Visual power grid monitoring method, system and equipment based on aerial view platform and medium

Abstract

The invention discloses a power grid visual monitoring method, system and device based on an aerial view platform and a medium, and relates to the technical field of power grid monitoring, and the method comprises the steps: obtaining point cloud data of power grid equipment, user operation data, historical maintenance data and power grid operation data; constructing a digital twinborn model, and taking output data of the digital twinborn model as initial power grid state data; determining position information of the power grid equipment according to the point cloud data, and determining fault information of the power grid equipment according to the historical maintenance data; performing simulation analysis on the position information and the fault information, and determining a predicted fault rate of each power grid device; determining the updating frequency of each power grid device according to the position information, the predicted fault rate and the historical maintenance data; and updating the initial power grid state data corresponding to each power grid device according to the updating frequency to obtain real-time power grid state data, and displaying the real-time power grid state data. According to the method, different sampling updating frequencies are set for different devices, and the data processing amount is reduced while the data is updated in time.

Description

Technical Field

[0001] The present invention relates to the field of power grid monitoring technology, and in particular to a power grid visualization monitoring method, system, equipment and medium based on a Zhikan platform. Background Art

[0002] At present, big data platforms such as the Southern Power Grid Zhikan Platform can be based on a unified power grid data model, use maps as the entrance, carry graphics, topology, and ledger management of all types of power grid equipment, realize the integration of geographic, physical, and management data, and expand new energy and integrated energy models on this basis, deepen the platform's ability to support business, and provide support for distributed power access design and operation monitoring, and distribution network intelligent planning under the new power system.

[0003] The existing power grid system is usually equipped with multiple power equipment and transmission lines. When monitoring the power grid equipment, a fixed sampling frequency is generally used to transmit the power grid data to the monitoring system to ensure timely data updates. However, if the sampling frequency is set to a higher frequency, the sampling frequency of the secondary equipment will be too frequent, increasing the data processing capacity of the monitoring system; if the sampling frequency is set to a lower frequency, the operating data of important equipment will not be updated in time, and there is a risk of inadequate monitoring. Therefore, the above-mentioned transmission method using a fixed sampling frequency cannot meet the demand for setting different sampling frequencies for different devices, which is not conducive to the automated operation of the entire monitoring system. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is: how to solve the problem that the sampling frequency of the existing method is too frequent, which leads to an increase in the data processing volume of the monitoring system, the operation data cannot be updated in time, and the monitoring is not in place.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a power grid visualization monitoring method based on the Zhikan platform, comprising: obtaining point cloud data of power grid equipment, as well as user operation data, historical maintenance data, and power grid operation data of corresponding power grid equipment; constructing a digital twin model based on the user operation data, historical maintenance data, point cloud data, and power grid operation data, and using the output data of the digital twin model as initial power grid status data; determining the location information of the power grid equipment based on the point cloud data, and determining the fault information of the power grid equipment based on the historical maintenance data; simulating and analyzing the location information and fault information to determine the predicted failure rate of each power grid equipment; determining the update frequency of each power grid equipment based on the location information, predicted failure rate, and historical maintenance data; updating the initial power grid status data corresponding to each power grid equipment according to the update frequency to obtain real-time power grid status data, and displaying the real-time power grid status data.

[0007] As a preferred solution of the power grid visualization monitoring method based on the Zhikan platform described in the present invention, wherein: the digital twin model includes a digital copy of each power grid device in the power grid; the determination of the update frequency of each power grid device includes determining the importance value of each power grid device based on location information, predicted failure rate and historical maintenance data; the update frequency of each power grid device is determined according to the mapping relationship between the importance value and the preset importance value and the update frequency.

[0008] As a preferred solution of the power grid visualization monitoring method based on the Zhikan platform described in the present invention, wherein: the importance value of each power grid equipment is determined based on the location information, predicted failure rate and historical maintenance data, including: respectively determining the location grade factor corresponding to the location information of each power grid equipment, and respectively determining the number of historical maintenance times corresponding to the historical maintenance data of each power grid equipment; the importance value of each power grid equipment is determined by matching the location grade factor, predicted failure rate and historical maintenance times.

[0009] As a preferred solution of the power grid visualization monitoring method based on the Zhikan platform described in the present invention, wherein: the importance value of each power grid equipment is determined by matching the location grade factor, predicted failure rate and historical maintenance times, including calculating the location grade factor, predicted failure rate and historical maintenance times according to a preset proportional coefficient to obtain the importance value of each power grid equipment; or inputting the location grade factor, predicted failure rate and historical maintenance times into a preset importance value database for matching to obtain the importance value of each power grid equipment.

