Power grid infrastructure engineering intelligent management and control system and method based on three-dimensional digital twinning

Abstract

The application discloses a kind of based on three-dimensional digital twinning's power grid infrastructure engineering intelligent management and control system and method, it is related to power grid infrastructure engineering management and control field, including: to power grid infrastructure is virtually modeled, builds power grid infrastructure numerical twin expected model;The progress of each link of power grid infrastructure engineering is carried out data acquisition, and is carried out digitization and standardization processing;The data of image acquisition are handled;The actual deviation degree of each link progress of power grid infrastructure is calculated;Comprehensive evaluation and forecast whether the progress of each link of existing power grid infrastructure engineering can complete project as expected;Establish three-dimensional digital twinning control platform of power grid infrastructure engineering, receive, store and display the numerical change of each link, and observe the progress change of each link of power grid infrastructure engineering by adjusting model parameter.Effectively improve the management efficiency of power grid infrastructure engineering, progress comprehensive evaluation ability and resource integration ability, reduce the island phenomenon of each link.

Description

Technical Field

[0001] This invention relates to the field of power grid infrastructure project management and control, specifically to an intelligent management and control system and method for power grid infrastructure projects based on three-dimensional digital twins. Background Technology

[0002] Power grid infrastructure construction is subject to various constraints. Whether a power grid infrastructure project can be completed according to the expected plan and timeline depends on the coordinated efforts of all stages. Traditional power grid infrastructure project management is affected by data management at each stage, leading to inconsistent data standards and data silos. This results in management chaos and construction delays. With the development of 3D digital twin technology, visualized and intelligent management can effectively improve the management efficiency, progress assessment capabilities, and resource integration capabilities of each stage of power grid infrastructure projects, reduce data silos, and create an immersive experience for power grid infrastructure project progress management through virtual and real interaction, thereby improving the transparency and rationalization of power grid infrastructure construction.

[0003] The current challenge of 3D digital twin technology lies in the lack of ability to integrate data from various stages and the ability to interact between actual data from various stages and virtual data. This results in poor visual effects of 3D digital twin models and poor system performance when handling large-scale real-time data applications. Consequently, it fails to improve the management efficiency, progress assessment capabilities, and resource integration capabilities of various stages of power grid infrastructure projects, and easily leads to the existence of isolated systems in each stage. Summary of the Invention

[0004] To address the aforementioned technical problems, this paper provides an intelligent management and control system and method for power grid infrastructure projects based on three-dimensional digital twins. This technical solution solves the problems mentioned in the background, such as the lack of data integration capabilities for various stages and the inability to interact between actual data and virtual data. This results in poor visual effects of the three-dimensional digital twin model and poor system performance when handling large-scale real-time data applications. Consequently, it fails to improve the management efficiency, comprehensive progress assessment capabilities, and resource integration capabilities of various stages of power grid infrastructure projects, and easily leads to the problem of isolated stages.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] A method for intelligent management and control of power grid infrastructure projects based on three-dimensional digital twins, characterized by comprising:

[0007] Based on the design drawings and engineering plans of power grid infrastructure projects, a virtual model of the physical environment of power grid infrastructure is constructed using numerical twin software to build a numerical twin expected model of power grid infrastructure.

[0008] Based on Internet of Things (IoT) technology, the monitoring equipment group collects data on the progress of each stage of the power grid infrastructure project in real time, and performs digitization and standardization processing on the data.

[0009] The data from the image acquisition is processed based on the power grid infrastructure project progress equalization algorithm.

[0010] Based on the real-time data collected by the monitoring equipment group, the actual deviation of the progress of each stage of power grid infrastructure construction is calculated.

[0011] Based on the LSTM neural network algorithm model, we comprehensively evaluate and predict whether the progress of each stage of the existing power grid infrastructure project can be completed as expected.

[0012] Establish a three-dimensional digital twin control platform for power grid infrastructure projects to receive, store, and display numerical changes in various stages of the power grid infrastructure projects, and to observe the progress changes in various stages of the power grid infrastructure projects by adjusting model parameters.

[0013] Preferably, the step of building a power grid infrastructure numerical twin expectation model by virtually modeling the physical environment of the power grid infrastructure based on the design drawings and engineering plans of the power grid infrastructure project using numerical twin software specifically includes:

[0014] Based on the design drawings and engineering plans of the power grid infrastructure project, preprocessed information on the construction site and surrounding environment is obtained through map information;

[0015] Based on actual infrastructure needs, the pre-processed information of construction sites and their surrounding environment is further refined through manual modeling and BIM modeling.

[0016] Set up a phased time series for power grid infrastructure projects and extract the phased progress characteristics of each stage;

[0017] Based on numerical twin software, virtual modeling of the physical environment of power grid infrastructure is carried out to control and display virtual values ​​of project progress, equipment operation values, and environmental monitoring values ​​at each stage.

