Data analysis method, device and equipment of power transmission line and storage medium

Abstract

The invention discloses a data analysis method for a power transmission line, and the method comprises the steps: obtaining historical monitoring data in the power transmission line in response to a data analysis operation for the power transmission line; constructing a first data analysis knowledge graph corresponding to the power transmission line according to the historical monitoring data; analyzing a knowledge graph through the first data, and obtaining a first feature corresponding to the power transmission line; and constructing a first data analysis model according to the first feature, and performing data analysis operation on the current monitoring data through the first data analysis model. The invention further discloses a corresponding device, equipment and a storage medium. By implementing the method, the relevance between the monitoring data can be deeply analyzed, and the accuracy of a data analysis result is improved.

Description

Technical Field

[0001] The present invention relates to the field of big data, and in particular to a data analysis method, device, equipment and storage medium for a power transmission line. Background Art

[0002] Transmission lines are an important part of the power system, and their stable operation plays a key role in ensuring the reliable supply of electricity. Since transmission lines are affected by various factors such as environmental conditions and equipment aging during operation, real-time acquisition and analysis of monitoring data is very necessary to ensure the reliability and safety of the lines. By effectively analyzing and processing the monitoring data, abnormal situations can be identified in a timely manner, and necessary maintenance measures can be taken to avoid the adverse effects of faults on the power grid.

[0003] At present, the analysis of monitoring data in transmission lines usually adopts a relatively simple evaluation system. In this method, the evaluation system is trained by using historical monitoring data, and the trained evaluation system is used to analyze the monitoring data in the transmission lines. However, only through the above method, the evaluation system after simple training cannot deeply analyze the correlation between the monitoring data. Especially when there is a large amount of monitoring data, the above evaluation system cannot fully reflect the complex operating conditions of the transmission line. Therefore, there is a problem of low accuracy of the data analysis results given in the end. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a data analysis method, device, equipment and storage medium for a transmission line, which can deeply analyze the correlation between monitoring data and improve the accuracy of data analysis results.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: As a first aspect of the present invention, a data analysis method for a transmission line is provided, which includes the following steps: in response to a data analysis operation on the transmission line, historical monitoring data in the transmission line is obtained; based on the historical monitoring data, a first data analysis knowledge graph corresponding to the transmission line is constructed; through the first data analysis knowledge graph, a first feature corresponding to the transmission line is obtained, the first feature includes a tower inclination feature, a conductor stress feature, and a cross-span section structure feature; a first data analysis model is constructed according to the first feature, and a data analysis operation is performed on the current monitoring data through the first data analysis model.

[0006] Optionally, based on the historical monitoring data, a first data analysis knowledge graph corresponding to the transmission line is constructed, specifically including: classifying the historical monitoring data, and obtaining feature association relationships between the historical monitoring data based on the classification results, the feature association relationships including the tower inclination relationship, the conductor tension and tower force relationship, and the spatial structure relationship of the crossing and spanning sections; using the historical monitoring data as nodes and the feature association relationships as edges to construct the first data analysis knowledge graph.

[0007] Optionally, obtaining a first feature corresponding to the power transmission line through the first data analysis knowledge graph specifically includes: obtaining a target feature value corresponding to the feature to be confirmed through the following formula:

[0008]

[0009] Among them, K k is the target feature value, k represents the feature type corresponding to the feature to be confirmed, and f k is a summary function used to calculate the target feature value of the kth type of features to be confirmed. The summary function includes the average function, the weighted function, and the time series analysis function. is the first set of nodes of the kth type, is the second set of the k-th edge, v is the node attribute corresponding to any element in the first set, and e is the edge attribute corresponding to any element in the second set. Represents a set of node attributes and edge attributes; determines whether the target feature value is greater than or equal to the preset condition feature value corresponding to the first feature; if the target feature value is greater than or equal to the preset condition feature value corresponding to the first feature, the feature to be confirmed is used as the first feature.

