to data processing and display.

[0027] is dependent on the latitude The meridian arc length function, which is usually a function expression of latitude derived based on the parameters of the earth ellipsoid and the geometric relationships related to the meridian, is used to reflect the influence of the meridian arc length at different latitudes on the calculation of the east-west coordinates. The earth is an approximate ellipsoid, and the meridian arc lengths at different latitudes are different. This function incorporates the changes in the meridian arc length caused by the geometric shape of the earth into the calculation. It can accurately calculate the contribution of the length factor in the meridian direction to the east-west coordinates according to the specific latitude, so that the converted coordinates can accurately reflect the position of geographical features in the east-west direction relative to the central meridian, ensuring that the plane coordinates after the projection transformation conform to the actual spatial characteristics of the earth.

[0028] , is the longitude of the central meridian, and the longitude difference is used to determine the positional relationship of the current coordinate point relative to the central meridian, so as to accurately determine its plane coordinate position in the east-west direction in the projection. And the subsequent high-order term expansion is to more accurately approximate the actual projection transformation situation, considering the subtle influence brought by different powers of the longitude difference and comprehensively calculating in combination with the latitude factor.

[0029] Step 202, calculate the north-south coordinate y (also based on the relevant principles of the Universal Transverse Mercator projection UTM): Here is the scale factor, and its function is the same as in the coordinate calculation. is the radius of curvature function that depends on the latitude . Since the earth is an ellipsoid, the radii of curvature at different latitudes are different. This function reflects the influence of this geometric characteristic on the calculation of the north-south coordinates, enabling the accurate determination of the plane coordinate position in the north-south direction according to the latitude in the projection transformation.

[0030] is a reference latitude within the projection area (such as the starting latitude of the projection zone, etc.), reflects the difference between the current latitude and the reference latitude, and is used to accurately determine the north-south coordinate position on the basis of considering factors such as the earth's curvature. The subsequent high-order terms are also to more precisely consider the detailed influence of the changes in relevant geometric quantities such as the meridian arc length brought about by the latitude change on the north-south coordinates, are respectively the meridian arc length functions with respect to the latitude The first derivative and the third derivative are involved in the calculation to more precisely reflect the influence brought by the latitude change. Especially when considering the characteristics of the Earth's curved surface and the complex geometric relationships between different latitudes, these derivative terms help to more accurately achieve the conversion from longitude and latitude to plane coordinates in the north-south direction, improve the accuracy of the entire coordinate conversion, and further enable the digital twin model and GIS geographical data to be fused under more accurate coordinate correspondence.

[0031] Step 3, perform the conversion based on the Earth ellipsoid parameters: During the conversion process, the conversion operation from longitude and latitude to the corresponding UTM plane coordinates should be completed based on the Earth's ellipsoid parameters. Specifically: Scale factor: There is a scale factor , which plays a role in performing corresponding adjustments such as scaling the coordinate values during the conversion to ensure that the converted plane coordinates can accurately reflect the relative position relationship and distance ratio in the actual geographical space, etc. For example, appropriate values may be set according to different projection area ranges or accuracy requirements to guarantee the accuracy of the conversion. In the UTM projection, a fixed scale factor is usually adopted to control the length deformation after projection. Generally, the commonly used scale factor k = 0.9996, the purpose of which is to make the projected map can, to a certain extent, ensure that the angles are not deformed (equiangular projection characteristic) and at the same time appropriately control the length deformation within an acceptable range, facilitating applications such as map measurement.

[0032] Central meridian: Define a central meridian , which is a key reference line in the entire projection conversion process. In projection methods such as the UTM projection for converting many geographical coordinates to plane coordinates, the central meridian is an important reference, and around it, the plane coordinate positions of each geographical coordinate point after conversion are determined. Points with different longitudes have specific conversion calculation relationships relative to the central meridian to ensure the rationality and accuracy of the plane coordinate system after projection conversion. The UTM projection divides the Earth into 60 zones in the longitude direction, and each zone has a central meridian, and its calculation formula: In the formula, n is the projection zone number, represents the floor operation. The central meridian is the reference meridian of this projection zone, and projection transformation is carried out from this meridian as the center to both sides during projection.