[0018] Based on the lightweight processing of the virtual model, a numerical twin prediction model for power grid infrastructure is built.

[0019] Preferably, the process of collecting real-time data on the progress of various stages of the power grid infrastructure project through monitoring equipment groups based on Internet of Things (IoT) technology, and then digitizing and standardizing the data, specifically includes:

[0020] Based on the requirements of the numerical twin prediction model for power grid infrastructure, monitoring equipment groups are set up at corresponding locations and in the construction areas of each stage to collect data on the progress of each stage.

[0021] The monitoring equipment group includes: environmental monitoring sensors, image acquisition equipment, power grid equipment numerical monitoring devices, a data manual reporting platform, and infrastructure material monitoring equipment.

[0022] Based on IoT technology, it is used to receive monitoring data collected by the monitoring equipment group in real time and to digitize and standardize the data.

[0023] Preferably, the processing of image acquisition data based on the power grid infrastructure project progress equalization algorithm specifically includes:

[0024] By using aerial photography or image acquisition equipment set up at fixed locations, images of the entire power grid infrastructure project are collected regularly to obtain three-dimensional images of the actual progress of the infrastructure project.

[0025] Based on the progress of the 3D map of the physical progress of the infrastructure project, calculate the progress of each stage of construction for image acquisition;

[0026] A progress balancing algorithm model based on power grid infrastructure projects is established to process the data collected from images and comprehensively evaluate the current physical progress of the infrastructure projects.

[0027] Based on big data analysis, obtain the equilibrium threshold for the progress of power grid infrastructure projects during the image acquisition phase;

[0028] Determine whether the progress balance coefficient of the power grid infrastructure project that is acquiring images is greater than the expected threshold. If it is, it means that the progress of the power grid infrastructure project that is acquiring images can meet the overall project construction goals. If not, it means that the current progress of the image acquisition stage is slow and needs to be analyzed and adjusted according to the construction progress of each stage of image acquisition to accelerate the project construction.

[0029] The progress expression for each stage of image acquisition is as follows:

[0030]

[0031] In the formula, Z i To represent the progress of the i-th stage of image acquisition, let α be the importance weight of the completed infrastructure construction portion of the i-th stage, and y be the completed infrastructure construction portion of the i-th stage. i Let represent the total infrastructure construction volume for the i-th stage;

[0032] The expression for the power grid infrastructure project progress equalization algorithm is as follows:

[0033]

[0034] In the formula, Z eve δ is the progress balancing coefficient for power grid infrastructure projects used for image acquisition.i The deviation coefficient represents the progress of the i-th stage of image acquisition, where n is the number of stages involved in image acquisition.

[0035] Preferably, the step of calculating the actual deviation of the progress of each stage of power grid infrastructure construction based on the data collected in real time by the monitoring equipment group specifically includes:

[0036] Based on the phased progress characteristics of each stage set by the numerical twin prediction model of power grid infrastructure, a standard library of phased progress of power grid infrastructure projects is established based on the phased time series of power grid infrastructure projects.

[0037] Based on the phased time series of power grid infrastructure projects, a phased actual progress matrix of power grid infrastructure projects is established according to the progress data of each stage collected by the monitoring equipment group in the time series.

[0038] Based on the comparison between the phased actual progress matrix of power grid infrastructure projects and the phased progress standard library of power grid infrastructure projects under the same time series, the actual deviation of the progress of each stage of power grid infrastructure construction is calculated.

[0039] Based on big data analysis, the critical value range of the actual deviation of the progress of each stage of power grid infrastructure construction is obtained;

[0040] Determine whether the actual deviation of the progress of each stage of power grid infrastructure construction exceeds the critical value range. If so, it means that the actual infrastructure work arrangement of that stage needs to be adjusted immediately. If not, it means that the actual infrastructure work arrangement of that stage is still within the acceptable range and needs to be further confirmed.

[0041] Based on the actual deviation of the progress of each stage of power grid infrastructure construction, a matrix of the actual deviation of the progress of each stage of power grid infrastructure construction is established.

[0042] The expression for the actual deviation of the progress of each stage of the power grid infrastructure construction is as follows:

[0043]

[0044] In the formula, ε i Let τ be the deviation of the actual progress of the i-th stage of power grid infrastructure construction, τ be the deviation coefficient, and σ be a constant. j For the progress data of the j-th group of the i-th stage under the same time series, The preset data is for the i-th stage of the progress in the standard library of phased progress of power grid infrastructure projects under the same time series, and m is the number of sets of stage progress data collected multiple times under the same time series.

