Method, system and equipment for measuring impact grounding resistance of base tower and medium

Abstract

The invention discloses a method, a system, equipment and a medium for measuring the impact grounding resistance of a base tower, and particularly relates to the technical field of high voltage, and the technical key points are as follows: establishing a factor directed graph based on a first influence factor set constructed by environment characteristics and soil characteristics of a base tower mounting area and in combination with a pre-constructed factor association rule; processing the node features by using a random forest to obtain an influence factor generation model; obtaining a second influence factor set constructed by the environmental characteristics and soil characteristics of the base tower installation area at the current measurement moment, and inputting the second influence factor set into the influence factor generation model to obtain an influence factor at the current measurement moment; inputting impact current into a grounding loop formed by the first base tower and the second base tower, and measuring to obtain the initial impact grounding resistance of the grounding device of the second base tower; and correcting the initial impact grounding resistance by using the influence factor, and outputting the corrected impact grounding resistance.

Description

Technical Field

[0001] The present invention relates to the field of high voltage technology, and in particular to a method, system, equipment and medium for measuring the impact grounding resistance of a base tower. Background Art

[0002] The primary function of a lightning protection grounding device on a transmission line tower is to effectively dissipate lightning current into the ground when the power system or power equipment is struck by lightning, while also stabilizing the grounding device's potential to ground within a safe range to prevent lightning overvoltage strikes. The operating status of the lightning protection grounding device is directly related to the safe and stable operation of the transmission line, and surge resistance is a key indicator of the lightning protection characteristics of a transmission line tower. The grounding device must not only be able to withstand power-frequency short-circuit fault currents but, more importantly, meet the requirements of lightning current surges. However, when measuring surge grounding resistance on towers, the results are often affected by environmental factors and soil properties, resulting in inaccurate measurements, which can lead to serious consequences. Therefore, accurate measurement of surge grounding resistance on power line towers is extremely important.

[0003] A Chinese patent publication numbered CN108008197A discloses a tower impulse grounding resistance measurement method that considers soil spatial moisture distribution. This technical solution considers the impact of soil spatial moisture distribution on the overall impulse grounding resistance. A Chinese patent publication numbered CN108008198A discloses a ground grid impulse grounding resistance measurement method that considers ground grid temperature. This technical solution considers the impact of the ground grid surrounding temperature distribution on the overall impulse grounding resistance. A Chinese patent publication numbered CN108020725A discloses a ground grid impulse grounding resistance measurement method under the influence of different soil pH levels. This technical solution considers the impact of soil pH on the overall impulse grounding resistance. However, the above-mentioned existing technical solutions only consider a single influencing factor on the impact grounding resistance measurement, while the impact grounding resistance measurement is affected by multiple factors at the same time. At the same time, the above-mentioned existing technologies do not consider the interaction between different influencing factors. This relatively independent measurement method that only considers a single factor is difficult to cope with complex geographical environments, and it is difficult to obtain accurate measurement data in complex environments.

[0004] Therefore, the present invention aims to provide a method, system, device and medium for measuring the impact grounding resistance of a base tower to solve the above-mentioned related problems. Summary of the Invention

[0005] The technical problem to be solved by the present invention is that the existing impact grounding resistance measurement method only considers a single influencing factor and is difficult to cope with complex geographical environments, resulting in a lack of measurement data accuracy. The purpose is to provide a base tower impact grounding resistance measurement method, system, equipment and medium. By integrating environmental characteristics and soil characteristics, a factor directed graph that characterizes the correlation between multiple influencing factors is constructed, the multi-factor interaction relationship is made explicit, the synergistic influence between multiple influencing factors is captured, and comprehensive modeling of the multi-dimensional characteristics of the measurement area is achieved; the features of the factor directed graph are extracted by a graph neural network and processed using a random forest algorithm to obtain an influence factor generation model that integrates the synergistic relationship of multiple factors to generate influence factors; at the same time, the influence factor output by the influence factor generation model of the present invention integrates the comprehensive effects of multiple factors, rather than a single physical quantity correction, and performs multi-dimensional physical constraint correction on the initial impact grounding resistance value, thereby solving the accuracy loss of traditional methods in dynamic environments and the scenario limitations of traditional static corrections, and being able to achieve high-precision measurement in extreme environments.