[0010] As a preferred solution of the power grid visualization monitoring method based on the Zhikan platform described in the present invention, wherein: the determination of the predicted failure rate of each power grid device includes obtaining historical fault type, historical fault time and fault location data; constructing and training a gradient boosting machine model based on historical fault type, historical fault time, fault location data and power grid operation data, and when the loss function of the gradient boosting machine model is less than a preset loss value, obtaining a trained gradient boosting machine model; extracting the fault type, fault time and fault location data from the location information and fault information, and simulating and analyzing the fault type, fault time and fault location data based on the trained gradient boosting machine model to determine the predicted failure rate of each power grid device.

[0011] As a preferred solution of the power grid visualization monitoring method based on the Zhikan platform described in the present invention, wherein: the updating of the initial power grid status data includes obtaining updated point cloud data and updated historical maintenance data of the power grid equipment when the update frequency is met; determining the updated location information according to the updated point cloud data, and determining the updated fault information according to the updated historical maintenance data; using the digital twin model to simulate and analyze the updated location information and the updated fault information to determine the updated predicted failure rate of each power grid equipment; determining the update frequency of each power grid equipment according to the updated location information, the updated predicted failure rate and the updated historical maintenance data, so as to update the initial power grid status data corresponding to each power grid equipment according to the update frequency.

[0012] As a preferred solution of the power grid visualization monitoring method based on the Zhikan platform described in the present invention, the display of real-time power grid status data includes displaying the real-time power grid status data through any one of 3D charts, radar charts, topology charts, and heat charts. The real-time power grid status data includes abnormal trend charts, abnormal proportion analysis results, equipment alarm analysis results, and equipment failure trend charts.

[0013] Another object of the present invention is to provide a system for a visual monitoring method of a power grid based on the Zhikan platform, which can solve the problem of visual monitoring of a power grid based on the Zhikan platform by constructing a visual monitoring system of a power grid based on the Zhikan platform.

[0014] In order to solve the above technical problems, the present invention provides the following technical solutions: a power grid visualization monitoring system based on the Zhikan platform, including a data acquisition module, a state output module, an information determination module, a fault prediction module, a frequency determination module and a data display module; the data acquisition module is used to acquire point cloud data of power grid equipment, as well as user operation data, historical maintenance data and power grid operation data of the corresponding power grid equipment; the state output module is used to build a digital twin model according to the user operation data, historical maintenance data, point cloud data and power grid operation data, and use the output data of the digital twin model as initial power grid state data; the information determination module is used to determine the location information of the power grid equipment according to the point cloud data, and determine the fault information of the power grid equipment according to the historical maintenance data; the fault prediction module is used to simulate and analyze the location information and fault information to determine the predicted failure rate of each power grid equipment; the frequency determination module is used to determine the update frequency of each power grid equipment according to the location information, the predicted failure rate and the historical maintenance data; the data display module is used to update the initial power grid state data corresponding to each power grid equipment according to the update frequency, obtain real-time power grid state data, and display the real-time power grid state data.

[0015] A computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the power grid visualization monitoring method based on the Zhikan platform as described above are implemented.

[0016] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the power grid visualization monitoring method based on the Zhikan platform as described above.

[0017] The beneficial effects of the present invention are as follows: the power grid visualization monitoring method based on the Zhikan platform provided by the present invention can determine the update frequency of each power grid device according to the location information, predicted failure rate and historical maintenance data of each power grid device. Specifically, the fault information of the power grid device is determined through historical maintenance data and then the failure rate is simulated to determine the update frequency of each power grid device, so that the monitoring frequency of the power grid device is adjusted to reduce the data processing volume; according to the location information, predicted failure rate and historical maintenance data, the importance value of each power grid device is determined, and the mapping relationship between the importance value and the preset importance value and the update frequency is achieved, so as to set different sampling update frequencies for different devices, reduce the data processing volume while meeting the needs of timely data update and timely monitoring, thereby improving the operating efficiency of the monitoring system and facilitating the automated operation of the entire monitoring system. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0019] Figure 1 A flowchart of a method for visually monitoring a power grid based on the Zhikan platform is provided for the first embodiment of the present invention.

[0020] Figure 2 A structural diagram of a power grid visualization monitoring system based on the Zhikan platform provided for the second embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0022] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0023] Example 1, reference Figure 1 , which is the first embodiment of the present invention, and this embodiment provides a power grid visualization monitoring method based on the Zhikan platform, including: obtaining point cloud data of power grid equipment, as well as user operation data, historical maintenance data, and power grid operation data of corresponding power grid equipment; building a digital twin model according to the user operation data, historical maintenance data, point cloud data, and power grid operation data, and using the output data of the digital twin model as initial power grid state data; determining the location information of the power grid equipment according to the point cloud data, and determining the fault information of the power grid equipment according to the historical maintenance data; simulating and analyzing the location information and fault information to determine the predicted failure rate of each power grid equipment; determining the update frequency of each power grid equipment according to the location information, the predicted failure rate, and the historical maintenance data; updating the initial power grid state data corresponding to each power grid equipment according to the update frequency to obtain real-time power grid state data, and displaying the real-time power grid state data.

