MOA leakage current correction method and correction system for eliminating interference of external factors

Abstract

The invention discloses an MOA leakage current correction method and system capable of eliminating external factor interference. The method comprises the steps that leakage current monitoring data I of a lightning arrester and meteorological factor data in a same time period are collected; a box plot method is adopted for the leakage current monitoring data I, outliers different from normal conditions are eliminated, and normal leakage current monitoring data I1 are obtained; establishing a fitting model based on the normal leakage current monitoring data I1 and the meteorological factor data, and performing optimization processing on the fitting model to obtain an optimal fitting model; and correcting the leakage current monitoring data I based on the optimal fitting model to obtain leakage current monitoring data Icorrect with meteorological factors eliminated. According to the method, more accurate reference information is provided for operation and maintenance personnel, the operation and maintenance personnel are helped to better understand the operation state of the MOA, and the operation safety, stability and maintenance efficiency of the MOA are improved.

Description

Technical Field

[0001] The invention belongs to the technical field of power systems, and in particular to a MOA leakage current correction method and correction system for eliminating interference from external factors. Background Art

[0002] During long-term operation, the arrester (MOA) may be affected by environmental and aging factors, resulting in performance degradation or failure. If the arrester fails or fails, the equipment in the power grid will be damaged by overvoltage, and even equipment damage or power grid failure will occur. In order to improve its protection effect, service life and protect the equipment in the power grid, the arrester is often tested online to detect its leakage current data. Through the leakage current data, the insulation status of the arrester can be understood in real time to determine whether it is operating normally. When the leakage current is abnormal, it can be discovered and handled in time to prevent the arrester from being damaged due to insulation failure;

[0003] At present, the leakage current data measurement of the corresponding lightning arrester is often measured through an online monitoring device. However, the existing online monitoring device is greatly affected by environmental meteorological factors during the measurement process, such as temperature and humidity. As the temperature and humidity change, the leakage current data will also change. However, the existing online monitoring device does not introduce the analysis of the effect of temperature and humidity on the leakage current data, and eliminate the influence of temperature and humidity on the leakage current data, which leads to fluctuations in the monitoring data, and the accuracy of the detected data is poor, making the comparison and analysis of the data complicated. Summary of the invention

[0004] The present invention provides a MOA leakage current correction method and correction system for eliminating interference from external factors. By establishing a fitting model between air temperature, humidity and MOA leakage current, the monitoring data can be normalized to the same meteorological conditions, the influence of air temperature and humidity on leakage current data can be eliminated, and the precision and accuracy of the detection data can be improved.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] The present invention discloses a MOA leakage current correction method for eliminating interference from external factors, comprising the following steps:

[0007] Collect the leakage current monitoring data I of the arrester and the meteorological factor data in the same period;

[0008] A box plot method is used for the leakage current monitoring data I to remove outliers that are different from normal conditions, thereby obtaining normal leakage current monitoring data I1;

[0009] Establishing a fitting model based on the normal leakage current monitoring data I1 and the meteorological factor data, and optimizing the fitting model to obtain an optimal fitting model;

[0010] The leakage current monitoring data I is corrected based on the optimal fitting model to obtain the leakage current monitoring data I eliminating the meteorological factors. correct .

[0011] Preferably, the meteorological factors include temperature data T and humidity data Rh.

[0012] Preferably, the box plot method comprises:

[0013] Propose the lower quartile Q1 and the upper quartile Q3 of the leakage current monitoring data I;

[0014] The upper threshold TH is calculated based on the lower quartile Q1 and the upper quartile Q3 UP and the lower threshold TH down ;

[0015] By comparing the data values ​​in the leakage current monitoring data I with the upper threshold TH UP and the threshold value TH down A comparison is performed, and outliers are marked and removed from the leakage current monitoring data I. The data gaps generated after the removal are supplemented to obtain the normal leakage current monitoring data I1.