[0010] Optionally, after constructing a first data analysis model based on the first feature and performing data analysis operations on the current monitoring data through the first data analysis model, the method also includes: obtaining abnormal monitoring data in the current monitoring data through the first data analysis model; correcting the abnormal monitoring data in a preset manner, and constructing a second data analysis knowledge graph through the corrected current monitoring data; obtaining a second feature corresponding to the transmission line through the second data analysis knowledge graph, and improving the first data analysis model into a second data analysis model through the second feature; and performing data analysis operations on the current monitoring data through the second data analysis model.

[0011] Optionally, obtaining abnormal monitoring data in the current monitoring data by using the first data analysis model specifically includes: calculating the fault probability that the abnormal monitoring data exists in the current monitoring data by using the following formula:

[0012]

[0013] Among them, y is the failure probability, g is the failure probability evaluation function, Z(K) is the set of the first feature, θ i is the weight parameter corresponding to the first feature of the i-th category, m is the total number of types of the first feature, z i is the eigenvalue corresponding to the first feature of the i-th category, ∈ is the model error term; if it is confirmed that the fault probability is greater than the preset fault probability, the abnormal monitoring data in the current monitoring data is obtained according to the fault probability.

[0014] Optionally, abnormal monitoring data in the current monitoring data is obtained according to the fault probability, specifically including: obtaining the fault data to be confirmed, the fault data to be confirmed is any monitoring data in the current monitoring data; calculating the contribution value of the fault data to be confirmed to the fault probability; if it is confirmed that the contribution value is greater than the preset contribution value, the fault data to be confirmed is confirmed as abnormal monitoring data.

[0015] Optionally, the abnormal monitoring data is corrected according to a preset method, specifically including: calculating the abnormal characteristic value of the abnormal monitoring data, and confirming the abnormal data type corresponding to the abnormal monitoring data based on the abnormal characteristic value; obtaining the correction method corresponding to the abnormal data type in a preset correction database, the preset correction database is used to store the correspondence between the abnormal data type and the correction method, the correction method including the interpolation correction method, the mean smoothing correction method and the limiting correction method; and correcting the abnormal monitoring data according to the correction method.

[0016] As a second aspect of the present invention, a data analysis device for a power transmission line is also provided, which includes an acquisition module and a processing module, wherein:

[0017] An acquisition module is used to obtain historical monitoring data in the transmission line in response to a data analysis operation on the transmission line; construct a first data analysis knowledge graph corresponding to the transmission line based on the historical monitoring data; and obtain a first feature corresponding to the transmission line through the first data analysis knowledge graph, the first feature including a tower inclination feature, a conductor stress feature, and a cross-span section structure feature.

[0018] The processing module is used to construct a first data analysis model according to the first feature, and perform data analysis operations on the current monitoring data through the first data analysis model.

[0019] As a third aspect of the present invention, an electronic device is also provided, including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes any one of the methods described above.

[0020] As a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor as any one of the methods described above.

[0021] The implementation of the embodiments of the present invention has the following beneficial effects:

[0022] The present invention provides a data analysis, device, equipment and storage medium for a transmission line. By responding to a data analysis operation on a transmission line, historical monitoring data in the transmission line is obtained, and a first data analysis knowledge graph corresponding to the transmission line is constructed based on the historical monitoring data. A first feature corresponding to the transmission line is obtained through the first data analysis knowledge graph, and a first data analysis model is constructed based on the first feature. A data analysis operation is performed on the current monitoring data through the first data analysis model, thereby constructing a first data analysis model through the complex historical monitoring data association features in the first data analysis knowledge graph, and performing data analysis operations through the first data analysis model, which greatly improves the accuracy of the data analysis results.

[0023] In the present invention, by performing classification operations on historical monitoring data and obtaining feature association relationships between historical monitoring data based on the classification results, a first data analysis knowledge graph is constructed with historical monitoring data as nodes and feature association relationships as edges, thereby providing a data basis for the construction of a first data analysis model, so as to facilitate the construction of the first data analysis model based on the complex historical monitoring data association features in the first data analysis knowledge graph, thereby greatly improving the accuracy of the data analysis results of the first data analysis model.

