Method and system for evaluating credibility of digital twin data of power grid equipment

Abstract

The invention discloses a power grid equipment digital twin data credibility evaluation method and system, and the method comprises the steps: obtaining power transmission and transformation equipment data, carrying out the preprocessing of the data, and carrying out the feature extraction based on the preprocessed data; defining evaluation indexes and weights corresponding to the indexes according to the data characteristics of the power transmission and transformation equipment, and constructing a power transmission and transformation equipment input data quality evaluation model to quantitatively evaluate the input data quality of the digital twin model; and establishing a power transmission and transformation equipment fault diagnosis model based on the data after quantitative evaluation, and performing fault analysis and prediction based on the power transmission and transformation equipment fault diagnosis model. The state of the power transmission and transformation equipment of the power grid can be effectively detected, the fault prediction accuracy is improved, and a scientific basis is provided for intelligent management and operation and maintenance of the power grid.

Description

Technical Field

[0001] The present invention relates to the technical field of smart grids, and in particular to a method and system for credible assessment of digital twin data of power grid equipment. Background Art

[0002] The stability of power supply is an urgent problem to be solved in the construction of modern society. As the key link of power transmission and conversion, the working status of power transmission and transformation equipment has an important impact on the reliability and quality of power supply of the power grid. In the current development trend of the power grid and the digitalization process of modern society, intelligent management and operation and maintenance have gradually become core needs, aiming to achieve more accurate status detection, fault detection and efficient power grid maintenance and dispatching of power transmission and transformation equipment to ensure the continuous and stable operation of the entire national power system. Digital twin technology, with its ability to build a digital model that is highly similar to the physical reality in virtual space, provides a new idea and method for the status monitoring and fault prediction of power transmission and transformation equipment in the power grid. With the help of the digital twin model, the working status of the power transmission and transformation equipment of the power grid can be reflected in real time, and the performance table under different conditions can be simulated, thereby providing technical support for the optimized operation and maintenance and fault detection of the equipment.

[0003] However, the effectiveness and reliability of digital twin technology are closely related to the quality of input data of power transmission and transformation equipment. In the actual application scenarios of power grids, the collection of its operating data and environmental parameters faces many challenges. First, the data sources of power transmission and transformation equipment include a variety of sensors and monitoring systems, which are widely sourced and cannot be completely unified in format and accuracy, that is, consistency is difficult to guarantee. At the same time, the working environment of power transmission and transformation equipment is complex, and there are many interferences such as electromagnetic interference, which affects the accuracy. In addition, how to ensure the validity and integrity of data under long-term work, as well as the collaborative credibility between data, is also one of the challenges facing the current digital twin technology. At present, for the evaluation of input data quality, single-dimensional data characteristic analysis is mostly used, lacking a comprehensive and integrated evaluation of data. For the application scenarios of digital twins, how to combine the real-time operation data, environmental parameters and historical maintenance records of the equipment to comprehensively evaluate the credibility of the data to ensure that the digital twin model can accurately reflect the true status of the equipment is still insufficient. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides a method and system for credible assessment of digital twin data of power grid equipment to solve the problems mentioned in the background technology.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, an embodiment of the present invention provides a method for credible assessment of digital twin data of power grid equipment, comprising: acquiring data of power transmission and transformation equipment, preprocessing the data, and extracting features based on the preprocessed data;

[0009] According to the data characteristics of power transmission and transformation equipment, the evaluation indicators and the corresponding weights of each indicator are defined, and a power transmission and transformation equipment input data quality evaluation model is constructed to quantitatively evaluate the input data quality of the digital twin model;

[0010] A power transmission and transformation equipment fault diagnosis model is established based on the quantitatively evaluated data, and fault analysis and prediction are performed based on the power transmission and transformation equipment fault diagnosis model.

