Online monitoring data feature extraction method and device of extra-high voltage alternating current equipment and electronic equipment

Abstract

The invention relates to the technical field of power systems, in particular to an online monitoring data feature extraction method and device for extra-high voltage alternating current equipment, electronic equipment and a storage medium. The method comprises the steps of performing feature data extraction on online monitoring data of the extra-high voltage alternating current equipment; calculating an evaluation index of the feature data; calculating the extraction accuracy of the feature data based on the evaluation indexes; and if the extraction accuracy is greater than or equal to a preset value, outputting the feature data. More representative feature data can be extracted from online monitoring data, reliable data support is provided for fault diagnosis and state evaluation, and safe and stable operation of a power system can be maintained.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and particularly relates to a method, device, electronic device and storage medium for extracting on-line monitoring data characteristics of ultra-high voltage AC equipment. Background Art

[0002] With the rapid development of power systems, ultra-high voltage AC equipment, as a core component of power transmission, its safe and stable operation is crucial to the reliability of the entire power grid. To ensure the performance of these devices and prevent potential failures, the application of condition monitoring and fault warning technologies has become increasingly widespread. Currently, the on-line monitoring of ultra-high voltage AC equipment mainly relies on a large amount of data collected by various sensors, and these data contain detailed information about the operating state of the equipment.

[0003] Although the existing monitoring technologies can provide a large amount of data, directly using the monitoring data for subsequent fault diagnosis and state assessment has low reliability and is insufficient to support the safe and stable operation of the power system. Summary of the Invention

[0004] In view of this, the embodiments of the present application provide a method, device, electronic device and storage medium for extracting on-line monitoring data characteristics of ultra-high voltage AC equipment, which can extract more representative characteristic data from on-line monitoring data, provide reliable data support for fault diagnosis and state assessment, and is conducive to maintaining the safe and stable operation of the power system.

[0005] The first aspect of the embodiments of the present application provides a method for extracting on-line monitoring data characteristics of ultra-high voltage AC equipment, including:

[0006] Extracting characteristic data from the on-line monitoring data of ultra-high voltage AC equipment;

[0007] Calculating an evaluation index of the characteristic data;

[0008] Calculating the extraction accuracy rate of the characteristic data based on the evaluation index;

[0009] If the extraction accuracy rate is greater than or equal to a preset value, output the characteristic data.

[0010] In one embodiment, the characteristic data includes partial discharge characteristic data, and the partial discharge characteristic data includes at least one of the peak value, mean value, variance, root mean square value, rise time and fall time of the partial discharge signal.

[0011] In one embodiment, the characteristic data includes dissolved gas in oil characteristic data, and the dissolved gas in oil characteristic data includes at least one of the average concentration, maximum concentration, minimum concentration, concentration change range, concentration change rate, concentration standard deviation, concentration coefficient of variation, concentration trend, and concentration mutation over time of the dissolved gas in oil.

[0012] In one embodiment, the evaluation indicators include at least one of integrity, uniqueness, timeliness, consistency, and rationality;

[0013] Calculating the evaluation indicators of the characteristic data includes:

[0014] Using the formula to calculate the integrity of the characteristic data, using the formula to calculate the uniqueness of the characteristic data, using the formula to calculate the timeliness of the characteristic data, using the formula to calculate the consistency of the characteristic data, and using the formula to calculate at least one of the rationality of the characteristic data;

[0015] where m is the number of data records in the monitoring data record set, n is the number of attribute parameter columns in the monitoring data record set, r ij is the element corresponding to the jth attribute parameter column of the ith record in the monitoring data record set, c(r ij ) is the integrity boolean value of r ij , u(r ij ) is the uniqueness boolean value of r ij , t(r ij ) is the timeliness boolean value of r ij , co(r ij ) is the consistency boolean value of r ij , ra(r ij ) is the rationality boolean value of r ij , Com. is the integrity of the characteristic data, Uniq. is the uniqueness of the characteristic data, Tim. is the timeliness of the characteristic data, Con. is the consistency of the characteristic data, and Rat. is the rationality of the characteristic data.

[0016] In one embodiment, calculating the extraction accuracy rate of each characteristic data based on the evaluation indicators includes:

[0017] According to the formula D k =[A k T to calculate the quantization value D k of the evaluation indicator;

[0018] According to the formula ​Calculate the extraction accuracy rate Q of each of the feature data;

[0019] where A k is the k-th evaluation index of the feature data, k = 1, 2, …, K, and K is the number of evaluation indexes.