[0006] The present invention is achieved through the following technical solutions: A method for measuring the impact grounding resistance of a base tower, the method comprising: Based on a first set of influencing factors constructed from the environmental characteristics and soil characteristics of the base tower installation area, combined with pre-constructed factor association rules, a factor directed graph is established; wherein the factor association rules are used to characterize the association relationship between different influencing factors; Graph neural networks are used to extract node features from the factor directed graph, and random forests are used to process the node features to obtain an influencing factor generation model; Obtaining a second influencing factor set constructed based on environmental characteristics and soil characteristics of the base tower installation area at the current measurement moment, and inputting the second influencing factor set into an influencing factor generation model to obtain an influencing factor at the current measurement moment; Inputting an impulse current into a grounding loop formed by the first pole tower and the second pole tower, and measuring an initial impulse grounding resistance of a grounding device of the second pole tower; The initial impulse grounding resistance is corrected using the influencing factor and the corrected impulse grounding resistance is output.

[0007] Furthermore, based on the first influencing factor set constructed by the environmental characteristics and soil characteristics of the base tower installation area, combined with the pre-constructed factor association rules, a factor directed graph is established, specifically: A first set of influencing factors is constructed based on the environmental characteristics and soil characteristics of the base tower installation area at historical moments, wherein the environmental characteristics include regional temperature and regional altitude; and the soil characteristics include soil moisture, soil resistivity, and soil salinity; Based on pre-built factor association rules, the association relationship between the influencing factors of environmental characteristics and soil characteristics is obtained; Each influencing factor is taken as a graph node and the relationship between influencing factors is taken as an edge to construct a factor directed graph.

[0008] Furthermore, we use graph neural networks to extract node features from the factor directed graph, and use random forests to process the node features to obtain an influencing factor generation model, specifically: Utilize graph neural networks to randomly extract feature information of factor directed graphs and generate multiple node feature matrices; Generate classification and regression trees of multiple node feature matrices based on the random forest algorithm, and calculate the Gini coefficients of multiple node feature matrices; For the multiple node feature matrices where the current node of the classification and regression tree is located, when the Gini coefficients of the multiple node feature matrices are not less than the Gini coefficient threshold, the Gini coefficient of each feature information in the node feature matrix where the current node is located is calculated; when the Gini coefficients of the multiple node feature matrices are less than the Gini coefficient threshold, the random forest algorithm returns to the child decision tree and stops recursion; The feature information corresponding to the minimum Gini coefficient among the Gini coefficients of each feature information is used as the optimal feature information, and the corresponding node feature matrix is divided into a first feature matrix and a second feature matrix based on the optimal feature information, and the first feature matrix and the second feature matrix are used as the left child node and the right child node of the current node respectively; Calculate the Gini coefficient of the first feature matrix and the second feature matrix. When the Gini coefficient of the first feature matrix and the second feature matrix is less than the Gini coefficient threshold, the random forest algorithm returns to the child decision tree and stops recursion, generating multiple decision trees. Under the pre-built relationship constraints, multiple classifiers learn multiple decision trees to obtain an impact factor generation model.

[0009] Furthermore, the method also includes: constructing relationship constraints based on pre-constructed factor association rules; wherein the relationship constraints include regional temperature-soil moisture constraints, soil moisture-soil resistivity constraints, and regional temperature-soil salinity constraints.

[0010] Furthermore, the regional temperature-soil moisture constraint is specifically: ,in, Indicates soil moisture, represents the regional temperature, are constraint parameters, represents the saturation temperature threshold; the soil moisture-soil resistivity constraint is specifically: ,in, represents the soil resistivity, , represents the dry soil resistivity, It represents the coefficient that controls the growth rate of resistivity in dry area as humidity decreases; represents the soil moisture threshold; Indicates the resistivity of water; Indicates the sensitivity of soil resistivity changes in moisture-saturated areas; represents the Archie index, , Indicates the soil saturation moisture in the moisture-saturated area, represents the saturation factor, represents the transition region weight, The regional temperature-soil salinity constraint is specifically: ,in, Indicates soil salinity. , Indicates the base salt content, represents the attenuation coefficient of the frozen zone, Indicates the reference temperature, Indicates the freezing temperature threshold, represents the linear coefficient of the transition region, represents the Gaussian attenuation coefficient in the transition region, represents the threshold temperature, Indicates the saturated salt content of the soil. represents the hyperbolic tangent function, Saturation coefficient.