[0024] In the present invention, abnormal monitoring data in the current monitoring data is obtained through the first data analysis model, the abnormal monitoring data is corrected according to a preset method, and a second data analysis knowledge graph is constructed through the corrected current monitoring data; the second feature corresponding to the transmission line is obtained through the second data analysis knowledge graph, and the first data analysis model is improved into the second data analysis model through the second feature; data analysis operations are performed on the current monitoring data through the second data analysis model, so that the first data analysis model is improved into the second data analysis model through the corrected current monitoring data, thereby further improving the accuracy of the data analysis results of the data analysis model. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, without paying creative labor, other drawings obtained based on these drawings still belong to the scope of the present invention.

[0026] Figure 1 It is a main flow diagram of an embodiment of a data analysis method for a power transmission line provided by the present invention;

[0027] Figure 2 It is a module schematic diagram of an embodiment of a data analysis device for a power transmission line provided by the present invention;

[0028] Figure 3 It is a structural schematic diagram of an embodiment of an electronic device provided by the present invention.

[0029] Explanation of the reference numerals: 21, acquisition module; 22, processing module; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0030] In order to make the objectives, technical solutions and advantages of the present invention more clear, the present invention will be further described in detail below with reference to the accompanying drawings.

[0031] like Figure 1 As shown,

[0032] Please refer to Figure 1 , which shows a schematic flow chart of a data analysis method for a power transmission line provided by an embodiment of the present invention, the flow chart mainly includes the following steps: S101 to S104.

[0033] Step S101 : in response to a data analysis operation on a power transmission line, obtaining historical monitoring data in the power transmission line.

[0034] Specifically, when a user performs data analysis operations on a transmission line, historical monitoring data of the transmission line is obtained. The historical monitoring data generally includes different types of data information, including but not limited to: tower inclination data, which reflects the change in the inclination of the tower and is used to evaluate the stability and structural health of the tower; conductor force data, including characteristic values ​​such as conductor tension and sag. These data are used to monitor the stress state of the conductor under temperature and load changes, and to analyze whether the conductor has problems such as excessive stretching; cross-span structure data, which mainly records the distance and location of the transmission line crossing other structures such as roads, railways, buildings, etc., as well as the state of the conductors in the area, and is used to evaluate the safety of the cross-span section; electrical parameter data, including voltage, current, power factor, etc., which can reflect the electrical state of the transmission line. In the embodiments provided by the present invention, historical monitoring data can be obtained in a variety of ways, including but not limited to: the database of the real-time monitoring system, modern power transmission lines are usually equipped with online monitoring equipment, which transmits the collected data to the central database in real time, and can directly access the database to call historical data by time or event; Internet of Things (IoT) equipment collection, sensors are installed at key locations of the power transmission line, such as tilt sensors, stress sensors, electrical parameter sensors, etc. The data collected by these devices will be collected into the data platform through the Internet of Things for subsequent calls. The present invention does not limit the collection method of historical monitoring data.

[0035] Step S102: construct a first data analysis knowledge graph corresponding to the transmission line based on historical monitoring data.

[0036] Specifically, the historical monitoring data are classified, and the characteristic correlation relationship between the historical monitoring data is obtained according to the classification results. The characteristic correlation relationship includes the relationship between the inclination of the tower, the relationship between the tension of the conductor and the force of the tower, and the spatial structure relationship of the crossing and spanning section. The steps of the classification operation are as follows: First, the data are divided into different categories according to the content of the historical monitoring data. Then, different data processing is performed for different types of data. For example, for the tower data, the inclination angle and deformation data are extracted; for the conductor data, the tension and sag are extracted; for the crossing and spanning section data, the spanning distance, the ground wire position and other data are extracted; for the environmental data, the temperature is extracted. , humidity, wind speed and other data. After that, the extracted data is standardized so that the data can be better compared and associated in the map. For example, the values ​​of tension and tilt angle are converted into a unified dimension. Finally, the feature correlation relationship is extracted according to the correlation of different data categories, including but not limited to: the tower tilt relationship, which describes the change law between the tower tilt data; the conductor tension and tower force relationship, which describes the influence of the conductor tension on the tower force; the spatial structure relationship of the cross-span section, which describes the position and distance relationship between the transmission line and the cross-span structure; the first data analysis knowledge is constructed with historical monitoring data as nodes and feature correlation relationships as edges. The steps of graph recognition include S21 to S24. S21, establishing nodes: taking the feature items in the historical monitoring data as nodes, defining the specific features of each type of data, including but not limited to the inclination angle of the pole tower, the tension value of the conductor, etc., and taking the above specific features as the nodes of the first data analysis knowledge graph, for example, establishing "pole tower inclination node", "conductor tension node", "ambient temperature node", etc.; S22, defining the type of edge: defining the type of edge according to the feature association relationship extracted above, different types of data nodes have different relationship edges, such as the "force relationship edge" of the associated pole tower and the conductor, the "environmental impact edge" of the associated pole tower and the environment, and the associated cross "Spatial structure relationship edges" that span segments and conductors, etc.; S23, building association relationships between nodes: assigning specific weights and attributes to the nodes and edges in the first data analysis knowledge graph. For example, according to the conductor tension and tower force characteristics, calculate their association strength and use it as the weight of the "force relationship edge"; S24, knowledge graph structure optimization: structurally optimize the initially constructed first data analysis knowledge graph, simplify the graph structure by removing redundant edges, merging similar nodes, etc., to improve the efficiency of subsequent analysis, and store the optimized first data analysis knowledge graph to ensure that it can be accessed and updated in real time during subsequent data analysis.