[0020] In one embodiment, the extraction of feature data from the on-line monitoring data of UHV AC equipment includes:

[0021] Filter the partial discharge signal in the on-line monitoring data by using a filter to obtain a filtered partial discharge signal, and extract partial discharge feature data from the filtered partial discharge signal;

[0022] Extract dissolved gas in oil feature data from the on-line monitoring data; wherein, the dissolved gas in oil feature data includes a concentration change rate, and the concentration change rate is calculated based on a time window;

[0023] After calculating the extraction accuracy rate of the feature data based on the evaluation index, it further includes:

[0024] If the extraction accuracy rate is less than a preset value, adjust the parameters of the filter and the time window, and return to the step of extracting feature data from the on-line monitoring data of UHV AC equipment.

[0025] A second aspect of the embodiments of the present application provides an on-line monitoring data feature extraction device for UHV AC equipment, including:

[0026] A feature data extraction module, configured to extract feature data from the on-line monitoring data of UHV AC equipment;

[0027] An evaluation index calculation module, configured to calculate the evaluation index of the feature data;

[0028] An extraction accuracy rate calculation module, configured to calculate the extraction accuracy rate of the feature data based on the evaluation index;

[0029] A feature data output module, configured to output the feature data if the extraction accuracy rate is greater than or equal to a preset value.

[0030] In one embodiment, the extraction accuracy rate calculation module is further configured to:

[0031] According to the formula D k = [A k T calculate the quantization value D of the evaluation index k ;

[0032] According to the formula calculate the extraction accuracy rate Q of each of the feature data;

[0033] wherein, A k is the k-th evaluation index of the characteristic data, k = 1, 2, …, K, and K is the number of evaluation indexes.

[0034] The third aspect of the embodiments of the present application provides an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the electronic device implements the on-line monitoring data feature extraction method for extra-high voltage AC equipment provided in the first aspect of the embodiments of the present application.

[0035] The fourth aspect of the embodiments of the present application provides a computer program product, including a computer program. When the computer program is run, the method described in the first aspect of the embodiments of the present application is executed.

[0036] The on-line monitoring data feature extraction method for extra-high voltage AC equipment provided in the first aspect of the embodiments of the present application can effectively extract key features of partial discharge and dissolved gases in oil closely related to the equipment state from a large amount of original monitoring data by extracting characteristic data from the on-line monitoring data of extra-high voltage AC equipment. This process not only simplifies the subsequent data processing and analysis work, but also provides a solid foundation for accurate state assessment. Calculate the evaluation indexes of the characteristic data and calculate the extraction accuracy rate based on these indexes, so that the quality of the extracted characteristic data can be quantified, ensuring that only high-quality data will be output for further analysis. It is possible to identify data quality problems that may affect the data analysis results at an early stage and improve the reliability and accuracy of the final output data through iterative optimization, providing reliable data support for fault diagnosis and state assessment, and further enhancing the operation stability and security of the entire system.

[0037] It can be understood that the beneficial effects of the above second aspect to the fourth aspect can refer to the relevant descriptions in the above first aspect and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0039] Figure 1 is a schematic flowchart of an on-line monitoring data feature extraction method for extra-high voltage AC equipment provided by an embodiment of the present application;

[0040] Figure 2 It is a schematic flowchart of a method for extracting characteristics of on-line monitoring data of UHV AC equipment provided by another embodiment of the present application;

[0041] Figure 3 It is a schematic flowchart of a method for extracting characteristics of on-line monitoring data of UHV AC equipment provided by another embodiment of the present application;

[0042] Figure 4 It is a schematic structural diagram of an on-line monitoring data feature extraction device provided by an embodiment of the present application;

[0043] Figure 5 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0044] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system architectures, technologies, etc. are presented in order to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0045] It should be understood that when used in the specification of the present application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0046] It should also be understood that the term "and / or" as used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0047] The reference to "one embodiment" or "some embodiments" etc. described in the specification of the present application means that a specific feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the present application. Thus, the phrases "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0048] Such as Figure 1As shown in the figure, the method for extracting the characteristics of on-line monitoring data of UHV AC equipment provided by the embodiments of the present application includes the following steps S101 to S104:

[0049] Step S101: Extract characteristic data from the on-line monitoring data of UHV AC equipment.