[0011] As a preferred solution of the method for credible assessment of digital twin data of power grid equipment described in the present invention, the data preprocessing includes: using an empirical mode decomposition method to perform signal denoising;

[0012] The eigenmode function is expressed as:

[0013]

[0014] Where N is the total number of data points, E min (i) represents the upper envelope defined by the local maximum at time point i, E max (i) represents the lower envelope defined by the local minimum at time point i;

[0015] Assume that the original signal is x(t), use cubic spline interpolation to determine the maximum and minimum values, obtain the upper and lower envelopes, and calculate the average value of the envelope, denoted as m 1 , the envelope average value is taken from the original signal and expressed as:

[0016] h 1 =x(t)-m 1

[0017] If the difference h 1 Satisfies the eigenmode function, then h 1 =c 1 If not satisfied, then h 1 = x(t), repeat the calculation to obtain m 11 , and calculate h 11 =h 1 -m 11 .

[0018] As a preferred solution of the method for credible assessment of digital twin data of power grid equipment described in the present invention, it also includes: if the eigenmode function is not satisfied, repeating k iterations until the requirement is satisfied, and recording the obtained signal as c 1 =h 1k , where h 1k =h 1(k-1) -m 1k ;

[0019] Separate c from x(t) 1 , we get r 1 =x(t)-c n , r 1 (t) is used as the signal to be decomposed, and the iterative process is repeated to obtain the second component c that meets the requirements of the eigenmode function. 2 After n iterations, n components will be obtained; n eigenmode components and one r n get:

[0020]

[0021] As a preferred solution of the method for credible assessment of digital twin data of power grid equipment described in the present invention, wherein: extracting features based on the preprocessed data includes: decomposing the signal based on a wavelet basis function to obtain a decomposition coefficient;

[0022] The decomposition coefficients are reconstructed to extract signal details within a single frequency band and determine the frequency bands in which the signal is concentrated, and power spectrum analysis is performed on the signal for feature extraction.

[0023] As a preferred solution of the trusted evaluation method of digital twin data of power grid equipment described in the present invention, wherein: evaluation indicators and corresponding weights of each indicator are defined according to the data characteristics of power transmission and transformation equipment, and a power transmission and transformation equipment input data quality evaluation model is constructed to quantitatively evaluate the input data quality of the digital twin model, including: according to the characteristics of power transmission and transformation equipment data, completeness, accuracy, correctness and effectiveness are selected as evaluation indicators, and weights are determined according to expert scores, and the calculation is as follows:

[0024]

[0025] Among them, l max represents the maximum eigenvalue in the judgment matrix, and n represents the number of evaluation indicators;

[0026] The consistency judgment result is P. If P=0, the evaluation setting is reasonable and the weight is valid. If P<0.1, the expected consistency level is achieved. If P>0.1, the weight is invalid and needs to be redivided.

[0027] After defining each indicator and its corresponding weight, data mining technology is introduced to calculate and construct a quality assessment model for input data of power transmission and transformation equipment.

[0028] As a preferred solution of the method for credible assessment of digital twin data of power grid equipment described in the present invention, it also includes: when performing multidimensional data mining, outlier mining is performed in combination with the relationship between each indicator. If the results calculated by the formula are inconsistent, they are regarded as abnormal data; when calculating, it is assumed that the input dependent variable indicator is y and the independent variable indicator is x, where x is a set of power transmission and transformation equipment data, expressed as x={x 1 ,x 2 ,x 3 ,…,x n}, and combine the prediction method to calculate the residual:

[0029]

[0030] in, represents the predicted value;

[0031] Solve the deviation degree A sequence:

[0032]

[0033] Combined with the deviation tolerance to detect the deviation degree sequence, the tolerance parameter T is set. When T=0, the input data quality assessment model of the power transmission and transformation equipment is used to detect whether the measured value is consistent with the predicted value to judge the quality of the power grid data; when T≠0, the model is used to detect the deviation between the actual value and the predicted value acceptable to the user.