[0016] Preferably, extracting the lower quartile Q1 and the upper quartile Q3 from the leakage current monitoring data I comprises:

[0017] Arranging the leakage current monitoring data I in order of size to obtain a data set of the leakage current monitoring data I;

[0018] The data set is divided into four sub-datasets with the same number of values; the sub-dataset at the smallest value in the data set is the number at the 25th position, and these data values ​​are extracted to obtain the lower quartile Q1; the sub-dataset at the largest value in the data set is the number at the 75th position, and these data values ​​are extracted to obtain the upper quartile Q3.

[0019] Preferably, the upper threshold TH UP for

[0020] TH UP =Q3+(Q3-Q1)

[0021] The lower threshold TH down for

[0022] TH down =Q3+(Q3-Q1)

[0023] Among them, Q3 is the upper quartile and Q1 is the lower quartile.

[0024] Preferably, the data supplementation includes:

[0025] The data supplement adopts the previous data value I at the data vacancy position i-1 and the next data value I at the data gap position i+1 The average value of is replaced to obtain the data set of leakage current monitoring data I under normal conditions;

[0026] The calculation formula for the data supplement is:

[0027]

[0028] Among them, I i-1 is the previous data value at the data vacancy position, I i+1 It is the next data value at the data gap position.

[0029] Preferably, the optimization process of the fitting model includes:

[0030] The leakage current monitoring data I is randomly divided into K mutually exclusive leakage current monitoring sub-data sets, and the meteorological factor data is correspondingly randomly divided into K mutually exclusive meteorological sub-data sets;

[0031] Based on the leakage current monitoring sub-dataset and the meteorological sub-dataset inputted into the fitting model, K training models are obtained by training;

[0032] Obtain an average value of the MSE of the K training models, and use the average value of the MSE of the K training models as an optimization indicator to obtain the optimal hyperparameter through the particle swarm optimization algorithm;

[0033] The fitting model is retrained based on the optimal hyperparameters to obtain an optimal fitting model.

[0034] Preferably, the construction of the fitting model includes:

[0035] Constructing a model construction data set based on the normal leakage current monitoring data I1 as output features, the air temperature data T and the humidity data Rh as input features;

[0036] The model building data set is trained using a support vector machine algorithm to establish the fitting model.

[0037] Preferably, the correction of the leakage current monitoring data I based on the optimal fitting model includes:

[0038] The meteorological factor data is input into the optimal fitting model to obtain the leakage current prediction value I * ;

[0039] Based on the set reference condition, find the data value corresponding to the reference condition in the leakage current monitoring data I, and record it as the real data I base ;

[0040] Based on the real data I base and the leakage current prediction value I * Correct the leakage current monitoring data I to obtain the leakage current monitoring data I eliminating the meteorological factors correct .

[0041] The present invention also discloses a MOA leakage current correction system for eliminating interference from external factors, comprising:

[0042] The acquisition module is used to collect the leakage current monitoring data I of the arrester and the meteorological factor data in the same period;

[0043] A processing module is used to remove outliers from the leakage current monitoring data I that are different from normal conditions, and then establish a fitting model through the processed data and the meteorological factor data, and optimize the fitting model to obtain the optimal fitting model;

[0044] The correction module, which connects the acquisition module and the correction module, is used to correct the leakage current monitoring data I based on the optimal fitting model and the meteorological factor data to obtain the leakage current monitoring data I that eliminates the meteorological factor. correct ;

[0045] Output module, the output module is connected to the correction module for outputting the leakage current monitoring data I correct .

[0046] The present invention also discloses a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned MOA leakage current correction method for eliminating interference from external factors are implemented.

[0047] The present invention also discloses a computer-readable storage medium, including a computer program, which, when executed by a processor, implements the steps of the method for obtaining key parameters of the transient waveform generated by the operation of the isolation switch.