[0033] Longitude difference ensures projection area consistency: By calculating the longitude in the geographical coordinates and the central meridian the longitude difference , this longitude difference is utilized to ensure the consistency of the projected area. The longitude difference reflects the lateral position relationship of a point relative to the central meridian in the projection zone and is used to determine the coordinate components in the east-west direction during projection calculations. That is to say, within the entire projection conversion area, the geographical coordinates of each position are accurately converted into the plane coordinate system according to the longitude difference from the central meridian and the established projection rules, so that the converted plane coordinates can maintain good spatial consistency within the corresponding area, facilitating subsequent operations such as the fusion application of geographical data and digital twin models.

[0034] Radius of curvature dependent on latitude and function of the meridian arc length : Here and are functions of the radius of curvature and the meridian arc length dependent on latitude respectively. When converting from longitude and latitude to plane coordinates, since the Earth is an approximate ellipsoid and the geometric characteristics such as the Earth's curvature at different latitudes are different, it is necessary to consider the influence of latitude factors on coordinate conversion through and and such functions. For example, when calculating relevant quantities such as distance and angle in coordinate conversion, it is necessary to combine the radius of curvature and the change of the meridian arc length corresponding to different latitudes to accurately convert the geographical spatial position represented by longitude and latitude into the accurate position corresponding to the plane coordinates.

[0035] Radius of curvature It is a latitude-related quantity calculated based on the Earth ellipsoid model, reflecting the curvature characteristics of the Earth ellipsoid surface at that latitude. The calculation formula is , where is the semi-major axis of the Earth ellipsoid (for the WGS84 ellipsoid, ), is the first eccentricity of the Earth ellipsoid ( , is the flattening. For the WGS84 ellipsoid, ).

[0036] Function of the meridian arc length ( ): It is used to calculate the arc length corresponding to a certain latitude in the meridian direction and plays an important role in subsequent calculations for converting from longitude and latitude to UTM plane coordinates, determining the position relationship of coordinates in the meridian direction, etc.

[0037] The specific calculation formula is as follows: Where: When the coordinate conversion module converts the digital twin model and GIS geographic data, through the detailed operations in the above aspects and considering relevant parameters, it realizes the accurate conversion from geographic coordinates (longitude and latitude) to UTM plane coordinates, laying a foundation for the effective integration of the two in the follow-up. Mathematical formulas play a crucial role in the coordinate conversion module. By considering factors such as the ellipsoidal shape of the earth, different projection parameters, and the mutual relationship between geographic coordinates, etc., they achieve the accurate conversion from geographic coordinates (longitude and latitude) to UTM plane coordinates, providing a reliable coordinate basis for the in-depth integration of digital twin and GIS, enabling the integrated system to accurately perform operations such as data interaction, analysis, and visualization display under a unified spatial framework, and better serving various actual application scenarios.

[0038] This embodiment provides a specific optimization method, specifically: Optimize the fused data, and use the support vector machine to optimize the data, including the objective function for linearly separable problems and the objective function for non-linearly separable problems: The data fusion module fuses the spatial data of the digital twin and GIS, and uses machine learning and data mining algorithms to optimize and fuse multi-source data, providing real-time and accurate analysis results.

[0039] The sources of the fused data are extensive, including but not limited to device status data, sensor data in the digital twin, and geographic spatial data in GIS (such as terrain data, land use data, etc.). This module innovatively adopts an intelligent weighted average method, and the formula is: Among them, is the fused result, is the measurement value of the th data source, is the weight of the th data source, is the number of data sources.