[0034] As a preferred solution of the trusted evaluation method of digital twin data of power grid equipment described in the present invention, wherein: a fault diagnosis model of power transmission and transformation equipment is established based on the data after quantitative evaluation, and fault analysis and prediction based on the fault diagnosis model of power transmission and transformation equipment includes:

[0035] Select sample data and feature variables, standardize the sample data, and divide it into pre-training set, optimization set and test set according to a fixed ratio;

[0036] Encode the fault type and status of power transmission and transformation equipment;

[0037] A transformer fault diagnosis model based on a deep belief network is established, and the model parameters are initialized to random values. The shallow restricted Boltzmann machine layer of the model is pre-trained layer by layer using unlabeled samples in the pre-training set.

[0038] Use the labeled samples in the optimization set to tune the entire network through the back propagation algorithm to make the network performance close to the global optimum; save the trained network and test its diagnostic performance with the data samples in the test set;

[0039] The fault analysis model is optimized according to the computing power index of the system operation equipment, the system operation time index and the system accuracy index to realize fault analysis and prediction.

[0040] In a second aspect, the present invention provides a power grid equipment digital twin data trust evaluation system, comprising:

[0041] A data acquisition and processing module, used to acquire data of power transmission and transformation equipment, pre-process the data, and perform feature extraction based on the pre-processed data;

[0042] The evaluation module is used to define the evaluation indicators and the corresponding weights of each indicator according to the data characteristics of the power transmission and transformation equipment, and to build an evaluation model to quantitatively evaluate the input data quality of the digital twin model;

[0043] The fault prediction module is used to establish a power transmission and transformation equipment fault diagnosis model based on the quantitatively evaluated data, and to perform fault analysis and prediction based on the power transmission and transformation equipment fault diagnosis model.

[0044] In a third aspect, the present invention provides an electronic device, comprising:

[0045] Memory and processor;

[0046] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method for trustworthy assessment of digital twin data of power grid equipment are implemented.

[0047] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the method for trustworthy assessment of digital twin data of power grid equipment.

[0048] Compared with the prior art, the present invention has the following beneficial effects: the present invention collects equipment operation data and environmental parameters in real time, combines historical maintenance records, and uses big data mining technology to conduct a comprehensive analysis of the consistency, accuracy, and completeness of the data; further introduces a data quality scoring system to quantify the credibility of the input data to ensure the reliability of the digital twin model; it can effectively detect the status of power transmission and transformation equipment in the power grid, improve the accuracy of fault prediction, and provide a scientific basis for the intelligent management and operation and maintenance of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0050] Figure 1 A method flow chart of a method and system for trustworthy assessment of digital twin data of power grid equipment described in one embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0052] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0053] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0054] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0055] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0056] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0057] Example 1

[0058] Reference Figure 1 , is an embodiment of the present invention, which provides a method for credible assessment of digital twin data of power grid equipment, including:

[0059] S100: Acquire power transmission and transformation equipment data, preprocess the data, and perform feature extraction based on the preprocessed data;

[0060] In the embodiment of the present application, the acquired power transmission and transformation equipment data may include electrical quantities, temperature, and vibration signals.

[0061] In the embodiment of the present application, data preprocessing includes: signal denoising using an empirical mode decomposition method;

[0062] The eigenmode function is expressed as:

[0063]

[0064] Where N is the total number of data points, E min (i) represents the upper envelope defined by the local maximum at time point i, E max (i) represents the lower envelope defined by the local minimum at time point i;

[0065] Assume that the original signal is x(t), use cubic spline interpolation to determine the maximum and minimum values, obtain the upper and lower envelopes, and calculate the average value of the envelope, denoted as m 1 , the envelope average value is taken from the original signal and expressed as:

[0066] h 1 =x(t)-m 1

[0067] If the difference h 1 Satisfies the eigenmode function, then h 1 =c 1 If not satisfied, then h 1 = x(t), repeat the calculation to obtain m 11 , and calculate h 11 =h 1 -m 11 .

[0068] In the embodiment of the present application, it also includes: if the eigenmode function is not satisfied, repeating k iterations until the requirement is satisfied, and recording the obtained signal as c 1 =h 1k , where h 1k =h 1(k-1) -m 1k ;

[0069] Separate c from x(t) 1 , we get r 1 =x(t)-c n , r 1 (t) is used as the signal to be decomposed, and the iterative process is repeated to obtain the second component c that meets the requirements of the eigenmode function. 2 After n iterations, n components will be obtained; n eigenmode components and one r n get:

[0070]

[0071] It should be noted that the data of power transmission and transformation equipment is preprocessed to improve the signal quality through operations such as amplification, filtering, and conversion. Among them, filtering is crucial because it involves removing noise from the signal. In this case, the empirical mode decomposition method can be used to denoise the signal.