[0024] S1. Obtain point cloud data of power grid equipment, as well as user operation data, historical maintenance data, and power grid operation data of corresponding power grid equipment.

[0025] S2. Build a digital twin model based on user operation data, historical maintenance data, point cloud data, and power grid operation data, and use the output data of the digital twin model as initial power grid state data; wherein the digital twin model includes a digital copy of each power grid device in the power grid.

[0026] S3. Determine the location information of the power grid equipment based on the point cloud data, and determine the fault information of the power grid equipment based on the historical maintenance data.

[0027] S4. Perform simulation analysis on the location information and fault information to determine the predicted failure rate of each power grid device.

[0028] S5. Determine the update frequency of each power grid device based on the location information, predicted failure rate and historical maintenance data.

[0029] S6. Update the initial grid status data corresponding to each grid device according to the update frequency to obtain real-time grid status data, and display the real-time grid status data.

[0030] It should be noted that the big data platform is a platform or data processing terminal that uses digital means to reengineer processes, drive service changes, and improve user experience. This platform uses map technology as a carrier, is driven by geographic, physical, and management data, and is one of the new generation of digital power grid operation basic platforms for the entire network and society. It integrates data from the power generation production field, explores multi-dimensional and three-dimensional fusion analysis and display of data, and realizes seamless connection between business specifications and IT system construction. In addition, the big data platform also carries the graphics, topology, and ledger management of all types of power grid equipment, realizes the integration of geographic, physical, and management data, and expands applications such as new energy and integrated energy services on this basis.

[0031] Optionally, the big data platform includes the Zhikan platform, and may also be other data processing terminals with data comprehensive processing functions, which is not limited in the present invention.

[0032] Accordingly, continue to refer to Figure 1 The embodiment of the present invention provides a visual monitoring method for a power grid based on the Zhikan platform, which is executed by a data processing terminal and includes the following steps:

[0033] S1. Obtain point cloud data of power grid equipment, as well as user operation data, historical maintenance data, and power grid operation data of corresponding power grid equipment.

[0034] S2. Build a digital twin model based on user operation data, historical maintenance data, point cloud data, and power grid operation data, and use the output data of the digital twin model as initial power grid state data; wherein the digital twin model includes a digital copy of each power grid device in the power grid.

[0035] S3. Determine the location information of the power grid equipment based on the point cloud data, and determine the fault information of the power grid equipment based on the historical maintenance data.

[0036] S4. Perform simulation analysis on the location information and fault information to determine the predicted failure rate of each power grid device.

[0037] S5. Determine the update frequency of each power grid device based on the location information, predicted failure rate and historical maintenance data.

[0038] S6. Update the initial grid status data corresponding to each grid device according to the update frequency to obtain real-time grid status data, and display the real-time grid status data.

[0039] The embodiments of the present invention can determine the update frequency of each power grid device according to the location information, predicted failure rate and historical maintenance data of each power grid device, and set different sampling update frequencies for different devices. While meeting the requirements of timely data update and timely monitoring, the amount of data processing is reduced, thereby improving the operating efficiency of the monitoring system and facilitating the automated operation of the entire monitoring system.

[0040] In step S1, point cloud data of power grid equipment, as well as user operation data, historical maintenance data, and power grid operation data of the corresponding power grid equipment are obtained.

[0041] Point cloud data is a data structure that represents the surface of an object or environment through a collection of a large number of points in three-dimensional space. Each point usually contains X, Y, and Z coordinates, and may contain other attributes such as color, reflection intensity, timestamp, etc. Point cloud data can be acquired by drone-mounted cameras or lidars to facilitate subsequent modeling through digital twin models.

[0042] Among them, user operation data includes user-entered setting parameters, special monitoring settings, display requirements, etc., such as marking a certain power grid equipment. Historical maintenance data includes historical fault types, historical fault times, historical maintenance times, historical maintenance operation records and other data, which are used to record the process from fault occurrence to fault resolution; power grid operation data includes current, voltage, power, temperature, etc., which can be obtained through sensors.

[0043] In step S2, a digital twin model is constructed based on user operation data, historical maintenance data, point cloud data, and power grid operation data, and the output data of the digital twin model is used as initial power grid state data; wherein the digital twin model includes a digital copy of each power grid device in the power grid.