[0011] Furthermore, the grounding loop formed by the first base tower and the second base tower is specifically composed of the OPGW ground wire connected between the first base tower, the second base tower, the grounding down conductor of the first base tower, the grounding down conductor of the second base tower, the first base tower, the grounding device of the first base tower, the grounding device of the second base tower and the second base tower.

[0012] The present invention further provides a base tower impulse grounding resistance measurement system, which is used in any one of the above base tower impulse grounding resistance measurement methods, and the system includes: The first module is configured to establish a factor directed graph based on a first set of influencing factors constructed based on environmental characteristics and soil characteristics of the base tower installation area, in combination with pre-established factor association rules; wherein the factor association rules are used to characterize the association relationship between different influencing factors; The second module is used to extract node features from the factor directed graph using graph neural networks and process the node features using random forests to obtain an impact factor generation model; The third module is used to obtain a second influencing factor set constructed by the environmental characteristics and soil characteristics of the base tower installation area at the current measurement moment, and input the second influencing factor set into the influencing factor generation model to obtain the influencing factor at the current measurement moment; The fourth module is used to input an impulse current into the grounding loop formed by the first base tower and the second base tower, and measure the initial impulse grounding resistance of the grounding device of the second base tower; The fifth module is used to correct the initial impulse grounding resistance using the influencing factor and output the corrected impulse grounding resistance.

[0013] The present invention also provides a computer device, comprising a system memory and a processor, wherein the system memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0014] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any one of the methods described above are implemented.

[0015] The present invention also provides a computer program product comprising instructions, which, when executed by a computer device cluster, enables the computer device cluster to execute any of the above methods. Compared with the prior art, the present invention has the following advantages and beneficial effects: In the present invention, by integrating environmental characteristics and soil characteristics, a factor directed graph that characterizes the correlation between multiple influencing factors is constructed, the multi-factor interaction relationship is made explicit, the synergistic influence between multiple influencing factors is captured, and comprehensive modeling of the multi-dimensional characteristics of the measurement area is achieved; the features of the factor directed graph are extracted by a graph neural network, and processed by a random forest algorithm to obtain an influencing factor generation model that integrates the synergistic relationship of multiple factors to generate influencing factors; at the same time, the influencing factors output by the influencing factor generation model of the present invention integrate the comprehensive effects of multiple factors, rather than a single physical quantity correction, and perform multi-dimensional physical constraint correction on the initial impact grounding resistance value, thereby solving the accuracy loss of traditional methods in dynamic environments, solving the scenario limitations of traditional static corrections, and being able to achieve high-precision measurements in extreme environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the examples. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be considered as limiting the scope. A person of ordinary skill in the art can also derive other relevant drawings based on these drawings without inventive effort. In the drawings: Figure 1This is a flow chart of a method for measuring the impact grounding resistance of a base tower in this embodiment; Figure 2 Schematic diagram of the structure of a base tower impact grounding resistance measurement system in this embodiment; Figure 3 This is a structural diagram of a computer device in this embodiment. DETAILED DESCRIPTION

[0017] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be appreciated by those skilled in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0018] In this disclosure, unless otherwise specified, the use of terms such as "first" and "second" to describe various elements is not intended to limit the positional relationship, temporal relationship, or importance relationship of these elements. Such terms are only used to distinguish one element from another. In some examples, the first element and the second element may refer to the same instance of the element, while in some cases, based on the context of the description, they may also refer to different instances.

[0019] The terms used in the descriptions of various examples in this disclosure are for the purpose of describing specific examples only and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element may be one or more. In addition, the term "and / or" used in this disclosure encompasses any one and all possible combinations of the listed items.