[0040] In the weighted average method, the determination of the weight is not simply based on the quality and accuracy of the data source, but combines multi-dimensional factors such as the timeliness of the data, the relevance of the data to the target analysis task, and the reliability of the data in historical analysis, and is dynamically learned and adjusted through deep learning algorithms. This is the key innovation point that differentiates it from traditional data fusion methods. Optimize the fused data, and use the support vector machine (SVM) to optimize the data. For linearly separable problems, the objective function: makes: .

[0041] Among them, is the normal vector of the hyperplane, is the bias; is the th input data (here and in the data fusion formula represent data at different stages. in the data fusion formula is the original multi-source data, and here it is the fused data entering the SVM optimization stage); is the label of the th data. In the present invention, the SVM algorithm is used to optimize and classify the fused multi-source data. Its innovation lies in that for the linearly separable problem, an improved gradient descent algorithm is adopted to solve the objective function, which can converge quickly and find the optimal hyperplane, improving the classification efficiency and accuracy.

[0042] For the non-linearly separable problem, by introducing a kernel function, the data is mapped to a high-dimensional space for processing, and the following optimization problem is obtained: such that: Among them, is the regularization parameter, are the slack variables used to handle misclassified data, is the kernel function (such as Gaussian kernel, RBF kernel, etc.). The innovation of the present invention in dealing with the non-linearly separable problem is that according to the distribution characteristics of the data, a suitable kernel function and its parameters are automatically selected. By combining cross-validation and genetic algorithm, the blindness of kernel function selection in traditional SVM is avoided, and the classification and optimization ability for complex data is further improved.

[0043] The data fusion module, through this multi-stage, multi-algorithm fusion and optimization method, deeply integrates and processes the multi-source data from GIS and digital twin, thereby improving the accuracy and effectiveness of the analysis results and providing a high-quality data basis for subsequent visualization and analysis. In the present invention, the data fusion module combines the spatial and dynamic data from GIS and digital twin, and then classifies and optimizes the fused data through the SVM algorithm, thereby improving the accuracy and effectiveness of the analysis results. In this way, SVM classifies and optimizes the multi-source data to ensure that the fused data can accurately reflect the operating state and environmental conditions of the equipment.

[0044] The visualization and analysis module realizes the display and intelligent analysis of multi-dimensional data by integrating data analysis and visualization tools; the data analysis is realized through principal component analysis, specifically: The visualization and analysis module realizes the display and intelligent analysis of multi-dimensional data by integrating data analysis and visualization tools. The data analysis is achieved through principal component analysis, specifically as follows: Calculate the covariance matrix of the data set: Among them, is the data sample, is the sample mean, is the covariance matrix. Perform eigenvalue decomposition on the covariance matrix to obtain the eigenvectors and eigenvalues: , where, is the eigenvector, is the eigenvalue.

[0045] The innovation of this module lies in closely combining principal component analysis with data fusion and the SVM optimization results, dynamically screening the principal components according to the SVM classification results, highlighting the principal components related to the target analysis task, and improving the pertinence and efficiency of data analysis.

[0046] Its function is to project high-dimensional data into a two-dimensional or three-dimensional space through principal component analysis (covariance matrix) to generate visualization results such as heat maps and line charts, and display the correlation trends between the device operating status and environmental data.

[0047] For example, the visualization is presented through a heat map. The heat map uses different color codings to display the magnitude or distribution of values. The depth of the color indicates the high or low of the value, representing the intensity, trend, or correlation of the data. Moreover, the color mapping algorithm of the heat map adopts an adaptive color adjustment strategy, automatically selecting a suitable color gradient scheme according to the dynamic range and distribution characteristics of the data, making the visualization effect of the data more intuitive and accurate, and facilitating users to quickly understand the key information in the data.

[0048] The user interaction module is used to provide an interface that supports user interaction. Users can interact with the digital twin model and GIS geographical data through operations such as dragging and zooming, view the device and environmental status in real time, and generate analysis reports as needed.