[0044] It is worth noting that digital twin technology is a method of data monitoring and analysis by creating virtual digital copies of physical entities. In the big data platform "Southern Power Grid Zhikan", the application of digital twin technology is mainly reflected in the following aspects to achieve visual data monitoring: First, create an accurate digital copy of each physical device and component in the power grid. These digital copies can reflect the status and behavior of the physical entity; then, integrate sensor data, operation data and other relevant information from the physical power grid into the digital twin model to ensure that the digital copy can reflect the status of the physical entity in real time; then, through real-time data flow, the digital twin model is synchronized with the physical power grid. Any changes in the physical power grid will be immediately reflected in the digital copy. Finally, the digital twin model is displayed in the form of a graphical interface using the platform's visualization tools. Users can intuitively see the real-time status of the power grid through this interface. In addition, the digital twin model is equipped with machine learning algorithms, which can be used to analyze the historical data and current status of the power grid, as well as predict future trends and potential problems. In these ways, the digital twin technology is used to achieve comprehensive visual monitoring of the power grid, improving the operating efficiency, reliability and safety of the power grid.

[0045] Specifically, the digital twin model includes a digital copy of each grid device in the power grid. The establishment of the digital twin model is a process involving multiple steps, mainly including the following key links. First, it is necessary to collect data of physical entities, including user operation data, historical maintenance data, point cloud data, and grid operation data; then, the model can be defined using the digital twin definition language (DTDL) or other methods. The model is a generic definition of each entity type existing in the environment, describing a single type of entity based on attributes, relationships, and components; then, a digital twin is created, and a digital twin is created based on the defined model. These twins represent specific entities in the physical environment, such as buildings, machine parts, etc. Relationships are established between digital twins to reflect their interactions and connections in the physical world. Finally, real-time data is integrated into the digital twin model to ensure that the model can reflect the current state and behavior of the entity. After the model is established, the output data of the digital twin model is used as the initial grid state data. Exemplarily, tools such as AzureDigital Twins Explorer can also be used to visualize the initial grid state data, so as to better understand and analyze the digital twin model and realize real-time monitoring of the grid state.

[0046] In step S3, the location information of the power grid equipment is determined according to the point cloud data, and the fault information of the power grid equipment is determined according to the historical maintenance data.

[0047] It should be noted that the point cloud data in this embodiment is a data structure that represents the surface of an object or environment through a collection of a large number of points in three-dimensional space. Each point usually contains X, Y, and Z coordinates, and the location information of the power grid equipment is represented by the corresponding coordinates. The historical maintenance data includes historical fault types, historical fault times, historical maintenance times, historical maintenance operation records, etc., which are used to record the process from the occurrence of a fault to the resolution of the fault. Fault information related to the fault can be extracted and called from the historical maintenance data to facilitate subsequent fault prediction.

[0048] In step S4, the location information and the fault information are simulated and analyzed to determine the predicted fault rate of each power grid device.

[0049] It should be noted that the big data platform in this embodiment is configured with digital twin models and machine learning algorithms, such as random forests, gradient boosting machines, neural learning networks, etc., and learns through the data provided by the digital twin model to achieve fault prediction of power grid equipment.

[0050] Specifically, the location information and fault information are simulated and analyzed to determine the predicted failure rate of each power grid device, including:

[0051] Obtain historical fault type, historical fault time and fault location data;

[0052] According to the historical fault type, historical fault time, fault location data and power grid operation data, a gradient boosting machine model is constructed and trained. When the loss function of the gradient boosting machine model is less than a preset loss value, a trained gradient boosting machine model is obtained.

[0053] The fault type, fault time and fault location data are extracted from the location information and fault information, and the fault type, fault time and fault location data are simulated and analyzed based on the trained gradient boosting machine model to determine the predicted failure rate of each power grid equipment.

[0054] The fault information includes the historical fault type and the historical fault time. The corresponding fault location data can be found from the location information according to the fault information.

[0055] Exemplarily, this embodiment is described by taking the gradient boosting machine model as an example. The gradient boosting machine (GBM) is an integrated learning algorithm that minimizes the loss function by gradually adding a prediction weak model (usually a decision tree). The following are the steps for using the gradient boosting machine training model to identify fault modes: first, collect historical fault type, historical fault time and fault location data, clean the data, and process missing values, outliers and erroneous data. Next, select features that are helpful in identifying faults from the original data, and divide the data set into a training set and a test set, usually using a ratio of 70-30% or 80-20%. Then, define a loss function, such as a mean square error (MSE) loss function or judge by an expected value loss function, and iteratively train a new weak model on the training set, and each new model attempts to correct the residual of the previous model. Finally, when it is determined that the loss function of the gradient boosting machine model is less than the preset loss value, the trained gradient boosting machine model is obtained. It is worth noting that when using the gradient boosting machine, it is important to avoid overfitting, which can be achieved by setting appropriate parameters such as the learning rate, the maximum depth of the tree, and the minimum number of sample splits.