[0037] Step S103, obtaining a first feature corresponding to the transmission line through a first data analysis knowledge graph, wherein the first feature includes a tower tilt feature, a conductor stress feature, and a cross-span section structure feature.

[0038] Specifically, by taking the nodes and edges of the first data analysis knowledge graph as input and obtaining the first feature corresponding to the transmission line according to the feature extraction model, the steps are as follows: first, the target feature value corresponding to the feature to be confirmed is obtained by the following formula:

[0039]

[0040] Among them, K k is the target feature value, k represents the feature type corresponding to the feature to be confirmed, and f k is a summary function used to calculate the target feature value of the kth type of features to be confirmed. The summary function includes the average function, the weighted function, and the time series analysis function. is the first set of nodes of the kth type, is the second set of the k-th edge, v is the node attribute corresponding to any element in the first set, and e is the edge attribute corresponding to any element in the second set. Represents a collection of node attributes and edge attributes; determines whether the target feature value is greater than or equal to the preset condition feature value corresponding to the first feature, where the preset condition feature value is a specific threshold or standard parameter, which is used to determine whether the feature to be confirmed meets certain performance or structural requirements, and needs to be set differently according to different feature types. For example, for the structural stability threshold: it is used to determine whether the tower tilt feature is within a reasonable range to ensure the safety and stability of the tower structure; for the conductor tension threshold: it is used to determine the conductor force feature to ensure that the conductor tension is within a safe limit to prevent the conductor from being excessively relaxed or stretched; for the spatial distance safety threshold: it is used to determine the structural features of the crossing span section to ensure that the distance between the conductor and the spanning object is within a safe range to prevent Touch or short circuit risk; if the target feature value is greater than or equal to the preset condition feature value corresponding to the first feature, the feature to be confirmed is taken as the first feature, and the first feature includes but is not limited to: tower inclination feature, conductor force feature and cross-span section structure feature; finally, all the features to be confirmed whose target feature values ​​are greater than or equal to the preset condition feature value are taken as the set of first features. For example, if there are 4 features to be confirmed, namely K1, K2, K3, and K4, where the target feature values ​​corresponding to K1, K3, and K4 are greater than or equal to the preset condition feature value, and the target feature value corresponding to K2 is less than the preset condition feature value, then the set of first features can be expressed as Z(K)=[K1, K3, K4], where Z(K) is the set of first features.

[0041] Step S104: construct a first data analysis model according to the first feature, and perform data analysis operations on the current monitoring data through the first data analysis model.

[0042] Specifically, according to the type of the first feature, a suitable first data analysis model type is selected, and characteristic values ​​are calculated from the set of first features, and these characteristic values ​​are used as input variables of the model to construct a first data analysis model. By inputting the current monitoring data into the first data analysis model, a prediction result is output, that is, the failure probability of abnormal monitoring data in the monitoring data, and the failure probability output by the model is analyzed to determine whether the failure probability exceeds the preset failure probability, thereby identifying potential abnormal monitoring data and completing the data analysis operation.