[0050] In application, the characteristic data includes partial discharge characteristic data (such as peak value, mean value, variance, root mean square value, rise time, and fall time, etc.) and dissolved gas in oil characteristic data (such as average concentration, maximum concentration, minimum concentration, concentration change range, concentration change rate, concentration standard deviation, concentration coefficient of variation, concentration trend, and concentration mutation in time).

[0051] In application, the original data is also preprocessed, for example, noise interference is removed through filtering technology to ensure the quality of the data.

[0052] Step S102: Calculate the evaluation indexes of the characteristic data.

[0053] In application, the evaluation indexes include but are not limited to integrity, uniqueness, timeliness, consistency, and rationality. Integrity ensures that all necessary data is collected completely to avoid missing key information; uniqueness guarantees that there are no duplicate or redundant data entries; timeliness confirms that the data reflects the latest equipment status; consistency checks whether there are contradictions or inconsistencies between the data; and rationality helps to identify and exclude outliers or incorrect data.

[0054] Step S103: Calculate the extraction accuracy rate of the characteristic data based on the evaluation indexes.

[0055] In application, the extraction accuracy rate of the characteristic data can be calculated by using the weighted average method according to the importance degree of multiple evaluation indexes.

[0056] Step S104: If the extraction accuracy rate is greater than or equal to the preset value, output the characteristic data.

[0057] In application, the preset value can be set according to requirements, for example, 90%. If the extraction accuracy rate is greater than or equal to 90%, it is considered that the quality of the characteristic extraction reaches the standard, and the characteristic data is output. Otherwise, it is considered that the effect of the characteristic extraction does not reach the standard, and the process can return to step S101 to re-extract the characteristic data.

[0058] In application, each evaluation index and its weight, and the final extraction accuracy rate can also be displayed in the form of a chart or dashboard. This not only helps technicians quickly discover problems but also provides an intuitive basis for subsequent data optimization. In addition, when a certain evaluation index is lower than expected, a report or alarm can be automatically generated to remind relevant personnel to take measures in time.

[0059] In the embodiments of the present application, by extracting characteristic data from the on-line monitoring data of UHV AC equipment, key characteristics of partial discharge and dissolved gases in oil, which are closely related to the equipment state, can be effectively refined from a large amount of original monitoring data. This process not only simplifies the subsequent data processing and analysis work, but also provides a solid foundation for accurate state assessment. By calculating the evaluation indexes of the characteristic data and calculating the extraction accuracy based on these indexes, the quality of the extracted characteristic data can be quantified, so as to ensure that only high-quality data will be output for further analysis. It is possible to identify data quality problems that may affect the data analysis results at an early stage, and improve the reliability and accuracy of the finally output data through iterative optimization, providing reliable data support for fault diagnosis and state assessment, and further enhancing the operation stability and safety of the entire system.

[0060] In one embodiment, the characteristic data includes partial discharge characteristic data, and the partial discharge characteristic data includes at least one of the peak value, mean value, variance, root mean square value, rise time, and fall time of the partial discharge signal.

[0061] In application, Peak Value: the maximum amplitude of the signal, which helps to judge the discharge intensity. Wherein, is the sampling value of the signal;

[0062] Mean: reflecting the average level of the signal, which is often used for trend analysis. Wherein, N is the total number of sampling points of the signal;

[0063] Variance: describing the degree of signal fluctuation, a larger variance indicates instability;

[0064] Root Mean Square (RMS): used to measure the effective value of the signal, reflecting the overall energy of the signal;

[0065] Rise time and fall time: the time required for the signal to reach the maximum or minimum value, reflecting the dynamic characteristics of the discharge process. Determine the time points when the signal reaches 10% and 90% of the peak value according to the signal value to calculate the time difference.

[0066] The characteristic data of the embodiments of the present application includes partial discharge characteristic data. Taking the peak value, mean value, variance, root mean square value, rise time, and fall time of the partial discharge signal as the partial discharge characteristic data can comprehensively reflect various characteristics of the partial discharge phenomenon inside the equipment. For example, the peak value and mean value can be used to evaluate the discharge intensity and average level, while the rise time and fall time help to understand the dynamic characteristics of the discharge process. This multi-dimensional feature extraction method can provide richer information to describe the partial discharge behavior, thereby improving the accuracy and reliability of fault diagnosis. In addition, by filtering the partial discharge signal, noise interference can be effectively removed, further improving the quality of the characteristic data and ensuring the accuracy of subsequent analysis results.