[0056] Furthermore, the fault type, fault time and fault location data are extracted from the location information and fault information, and the fault type, fault time and fault location data are simulated and analyzed based on the trained gradient boosting model to determine the predicted failure rate of each power grid device. Exemplarily, the expected value η of the accuracy of the prediction result can be used to show whether the prediction result is ideal, including:

[0057]

[0058] Where n represents the number of model iterations; m represents the prediction result; and Q represents the predicted failure rate. Theoretically, the expected value η should be 1.0, and the effective range of η is set to ±0.05. When the expected value η is within the effective range, it proves that the prediction model has met the requirements of practical application. Otherwise, it proves that the model should continue to be optimized or the model is unusable. When the prediction model meets the requirements of practical application, the predicted failure rate of each power grid device can be determined.

[0059] In step S5, the update frequency of each power grid device is determined based on the location information, the predicted failure rate and the historical maintenance data.

[0060] It should be noted that, as time goes by, the digital twin model needs to be continuously updated to reflect the changes in the physical entity, ensure the accuracy and relevance of the model, and ensure the accuracy of monitoring. The present invention can set different update frequencies for different power grid equipment to achieve timely updates of the balancing system and reduce the demand for data volume.

[0061] In one embodiment, determining the update frequency of each power grid device based on the location information, the predicted failure rate, and the historical maintenance data includes:

[0062] Determine the importance of each power grid device based on location information, predicted failure rate and historical maintenance data;

[0063] The update frequency of each power grid device is determined according to the importance value and the mapping relationship between the preset importance value and the update frequency.

[0064] Among them, the mapping relationship between the importance value and the update frequency can be pre-configured in the server, for example, stored in the form of a database or a mapping table. After the importance value of each power grid device is calculated, the update frequency of each power grid device can be obtained through the mapping relationship between the importance value and the update frequency. Exemplarily, the mapping relationship between the importance value and the update frequency is shown in Table 1 below.

[0065] Table 1 Mapping relationship between importance value and update frequency

[0066]

[0067]

[0068] Furthermore, the importance value of each power grid equipment is determined based on the location information, predicted failure rate and historical maintenance data, including:

[0069] The location level factors corresponding to the location information of each power grid device are determined respectively, and the number of historical maintenance times corresponding to the historical maintenance data of each power grid device are determined respectively.

[0070] The importance value of each power grid equipment is determined by matching the location grade factor, predicted failure rate and historical maintenance times.

[0071] In one implementation, the importance value of each power grid device is determined by matching the location level factor, the predicted failure rate, and the number of historical maintenance times, including:

[0072] The location grade factor, predicted failure rate and historical maintenance times are calculated according to the preset proportionality coefficient to obtain the importance value of each power grid equipment.

[0073] It should be noted that the location level factor can be divided into "core level (for example, set to 80 points)", "important level (for example, set to 50 points)", and "secondary level (for example, set to 30 points)". The corresponding location level factor is determined according to the location information of the power grid equipment. The core level indicates that the location of the power grid equipment is very important, such as the node location of the substation. The number of historical maintenance times can be read and called from the historical maintenance data. For example, assuming the location level factor score a, predicted failure rate b, and historical maintenance times c, the coefficients are μ1, μ2, and μ3 respectively, and the corresponding importance value = μ1*a+μ2*b*100+μ3*c.

[0074] In another implementation, the importance value of each power grid device is determined by matching the location level factor, the predicted failure rate, and the number of historical maintenance times, including:

[0075] The location grade factor, predicted failure rate and historical maintenance times are input into a preset importance value database for matching to obtain the importance value of each power grid equipment.

[0076] Specifically, the importance value database can be pre-configured and stored in the memory of the big data platform. The importance value database can be determined based on simulation data or empirical values, and the importance value can be obtained by searching the corresponding database when applied. Exemplarily, when the location level factor is "core level", it can be recorded as a score a1, when the location level factor is "important level", it can be recorded as a score a2, and when the location level factor is "secondary level", it can be recorded as a score a3, where a1>a2>a3, the core level indicates that the location of the power grid equipment is very important, such as the node location of the power distribution center; the predicted failure rate of 0-10% can be recorded as a score b1, the predicted failure rate of 10-30% can be recorded as a score b2, and the predicted failure rate of more than 30% can be recorded as a score b3, where b3>b2>b1; the number of historical maintenance times 0-3 times can be recorded as a score c1, and the number of historical maintenance times more than 3 times can be recorded as a score c2, where c2 is greater than c1. It can be obtained that the score value of the importance value is the sum of the three, that is, a+b+c, the value of a is selected from a1, a2, and a3, the value of b is selected from b1, b2, and b3, and the value of c is selected from c1 and c2. It should be noted that the above interval division and database configuration are only examples, and the present invention does not limit this.