[0020] Example 1 In this embodiment, see Figure 1 , Figure 1 A schematic flow chart of a method for measuring the impact grounding resistance of a base tower is shown, wherein the method includes: S1: Based on a first set of influencing factors constructed based on the environmental characteristics and soil characteristics of the base tower installation area, combined with pre-constructed factor association rules, a factor directed graph is established; wherein the factor association rules are used to characterize the association relationship between different influencing factors; Specifically, in this embodiment, a first set of influencing factors is constructed based on the environmental characteristics and soil characteristics of the base tower installation area at historical moments, wherein the environmental characteristics include regional temperature and regional altitude; the soil characteristics include soil moisture, soil resistivity, and soil salinity; based on pre-constructed factor association rules, the correlation between the influencing factors in the environmental characteristics and soil characteristics is obtained; and a factor directed graph is constructed with each influencing factor as a graph node and the correlation between the influencing factors as an edge.

[0021] It should be noted that, in this embodiment, the environmental characteristics and soil characteristics of different base tower installation areas and at different historical moments are obtained, and the acquisition method adopts conventional technical means in this field, which will not be elaborated here; at the same time, factor association rules are constructed through the experience and knowledge of domain experts, such as: the relationship between regional temperature and soil moisture (high temperature will accelerate the evaporation of soil moisture, and low temperature will cause soil freezing), and the relationship between soil moisture and soil resistivity (increased humidity usually reduces soil resistivity, but there is a saturation effect), etc.; at the same time, the factor directed graph includes a construction method adopting conventional technical means in this field, which will not be elaborated here.

[0022] In this embodiment, by using a directed graph (DAG) to construct an influence relationship network between multiple factors, the mutual influence between different factors can be characterized. For example, taking regional temperature changes as an example, it not only directly affects the soil moisture evaporation rate, but also indirectly affects the soil condensation process by changing soil moisture. By using nodes to represent variables such as temperature, soil moisture, ion migration, and soil resistivity, and by labeling causal relationship weights on directed edges, the cascade effect between the geographical location of the pile foundation (altitude, longitude and latitude) and environmental factors can be intuitively presented. For example, in high-altitude areas, the lower atmospheric pressure causes the boiling point of water to drop, accelerating the evaporation of soil moisture, thereby affecting the ion conductive channels between soil particles and ultimately changing the soil resistivity. In coastal areas, the groundwater level fluctuations caused by tides and soil salinization form a two-way feedback mechanism, and loop edges need to be added to the model to characterize the dynamic coupling relationship. The above examples are only for illustrating the implementation methods that can be implemented in this embodiment and should not be understood as specific limitations on this technical solution.

[0023] S2: Graph neural networks are used to extract node features from the factor directed graph, and random forests are used to process the node features to obtain an influencing factor generation model; Specifically, in this embodiment, a graph neural network is used to randomly extract feature information of a factor directed graph and generate multiple node feature matrices; a classification regression tree of multiple node feature matrices is generated based on a random forest algorithm, and the Gini coefficients of the multiple node feature matrices are calculated; for the multiple node feature matrices where the current node of the classification regression tree is located, when the Gini coefficients of the multiple node feature matrices are not less than the Gini coefficient threshold, the Gini coefficient of each feature information in the node feature matrix where the current node is located is calculated; when the Gini coefficients of the multiple node feature matrices are less than the Gini coefficient threshold, the random forest algorithm returns to the child decision tree and stops recursion; each feature information is returned to the child decision tree. The feature information corresponding to the minimum Gini coefficient in the Gini coefficient is used as the optimal feature information. Based on the optimal feature information, the corresponding node feature matrix is divided into a first feature matrix and a second feature matrix, and the first feature matrix and the second feature matrix are used as the left child node and the right child node of the current node respectively; the Gini coefficients of the first feature matrix and the second feature matrix are calculated. When the Gini coefficients of the first feature matrix and the second feature matrix are less than the Gini coefficient threshold, the random forest algorithm returns the child decision tree and stops recursion to generate multiple decision trees; under pre-constructed relationship constraints, multiple classifiers learn multiple decision trees to obtain an influencing factor generation model.