[0045] Preferably, the step of comprehensively evaluating and predicting whether the progress of each stage of the existing power grid infrastructure project can be completed as expected, based on the LSTM neural network algorithm model, specifically includes:

[0046] Based on the numerical twin prediction model of power grid infrastructure and the standard library of phased progress of power grid infrastructure projects, we extract the phased comprehensive features of each stage of power grid infrastructure projects and establish a comprehensive feature matrix of power grid infrastructure projects.

[0047] The LSTM neural network algorithm model is trained and learned by the comprehensive feature matrix of power grid infrastructure projects, and the parameters are set and adjusted by combining historical data.

[0048] Based on the progress equilibrium coefficient of power grid infrastructure projects acquired through image acquisition and the actual deviation matrix of the progress of each stage of power grid infrastructure projects, a comprehensive feature matrix of the actual progress of power grid infrastructure projects is established.

[0049] The trained LSTM neural network algorithm model iteratively calculates the comprehensive feature matrix of the actual progress of the power grid infrastructure project, and comprehensively evaluates and predicts whether the progress of each stage of the existing power grid infrastructure project can be completed as expected.

[0050] If the project can be completed as expected, it will proceed according to the existing schedule. If the project cannot be completed as expected, an early warning will be issued, and adjustments and progress will be made to address the problematic aspects of the power grid infrastructure project based on the parameter feedback from the LSTM neural network algorithm model.

[0051] Preferably, the establishment of a three-dimensional digital twin control platform for power grid infrastructure projects, used to receive, store, and display numerical changes in various stages of the power grid infrastructure projects, and to observe the progress changes in various stages of the power grid infrastructure projects by adjusting model parameters, specifically includes:

[0052] Establish a three-dimensional digital twin control platform for power grid infrastructure projects, and use Internet of Things (IoT) technology to receive and store the numerical changes of each stage of power grid infrastructure projects in real time;

[0053] Based on the three-dimensional digital twin control platform for power grid infrastructure projects, it is used to build and run LSTM neural network algorithm models and display the calculation results of the models;

[0054] Based on the three-dimensional digital twin control platform for power grid infrastructure projects, the detection status of equipment, processes, and environment at each stage can be viewed through human-computer interaction;

[0055] Based on the three-dimensional digital twin control platform for power grid infrastructure projects, the progress and changes of each stage of the power grid infrastructure project, as well as the overall construction model, are observed by setting and adjusting different model parameters.

[0056] Furthermore, this solution proposes an intelligent management and control system for power grid infrastructure projects based on three-dimensional digital twins, used to implement the aforementioned intelligent management and control method for power grid infrastructure projects based on three-dimensional digital twins, including:

[0057] The expected model building module is used to build a numerical twin expected model of power grid infrastructure based on the design drawings and engineering plans of power grid infrastructure projects and using numerical twin software to virtually model the physical environment of power grid infrastructure.

[0058] The data acquisition module is used to collect data on the progress of various stages of power grid infrastructure projects in real time through monitoring equipment groups based on Internet of Things technology, and to digitize and standardize the data.

[0059] The progress evaluation module is used to process the data collected by the image based on the power grid infrastructure project progress equalization algorithm; calculate the actual deviation of the progress of each stage of the power grid infrastructure project based on the real-time data collected by the monitoring equipment group; and comprehensively evaluate and predict whether the progress of each stage of the existing power grid infrastructure project can be completed as expected based on the LSTM neural network algorithm model.

[0060] The control platform module is used to establish a three-dimensional digital twin control platform for power grid infrastructure projects. It is used to receive, store, and display numerical changes in various aspects of the power grid infrastructure projects, and to observe the progress changes in various aspects of the power grid infrastructure projects by adjusting model parameters.

[0061] Preferably, the progress evaluation module specifically includes:

[0062] An image processing unit is used to process image acquisition data based on a power grid infrastructure project progress equalization algorithm.

[0063] The progress deviation unit is used to calculate the actual deviation of the progress of each stage of power grid infrastructure construction based on the data collected in real time by the monitoring equipment group.

[0064] The progress evaluation unit is used to comprehensively evaluate and predict whether the progress of each stage of the existing power grid infrastructure project can be completed as expected, based on the LSTM neural network algorithm model.

[0065] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0066] By utilizing the design drawings and engineering plans of power grid infrastructure projects, a virtual model of the physical environment of power grid infrastructure is created using numerical twin software. This establishes a numerical twin expectation model for power grid infrastructure. Furthermore, by analyzing data from various stages of power grid infrastructure construction, a progress equilibrium coefficient and a matrix of actual deviations in progress at each stage are established. Based on this, the input matrix for the LSTM neural network algorithm model is determined. The LSTM neural network algorithm model is then used to comprehensively evaluate and predict whether the progress of each stage of the existing power grid infrastructure project can be completed as expected. Finally, a three-dimensional digital twin control platform for power grid infrastructure projects facilitates data interaction between the virtual and real worlds. This effectively improves the management efficiency, comprehensive progress assessment capabilities, and resource integration capabilities of power grid infrastructure projects, enhances dynamic control and command, and digital operation capabilities, and reduces the siloed nature of different stages. Attached Figure Description

[0067] Figure 1 This is a flowchart of an intelligent management and control method for power grid infrastructure projects based on three-dimensional digital twins, according to the present invention.