[0048] Compared with the prior art, the present invention has the following beneficial technical effects:

[0049] The present invention discloses a MOA leakage current correction method for eliminating external interference. In the method of the present invention, the leakage current monitoring data of the arrester and the meteorological factor data in the same period are collected, and the leakage current and meteorological factor data are comprehensively considered to more accurately evaluate the operating status of the arrester. Secondly, the outliers caused by various reasons (such as equipment failure, external interference, etc.) are identified and eliminated through the box plot method, which effectively improves the accuracy and reliability of the data. Then, a fitting model is established through the normal leakage current monitoring data I1 and the meteorological factor data, and the optimal fitting model is obtained through processing. Then, a quantitative relationship between the leakage current and the meteorological factors is established, so as to achieve accurate prediction and correction of the leakage current, and ensure the accuracy and reliability of the prediction results; finally, the leakage current monitoring data I is corrected based on the optimal fitting model to obtain the leakage current monitoring data I1 eliminating the meteorological factors. correct , accurately reflects the actual operating status of the arrester, and provides more valuable reference information for operation and maintenance personnel. At the same time, since the interference of meteorological factors is eliminated, the corrected data has higher stability and reliability, and can provide better guarantee for the long-term stable operation of the arrester. The method of the present invention not only improves the monitoring accuracy of the operating status of the arrester, but also improves the stability and reliability of the data by eliminating the interference of meteorological factors. In addition, the method of the present invention can also provide more accurate reference information for operation and maintenance personnel, help them better understand the operating status of MOA, and improve the operating safety, stability and maintenance efficiency of the arrester.

[0050] Furthermore, by identifying and calculating the lower quartile Q1 and upper quartile Q3 in the leakage current monitoring data, the method of the present invention can accurately determine the distribution range of the data, thereby determining which data values ​​are abnormal values ​​or outliers. Next, based on the lower quartile Q1 and upper quartile Q3, the threshold TH is calculated. UP and the lower threshold TH down The two thresholds provide a clear boundary for the judgment of abnormal values ​​or outliers, making the identification of outliers more objective and accurate, and making the leakage current monitoring data I1 under normal conditions more accurate and reliable.

[0051] Furthermore, in the method of the present invention, the leakage current monitoring data I is arranged in order of size to ensure the orderliness of the data set, which helps to observe the distribution of the data more intuitively, and then the ordered data set is divided into four sub-data sets with the same number of values. Each sub-data set represents 25% of the original data set, and can accurately locate the data at the 25% position, that is, the lower quartile Q1, and the data at the 75% position, that is, the upper quartile Q3. This method is not affected by extreme values ​​and can truly reflect the distribution of the data. Furthermore, reasonable thresholds can be set through the lower quartile Q1 and the upper quartile Q3 to identify and eliminate outliers in the data, thereby ensuring the accuracy and reliability of subsequent analysis.

[0052] Furthermore, after removing outliers, the method of the present invention supplements the data at the data vacancy position to ensure the continuity and integrity of the data; and the average value of the two data values ​​before and after the data vacancy is used for filling, which can better maintain the local characteristics of the data, maintain the local change trend of the data to the greatest extent, and improve the reliability of the data; at the same time, the method of the present invention is simple and easy to implement, and does not require complex calculations or additional data support. It only needs to find the two data values ​​before and after the vacancy position and perform simple arithmetic operations to obtain the filling value. This reduces the complexity and cost of data processing and improves the practicality and operability of the method.

[0053] Furthermore, in the method of the present invention, the collected meteorological factor data are input into the previously constructed and optimized fitting model, and the model calculates the corresponding leakage current prediction value I based on these data. * , making full use of the fitting model's accurate description of the relationship between meteorological factors and leakage current, thus achieving an accurate prediction of the leakage current of MOA under current meteorological conditions, and then finding the corresponding real data I of the leakage current monitoring data I under the baseline conditions by calculating the real leakage current data under the set baseline conditions as a reference base , ensuring that the correction process has a clear reference standard, making the correction result more reliable. Then, based on real data I base and the predicted value I * The original leakage current monitoring data I is corrected to eliminate the influence of meteorological factors on the leakage current monitoring data, and the leakage current data I that more accurately reflects the actual operating status of MOA is obtained. correct , which improves the accuracy and reliability of leakage current monitoring data, allowing operation and maintenance personnel to understand the operating status of MOA more accurately; at the same time, by eliminating the influence of meteorological factors, the corrected data can better reflect the performance changes of MOA itself, providing more valuable reference information for fault prediction and diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A schematic flow chart of a method for correcting MOA leakage current for eliminating interference from external factors according to the present invention;

[0055] Figure 2 A schematic diagram of a computer device provided by an embodiment of the present invention;