[0067] In one embodiment, the characteristic data includes dissolved gas in oil characteristic data, and the dissolved gas in oil characteristic data includes at least one of the average concentration, maximum concentration, minimum concentration, concentration change range, concentration change rate, concentration standard deviation, concentration coefficient of variation, concentration trend, and concentration mutation over time of the dissolved gas in oil.

[0068] In application, the average concentration: the average value of the gas concentration over a certain period of time, reflecting the typical concentration level during that period;

[0069] The maximum concentration: the highest gas concentration within a period of time, indicating the peak value of a specific component in the sample;

[0070] The minimum concentration: the lowest gas concentration within a period of time, which can reveal possible low-concentration components;

[0071] The concentration change range: the difference between the maximum concentration and the minimum concentration, reflecting the change range of the gas concentration;

[0072] The concentration change rate: the rate of change of the concentration over time, which may indicate the rate of gas generation, release, or consumption;

[0073] The concentration standard deviation: the degree of dispersion of the concentration data, revealing the instability of the concentration change;

[0074] The concentration coefficient of variation: the ratio of the concentration standard deviation to the average concentration, used to compare the degree of concentration variation of different samples;

[0075] The concentration trend: the trend of the concentration over time, used to discover long-term change patterns;

[0076] The concentration mutation over time: the concentration suddenly changes within a short period of time, which may indicate an unexpected event.

[0077] Among them, the concentration change rate can be calculated according to the time window.

[0078] The characteristic data of the embodiments of the present application includes dissolved gas in oil characteristic data, and the dissolved gas in oil characteristic data includes various parameters such as average concentration, maximum concentration, minimum concentration, concentration change range, concentration change rate, concentration standard deviation, concentration coefficient of variation, concentration trend, and concentration mutation over time. These parameters can comprehensively reflect the changes in the gas components in the equipment insulating oil, thus providing an important basis for equipment condition assessment. In addition, by dynamically adjusting the size of the time window for calculating the concentration change rate, it is possible to more sensitively capture the concentration fluctuations in the short term, which is of great significance for timely detecting potential faults. It can improve the prediction ability of equipment state changes, thereby realizing earlier and more accurate fault warnings, and significantly enhancing the safety and reliability of the power system.

[0079] In one embodiment, the evaluation indicators include at least one of integrity, uniqueness, timeliness, consistency, and rationality;

[0080] Calculating the evaluation indicators of the feature data includes:

[0081] Using the formula to calculate the integrity of the feature data, using the formula to calculate the uniqueness of the feature data, using the formula to calculate the timeliness of the feature data, using the formula to calculate the consistency of the feature data, using the formula to calculate at least one of the rationality of the feature data;

[0082] where m is the number of data records in the monitoring data record set, n is the number of attribute parameter columns in the monitoring data record set, and r ij is the element corresponding to the j-th attribute parameter column of the i-th record in the monitoring data record set. c(r ij ) is the integrity boolean value of r ij , when r ij is a non-negative constant, the value of c(r ij ) is taken as 1, and when r ij is a negative number or other form, the value of c(r ij ) is taken as 0. u(r ij ) is the uniqueness boolean value of r ij , when r ij has duplicate values, the value of u(r ij ) is taken as 1, and when r ij is a unique value, the value of u(r ij ) is taken as 0. t(r ij ) is the timeliness boolean value of r ij , when r ij has the correct time sequence, the value of t(r ij ) is taken as 1, and when r ij has an incorrect time sequence, the value of t(r ij ) is taken as 0. co(r ij ) is the consistency boolean value of r ij , when r ij has consistent data, the value of co(r ij ) is taken as 1, and when r ij has inconsistent data, the value of co(r ij ) is taken as 0, where data with a higher statistical correlation with the previous time stamp than the statistical correlation between two attribute columns is considered consistent; otherwise, the data is considered inconsistent. ra(r ij ) is the rationality boolean value of r ij , when r ij has reasonable data, the value of ra(r ij) takes the value of 1 when r ij When the data is unreasonable, ra(r ij ) takes the value of 0, where data with consistent formats or values within a reasonable range is considered reasonable; otherwise, it is considered unreasonable. Com. represents the integrity of the feature data, Uniq. represents the uniqueness of the feature data, Tim. represents the timeliness of the feature data, Con. represents the consistency of the feature data, and Rat. represents the reasonableness of the feature data.