[0068] Figure 2 The flowchart of the image acquisition data processing algorithm based on the power grid infrastructure project progress equalization algorithm of the present invention is shown below.

[0069] Figure 3 This invention provides a flowchart for calculating the actual deviation of the progress of each stage of power grid infrastructure construction based on real-time data collected by the monitoring equipment group.

[0070] Figure 4 This invention provides a flowchart for comprehensively evaluating and predicting whether the progress of each stage of existing power grid infrastructure projects can be completed as expected, based on the LSTM neural network algorithm model. Detailed Implementation

[0071] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.

[0072] Reference Figure 1 As shown, a method for intelligent management and control of power grid infrastructure projects based on three-dimensional digital twins includes:

[0073] Based on the design drawings and engineering plans of power grid infrastructure projects, a virtual model of the physical environment of power grid infrastructure is constructed using numerical twin software to build a numerical twin expected model of power grid infrastructure.

[0074] Based on Internet of Things (IoT) technology, the monitoring equipment group collects data on the progress of each stage of the power grid infrastructure project in real time, and performs digitization and standardization processing on the data.

[0075] The data from the image acquisition is processed based on the power grid infrastructure project progress equalization algorithm.

[0076] Based on the real-time data collected by the monitoring equipment group, the actual deviation of the progress of each stage of power grid infrastructure construction is calculated.

[0077] Based on the LSTM neural network algorithm model, we comprehensively evaluate and predict whether the progress of each stage of the existing power grid infrastructure project can be completed as expected.

[0078] Establish a three-dimensional digital twin control platform for power grid infrastructure projects to receive, store, and display numerical changes in various stages of the power grid infrastructure projects, and to observe the progress changes in various stages of the power grid infrastructure projects by adjusting model parameters.

[0079] Understandably, this solution utilizes the design drawings and engineering plans of power grid infrastructure projects. Based on numerical twin software, it virtually models the physical environment of the power grid infrastructure, establishing a numerical twin expected model. By analyzing data from various stages of the power grid infrastructure project, it establishes a progress equilibrium coefficient for image acquisition and a matrix representing the actual deviation of progress at each stage. Based on this, it determines the input matrix for the LSTM neural network algorithm model. The LSTM neural network algorithm model then comprehensively evaluates and predicts whether the progress of each stage of the existing power grid infrastructure project can be completed as expected. Finally, a three-dimensional digital twin control platform for power grid infrastructure projects facilitates data interaction between the virtual and real worlds. This effectively improves the management efficiency, comprehensive progress assessment capabilities, and resource integration capabilities of power grid infrastructure projects, enhances dynamic control and command, and digital operation capabilities, and reduces the siloed nature of different stages.

[0080] Reference Figure 2 As shown, the processing of image acquisition data based on the power grid infrastructure project progress equalization algorithm specifically includes:

[0081] By using aerial photography or image acquisition equipment set up at fixed locations, images of the entire power grid infrastructure project are collected regularly to obtain three-dimensional images of the actual progress of the infrastructure project.

[0082] Based on the progress of the 3D map of the physical progress of the infrastructure project, calculate the progress of each stage of construction for image acquisition;

[0083] A progress balancing algorithm model based on power grid infrastructure projects is established to process the data collected from images and comprehensively evaluate the current physical progress of the infrastructure projects.

[0084] Based on big data analysis, obtain the equilibrium threshold for the progress of power grid infrastructure projects during the image acquisition phase;

[0085] Determine whether the progress balance coefficient of the power grid infrastructure project that is acquiring images is greater than the expected threshold. If it is, it means that the progress of the power grid infrastructure project that is acquiring images can meet the overall project construction goals. If not, it means that the current progress of the image acquisition stage is slow and needs to be analyzed and adjusted according to the construction progress of each stage of image acquisition to accelerate the project construction.

[0086] The progress expression for each stage of image acquisition is as follows:

[0087]

[0088] In the formula, Z i To represent the progress of the i-th stage of image acquisition, let α be the importance weight of the completed infrastructure construction portion of the i-th stage, and y be the completed infrastructure construction portion of the i-th stage. i Let represent the total infrastructure construction volume for the i-th stage;

[0089] The expression for the power grid infrastructure project progress equalization algorithm is as follows:

[0090]

[0091] In the formula, Z eve δ is the progress balancing coefficient for power grid infrastructure projects used for image acquisition. i The deviation coefficient represents the progress of the i-th stage of image acquisition, where n is the number of stages involved in image acquisition.