[0056] Figure 3 The block diagram is a chip provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0057] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0058] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise", "axial", "radial", "circumferential" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0059] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection, an electrical connection, or a communication; it can be a direct connection, or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0060] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may include that the first and second features are in direct contact, or may include that the first and second features are not in direct contact but are in contact through another feature between them. Moreover, a first feature being "above", "above" and "above" a second feature includes that the first feature is directly above and obliquely above the second feature, or simply indicates that the first feature is higher in level than the second feature. A first feature being "below", "below" and "below" a second feature includes that the first feature is directly above and obliquely above the second feature, or simply indicates that the first feature is lower in level than the second feature.

[0061] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0062] See also Figure 1 The present invention discloses a method for correcting MOA leakage current by eliminating interference from external factors, comprising the following steps:

[0063] Collect the leakage current monitoring data I of the arrester and the meteorological factors in the same period.

[0064] Specifically, the leakage current monitoring data I of the lightning arrester is collected; at the same time, the meteorological factors of the same period as the leakage current monitoring data I of the lightning arrester are obtained, and the meteorological factors include temperature data T and humidity data Rh; that is, the temperature data T of the same period as the leakage current monitoring data I of the lightning arrester is obtained, and the humidity data Rh of the same period as the leakage current monitoring data I of the lightning arrester is collected; and the temperature data T, humidity data Rh and leakage current monitoring data I in the same period are sorted and stored.

[0065] The box plot method is used for the leakage current monitoring data I to remove outliers that are different from the normal situation and obtain the normal leakage current monitoring data I1.

[0066] Specifically, due to the interference of MOA overvoltage operation and electromagnetic environment, outliers different from normal conditions may be generated in the leakage current data, which are removed by the box plot method.

[0067] The box plot method includes:

[0068] Extract the lower quartile Q1 and the upper quartile Q3 from the leakage current monitoring data I; that is, arrange the leakage current monitoring data I in order of size to obtain a data set of the leakage current monitoring data I, divide the data set into four sub-data sets with the same number of values, and the sub-data set at the minimum value in the data set is the number at the 25% position, and these data values ​​are extracted to obtain the lower quartile Q1; the sub-data set at the maximum value in the data set is the number at the 75% position, and these data values ​​are extracted to obtain the upper quartile Q3; calculate the upper threshold TH according to the lower quartile Q1 and the upper quartile Q3 UPand the lower threshold TH down .

[0069] Upper threshold TH UP The calculation formula is:

[0070] TH UP =Q3+(Q3-Q1) (1)

[0071] Among them, Q3 is the upper quartile and Q1 is the lower quartile.

[0072] Lower threshold TH down The calculation formula is:

[0073] TH down =Q3+(Q3-Q1) (2)

[0074] Among them, Q3 is the upper quartile and Q1 is the lower quartile.

[0075] By comparing the data values ​​in the leakage current monitoring data I with the upper threshold TH UP and the lower threshold TH down Compare and judge the data value in the leakage current monitoring data I, and set the data value in the leakage current monitoring data I to be less than the lower threshold value TH down Or greater than the upper threshold TH UP The data value is marked as an outlier. After the comparison is completed, the marked data value is removed from the data set, and then the i-th data value I in the data gap in the data set is i The data is supplemented by using the previous data value I at the data vacancy position. i-1 and the next data value I at the data gap position i+1 The average value of is replaced to obtain the data set of leakage current monitoring data I under normal conditions;

[0076] The calculation formula for data supplement is:

[0077]

[0078] Among them, I i-1 is the previous data value at the data gap position, I i+1 It is the next data value at the data gap position.

[0079] A fitting model is established based on the normal leakage current monitoring data I1 and the meteorological factor data, and the fitting model is optimized to obtain the optimal fitting model;

[0080] Specifically, the normal leakage current monitoring data I1 is used as the output feature, the temperature data T and the humidity data Rh are used as the input features to form a data set, and the support vector machine algorithm is used for training to establish a fitting model;

[0081] The expression of the fitted model is:

[0082] I=f(T,Rh) (4)

[0083] Among them, I is the leakage current monitoring data I1, T is the temperature data, and Rh is the humidity data.