[0077] In step S6, the initial grid state data corresponding to each grid device is updated according to the update frequency to obtain real-time grid state data, and the real-time grid state data is displayed.

[0078] Exemplarily, real-time power grid status data can be displayed in any of the following ways: 3D charts, radar charts, topology charts, and heat maps. The real-time power grid status data includes abnormal trend charts, abnormal proportion analysis results, equipment alarm analysis results, and equipment failure trend charts.

[0079] In order to facilitate the understanding of the present invention, some preferred embodiments of the present invention are further described below.

[0080] In one implementation, the method further includes:

[0081] When the update frequency is met, the updated point cloud data of the power grid equipment and the updated historical maintenance data are obtained;

[0082] Determine updated location information based on updated point cloud data, and determine updated fault information based on updated historical maintenance data;

[0083] Use the digital twin model to simulate and analyze the updated location information and updated fault information to determine the updated predicted failure rate of each power grid device;

[0084] The update frequency of each power grid device is determined according to the updated location information, the updated predicted failure rate and the updated historical maintenance data, so as to update the initial power grid state data corresponding to each power grid device according to the update frequency.

[0085] In this embodiment, after each data update, the updated point cloud data of the power grid equipment and the updated historical maintenance data are obtained. Since the data has changed, the corresponding update frequency also needs to change accordingly. Steps S3-S5 need to be called again to obtain a new update frequency to achieve closed-loop control of the entire system. The process of calculating the update frequency has been described in detail in steps S3-S5 and will not be repeated here.

[0086] In summary, the present invention provides a power grid visualization monitoring method based on the Zhikan platform, including: obtaining point cloud data of power grid equipment, as well as user operation data, historical maintenance data, and power grid operation data of corresponding power grid equipment; constructing a digital twin model based on the user operation data, historical maintenance data, point cloud data, and power grid operation data, and using the output data of the digital twin model as initial power grid state data; wherein the digital twin model includes a digital copy of each power grid equipment in the power grid; determining the location information of the power grid equipment based on the point cloud data, and determining the fault information of the power grid equipment based on the historical maintenance data; simulating and analyzing the location information and fault information to determine the predicted failure rate of each power grid equipment; determining the update frequency of each power grid equipment based on the location information, predicted failure rate and historical maintenance data; updating the initial power grid state data corresponding to each power grid equipment according to the update frequency to obtain real-time power grid state data, and displaying the real-time power grid state data.

[0087] The present invention can determine the update frequency of each power grid device according to the location information, predicted failure rate and historical maintenance data of each power grid device, and set different sampling update frequencies for different devices. It can reduce the data processing volume while meeting the requirements of timely data update and timely monitoring, thereby improving the operating efficiency of the monitoring system and facilitating the automated operation of the entire monitoring system.

[0088] Example 2, reference Figure 2 , which is the second embodiment of the present invention. It is different from the previous embodiment in that it provides a power grid visualization monitoring system based on the Zhikan platform, including: a data acquisition module 100, a state output module 200, an information determination module 300, a fault prediction module 400, a frequency determination module 500 and a data display module 600.

[0089] The data acquisition module 100 is used to acquire point cloud data of power grid equipment, as well as user operation data, historical maintenance data, and power grid operation data of the corresponding power grid equipment.

[0090] The state output module 200 is used to build a digital twin model based on user operation data, historical maintenance data, point cloud data and power grid operation data, and use the output data of the digital twin model as initial power grid state data.

[0091] The information determination module 300 is used to determine the location information of the power grid equipment according to the point cloud data, and to determine the fault information of the power grid equipment according to the historical maintenance data.

[0092] The fault prediction module 400 is used to perform simulation analysis on the location information and the fault information to determine the predicted fault rate of each power grid device.

[0093] The frequency determination module 500 is used to determine the update frequency of each power grid device according to the location information, the predicted failure rate and the historical maintenance data.

[0094] The data display module 600 is used to update the initial grid state data corresponding to each grid device according to the update frequency, obtain the real-time grid state data, and display the real-time grid state data.