[0092] Understandably, during the progress of power grid infrastructure projects, monitoring of different stages often requires the use of image acquisition equipment to capture images of the on-site environment. By analyzing the image data, the extent to which the completed infrastructure construction in each stage represents a portion of the overall infrastructure project can be determined. This allows for the analysis of the progress of power grid infrastructure projects at each stage. However, since the importance of completing different parts of the power grid infrastructure project varies, it is necessary to use big data analysis to obtain the importance weight of the completed infrastructure construction in each stage, thereby balancing the errors in the progress of power grid infrastructure projects at each stage.

[0093] Reference Figure 3 As shown, the calculation of the actual deviation of the progress of each stage of power grid infrastructure construction based on the data collected in real time by the monitoring equipment group specifically includes:

[0094] Based on the phased progress characteristics of each stage set by the numerical twin prediction model of power grid infrastructure, a standard library of phased progress of power grid infrastructure projects is established based on the phased time series of power grid infrastructure projects.

[0095] Based on the phased time series of power grid infrastructure projects, a phased actual progress matrix of power grid infrastructure projects is established according to the progress data of each stage collected by the monitoring equipment group in the time series.

[0096] Based on the comparison between the phased actual progress matrix of power grid infrastructure projects and the phased progress standard library of power grid infrastructure projects under the same time series, the actual deviation of the progress of each stage of power grid infrastructure construction is calculated.

[0097] Based on big data analysis, the critical value range of the actual deviation of the progress of each stage of power grid infrastructure construction is obtained;

[0098] Determine whether the actual deviation of the progress of each stage of power grid infrastructure construction exceeds the critical value range. If so, it means that the actual infrastructure work arrangement of that stage needs to be adjusted immediately. If not, it means that the actual infrastructure work arrangement of that stage is still within the acceptable range and needs to be further confirmed.

[0099] Based on the actual deviation of the progress of each stage of power grid infrastructure construction, a matrix of the actual deviation of the progress of each stage of power grid infrastructure construction is established.

[0100] The expression for the actual deviation of the progress of each stage of the power grid infrastructure construction is as follows:

[0101]

[0102] In the formula, ε i Let τ be the deviation of the actual progress of the i-th stage of power grid infrastructure construction, τ be the deviation coefficient, and σ be a constant. j For the progress data of the j-th group of the i-th stage under the same time series, The preset data is for the i-th stage of the progress in the standard library of phased progress of power grid infrastructure projects under the same time series, and m is the number of sets of stage progress data collected multiple times under the same time series.

[0103] Understandably, by using the phased preset values ​​of each stage of the power grid infrastructure numerical twin prediction model, the standard library of phased progress of power grid infrastructure projects, and based on the actual progress data of each stage of power grid infrastructure, the deviation between the preset data and the actual data is calculated using the expression of the actual deviation of the progress of each stage of power grid infrastructure. Based on big data analysis, the critical value range of the actual deviation of the progress of each stage of power grid infrastructure is obtained. By comparing and judging, the work arrangements of each stage are adjusted and confirmed, thereby achieving effective management and control of the actual progress of each stage.

[0104] Reference Figure 4 As shown, the method of comprehensively evaluating and predicting whether the progress of each stage of existing power grid infrastructure projects can be completed as expected, based on the LSTM neural network algorithm model, specifically includes:

[0105] Based on the numerical twin prediction model of power grid infrastructure and the standard library of phased progress of power grid infrastructure projects, we extract the phased comprehensive features of each stage of power grid infrastructure projects and establish a comprehensive feature matrix of power grid infrastructure projects.

[0106] The LSTM neural network algorithm model is trained and learned by the comprehensive feature matrix of power grid infrastructure projects, and the parameters are set and adjusted by combining historical data.

[0107] Based on the progress equilibrium coefficient of power grid infrastructure projects acquired through image acquisition and the actual deviation matrix of the progress of each stage of power grid infrastructure projects, a comprehensive feature matrix of the actual progress of power grid infrastructure projects is established.

[0108] The trained LSTM neural network algorithm model iteratively calculates the comprehensive feature matrix of the actual progress of the power grid infrastructure project, and comprehensively evaluates and predicts whether the progress of each stage of the existing power grid infrastructure project can be completed as expected.

[0109] If the project can be completed as expected, it will proceed according to the existing schedule. If the project cannot be completed as expected, an early warning will be issued, and adjustments and progress will be made to address the problematic aspects of the power grid infrastructure project based on the parameter feedback from the LSTM neural network algorithm model.