[0084] Fitting the model for optimization includes:

[0085] The K-fold cross-validation method is used to randomly divide the leakage current monitoring data I into K mutually exclusive leakage current monitoring sub-datasets, and the meteorological factor data is also randomly divided into K mutually exclusive meteorological sub-datasets accordingly;

[0086] The leakage current monitoring sub-dataset is used as the output sign and the meteorological sub-dataset is used as the input feature. They are input into the fitting model and K training models are obtained through training.

[0087] Get the average value of the MSE of the K training models, and use the average value of the MSE of the K training models as the optimization indicator to obtain the optimal hyperparameters through the particle swarm optimization algorithm (PSO);

[0088] Based on the optimal hyperparameters, the fitting model is retrained through the support vector machine algorithm to obtain the optimal fitting model, which improves the generalization performance of the model, can effectively evaluate the performance of the model on a limited data set, and avoid overfitting. At the same time, through the particle swarm optimization algorithm (PSO), the average of the MSE of K models is used as the optimization index to optimize the hyperparameters of the support vector machine algorithm (penalty factor C and kernel function parameter γ) to obtain the optimal hyperparameters, so as to further improve the prediction ability and robustness of the model.

[0089] The leakage current monitoring data I is corrected based on the optimal fitting model to obtain the leakage current monitoring data I2 after eliminating meteorological factors.

[0090] Specifically, the temperature data T and humidity data Rh are input into the optimal fitting model to obtain the leakage current prediction value I*; a reference condition is selected (the reference condition is set to be 25°C temperature and 50% humidity), and the corresponding data value under the reference condition is found in the leakage current monitoring data I, which is recorded as the real data I base , through real data I base Correct the leakage current monitoring data I to obtain the leakage current monitoring data I after eliminating meteorological factors correct .

[0091] The corrected calculation expression is:

[0092] I correct =I base +(I * -I) (2)

[0093] Among them, I correct To eliminate the leakage current monitoring data of meteorological factors, I is the leakage current monitoring data and I* is the leakage current prediction value.

[0094] Through data correction, the leakage current monitoring data can be converted to the same reference conditions (air temperature and humidity), thereby eliminating the influence of temperature and humidity factors on the leakage current and improving the reliability and accuracy of MOA online monitoring.

[0095] The present invention also discloses a MOA leakage current correction system for eliminating interference from external factors, which can be used to implement the above-mentioned MOA leakage current correction method for eliminating interference from external factors. Specifically, the MOA leakage current correction system for eliminating interference from external factors includes an acquisition module, a processing module, a correction module and an output module:

[0096] Among them, the acquisition module is used to collect the leakage current monitoring data I of the arrester (MOA) and the meteorological factor data in the same period;

[0097] The processing module is used to remove outliers that are different from normal conditions from the leakage current monitoring data I, then establish a fitting model through the processed data and meteorological factor data, and optimize the fitting model to obtain the optimal fitting model.

[0098] The processing module includes an outlier removal unit, a model building unit and an optimization verification unit; wherein the outlier removal unit data is connected to the model building unit and the acquisition module, and is used to remove outliers that are different from normal conditions in the leakage current monitoring data I, and supplement the data of the cleared positions in the leakage current monitoring data I to obtain the normal leakage current monitoring data I1; the model building unit data is connected to the optimization verification unit and the acquisition module, and is used to obtain the normal leakage current monitoring data I1 and the meteorological factor data to construct a fitting model; the optimization verification unit is used to verify and optimize the fitting model through the K-fold cross-validation method to obtain the optimal fitting model.

[0099] The correction module, which connects the acquisition module and the correction module, is used to correct the leakage current monitoring data I based on the optimal fitting model and the meteorological factor data to obtain the leakage current monitoring data I that eliminates the meteorological factor. correct .

[0100] Output module, the output module is connected to the correction module for outputting the leakage current monitoring data I correct .

[0101] The present invention also discloses a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a terminal device for storing programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and the extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory, or a non-volatile memory (Non-Volatile Memory), such as at least one disk memory.