[0083] The evaluation indicators in the embodiments of this application include at least one of integrity, uniqueness, timeliness, consistency, and reasonableness. Each evaluation indicator is directly related to the quality performance of the data in different aspects. For example, integrity can ensure that all necessary data is collected completely, uniqueness can avoid the influence of duplicate or redundant data, timeliness and consistency ensure that the data reflects the real state within the same time period, and reasonableness helps to exclude outliers or incorrect data. Using a standardized method to quantify data quality can objectively judge whether the data is suitable for subsequent analysis and decision support. By using the above formulas to calculate the evaluation indicators such as the integrity, uniqueness, timeliness, consistency, and reasonableness of the feature data, the quality of the extracted feature data can be systematically evaluated. In this way, high-quality data can be effectively screened out, the risk of misjudgment caused by data quality problems can be reduced, and the stability of the power system can be enhanced.

[0084] In one embodiment, calculating the extraction accuracy rate of each feature data based on the evaluation indicators includes:

[0085] According to the formula D k =[A k T Calculate the quantization value D of the evaluation indicator k ;

[0086] According to the formula Calculate the extraction accuracy rate Q of each feature data;

[0087] Where A k is the k-th evaluation indicator of the feature data, k = 1, 2,..., K, and K is the number of evaluation indicators. W k is the weight of the evaluation indicator,

[0088] In applications, the importance of each evaluation indicator may be different, so it is necessary to assign corresponding weights W k to each indicator. The weights can be adjusted according to specific application scenarios and requirements. When the evaluation indicators are integrity, uniqueness, timeliness, consistency, and reasonableness, K is 5. A k As k takes 1, 2,..., K respectively, A k ​They are Integrity (Com.), Uniqueness (Uniq.), Timeliness (Tim.), Consistency (Con.), and Rationality (Rat.) respectively. The order of each evaluation index is not limited, as long as each evaluation index is taken into account.

[0089] In the embodiment of the present application, the evaluation index of each feature data is calculated through the above formula, and the extraction accuracy rate is calculated based on these quantization values. This not only avoids the deviation of subjective judgment, ensures the consistency, accuracy, and objectivity of the evaluation results, but also can comprehensively reflect the overall quality of the data, guide the optimization of targeted data processing strategies, thereby significantly improving the reliability and accuracy of subsequent fault diagnosis and condition monitoring. Through this data-driven closed-loop feedback mechanism, the extraction accuracy rate of feature data can be continuously improved, and further enhance the stability and security of the power system.

[0090] In one embodiment, as Figure 2 shown, step S101 includes the following steps S1011 and S1012:

[0091] Use a filter to filter the partial discharge signal in the on-line monitoring data to obtain the filtered partial discharge signal, and extract the partial discharge feature data from the filtered partial discharge signal;

[0092] Extract the dissolved gas in oil feature data from the on-line monitoring data; wherein, the dissolved gas in oil feature data includes the concentration change rate, and the concentration change rate is calculated based on a time window.

[0093] In one embodiment, as Figure 3 shown, after calculating the extraction accuracy rate of the feature data based on the evaluation index, it further includes step S105:

[0094] Step S105, if the extraction accuracy rate is less than the preset value, adjust the parameters of the filter and the time window, and return to the step of extracting the feature data from the on-line monitoring data of the UHV AC equipment.

[0095] In application, dynamically adjust the size of the time window for calculating the concentration change rate according to the working state of the monitoring device, so as to use a larger window during the stable period to smooth the fluctuations and a smaller window during the changing period to quickly respond to changes. When adjusting the parameters of the filter and the time window, and return to the step of extracting the feature data from the on-line monitoring data of the UHV AC equipment, and then judge again whether the extraction accuracy rate is greater than or equal to the preset value. If it still does not meet the requirement, continue to return to the step of extracting the feature data from the on-line monitoring data of the UHV AC equipment.

[0096] When the extraction accuracy rate of feature data in the embodiments of the present application is lower than the preset value, by adjusting the parameters of the filter and the time window and returning to the feature data extraction step, effective improvement of low-quality data can be achieved. A closed-loop feedback mechanism is provided, allowing dynamic adjustment of the data processing strategy according to real-time evaluation results until the expected accuracy rate requirement is met. By continuously optimizing the filter settings and the time window size, not only can noise interference be removed, but also key features can be captured more precisely, thereby improving the overall quality of the feature data. This method ensures that even if the ideal effect is not achieved in the initial extraction process, high-quality data that meets the requirements can be finally obtained through iterative optimization, greatly enhancing the robustness and reliability of the system.