[0110] Understandably, since power grid infrastructure construction is a long-term undertaking, the comprehensive impact of time series on the final project progress needs to be considered. Therefore, the existing LSTM neural network algorithm model has a good convergence effect in predicting the progress of power grid infrastructure projects. By confirming the progress equilibrium coefficient of power grid infrastructure projects through image acquisition in the early stage and the actual deviation matrix of the progress of each stage of power grid infrastructure projects, a comprehensive feature matrix of the actual progress of power grid infrastructure projects is established. This matrix is ​​used as the input matrix of the LSTM neural network algorithm model, thereby comprehensively evaluating and predicting whether the progress of each stage of the existing power grid infrastructure project can be completed as expected, thus realizing comprehensive management of the progress of each stage of the power grid infrastructure project.

[0111] Furthermore, based on the same inventive concept as the aforementioned intelligent management and control method for power grid infrastructure projects based on three-dimensional digital twins, this solution proposes an intelligent management and control system for power grid infrastructure projects based on three-dimensional digital twins, comprising:

[0112] The expected model building module is used to build a numerical twin expected model of power grid infrastructure based on the design drawings and engineering plans of power grid infrastructure projects and using numerical twin software to virtually model the physical environment of power grid infrastructure.

[0113] The data acquisition module is used to collect data on the progress of various stages of power grid infrastructure projects in real time through monitoring equipment groups based on Internet of Things technology, and to digitize and standardize the data.

[0114] The progress evaluation module is used to process the data collected by the image based on the power grid infrastructure project progress equalization algorithm; calculate the actual deviation of the progress of each stage of the power grid infrastructure project based on the real-time data collected by the monitoring equipment group; and comprehensively evaluate and predict whether the progress of each stage of the existing power grid infrastructure project can be completed as expected based on the LSTM neural network algorithm model.

[0115] The control platform module is used to establish a three-dimensional digital twin control platform for power grid infrastructure projects, and to receive, store and display numerical changes in various aspects of power grid infrastructure projects, as well as to observe the progress changes in various aspects of power grid infrastructure projects by adjusting model parameters.

[0116] The progress evaluation module specifically includes:

[0117] An image processing unit is used to process image acquisition data based on a power grid infrastructure project progress equalization algorithm.

[0118] The progress deviation unit is used to calculate the actual deviation of the progress of each stage of power grid infrastructure construction based on the data collected in real time by the monitoring equipment group.

[0119] The progress evaluation unit is used to comprehensively evaluate and predict whether the progress of each stage of the existing power grid infrastructure project can be completed as expected, based on the LSTM neural network algorithm model.

[0120] In summary, the advantages of this invention are as follows: By using design drawings and engineering plans for power grid infrastructure projects, a virtual model of the physical environment of the power grid infrastructure is created using numerical twin software. This establishes a numerical twin expected model of the power grid infrastructure. Furthermore, by analyzing data from various stages of the power grid infrastructure project, a progress equilibrium coefficient and a matrix of actual deviations in progress for each stage are established. Based on this, the input matrix of the LSTM neural network algorithm model is determined. The LSTM neural network algorithm model is then used to comprehensively evaluate and predict whether the progress of each stage of the existing power grid infrastructure project can be completed as expected. Finally, a three-dimensional digital twin control platform for power grid infrastructure projects facilitates data interaction between the virtual and real worlds. This effectively improves the management efficiency, comprehensive progress assessment capabilities, and resource integration capabilities of power grid infrastructure projects, enhances the dynamic control and command and digital operation capabilities of power grid infrastructure projects, and reduces the siloed nature of each stage.