[0102] The processor may load and execute one or more instructions stored in a computer-readable storage medium to implement the corresponding steps of the method for obtaining key parameters of transient waveforms generated by the disconnector operation in the above embodiment; the processor may load and execute the following steps:

[0103] The leakage current monitoring data I of the arrester (MOA) and the meteorological factor data in the same period are collected; the box plot method is used for the leakage current monitoring data I to remove the outliers that are different from the normal situation, and the normal leakage current monitoring data I1 is obtained; a fitting model is established based on the normal leakage current monitoring data I1 and the meteorological factor data, and the fitting model is optimized to obtain the optimal fitting model; based on the optimal fitting model, the leakage current monitoring data I is corrected to obtain the leakage current monitoring data I1 after eliminating the meteorological factors. correct .

[0104] See also Figure 2 The terminal device is a computer device. The computer device 60 of this embodiment includes: a processor 61, a memory 62, and a computer program 63 stored in the memory 62 and executable on the processor 61. When the computer program 63 is executed by the processor 61, the method for calculating the composition of fluid in the reservoir transformation wellbore in the embodiment is implemented. To avoid repetition, it is not described one by one here. Alternatively, when the computer program 63 is executed by the processor 61, the functions of each model / unit in the calculation system for the composition of fluid in the reservoir transformation wellbore in the embodiment are implemented. To avoid repetition, it is not described one by one here.

[0105] The computer device 60 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The computer device 60 may include, but is not limited to, a processor 61 and a memory 62. Those skilled in the art will appreciate that Figure 2It is only an example of the computer device 60 and does not constitute a limitation of the computer device 60. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the computer device may also include input and output devices, network access devices, buses, etc.

[0106] The processor 61 may be a central processing unit (CPU), or other general-purpose processors, central processing units, graphics 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, data processing logic based on quantum computing, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0107] The memory 62 may be an internal storage unit of the computer device 60, such as a hard disk or memory of the computer device 60. The memory 62 may also be an external storage device of the computer device 60, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the computer device 60.

[0108] Furthermore, the memory 62 may include both an internal storage unit of the computer device 60 and an external storage device. The memory 62 is used to store computer programs and other programs and data required by the computer device. The memory 62 may also be used to temporarily store data that has been output or is to be output.

[0109] Any reference to memory, database or other media used in the embodiments provided in the present application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0110] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0111] See also Figure 3 , the terminal device is a chip, and the chip 600 of this embodiment includes a processor 622, which may be one or more, and a memory 632 for storing a computer program executable by the processor 622. The computer program stored in the memory 632 may include one or more modules, each corresponding to a set of instructions. In addition, the processor 622 may be configured to execute the computer program to execute the above-mentioned generalizable monocular absolute depth map estimation method.

[0112] In addition, the chip 600 may further include a power supply component 626 and a communication component 650, wherein the power supply component 626 may be configured to perform power management of the chip 600, and the communication component 650 may be configured to implement communication, for example, wired or wireless communication, of the chip 600. In addition, the chip 600 may further include an input / output interface 658. The chip 600 may operate based on an operating system stored in the memory 632.

[0113] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the attached claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved.

[0114] In addition, it should be understood that although this specification is described in accordance with the implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other implementation modes that can be understood by those skilled in the art. The above content is only to illustrate the technical idea of ​​the present invention, and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution according to the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A method for correcting MOA leakage current by eliminating external interference, characterized in that: The following steps are involved: Collect the leakage current monitoring data I of the arrester and the meteorological factor data in the same period; A box plot method is used for the leakage current monitoring data I to remove outliers that are different from normal conditions, thereby obtaining normal leakage current monitoring data I1; Establishing a fitting model based on the normal leakage current monitoring data I1 and the meteorological factor data, and optimizing the fitting model to obtain an optimal fitting model; The leakage current monitoring data I is corrected based on the optimal fitting model to obtain the leakage current monitoring data I eliminating the meteorological factors. correct .

2. A MOA leakage current correction method for eliminating external interference according to claim 1, characterized in that: The meteorological factors include temperature data T and humidity data Rh.