[0043] In a possible implementation, step S104 also includes: obtaining abnormal monitoring data in the current monitoring data through the first data analysis model; correcting the abnormal monitoring data according to a preset method, and constructing a second data analysis knowledge graph through the corrected current monitoring data; obtaining a second feature corresponding to the transmission line through the second data analysis knowledge graph, and improving the first data analysis model into a second data analysis model through the second feature; and performing data analysis operations on the current monitoring data through the second data analysis model.

[0044] Specifically, the abnormal monitoring data in the current monitoring data is obtained by the first data analysis model, and the specific steps are as follows: the fault probability of the abnormal monitoring data in the current monitoring data is calculated by the following formula:

[0045]

[0046] Among them, y is the failure probability, g is the failure probability evaluation function, Z(K) is the set of the first feature, θ i is the weight parameter corresponding to the first feature of the i-th category, m is the total number of types of the first feature, z i is the eigenvalue corresponding to the first feature of the i-th category, ∈ is the model error term, which represents the error between the model prediction value and the true value. The error term can come from a variety of factors, such as data noise, simplified assumptions of the model, incomplete feature extraction, etc. In an embodiment of the present invention, the model error term can be obtained in a variety of ways, for example: historical data residual analysis: based on a large amount of historical monitoring data, the residual between the model prediction value and the true value is calculated, and the mean and variance of these residuals are used to estimate the error term. Specifically, assuming that the error term conforms to a certain statistical distribution (such as a normal distribution), the error term can be fitted and obtained by the mean and standard deviation of the historical residual data; model cross-validation: through the cross-validation technique, the data set is divided into a training set and a validation set, the training set is used for model training, and then the error distribution of the model is evaluated in the validation set to estimate the model error term; Bayesian estimation: through the Bayesian estimation method, the model error term is used as a random variable, and is estimated in combination with prior information and observed data.

[0047] In this process, the prior distribution and likelihood function of the error term can be combined, and the optimal estimate of the error term can be calculated through the posterior distribution. If it is confirmed that the fault probability is greater than the preset fault probability, the abnormal monitoring data in the current monitoring data is obtained according to the fault probability, and then the to-be-confirmed fault data is obtained. The to-be-confirmed fault data is any monitoring data in the current monitoring data, and the contribution value of the to-be-confirmed fault data to the fault probability is calculated. If the confirmed contribution value is greater than the preset contribution value, the to-be-confirmed fault data is confirmed as abnormal monitoring data; the abnormal monitoring data is corrected according to the preset method, and the second data analysis knowledge graph is constructed through the corrected current monitoring data. The steps for correcting the abnormal monitoring data according to the preset method are as follows: Calculate the abnormal characteristic value of the abnormal monitoring data, and confirm the abnormality corresponding to the abnormal monitoring data according to the abnormal characteristic value. Data type; obtain the correction method corresponding to the abnormal data type in the preset correction database, the preset correction database is used to store the corresponding relationship between the abnormal data type and the correction method, and the correction method includes an interpolation correction method, a mean smoothing correction method and a limit correction method; correct the abnormal monitoring data according to the correction method, for example, when the abnormal characteristic value is missing or significantly deviates from the historical mean, the characteristic values ​​of adjacent time points are interpolated to correct the abnormal characteristic value; when the abnormal characteristic value fluctuates violently, the fluctuation is smoothed by taking the mean of the characteristic values ​​of adjacent time points; when the abnormal characteristic value exceeds the reasonable range, it is corrected to the preset maximum or minimum limit to ensure that the characteristic value conforms to the reasonable range. Afterwards, through the corrected current monitoring data, a second data analysis knowledge graph is constructed according to the method described in step S102, and through the second data analysis knowledge graph, the second feature corresponding to the transmission line is obtained, and the first data analysis model is improved to the second data analysis model through the second feature, so as to perform data analysis operations according to the improved second data analysis model, thereby improving the accuracy of model analysis.

[0048] The present invention adopts the above method, responds to the data analysis operation on the transmission line, obtains the historical monitoring data in the transmission line, and constructs the first data analysis knowledge graph corresponding to the transmission line based on the historical monitoring data, and obtains the first feature corresponding to the transmission line through the first data analysis knowledge graph, and then constructs the first data analysis model according to the first feature, and performs data analysis operation on the current monitoring data through the first data analysis model, so as to construct the first data analysis model through the complex historical monitoring data association features in the first data analysis knowledge graph, and perform data analysis operation through the first data analysis model, thereby greatly improving the accuracy of the data analysis results.