[0121] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A power grid infrastructure engineering intelligent management and control method based on three-dimensional digital twinning, characterized in that, The application relates to a method for monitoring progress of a power grid infrastructure project. According to design drawings and engineering schemes of the power grid infrastructure project, a virtual model of an entity environment of the power grid infrastructure is established based on numerical twin software, and a numerical twin expected model of the power grid infrastructure is built; Based on Internet of Things technology, data of each link of the power grid infrastructure project is collected in real time by a monitoring equipment group, and the data is digitized and standardized; Based on a power grid infrastructure project progress equalization algorithm, the collected data is processed; According to the data collected by the monitoring equipment group in real time, the actual deviation degree of the progress of each link of the power grid infrastructure is calculated; Based on an LSTM neural network algorithm model, whether the progress of each link of the existing power grid infrastructure project can complete the project as expected is comprehensively judged and predicted; A three-dimensional digital twin control platform of the power grid infrastructure project is established to receive, store and display numerical changes of each link of the power grid infrastructure project, and to observe progress changes of each link of the power grid infrastructure project by adjusting model parameters; The power grid infrastructure project progress equalization algorithm specifically comprises: According to the progress of the entity progress three-dimensional graph of the infrastructure project, the progress degree of each link construction for image acquisition is calculated; Based on the power grid infrastructure project progress equalization algorithm model, the data collected by image acquisition is processed, and the entity progress of the current infrastructure project is comprehensively judged; The progress degree expression of each link construction for image acquisition is: In the formula, Z i The construction progress degree of the i th link for image acquisition is α, the importance weight of the i th link completed infrastructure construction part, y is the infrastructure construction part completed by the i th link, Y i The total infrastructure engineering quantity of the i th link; The power grid infrastructure project progress equalization algorithm expression is: In the formula, Z eve The progress balance coefficient of the power grid infrastructure project for image acquisition is δ i The deviation coefficient of the construction progress degree of the i th link for image acquisition, and n is the number of links for image acquisition The calculation of the actual deviation degree of the progress of each link of the power grid infrastructure specifically comprises: According to the phase progress characteristic of each link set by the numerical twin expected model of the power grid infrastructure, a phase progress standard library of the power grid infrastructure project is established based on a phase time sequence of the power grid infrastructure project; Based on the phase time sequence of the power grid infrastructure project, a phase actual progress matrix of the power grid infrastructure project is established according to the progress data of each link collected by the monitoring equipment group in the time sequence; According to the comparison between the phase actual progress matrix of the power grid infrastructure project and the phase progress standard library of the power grid infrastructure project in the same time sequence, the actual deviation degree of the progress of each link of the power grid infrastructure is calculated; According to the actual deviation degree of the progress of each link of the power grid infrastructure, an actual deviation degree matrix of the progress of each link of the power grid infrastructure is established; The actual deviation degree expression of the progress of each link of the power grid infrastructure is: In the formula, ε i is the actual deviation degree of the i th link of power grid infrastructure progress, τ is the deviation coefficient, is a constant, x j is the i th link of the j th group of link progress data under the same time sequence, is the i th link of the preset data in the standard library of power grid infrastructure project phased progress under the same time sequence, and m is the number of groups of collected link progress data under the same time sequence. The comprehensive judgment and prediction of whether the progress of each link of the existing power grid infrastructure project can complete the project as expected based on the LSTM neural network algorithm model specifically comprises: According to the progress equalization coefficient of the power grid infrastructure project for image acquisition and the actual deviation degree matrix of the progress of each link of the power grid infrastructure, an actual progress comprehensive characteristic matrix of the power grid infrastructure project is established; The input actual progress comprehensive characteristic matrix of the power grid infrastructure project is iteratively calculated by the trained LSTM neural network algorithm model, and whether the progress of each link of the existing power grid infrastructure project can complete the project as expected is comprehensively judged and predicted.

2. The power grid infrastructure engineering intelligent management and control method based on three-dimensional digital twinning according to claim 1, characterized in that, The virtual modeling of the power grid infrastructure entity environment based on the numerical twin software, the control and display of the virtual numerical, equipment operation numerical and environment monitoring numerical of the engineering progress of each link, and the construction of the power grid infrastructure numerical twin prospective model according to the light processing of the virtual model specifically include: According to the design drawings and engineering scheme of the power grid infrastructure project, the preprocessing information of the construction point and the surrounding environment is obtained through the map information; According to the actual infrastructure demand, the preprocessing information of the construction point and the surrounding environment is further refined by manual modeling and BIM modeling; Set the stage time sequence of the power grid infrastructure project, and extract the stage progress characteristics of each link; Based on the numerical twin software, the virtual modeling of the power grid infrastructure entity environment is carried out, and the virtual numerical, equipment operation numerical and environment monitoring numerical of the engineering progress of each link are controlled and displayed; According to the light processing of the virtual model, the power grid infrastructure numerical twin prospective model is built.

3. The power grid infrastructure engineering intelligent management and control method based on three-dimensional digital twinning according to claim 2, characterized in that, The data acquisition of each link progress of the power grid infrastructure project is carried out by monitoring equipment group in real time, and the data is digitized and standardized based on the Internet of Things technology, which specifically includes: According to the demand of the power grid infrastructure numerical twin prospective model, the monitoring equipment group is set at the corresponding point information and each link construction area to collect the data of each link progress; Among them, the monitoring equipment group includes: environmental monitoring sensor, image acquisition equipment, power grid equipment numerical monitoring device, data manual reporting platform and infrastructure material monitoring equipment; Based on the Internet of Things technology, the monitoring data collected by the monitoring equipment group is received in real time, and the data is digitized and standardized.

4. The power grid infrastructure engineering intelligent management and control method based on three-dimensional digital twinning according to claim 3, characterized in that, The data collected by image acquisition is processed based on the power grid infrastructure engineering progress equalization algorithm, which specifically includes: The overall situation of the power grid infrastructure project is regularly imaged by using aerial photography or fixed position image acquisition equipment, and the entity progress three-dimensional graph of the infrastructure project is obtained; According to big data analysis, the equalization threshold of the power grid infrastructure engineering progress in the image acquisition link is obtained; Determine whether the equalization coefficient of the power grid infrastructure engineering progress in the image acquisition link is greater than the expected threshold. If yes, it means that the progress of the image acquisition link can meet the construction goal of the overall project. If not, it means that the existing image acquisition link is slow, and the construction progress of each link in the image acquisition link needs to be analyzed and adjusted to speed up the construction.