3. A MOA leakage current correction method for eliminating external interference according to claim 1, characterized in that: The box plot method includes: Propose the lower quartile Q1 and the upper quartile Q3 of the leakage current monitoring data I; The upper threshold TH is calculated based on the lower quartile Q1 and the upper quartile Q3 UP and the lower threshold TH down ; By comparing the data values ​​in the leakage current monitoring data I with the upper threshold TH UP and the threshold value TH down A comparison is performed, and outliers are marked and removed from the leakage current monitoring data I. The data gaps generated after the removal are supplemented to obtain the normal leakage current monitoring data I1.

4. A MOA leakage current correction method for eliminating external interference according to claim 3, characterized in that: The extracting the lower quartile Q1 and the upper quartile Q3 from the leakage current monitoring data I comprises: Arranging the leakage current monitoring data I in order of size to obtain a data set of the leakage current monitoring data I; The data set is divided into four sub-datasets with the same number of values; the sub-dataset at the smallest value in the data set is the number at the 25th position, and these data values ​​are extracted to obtain the lower quartile Q1; the sub-dataset at the largest value in the data set is the number at the 75th position, and these data values ​​are extracted to obtain the upper quartile Q3.

5. The MOA leakage current correction method for eliminating external interference according to claim 3 is characterized in that: The upper threshold TH UP for TH UP =Q3+(Q3-Q1) The lower threshold TH down TH down =Q3+(Q3-Q1) Among them, Q3 is the upper quartile and Q1 is the lower quartile.

6. A MOA leakage current correction method for eliminating external interference according to claim 3, characterized in that: The data supplement includes: The data supplement adopts the previous data value I at the data vacancy position i-1 and the next data value I at the data gap position i+1 The average value of is replaced to obtain the data set of leakage current monitoring data I under normal conditions; The calculation formula for the data supplement is: Among them, I i-1 is the previous data value at the data vacancy position, I i+1 It is the next data value at the data gap position.

7. A MOA leakage current correction method for eliminating external interference according to claim 1, characterized in that: The optimization process of the fitting model includes: The leakage current monitoring data I is randomly divided into K mutually exclusive leakage current monitoring sub-data sets, and the meteorological factor data is correspondingly randomly divided into K mutually exclusive meteorological sub-data sets; Based on the leakage current monitoring sub-dataset and the meteorological sub-dataset inputted into the fitting model, K training models are obtained by training; Obtain an average value of the MSE of the K training models, and use the average value of the MSE of the K training models as an optimization indicator to obtain the optimal hyperparameter through the particle swarm optimization algorithm; The fitting model is retrained based on the optimal hyperparameters to obtain an optimal fitting model.

8. A MOA leakage current correction method for eliminating external interference according to claim 7, characterized in that: The construction of the fitting model includes: Constructing a model construction data set based on the normal leakage current monitoring data I1 as output features, the air temperature data T and the humidity data Rh as input features; The model building data set is trained using a support vector machine algorithm to establish the fitting model.

9. The MOA leakage current correction method for eliminating external interference according to claim 1, characterized in that: The correcting of the leakage current monitoring data I based on the optimal fitting model includes: The meteorological factor data is input into the optimal fitting model to obtain the leakage current prediction value I * ; Based on the set reference condition, find the data value corresponding to the reference condition in the leakage current monitoring data I, and record it as the real data I base ; Based on the real data I base and the leakage current prediction value I * Correct the leakage current monitoring data I to obtain the leakage current monitoring data I eliminating the meteorological factors correct .

10. A MOA leakage current correction system for eliminating external interference, characterized in that: include: The acquisition module is used to collect the leakage current monitoring data I of the arrester and the meteorological factor data in the same period; A processing module is used to remove outliers from the leakage current monitoring data I that are different from normal conditions, and then establish a fitting model through the processed data and the meteorological factor data, and optimize the fitting model to obtain the optimal fitting model; The correction module, which connects the acquisition module and the correction module, is used to correct the leakage current monitoring data I based on the optimal fitting model and the meteorological factor data to obtain the leakage current monitoring data I that eliminates the meteorological factor. correct ; Output module, the output module is connected to the correction module for outputting the leakage current monitoring data I correct .

Images