[0024] It should be noted that in this embodiment, the Gini coefficient is used to measure the uncertainty of the random forest algorithm. The smaller the uncertainty, the better the random forest algorithm. The feature information is randomly sampled from the factor directed graph and multiple node feature matrices are generated. Therefore, assuming that the probability of generating the influencing factor in the node feature matrix is p, the Gini coefficient of the probability distribution is as follows: Calculated; then in the node feature matrix, the number of nodes is defined as |D|, the impact factor is defined as |C|, and the Gini coefficient expression is: , Furthermore, if the node feature matrix is divided into D1 and D2 by the optimal feature information A, the expression of the Gini coefficient of the node feature matrix is defined as: , where D1 represents the first feature matrix and D2 represents the second feature matrix. Gini(D,A) represents the uncertainty of the node feature matrix. D is grouped by the optimal feature information A. The smaller the Gini coefficient, the lower the uncertainty of the node feature matrix, resulting in a higher accuracy of the final generated result.

[0025] At the same time, in this embodiment, it also includes: constructing relationship constraints based on pre-constructed factor association rules; the relationship constraints include regional temperature-soil moisture constraints, soil moisture-soil resistivity constraints, and regional temperature-soil salinity constraints; The regional temperature-soil moisture constraints are as follows: ,in, Indicates soil moisture, represents the regional temperature, All represent constraint parameters, such as It means that the soil moisture decreases by 0.05% for every 1℃ increase in regional temperature. Indicates the saturation temperature threshold, It indicates that the downward trend of soil moisture slows down when the regional temperature exceeds 30℃; The soil moisture-soil resistivity constraint is specifically: ,in, represents the soil resistivity, , Represents the dry soil resistivity, which indicates the resistivity when the soil moisture is 0 and is determined by the conductive properties of solid particles; It represents the coefficient of the growth rate of the resistivity in the dry area as the humidity decreases, ; It represents the soil moisture threshold, which indicates the dividing point between the dry zone and the transition zone. When it is lower than this value, the soil moisture is discontinuous and the resistivity rises sharply. Represents the resistivity of water. The soil resistivity in the moisture saturated area approaches this value. Indicates the sensitivity of soil resistivity changes in moisture-saturated areas, and this value is related to soil texture; represents the Archie index, which is used to describe the effect of pore tortuosity on soil resistivity. ; Indicates the soil saturation moisture in the moisture saturated area. This value indicates the moisture (water content) when the soil is fully saturated and is determined by the porosity; Represents the saturation factor, which is used to adjust the nonlinear contribution of humidity to resistivity. ; Represents the transition region weight, which is used to balance the resistivity contribution of the dry region and the saturated region. ; It should be noted that, in this embodiment, the dry area refers to the area where the soil moisture is The transition area refers to the area where the soil moisture is between The saturated area refers to the area where the soil moisture is The area of the interval.

[0026] For example, in the clay scene, , , , , , , , .

[0027] The regional temperature-soil salinity constraints are as follows: ,in, Indicates soil salinity. , Indicates the base salt content, It represents the freezing zone attenuation coefficient, which is used to control the rate of reduction of salt content as the temperature drops at low temperatures; Indicates the base temperature, which is used as a reference point for regional temperature changes. It corresponds to the soil salinity under standard conditions and is used to normalize temperature effects. Indicates the freezing temperature threshold, meaning that below this temperature, soil moisture freezes, salt crystallizes and precipitates, resulting in a decrease in salt content; represents the linear coefficient of the transition region, which is used to describe the promoting effect of temperature on salt dissolution; represents the Gaussian attenuation coefficient in the transition region, which is used to reflect the equilibrium effect of temperature on dissolution and evaporation, e.g. It indicates that the peak is broad near the threshold temperature (the equilibrium effect of reaction temperature on dissolution and evaporation); The threshold temperature represents the dividing point between the high temperature zone and the transition zone. When the temperature is lower than this, salt dissolution is dominant, while when the temperature is higher than this, evaporation and concentration are dominant. It indicates the saturated salt content of the soil, which represents the limit of soil salt under high temperature evaporation, at which point the salt cannot be further concentrated; represents the hyperbolic tangent function, Saturation coefficient, which controls the rate at which the salinity approaches the saturation salinity of the soil, e.g. This means that for every 1°C increase, the salt content approaches 10% of the saturation value (the speed at which salt concentrates to saturation when high temperature accelerates evaporation); It should be noted that, in this embodiment, the frozen area refers to the The transition area is the area within the interval. The high temperature area is the area within the range. The area within the interval.