[0049] Please refer to Figure 2 , which shows a module schematic diagram of a data analysis device for a power transmission line provided by an embodiment of the present invention, the device includes an acquisition module 21 and a processing module 22, wherein:

[0050] The acquisition module 21 is used to obtain historical monitoring data in the transmission line in response to the data analysis operation on the transmission line; construct a first data analysis knowledge graph corresponding to the transmission line based on the historical monitoring data; obtain the first feature corresponding to the transmission line through the first data analysis knowledge graph, and the first feature includes the tower inclination feature, the conductor force feature and the cross-span section structure feature.

[0051] The processing module 22 is used to construct a first data analysis model according to the first feature, and perform data analysis operations on the current monitoring data through the first data analysis model.

[0052] In a possible implementation, the acquisition module 21 is used to construct a first data analysis knowledge graph corresponding to the transmission line based on historical monitoring data, specifically including: performing classification operations on the historical monitoring data, and obtaining feature association relationships between the historical monitoring data based on the classification results, the feature association relationships including the tower inclination relationship, the conductor tension and tower force relationship, and the spatial structure relationship of the crossing and spanning sections; constructing the first data analysis knowledge graph with historical monitoring data as nodes and feature association relationships as edges.

[0053] In a possible implementation, the acquisition module 21 is used to acquire the first feature corresponding to the power transmission line through the first data analysis knowledge graph, specifically including: acquiring the target feature value corresponding to the feature to be confirmed through the following formula:

[0054]

[0055] Among them, K k is the target feature value, k represents the feature type corresponding to the feature to be confirmed, and f k is a summary function used to calculate the target feature value of the kth type of features to be confirmed. The summary function includes the average function, the weighted function, and the time series analysis function. is the first set of nodes of the kth type, is the second set of the k-th edge, v is the node attribute corresponding to any element in the first set, and e is the edge attribute corresponding to any element in the second set. Represents a set of node attributes and edge attributes; determines whether the target feature value is greater than or equal to the preset condition feature value corresponding to the first feature; if the target feature value is greater than or equal to the preset condition feature value corresponding to the first feature, the feature to be confirmed is used as the first feature.

[0056] In one possible implementation, the processing module 22 is used to construct a first data analysis model based on the first feature, and after performing data analysis operations on the current monitoring data through the first data analysis model, obtain abnormal monitoring data in the current monitoring data through the first data analysis model; correct the abnormal monitoring data in a preset manner, and construct a second data analysis knowledge graph through the corrected current monitoring data; obtain the second feature corresponding to the transmission line through the second data analysis knowledge graph, and improve the first data analysis model into a second data analysis model through the second feature; and perform data analysis operations on the current monitoring data through the second data analysis model.

[0057] In a possible implementation, the processing module 22 is used to obtain abnormal monitoring data in the current monitoring data through the first data analysis model, specifically including: calculating the fault probability that the abnormal monitoring data exists in the current monitoring data through the following formula:

[0058]

[0059] Among them, y is the failure probability, g is the failure probability evaluation function, Z(K) is the set of the first feature, θ i is the weight parameter corresponding to the first feature of the i-th category, m is the total number of types of the first feature, z i is the eigenvalue corresponding to the first feature of the i-th category, ∈ is the model error term; if it is confirmed that the fault probability is greater than the preset fault probability, the abnormal monitoring data in the current monitoring data is obtained according to the fault probability.

[0060] In a possible implementation, the processing module 22 is used to obtain abnormal monitoring data in the current monitoring data based on the fault probability, specifically including: obtaining the fault data to be confirmed, the fault data to be confirmed is any monitoring data in the current monitoring data; calculating the contribution value of the fault data to be confirmed to the fault probability; if it is confirmed that the contribution value is greater than the preset contribution value, the fault data to be confirmed is confirmed as abnormal monitoring data.