[0049] The system also includes a real-time data update module. The real-time data update module is used to collect data from the data source in real time and perform noise suppression and data update through the Kalman filtering algorithm to ensure that the data of the digital twin model and the GIS system always remain consistent.

[0050] The Kalman filtering algorithm is specifically as follows: The real-time data update module is used to collect data from the data source in real time and perform noise suppression and data update through the Kalman filtering algorithm to ensure that the data of the digital twin model and the GIS system always remain consistent. The Kalman filtering algorithm is specifically, state equation: Among them, represents the system state, indicating the state vector of the system at moment. It contains the state information of various variables concerned by users in the system. For example, in the digital twin and GIS fusion system, it includes the states of physical quantities such as the position, speed, and temperature of the equipment. A is the state transition matrix, which describes the state change law of the system from moment to moment . The elements of this matrix are determined according to the physical model or empirical knowledge of the system. For example, if the system is a simple object moving in a uniform straight line, is a matrix related to speed and time, which converts the position state at the previous moment to the position state at the current moment. is the state vector of the system at moment , and it is the basis for calculating the current state .

[0051] This term represents the influence of the control input of the system on the state. is the control input matrix, which maps the control input (such as the control instructions of the equipment, such as adjusting the running speed and direction of the equipment) to the state space, thereby changing the state of the system. is the process noise vector. In an actual system, due to various unpredictable factors (such as environmental interference, model errors, etc.), the state change of the system cannot be completely carried out according to the ideal state transition matrix and control input. is used to describe these uncertainties. It is usually assumed to be a Gaussian noise vector with a mean of zero, and its covariance matrix can be used to measure the magnitude and correlation of the process noise.

[0052] Observation equation: represents the observation vector at moment . is the observation matrix, which maps the state vector of the system to the observation space. Because we cannot directly observe all the state variables of the system, determines the conversion relationship from the state vector to the observation vector. For example, if we can only observe the position of the system and not directly observe the speed, will convert the state vector containing position and speed into an observation vector only containing position information. is the observation noise vector. Similar to the process noise, due to factors such as the accuracy limitations of sensors and environmental interference, there is also uncertainty in the observed values. The observation noise is also assumed to be a Gaussian noise vector with a mean of zero, and its covariance matrix is used to describe the characteristics of the observation noise. In the digital twin and GIS integration system, this may be the observed values of device status data or geospatial data obtained through sensors, such as the device location information obtained through a GPS sensor, the device temperature obtained through a temperature sensor, etc.

[0053] In summary, in the digital twin and GIS integration system, the process of the real-time data update module using the Kalman filter algorithm is as follows: First, based on the state estimate value at the previous moment and the current control input, the state at the current moment is predicted through the state equation. Then, combined with the observation equation, the observed values are used to correct the predicted state to make the state estimate more accurate. In this process, the Kalman filter algorithm cleverly weighs the predicted value and the observed value, and calculates the optimal state estimate value according to the covariance information of the process noise and the observation noise. Moreover, the innovation of this system lies in introducing a data credibility evaluation mechanism for the multi-source and complexity of data in the digital twin and GIS integration system, and dynamically adjusting the covariance matrices of the process noise and the observation noise according to the reliability of the data source and the stability of historical data. This can better adapt to the complex data environment, improve the filtering effect, and ensure the real-time and accuracy of the system data. The innovation of this module lies in improving the Kalman filter algorithm. For the multi-source and complexity of data in the digital twin and GIS integration system, a data credibility evaluation mechanism is introduced, and the covariance matrices of the process noise and the observation noise are dynamically adjusted according to the reliability of the data source and the stability of historical data, improving the adaptability and filtering effect of the Kalman filter algorithm in a complex data environment, and ensuring the real-time and accuracy of the system data.