[0097] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0098] The embodiments of the present application further provide an on-line monitoring data feature extraction device for UHV AC equipment, which is used to execute the steps in the embodiments of the on-line monitoring data feature extraction method for UHV AC equipment. The on-line monitoring data feature extraction device for UHV AC equipment can be a virtual appliance in an electronic device, run by the processor of the electronic device, or the electronic device itself.

[0099] As Figure 4 shown, an on-line monitoring data feature extraction device 100 for UHV AC equipment provided by the embodiments of the present application includes:

[0100] A feature data extraction module 101, which is used to extract feature data from the on-line monitoring data of UHV AC equipment;

[0101] An evaluation index calculation module 102, which is used to calculate the evaluation index of the feature data;

[0102] An extraction accuracy rate calculation module 103, which is used to calculate the extraction accuracy rate of the feature data based on the evaluation index;

[0103] A feature data output module 104, which is used to output the feature data if the extraction accuracy rate is greater than or equal to the preset value.

[0104] In one embodiment, the feature data includes partial discharge feature data, and the partial discharge feature data includes at least one of the peak value, mean value, variance, root mean square value, rise time, and fall time of the partial discharge signal.

[0105] In one embodiment, the feature data includes dissolved gas in oil feature data, and the dissolved gas in oil feature data includes at least one of the average concentration, maximum concentration, minimum concentration, concentration change range, concentration change rate, concentration standard deviation, concentration coefficient of variation, concentration trend, and concentration mutation over time of the dissolved gas in oil.

[0106] In one embodiment, the evaluation metrics include at least one of integrity, uniqueness, timeliness, consistency, and rationality;

[0107] The evaluation metric calculation module is further configured to:

[0108] Use the formula To calculate the integrity of the feature data, use the formula To calculate the uniqueness of the feature data, use the formula To calculate the timeliness of the feature data, use the formula To calculate the consistency of the feature data, use the formula To calculate at least one of the rationality of the feature data;

[0109] Where m is the number of data records in the monitoring data record set, n is the number of attribute parameter columns in the monitoring data record set, r ij Is the element corresponding to the jth attribute parameter column of the ith record in the monitoring data record set, c(r ij ) Is the integrity boolean value of r ij , u(r ij ) Is the uniqueness boolean value of r ij , t(r ij ) Is the timeliness boolean value of r ij , co(r ij ) Is the consistency boolean value of r ij , ra(r ij ) Is the rationality boolean value of r ij , Com. is the integrity of the feature data, Uniq. is the uniqueness of the feature data, Tim. is the timeliness of the feature data, Con. is the consistency of the feature data, and Rat. is the rationality of the feature data.

[0110] In one embodiment, the extraction accuracy calculation module is further configured to:

[0111] According to the formula D k =[A k T Calculate the quantization value D of the evaluation metric k ;

[0112] According to the formula Calculate the extraction accuracy Q of each feature data;

[0113] Where A​k is the k-th evaluation index of the feature data, where k = 1, 2, …, K, and K is the number of evaluation indices.

[0114] In one embodiment, the feature data extraction module is further configured to:

[0115] Filter the partial discharge signals in the online monitoring data by using a filter to obtain the filtered partial discharge signals, and extract the partial discharge feature data from the filtered partial discharge signals;

[0116] Extract the dissolved gas in oil feature data from the online monitoring data; wherein, the dissolved gas in oil feature data includes a concentration change rate, and the concentration change rate is calculated based on a time window;

[0117] It further includes an adjustment module, which is configured to:

[0118] If the extraction accuracy is less than a preset value, adjust the parameters of the filter and the time window, and return to the step of extracting the feature data from the online monitoring data of the UHV AC equipment.

[0119] In applications, each module in the online monitoring data feature extraction device of the UHV AC equipment can be a software program module, can also be implemented by different logic circuits integrated in a processor, or can also be implemented by multiple distributed processors.

[0120] As Figure 5 shown, an embodiment of the present application further provides an electronic device 200, including: at least one processor 201 ( Figure 5 only one processor is shown), a memory 202, and a computer program 203 stored in the memory 202 and executable on at least one processor 201. When the processor 201 executes the computer program 203, the steps in the above-mentioned various method embodiments are implemented.