[0095] It should be noted that the big data platform is a platform or data processing terminal that uses digital means to reengineer processes, drive service changes, and improve user experience. This platform uses map technology as a carrier, is driven by geographic, physical, and management data, and is one of the new generation of digital power grid operation basic platforms for the entire network and society. It integrates data from the power generation production field, explores multi-dimensional and three-dimensional fusion analysis and display of data, and realizes seamless connection between business specifications and IT system construction. In addition, the big data platform also carries the graphics, topology, and ledger management of all types of power grid equipment, realizes the integration of geographic, physical, and management data, and expands applications such as new energy and integrated energy services on this basis.

[0096] Optionally, the big data platform includes the Zhikan platform, and may also be other data processing terminals with data comprehensive processing functions, which is not limited in the present invention.

[0097] Accordingly, refer to Figure 2 The embodiment of the present invention provides a power grid visualization monitoring system based on the Zhikan platform, including:

[0098] The data acquisition module 100 is used to acquire point cloud data of power grid equipment, as well as user operation data, historical maintenance data, and power grid operation data of the corresponding power grid equipment.

[0099] The status output module 200 is used to build a digital twin model based on user operation data, historical maintenance data, point cloud data and power grid operation data, and use the output data of the digital twin model as initial power grid status data; wherein the digital twin model includes a digital copy of each power grid device in the power grid.

[0100] The information determination module 300 is used to determine the location information of the power grid equipment according to the point cloud data, and to determine the fault information of the power grid equipment according to the historical maintenance data.

[0101] The fault prediction module 400 is used to perform simulation analysis on the location information and the fault information to determine the predicted fault rate of each power grid device.

[0102] The frequency determination module 500 is used to determine the update frequency of each power grid device according to the location information, the predicted failure rate and the historical maintenance data.

[0103] The data display module 600 is used to update the initial grid state data corresponding to each grid device according to the update frequency, obtain the real-time grid state data, and display the real-time grid state data.

[0104] Optionally, the frequency determination module 500 is further configured to:

[0105] Determine the importance of each power grid device based on location information, predicted failure rate and historical maintenance data;

[0106] The update frequency of each power grid device is determined according to the importance value and the mapping relationship between the preset importance value and the update frequency.

[0107] Optionally, the frequency determination module 500 is further configured to:

[0108] Determine respectively the location level factor corresponding to the location information of each power grid device, and determine respectively the number of historical maintenance times corresponding to the historical maintenance data of each power grid device;

[0109] The importance value of each power grid equipment is determined by matching the location grade factor, predicted failure rate and historical maintenance times.

[0110] Optionally, the frequency determination module 500 is further configured to:

[0111] Calculate the location grade factor, predicted failure rate and historical maintenance times according to a preset proportionality coefficient to obtain the importance value of each power grid equipment; or

[0112] The location grade factor, predicted failure rate and historical maintenance times are input into a preset importance value database for matching to obtain the importance value of each power grid equipment.

[0113] Optionally, the fault prediction module 400 is further configured to:

[0114] Obtain historical fault type, historical fault time and fault location data;

[0115] According to the historical fault type, historical fault time, fault location data and power grid operation data, a gradient boosting machine model is constructed and trained. When the loss function of the gradient boosting machine model is less than a preset loss value, a trained gradient boosting machine model is obtained.

[0116] The fault type, fault time and fault location data are extracted from the location information and fault information, and the fault type, fault time and fault location data are simulated and analyzed based on the trained gradient boosting machine model to determine the predicted failure rate of each power grid equipment.

[0117] Optionally, the system is also used to:

[0118] When the update frequency is met, the updated point cloud data of the power grid equipment and the updated historical maintenance data are obtained;

[0119] Determine updated location information based on updated point cloud data, and determine updated fault information based on updated historical maintenance data;

[0120] Use the digital twin model to simulate and analyze the updated location information and updated fault information to determine the updated predicted failure rate of each power grid device;

[0121] The update frequency of each power grid device is determined according to the updated location information, the updated predicted failure rate and the updated historical maintenance data, so as to update the initial power grid state data corresponding to each power grid device according to the update frequency.

[0122] Optionally, the data display module 600 is further used for:

[0123] Real-time power grid status data is displayed through any of the following methods: 3D charts, radar charts, topology charts, and heat maps. The real-time power grid status data includes abnormal trend charts, abnormal proportion analysis results, equipment alarm analysis results, and equipment failure trend charts.