5. The power grid infrastructure engineering intelligent management and control method based on three-dimensional digital twinning according to claim 4, characterized in that, According to the data collected by the monitoring equipment group in real time, the actual deviation degree of the progress of each link of the power grid infrastructure is calculated, which specifically includes: Based on big data analysis, the critical value interval of the actual deviation degree of the progress of each link of the power grid infrastructure is obtained; Determine whether the actual deviation degree of the progress of each link of the power grid infrastructure is beyond the critical value interval. If yes, it means that the actual infrastructure work arrangement of this link needs to be adjusted immediately. If not, it means that the actual infrastructure work arrangement of this link is still within the acceptable range and needs to be further confirmed.

6. The power grid infrastructure engineering intelligent management and control method based on three-dimensional digital twinning according to claim 5, characterized in that, Based on the LSTM neural network algorithm model, the comprehensive judgment and prediction of whether the progress of each link of the existing power grid infrastructure project can complete the project as expected specifically include: According to the power grid infrastructure numerical twin expected model and the power grid infrastructure engineering phased progress standard library, the phased comprehensive characteristics of each link of the power grid infrastructure engineering are extracted, and a power grid infrastructure engineering comprehensive characteristic matrix is established; The LSTM neural network algorithm model is trained and learned through the power grid infrastructure engineering comprehensive characteristic matrix, and the parameters are set and adjusted in combination with historical data; If the project can be completed as expected, the existing project progress is promoted, if the project cannot be completed as expected, a warning is made, and the problem link of the power grid infrastructure engineering is adjusted and promoted according to the parameter feedback of the LSTM neural network algorithm model.

7. The power grid infrastructure engineering intelligent management and control method based on three-dimensional digital twinning according to claim 6, characterized in that, The power grid infrastructure engineering three-dimensional digital twin control platform is established for receiving, storing and displaying the numerical changes of each link of the power grid infrastructure engineering, and observing the progress changes of each link of the power grid infrastructure engineering by adjusting the model parameters, and specifically comprising: The power grid infrastructure engineering three-dimensional digital twin control platform is established to receive and store the numerical changes of each link of the power grid infrastructure engineering in real time by using the Internet of Things technology; Based on the power grid infrastructure engineering three-dimensional digital twin control platform, the LSTM neural network algorithm model is built and run, and the operation results of the model are displayed; Based on the power grid infrastructure engineering three-dimensional digital twin control platform, the detection state of each link of the equipment, process and environment can be viewed in a man-machine interactive manner; Based on the power grid infrastructure engineering three-dimensional digital twin control platform, different model parameters are set and adjusted to observe the progress changes of each link of the power grid infrastructure engineering and the overall construction model.

8. An intelligent management and control system for power grid infrastructure projects based on three-dimensional digital twinning, characterized in that, The method for realizing the three-dimensional digital twin-based power grid infrastructure engineering intelligent management and control method according to any one of claims 1-7 comprises: An expected model building module, the expected model building module is used for building a power grid infrastructure numerical twin expected model based on numerical twin software according to the design drawings and engineering scheme of the power grid infrastructure engineering; A data acquisition module, the data acquisition module is used for acquiring data of each link of the power grid infrastructure engineering in real time through a monitoring equipment group based on Internet of Things technology, and performing digitalization and standardization processing on the data; A progress evaluation module, the progress evaluation module is used for processing the collected data based on a power grid infrastructure engineering progress equalization algorithm, calculating the actual deviation degree of each link of the power grid infrastructure engineering based on the data collected in real time by the monitoring equipment group, and comprehensively evaluating and predicting whether each link of the existing power grid infrastructure engineering can complete the project as expected based on the LSTM neural network algorithm model; A control platform module, the control platform module is used for establishing a power grid infrastructure engineering three-dimensional digital twin control platform for receiving, storing and displaying the numerical changes of each link of the power grid infrastructure engineering, and observing the progress changes of each link of the power grid infrastructure engineering by adjusting the model parameters.

9. The power grid infrastructure engineering intelligent management and control system based on three-dimensional digital twinning of claim 8, wherein, The progress evaluation module specifically comprises: An image processing unit, the image processing unit is used for processing the collected data based on the power grid infrastructure engineering progress equalization algorithm; A progress deviation unit is configured to calculate the actual deviation degree of each link of the power grid infrastructure progress according to the data collected in real time by the monitoring device group; A progress evaluation unit is configured to comprehensively evaluate and predict whether each link of the existing power grid infrastructure project can complete the project as expected based on an LSTM neural network algorithm model.

Images