[0121] In applications, the electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that Figure 5 merely an example of the electronic device, which does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine some components, or different components.

[0122] In an application, the processor may be a Central Processing Unit (CPU), and the processor may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0123] In an application, in some embodiments, the memory may be an internal storage unit of an electronic device, such as a hard disk or memory of the electronic device. In other embodiments, the memory may also be an external storage device of the electronic device, for example, a plug-in hard disk equipped on the electronic device, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory may also include both an internal storage unit and an external storage device of the electronic device. The memory is used to store an operating system, application programs, a BootLoader, data, and other programs, such as program codes of computer programs. The memory may also be used to temporarily store data that has been output or is to be output.

[0124] It should be noted that for the content such as information interaction and execution process between the above-mentioned devices / units, since it is based on the same concept as the method embodiment of the present application, for its specific functions and the technical effects brought, reference may be specifically made to the method embodiment part, and details are not described herein again.

[0125] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiments can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of the functional units and modules are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0126] An embodiment of this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the foregoing method embodiments can be implemented.

[0127] An embodiment of this application provides a computer program product, including a computer program. When the computer program product runs on an electronic device, the electronic device is enabled to execute the steps in the foregoing method embodiments.

[0128] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above method embodiments of this application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps in the foregoing method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the device / electronic device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0129] In the above embodiments, the descriptions of the various embodiments have their own focuses. For parts not detailed or recorded in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0130] Those of ordinary skill in the art will realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0131] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be in electrical, mechanical or other forms.

[0132] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0133] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included in the protection scope of this application.

Claims

1. A method for extracting features from online monitoring data of ultra-high voltage AC equipment, characterized in that: include: Extract feature data from online monitoring data of UHV AC equipment; Calculating an evaluation index of the feature data; Calculate the extraction accuracy of the feature data based on the evaluation index; If the extraction accuracy is greater than or equal to a preset value, the feature data is output.

2. The method for extracting features from online monitoring data of UHV AC equipment according to claim 1, characterized in that: The characteristic data includes partial discharge characteristic data, and the partial discharge characteristic data includes at least one of a peak value, a mean value, a variance, a root mean square value, a rise time, and a fall time of a partial discharge signal.

3. The method for extracting features from online monitoring data of UHV AC equipment according to claim 1, characterized in that: The characteristic data include characteristic data of dissolved gas in oil, and the characteristic data of dissolved gas in oil include at least one of the average concentration, maximum concentration, minimum concentration, concentration change amplitude, concentration change rate, concentration standard deviation, concentration variation coefficient, concentration trend and concentration mutation over time of the dissolved gas in oil.

4. The method for extracting features from online monitoring data of UHV AC equipment according to claim 1, characterized in that: The evaluation index includes at least one of completeness, uniqueness, timeliness, consistency, and rationality; The calculating of the evaluation index of the characteristic data comprises: Using the formula Calculate the integrity of the characteristic data and use the formula Calculate the uniqueness of the characteristic data and use the formula Calculate the timeliness of the characteristic data and use the formula Calculate the consistency of the characteristic data using the formula Calculating at least one of the rationalities of the feature data; Among them, m is the number of data records contained in the monitoring data record set, n is the number of attribute parameter columns contained in the monitoring data record set, and r ij is the element corresponding to the jth attribute parameter column of the i-th record in the monitoring data record set, c(rij) is r ij The integrity Boolean value of u(rij) is r ij The uniqueness Boolean value of , t(rij) is r ij The Boolean value of the timeliness, co(rij) is r ij The consistency Boolean value of , ra(rij) is r ij The rationality Boolean value of the feature data, Com. is the integrity of the feature data, Uniq. is the uniqueness of the feature data, Tim. is the timeliness of the feature data, Con. is the consistency of the feature data, and Rat. is the rationality of the feature data.

5. The method for extracting features from online monitoring data of UHV AC equipment according to claim 1, characterized in that: Calculating the extraction accuracy of each feature data based on the evaluation index includes: According to formula D k =[A k ] T Calculate the quantitative value D of the evaluation index k ; According to the formula Calculate the extraction accuracy Q of each feature data; Among them, A k is the kth evaluation index of the feature data, k = 1, 2, ..., K, K is the number of evaluation indexes, W k is the weight of the evaluation indicator.