[0061] In one possible implementation, the processing module 22 is used to correct the abnormal monitoring data according to a preset method, specifically including: calculating the abnormal characteristic value of the abnormal monitoring data, and confirming the abnormal data type corresponding to the abnormal monitoring data based on the abnormal characteristic value; obtaining the correction method corresponding to the abnormal data type in a preset correction database, the preset correction database is used to store the correspondence between the abnormal data type and the correction method, the correction method including an interpolation correction method, a mean smoothing correction method and a limiting correction method; and correcting the abnormal monitoring data according to the correction method.

[0062] It should be noted that: when the device provided in the above embodiment realizes its functions, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and their specific implementation process is detailed in Figure 1 The described method embodiments are not described in detail here.

[0063] The present invention also provides an electronic device. Figure 3 , Figure 3 The electronic device may include: at least one processor 301 , at least one communication bus 302 , a user interface 303 , at least one network interface 304 , and a memory 305 .

[0064] The communication bus 302 is used to realize the connection and communication between these components.

[0065] The user interface 303 may include a display screen (Display) and a camera (Camera). The optional user interface 303 may also include a standard wired interface and a wireless interface.

[0066] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0067] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0068] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 , the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a data analysis application for a power transmission line.

[0069] exist Figure 3In the electronic device shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the data analysis application for the power transmission line stored in the memory 305. When executed by one or more processors 301, the electronic device executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present invention is not limited to the described order of actions, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present invention.

[0070] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions. When executed by one or more processors, the electronic device executes one or more of the methods described in the above embodiments.

[0071] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0072] In the several embodiments provided by the present invention, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0073] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0074] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0075] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0076] The implementation of the embodiments of the present invention has the following beneficial effects:

[0077] The present invention provides a data analysis, device, equipment and storage medium for a transmission line. By responding to a data analysis operation on a transmission line, historical monitoring data in the transmission line is obtained, and a first data analysis knowledge graph corresponding to the transmission line is constructed based on the historical monitoring data. A first feature corresponding to the transmission line is obtained through the first data analysis knowledge graph, and a first data analysis model is constructed based on the first feature. A data analysis operation is performed on the current monitoring data through the first data analysis model, thereby constructing a first data analysis model through the complex historical monitoring data association features in the first data analysis knowledge graph, and performing data analysis operations through the first data analysis model, which greatly improves the accuracy of the data analysis results.

[0078] In the present invention, by performing classification operations on historical monitoring data and obtaining feature association relationships between historical monitoring data based on the classification results, a first data analysis knowledge graph is constructed with historical monitoring data as nodes and feature association relationships as edges, thereby providing a data basis for the construction of a first data analysis model, so as to facilitate the construction of the first data analysis model based on the complex historical monitoring data association features in the first data analysis knowledge graph, thereby greatly improving the accuracy of the data analysis results of the first data analysis model.

[0079] In the present invention, abnormal monitoring data in the current monitoring data is obtained through the first data analysis model, the abnormal monitoring data is corrected according to a preset method, and a second data analysis knowledge graph is constructed through the corrected current monitoring data; the second feature corresponding to the transmission line is obtained through the second data analysis knowledge graph, and the first data analysis model is improved into the second data analysis model through the second feature; data analysis operations are performed on the current monitoring data through the second data analysis model, so that the first data analysis model is improved into the second data analysis model through the corrected current monitoring data, thereby further improving the accuracy of the data analysis results of the data analysis model.

[0080] The above disclosure is only a preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A data analysis method for a power transmission line, characterized in that: The method comprises: In response to a data analysis operation on a power transmission line, acquiring historical monitoring data in the power transmission line; Constructing a first data analysis knowledge graph corresponding to the transmission line according to the historical monitoring data; By analyzing the knowledge graph of the first data, a first feature corresponding to the transmission line is obtained, wherein the first feature includes a tower tilt feature, a conductor stress feature, and a cross-span section structure feature; A first data analysis model is constructed according to the first feature, and the data analysis operation is performed on the current monitoring data through the first data analysis model.