[0124] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0125] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0126] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0127] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0128] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A visual monitoring method for power grid based on the Zhikan platform, characterized by: include, Obtain point cloud data of power grid equipment, as well as user operation data, historical maintenance data, and power grid operation data of corresponding power grid equipment; A digital twin model is constructed based on user operation data, historical maintenance data, point cloud data, and power grid operation data, and the output data of the digital twin model is used as the initial power grid status data; Determine the location information of power grid equipment based on point cloud data, and determine the fault information of power grid equipment based on historical maintenance data; Simulate and analyze location information and fault information to determine the predicted failure rate of each power grid device; Determine the update frequency of each grid device based on location information, predicted failure rates and historical maintenance data; The initial grid status data corresponding to each grid device is updated according to the update frequency to obtain real-time grid status data, and the real-time grid status data is displayed.

2. The method for visual monitoring of power grid based on Zhikan platform according to claim 1, characterized in that: The digital twin model includes a digital replica of each grid device in the grid; Determining the update frequency of each power grid device includes determining the importance value of each power grid device based on location information, predicted failure rate and historical maintenance data; The update frequency of each power grid device is determined according to the importance value and the mapping relationship between the preset importance value and the update frequency.

3. The method for visual monitoring of power grid based on Zhikan platform according to claim 2, characterized in that: Determining the importance value of each power grid device according to the location information, predicted failure rate and historical maintenance data includes respectively determining the location level factor corresponding to the location information of each power grid device and respectively determining the number of historical maintenance times corresponding to the historical maintenance data of each power grid device; The importance value of each power grid equipment is determined by matching the location grade factor, predicted failure rate and historical maintenance times.

4. The method for visual monitoring of power grid based on Zhikan platform according to claim 3, characterized in that: The determining the importance value of each power grid device by matching the location grade factor, the predicted failure rate and the historical maintenance times includes calculating the location grade factor, the predicted failure rate and the historical maintenance times according to a preset proportionality coefficient to obtain the importance value of each power grid device; Alternatively, the location grade factor, predicted failure rate and historical maintenance times are input into a preset importance value database for matching to obtain the importance value of each power grid equipment.

5. The method for visual monitoring of power grid based on Zhikan platform according to claim 4, characterized in that: Determining the predicted failure rate of each power grid device includes obtaining historical failure type, historical failure time and failure location data; According to the historical fault type, historical fault time, fault location data and power grid operation data, a gradient boosting machine model is constructed and trained. When the loss function of the gradient boosting machine model is less than a preset loss value, a trained gradient boosting machine model is obtained. The fault type, fault time and fault location data are extracted from the location information and fault information, and the fault type, fault time and fault location data are simulated and analyzed based on the trained gradient boosting machine model to determine the predicted failure rate of each power grid equipment.

6. The method for visual monitoring of power grid based on Zhikan platform according to claim 5, characterized in that: The updating of the initial power grid state data includes obtaining updated point cloud data of power grid equipment and updated historical maintenance data when the update frequency is met; Determine updated location information based on updated point cloud data, and determine updated fault information based on updated historical maintenance data; Use the digital twin model to simulate and analyze the updated location information and updated fault information to determine the updated predicted failure rate of each power grid device; The update frequency of each power grid device is determined according to the updated location information, the updated predicted failure rate and the updated historical maintenance data, so as to update the initial power grid state data corresponding to each power grid device according to the update frequency.

7. The method for visual monitoring of power grid based on Zhikan platform according to claim 6, characterized in that: The display of real-time power grid status data includes displaying the real-time power grid status data through any one of 3D charts, radar charts, topology charts, and heat maps. The real-time power grid status data includes abnormal trend charts, abnormal proportion analysis results, equipment alarm analysis results, and equipment failure trend charts.

8. A system using the power grid visualization monitoring method based on the Zhikan platform as claimed in any one of claims 1 to 7, characterized in that: It comprises a data acquisition module (100), a state output module (200), an information determination module (300), a fault prediction module (400), a frequency determination module (500) and a data display module (600); The data acquisition module (100) is used to acquire point cloud data of power grid equipment, as well as user operation data, historical maintenance data, and power grid operation data of the corresponding power grid equipment; The state output module (200) is used to construct a digital twin model based on user operation data, historical maintenance data, point cloud data and power grid operation data, and use the output data of the digital twin model as initial power grid state data; The information determination module (300) is used to determine the location information of the power grid equipment according to the point cloud data, and to determine the fault information of the power grid equipment according to the historical maintenance data; The fault prediction module (400) is used to simulate and analyze the location information and fault information to determine the predicted fault rate of each power grid device; The frequency determination module (500) is used to determine the update frequency of each power grid device according to the location information, the predicted failure rate and the historical maintenance data; The data display module (600) is used to update the initial grid state data corresponding to each grid device according to the update frequency, obtain real-time grid state data, and display the real-time grid state data.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the power grid visualization monitoring method based on the Zhikan platform described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the power grid visualization monitoring method based on the Zhikan platform described in any one of claims 1 to 7 are implemented.

Images