[0028] For example, in a temperate grassland scenario, , , , , , , , , .

[0029] S3: obtaining a second influencing factor set constructed based on the environmental characteristics and soil characteristics of the base tower installation area at the current measurement moment, and inputting the second influencing factor set into the influencing factor generation model to obtain the influencing factor at the current measurement moment; S4: inputting an impulse current into the grounding loop formed by the first base tower and the second base tower, and measuring the initial impulse grounding resistance of the grounding device of the second base tower; Specifically, in this embodiment, the grounding loop formed by the first base tower and the second base tower is specifically composed of the OPGW ground wire connected between the first base tower, the second base tower, the grounding down conductor of the first base tower, the grounding down conductor of the second base tower, the first base tower, the grounding device of the first base tower, the grounding device of the second base tower, and the second base tower.

[0030] It should be noted that, in this embodiment, an impulse current generator is used to generate an impulse current with a steeper wave front and a larger amplitude. The impulse current flows through the grounding loop formed by the first base tower and the second base tower, and the initial impulse grounding resistance of the grounding device of the second base tower is finally measured. The measurement method adopts conventional technical means, which will not be described in detail here.

[0031] S5: Use the impact factor to correct the initial impulse grounding resistance and output the corrected impulse grounding resistance.

[0032] It should be noted that the impact factor generation model is used to generate an impact factor , using the impact factor Correct the initial impact grounding resistance. The correction formula is: ,in, Indicates the initial impact grounding resistance, Indicates the corrected impulse grounding resistance.

[0033] Specifically, in this embodiment, by integrating environmental characteristics and soil characteristics, a factor directed graph is constructed to characterize the correlation between multiple influencing factors, the interaction relationship between multiple factors is made explicit, the synergistic influence between multiple influencing factors is captured, and comprehensive modeling of the multi-dimensional characteristics of the measurement area is achieved; the features of the factor directed graph are extracted by a graph neural network, and processed using a random forest algorithm to obtain an influencing factor generation model that integrates the synergistic relationship of multiple factors to generate influencing factors; at the same time, the influencing factors output by the influencing factor generation model of the present invention integrate the comprehensive effects of multiple factors, rather than a single physical quantity correction, and perform multi-dimensional physical constraint correction on the initial impact grounding resistance value, thereby solving the accuracy loss of traditional methods in dynamic environments, solving the scenario limitations of traditional static corrections, and being able to achieve high-precision measurements in extreme environments.

[0034] Example 2 See also Figure 2 As shown, the present invention also provides a base tower impulse grounding resistance measurement system, which is used in any one of the above base tower impulse grounding resistance measurement methods, and the system includes: The first module 100 is configured to establish a factor directed graph based on a first set of influencing factors constructed based on environmental characteristics and soil characteristics of the base tower installation area, in combination with pre-established factor association rules; wherein the factor association rules are used to characterize the association relationship between different influencing factors; The second module 200 is used to extract node features in the factor directed graph using a graph neural network and process the node features using a random forest to obtain an influencing factor generation model; The third module 300 is configured to obtain a second influencing factor set constructed based on the environmental characteristics and soil characteristics of the base tower installation area at the current measurement time, and input the second influencing factor set into the influencing factor generation model to obtain the influencing factor at the current measurement time; The fourth module 400 is configured to input an impulse current into a grounding loop formed by the first base tower and the second base tower, and measure an initial impulse grounding resistance of a grounding device of the second base tower; The fifth module 500 is configured to correct the initial impulse grounding resistance using the influencing factor and output the corrected impulse grounding resistance.

[0035] It should be noted that the modules in the system of Example 2 correspond to the steps in the method of Example 1. The steps in the method of Example 1 have been described in detail in Example 1, and the contents of the modules in the system will not be described in detail in this Example 2.

[0036] Example 3 See also Figure 3 As shown, this embodiment further provides a computer device, including a system memory 1005 and a processor 1001, wherein the system memory 1005 stores a computer program, and the processor 1001 implements the steps of any of the above methods when executing the computer program.