2. The method according to claim 1, characterized in that The constructing, according to the historical monitoring data, a first data analysis knowledge graph corresponding to the transmission line specifically includes: Classifying the historical monitoring data, and obtaining characteristic correlation relationships between the historical monitoring data according to the classification results, wherein the characteristic correlation relationships include the tower tilt relationship, the conductor tension and tower force relationship, and the cross-span spatial structure relationship; The first data analysis knowledge graph is constructed with the historical monitoring data as nodes and the feature association relationships as edges.

3. The method according to claim 2, characterized in that The acquiring of the first feature corresponding to the power transmission line by analyzing the knowledge graph through the first data specifically includes: The target feature value corresponding to the feature to be confirmed is obtained through the following formula: Among them, K k is the target feature value, k represents the feature type corresponding to the feature to be confirmed, and f k is a summary function for calculating the target feature value of the k-th type of features to be confirmed, wherein the summary function includes an average function, a weighting function, and a time series analysis function. is the first set of nodes of the kth class, is the second set of the k-th type of edges, v is the node attribute corresponding to any element in the first set, and e is the edge attribute corresponding to any element in the second set, then represents a set of the node attributes and the edge attributes; Determine whether the target feature value is greater than or equal to a preset condition feature value corresponding to the first feature; If the target feature value is greater than or equal to the preset condition feature value corresponding to the first feature, the feature to be confirmed is used as the first feature.

4. The method according to claim 3, characterized in that After constructing a first data analysis model according to the first feature and performing the data analysis operation on the current monitoring data through the first data analysis model, the method further includes: Acquire abnormal monitoring data in the current monitoring data through the first data analysis model; Correcting the abnormal monitoring data in a preset manner, and constructing a second data analysis knowledge graph through the corrected current monitoring data; Obtain a second feature corresponding to the power transmission line through the second data analysis knowledge graph, and improve the first data analysis model into a second data analysis model through the second feature; The data analysis operation is performed on the current monitoring data through the second data analysis model.

5. The method according to claim 4, characterized in that The obtaining of abnormal monitoring data in the current monitoring data by using the first data analysis model specifically includes: The fault probability of the abnormal monitoring data existing in the current monitoring data is calculated by the following formula: Wherein, y is the failure probability, g is the failure probability evaluation function, Z(K) is the set of the first features, θ i is the weight parameter corresponding to the first feature of the i-th category, m is the total number of types of the first feature, z i is the eigenvalue corresponding to the first feature of the i-th category, ∈ is the model error term; If it is confirmed that the fault probability is greater than a preset fault probability, the abnormal monitoring data in the current monitoring data is obtained according to the fault probability.

6. The method according to claim 5, characterized in that The acquiring the abnormal monitoring data in the current monitoring data according to the failure probability specifically includes: Acquire the fault data to be confirmed, where the fault data to be confirmed is any monitoring data in the current monitoring data; Calculating the contribution value of the to-be-confirmed fault data to the fault probability; If it is confirmed that the contribution value is greater than the preset contribution value, the to-be-confirmed fault data is confirmed as the abnormal monitoring data.

7. The method according to claim 6, characterized in that The correcting of the abnormal monitoring data in a preset manner specifically includes: Calculating an abnormal feature value of the abnormal monitoring data, and confirming an abnormal data type corresponding to the abnormal monitoring data according to the abnormal feature value; Acquire a correction method corresponding to the abnormal data type in a preset correction database, wherein the preset correction database is used to store a corresponding relationship between the abnormal data type and the correction method, wherein the correction method includes an interpolation correction method, a mean smoothing correction method, and a limiting correction method; The abnormal monitoring data is corrected according to the correction method.

8. A data analysis device for a power transmission line, characterized in that: The device comprises an acquisition module and a processing module, wherein: The acquisition module is used to obtain historical monitoring data in the transmission line in response to a data analysis operation on the transmission line; construct a first data analysis knowledge graph corresponding to the transmission line according to the historical monitoring data; obtain a first feature corresponding to the transmission line through the first data analysis knowledge graph, wherein the first feature includes a tower tilt feature, a conductor force feature, and a cross-span section structure feature; The processing module is used to construct a first data analysis model according to the first feature, and perform the data analysis operation on the current monitoring data through the first data analysis model.

9. An electronic device, characterized in that: It includes a processor, a communication bus, a user interface, a network interface and a memory, wherein the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is performed.

Images