6. The method for extracting features from online monitoring data of UHV AC equipment according to claim 1, characterized in that: The feature data extraction of the online monitoring data of the UHV AC equipment includes: Using a filter to filter the partial discharge signal in the online monitoring data to obtain a filtered partial discharge signal, and extracting partial discharge characteristic data from the filtered partial discharge signal; Extracting characteristic data of dissolved gas in oil from the online monitoring data; wherein the characteristic data of dissolved gas in oil includes concentration change rate, and the concentration change rate is calculated based on a time window; After calculating the extraction accuracy of the feature data based on the evaluation index, the method further includes: If the extraction accuracy is less than a preset value, the parameters of the filter and the time window are adjusted, and the process returns to the step of extracting feature data from the online monitoring data of the UHV AC equipment.

7. A device for extracting features from online monitoring data of ultra-high voltage AC equipment, characterized in that: include: A feature data extraction module is used to extract feature data from online monitoring data of UHV AC equipment; An evaluation index calculation module, used to calculate the evaluation index of the feature data; An extraction accuracy calculation module, used to calculate the extraction accuracy of the feature data based on the evaluation index; The feature data output module is used to output the feature data if the extraction accuracy is greater than or equal to a preset value.

8. The online monitoring data feature extraction device for UHV AC equipment according to claim 7, characterized in that: The characteristic data includes partial discharge characteristic data, and the partial discharge characteristic data includes at least one of a peak value, a mean value, a variance, a root mean square value, a rise time, and a fall time of a partial discharge signal.

9. The online monitoring data feature extraction device for UHV AC equipment according to claim 7, characterized in that: The characteristic data include characteristic data of dissolved gas in oil, and the characteristic data of dissolved gas in oil include at least one of the average concentration, maximum concentration, minimum concentration, concentration change amplitude, concentration change rate, concentration standard deviation, concentration variation coefficient, concentration trend and concentration mutation over time of the dissolved gas in oil.

10. The online monitoring data feature extraction device for UHV AC equipment according to claim 7, characterized in that: The evaluation index includes at least one of completeness, uniqueness, timeliness, consistency, and rationality; The evaluation index calculation module is also used for: Using the formula Calculate the integrity of the characteristic data and use the formula Calculate the uniqueness of the characteristic data and use the formula Calculate the timeliness of the characteristic data and use the formula Calculate the consistency of the characteristic data using the formula Calculating at least one of the rationalities of the feature data; Among them, m is the number of data records contained in the monitoring data record set, n is the number of attribute parameter columns contained in the monitoring data record set, and r ij is the element corresponding to the jth attribute parameter column of the i-th record in the monitoring data record set, c(rij) is r ij The integrity Boolean value of u(rij) is r ij The uniqueness Boolean value of , t(rij) is r ij The Boolean value of the timeliness, co(rij) is r ij The consistency Boolean value of , ra(rij) is r ij The rationality Boolean value of the feature data, Com. is the integrity of the feature data, Uniq. is the uniqueness of the feature data, Tim. is the timeliness of the feature data, Con. is the consistency of the feature data, and Rat. is the rationality of the feature data.

11. The online monitoring data feature extraction device for UHV AC equipment according to claim 7, characterized in that: The extraction accuracy calculation module is also used for: According to formula D k =[A k ] T Calculate the quantitative value D of the evaluation index k ; According to the formula Calculate the extraction accuracy Q of each feature data; Among them, A k is the kth evaluation index of the feature data, k = 1, 2, …, K, and K is the number of evaluation indexes.

12. The online monitoring data feature extraction device for UHV AC equipment according to claim 7, characterized in that: The feature data extraction module is also used for: Using a filter to filter the partial discharge signal in the online monitoring data to obtain a filtered partial discharge signal, and extracting partial discharge characteristic data from the filtered partial discharge signal; Extracting characteristic data of dissolved gas in oil from the online monitoring data; wherein the characteristic data of dissolved gas in oil includes concentration change rate, and the concentration change rate is calculated based on a time window; Also included are tuning modules for: If the extraction accuracy is less than a preset value, the parameters of the filter and the time window are adjusted, and the process returns to the step of extracting feature data from the online monitoring data of the UHV AC equipment.

13. An electronic device, characterized in that: The electronic device comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the electronic device implements the method as claimed in any one of claims 1 to 6.

14. A computer-readable storage medium storing a computer program, characterized in that: The computer-readable storage medium stores a computer program, and 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.

Images