[0037] It should be noted that the processor 1001 is configured to execute the steps of the above method embodiments according to the instructions in the program code. Alternatively, the processor 1001 implements the functions of the modules / units in the above system / device embodiments when executing the computer program.

[0038] Specifically, in this embodiment, the computer program may be divided into one or more modules / units, one or more modules / units being stored in the system memory 1005 and executed by the processor 1001 to complete the present application. One or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal device.

[0039] The terminal device may be a computing device such as a desktop computer, laptop, PDA, or cloud server. The terminal device may include, but is not limited to, a processor 1001 and a system memory 1005. Those skilled in the art will appreciate that this does not limit the terminal device and may include more or fewer components than shown, or a combination of certain components, or different components. For example, the terminal device may also include an input / output device 1003, a network access device 1002, a bus 1006, and the like.

[0040] The processor 1001 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0041] The system memory 1005 can be an internal storage unit of the terminal device, such as a hard disk or memory of the terminal device. The system memory 1005 can also be the storage device 1004 of the terminal device, such as a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the terminal device. Furthermore, the system memory 1005 can also include both the internal storage unit of the terminal device and the storage device 1004. The system memory 1005 is used to store computer programs and other programs and data required by the terminal device. The system memory 1005 can also be used to temporarily store data that has been output or is about to be output.

[0042] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0043] Example 4 This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of any one of the above methods are implemented.

[0044] Among them, the computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, system or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk. Random Access Memory (RAM), Read-Only Memory (ROM), Erasable Programmable Read Only Memory (EPROM), a register, a hard disk, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above, or any other form of computer-readable storage medium known in the art.

[0045] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and the storage medium can be located in an application-specific integrated circuit (ASIC). In an embodiment of the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device.

[0046] Example 5 This embodiment further provides a computer program product comprising instructions. When the instructions are executed by a computer device cluster, the computer device cluster executes the method described in Embodiment 1.

[0047] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for measuring the impact grounding resistance of a base tower, characterized in that: Methods include: Based on a first set of influencing factors constructed from the environmental characteristics and soil characteristics of the base tower installation area, combined with pre-constructed factor association rules, a factor directed graph is established; wherein the factor association rules are used to characterize the association relationship between different influencing factors; Graph neural networks are used to extract node features from the factor directed graph, and random forests are used to process the node features to obtain an influencing factor generation model; Obtaining a second influencing factor set constructed based on environmental characteristics and soil characteristics of the base tower installation area at the current measurement moment, and inputting the second influencing factor set into an influencing factor generation model to obtain an influencing factor at the current measurement moment; Inputting an impulse current into a grounding loop formed by the first pole tower and the second pole tower, and measuring an initial impulse grounding resistance of a grounding device of the second pole tower; The initial impulse grounding resistance is corrected using the influencing factor and the corrected impulse grounding resistance is output.

2. The method for measuring the impact grounding resistance of a base tower according to claim 1, wherein: Based on the first set of influencing factors constructed by the environmental characteristics and soil characteristics of the base tower installation area, combined with the pre-built factor association rules, a factor directed graph is established, specifically: A first set of influencing factors is constructed based on the environmental characteristics and soil characteristics of the base tower installation area at historical moments, wherein the environmental characteristics include regional temperature and regional altitude; and the soil characteristics include soil moisture, soil resistivity, and soil salinity; Based on pre-built factor association rules, the association relationship between the influencing factors of environmental characteristics and soil characteristics is obtained; Each influencing factor is taken as a graph node and the relationship between influencing factors is taken as an edge to construct a factor directed graph.