[0054] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0055] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A digital twin and GIS fusion system, characterized by: It includes data acquisition module, coordinate conversion module, data fusion module, visualization and analysis module and user interaction module; among which, the data acquisition module collects GIS spatial data and transmits the GIS spatial data to the coordinate conversion module; The coordinate conversion module converts the collected data to ensure the matching between the digital twin model and the GIS spatial data; The data fusion module is used to fuse digital twin data and GIS spatial data after coordinate transformation, optimize the data and unify the format; The visualization and analysis module is used to analyze the fused data and use the analysis results for further processing and visualization; The user interaction module receives the data processed by the visualization and analysis module and displays the data to the user for real-time interactive feedback and decision support.

2. A digital twin and GIS fusion system according to claim 1, characterized in that: The coordinate conversion module converts the digital twin model to GIS geographic data, including the following steps: First, the coordinate conversion module uses the conversion function to convert the earth's spherical coordinates into UTM plane coordinates. Specifically, the spherical coordinates are converted into UTM plane coordinates by calculating the east-west plane coordinates and the north-south plane coordinates respectively. Then, based on the parameters of the earth ellipsoid, the conversion operation from longitude and latitude to the corresponding UTM plane coordinates is completed: by combining the changes in the radius of curvature corresponding to different latitudes and the arc length of the meridian, the geographic space position represented by the longitude and latitude is converted to the accurate position corresponding to the plane coordinates, thus completing the conversion.

3. A digital twin and GIS fusion system according to claim 2, characterized in that: The data fusion module fuses the spatial data of digital twins and GIS. The fusion adopts the intelligent weighted average method, which is as follows: in, is the result after fusion, For the The measured values ​​of the data sources, For the The weight of the data source, is the number of data sources.

4. A digital twin and GIS fusion system according to claim 3, characterized in that: The fused data is optimized using support vector machines, including the objective function of linear separable problems and the objective function of nonlinear separable problems: For linearly separable problems, the objective function is: So that: ; in, is the normal vector of the hyperplane, is bias; It is Input data; It is The label of the data.

5. A digital twin and GIS fusion system according to claim 4, characterized in that: For nonlinear separable problems, the kernel function is introduced to map the data into a high-dimensional space for processing, resulting in the following optimization problem: So that: in, is the normal vector of the hyperplane, is the regularization parameter, is a slack variable used to handle misclassified data. is the kernel function, is the bias, It is Input data.

6. A digital twin and GIS fusion system according to claim 5, characterized in that: The visualization and analysis module integrates data analysis and visualization tools to display and intelligently analyze multidimensional data. Data analysis is achieved through principal component analysis, specifically: Compute the covariance matrix of the dataset: in, is the data sample, is the sample mean, is the covariance matrix; perform eigenvalue decomposition on the covariance matrix to obtain eigenvectors and eigenvalues: ,in, is the feature vector, is the characteristic value.

7. The digital twin and GIS fusion system according to claim 5, characterized in that: Visualization is presented through heat maps, which use different color codes to show the size or distribution of values. The depth of color represents the high or low value, and the intensity, trend or correlation of the data.

8. A digital twin and GIS fusion system according to claim 7, characterized in that: The user interaction module is used to provide an interface that supports user interaction. Users can interact with the digital twin model and GIS geographic data through operations such as dragging and zooming, view the status of equipment and environment in real time, and generate analysis reports as needed.

9. A digital twin and GIS fusion system according to claim 8, characterized in that: The system also includes a real-time data update module, which is used to collect data from the data source in real time, and perform noise suppression and data updates through the Kalman filter algorithm to ensure that the data of the digital twin model and the GIS system always remain consistent.

10. A digital twin and GIS fusion system according to claim 9, characterized in that: The Kalman filter algorithm is specifically: Equation of state: in, Indicates the system status. The state vector of the system at time instant; This term represents the effect of the system's control input on the state; is the state transfer matrix, which describes the system from time To time The law of state change; Observation equation: Indicates at time The observation vector, is the observation matrix; is the observation noise vector, Indicates the system status.

Images