3. The method for measuring the impact grounding resistance of a base tower according to claim 1, wherein: Graph neural networks are used to extract node features from the factor directed graph, and random forests are used to process the node features to obtain an influencing factor generation model, specifically: Utilize graph neural networks to randomly extract feature information of factor directed graphs and generate multiple node feature matrices; Generate classification and regression trees of multiple node feature matrices based on the random forest algorithm, and calculate the Gini coefficients of multiple node feature matrices; For the multiple node feature matrices where the current node of the classification and regression tree is located, when the Gini coefficients of the multiple node feature matrices are not less than the Gini coefficient threshold, the Gini coefficient of each feature information in the node feature matrix where the current node is located is calculated; when the Gini coefficients of the multiple node feature matrices are less than the Gini coefficient threshold, the random forest algorithm returns to the child decision tree and stops recursion; The feature information corresponding to the minimum Gini coefficient among the Gini coefficients of each feature information is used as the optimal feature information, and the corresponding node feature matrix is divided into a first feature matrix and a second feature matrix based on the optimal feature information, and the first feature matrix and the second feature matrix are used as the left child node and the right child node of the current node respectively; Calculate the Gini coefficient of the first feature matrix and the second feature matrix. When the Gini coefficient of the first feature matrix and the second feature matrix is less than the Gini coefficient threshold, the random forest algorithm returns to the child decision tree and stops recursion, generating multiple decision trees. Under the pre-built relationship constraints, multiple classifiers learn multiple decision trees to obtain an impact factor generation model.

4. A method for measuring the impact grounding resistance of a base tower according to claim 1 or 3, characterized in that: The method further includes: constructing relationship constraints based on pre-constructed factor association rules; wherein the relationship constraints include regional temperature-soil moisture constraints, soil moisture-soil resistivity constraints, and regional temperature-soil salinity constraints.

5. The method for measuring the impact grounding resistance of a base tower according to claim 4, characterized in that: The regional temperature-soil moisture constraints are specifically: ,in, Indicates soil moisture, represents the regional temperature, are constraint parameters, represents the saturation temperature threshold; the soil moisture-soil resistivity constraint is specifically: ,in, represents the soil resistivity, , represents the dry soil resistivity, It represents the coefficient that controls the growth rate of resistivity in dry area as humidity decreases; represents the soil moisture threshold; Indicates the resistivity of water; Indicates the sensitivity of soil resistivity changes in moisture-saturated areas; represents the Archie index, , Indicates the soil saturation moisture in the moisture-saturated area, represents the saturation factor, represents the transition region weight, The regional temperature-soil salinity constraint is specifically: ,in, Indicates soil salinity. , Indicates the base salt content, represents the attenuation coefficient of the frozen zone, Indicates the reference temperature, Indicates the freezing temperature threshold, represents the linear coefficient of the transition region, represents the Gaussian attenuation coefficient in the transition region, represents the threshold temperature, Indicates the saturated salt content of the soil. represents the hyperbolic tangent function, Saturation coefficient.

6. The method for measuring the impact grounding resistance of a base tower according to claim 1, characterized in that: The grounding loop formed by the first base tower and the second base tower is specifically composed of the OPGW ground wire connected between the first base tower, the second base tower, the grounding down conductor of the first base tower, the grounding down conductor of the second base tower and the first base tower, the grounding device of the first base tower, the grounding device of the second base tower and the second base tower.

7. A tower impact grounding resistance measurement system, characterized in that: The system is used in a method for measuring the impact grounding resistance of a base tower according to any one of claims 1 to 6, and the system comprises: The first module is configured to establish a factor directed graph based on a first set of influencing factors constructed based on environmental characteristics and soil characteristics of the base tower installation area, in combination with pre-established factor association rules; wherein the factor association rules are used to characterize the association relationship between different influencing factors; The second module is used to extract node features from the factor directed graph using graph neural networks and process the node features using random forests to obtain an impact factor generation model; The third module is used to obtain a second influencing factor set constructed by the environmental characteristics and soil characteristics of the base tower installation area at the current measurement moment, and input the second influencing factor set into the influencing factor generation model to obtain the influencing factor at the current measurement moment; The fourth module is used to input an impulse current into the grounding loop formed by the first base tower and the second base tower, and measure the initial impulse grounding resistance of the grounding device of the second base tower; The fifth module is used to correct the initial impulse grounding resistance using the influencing factor and output the corrected impulse grounding resistance.

8. A computer device comprising a system memory and a processor, wherein the system memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. 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 method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising instructions, characterized in that When the instructions are executed by a computer device cluster, the computer device cluster is caused to perform the method according to any one of claims 1 to 6.

Images