[0072] In the embodiment of the present application, feature extraction based on preprocessed data includes: decomposing the signal based on a wavelet basis function to obtain a decomposition coefficient;

[0073] The decomposition coefficients are reconstructed to extract signal details within a single frequency band and determine the frequency bands in which the signal is concentrated, and power spectrum analysis is performed on the signal for feature extraction.

[0074] S200: defining evaluation indicators and corresponding weights of each indicator according to the data characteristics of the power transmission and transformation equipment, and constructing a power transmission and transformation equipment input data quality evaluation model to quantitatively evaluate the input data quality of the digital twin model;

[0075] In the embodiment of the present application, the evaluation indicators and the corresponding weights of each indicator are defined according to the data characteristics of the power transmission and transformation equipment, and the input data quality evaluation model of the power transmission and transformation equipment is constructed to quantitatively evaluate the input data quality of the digital twin model, including: according to the characteristics of the power transmission and transformation equipment data, completeness, accuracy, correctness and effectiveness are selected as evaluation indicators, and the weights are determined according to the expert scores, and the calculation is as follows:

[0076]

[0077] Among them, l max represents the maximum eigenvalue in the judgment matrix, and n represents the number of evaluation indicators;

[0078] The consistency judgment result is P. If P=0, the evaluation setting is reasonable and the weight is valid. If P<0.1, the expected consistency level is achieved. If P>0.1, the weight is invalid and needs to be redivided.

[0079] After defining each indicator and its corresponding weight, data mining technology is introduced to calculate and construct a quality assessment model for input data of power transmission and transformation equipment.

[0080] It should be noted that when mining abnormal data, if the amount of data is small, manual detection can be used; if it is a large amount of data, or a large number of states, it needs to be achieved through machine intelligence.

[0081] In the embodiment of the present application, it also includes: when performing multidimensional data mining, outlier mining is performed in combination with the relationship between each indicator. If the results calculated by the formula are inconsistent, they are regarded as abnormal data; when calculating, it is assumed that the input dependent variable indicator is y and the independent variable indicator is x, where x is a set of power transmission and transformation equipment data, expressed as x={x 1 ,x 2 ,x 3 ,…,x n}, and combine the prediction method to calculate the residual:

[0082]

[0083] in, represents the predicted value;

[0084] Solve the deviation degree A sequence:

[0085]

[0086] Combined with the deviation tolerance to detect the deviation degree sequence, the tolerance parameter T is set. When T=0, the input data quality assessment model of the power transmission and transformation equipment is used to detect whether the measured value is consistent with the predicted value to judge the quality of the power grid data; when T≠0, the model is used to detect the deviation between the actual value and the predicted value acceptable to the user.

[0087] It should be noted that the deviation degree sequence is detected in combination with the deviation tolerance. By setting the tolerance parameter, the flexibility of the evaluation model in calculation is ensured.

[0088] S300: Establishing a power transmission and transformation equipment fault diagnosis model based on the quantitatively evaluated data, and performing fault analysis and prediction based on the power transmission and transformation equipment fault diagnosis model;

[0089] In an embodiment of the present application, a power transmission and transformation equipment fault diagnosis model is established based on the quantitatively evaluated data, and fault analysis and prediction based on the power transmission and transformation equipment fault diagnosis model includes:

[0090] Select sample data and feature variables, standardize the sample data, and divide it into pre-training set, optimization set and test set according to a fixed ratio;

[0091] Encode the fault type and status of power transmission and transformation equipment;

[0092] A transformer fault diagnosis model based on a deep belief network is established, and the model parameters are initialized to random values. The shallow restricted Boltzmann machine layer of the model is pre-trained layer by layer using unlabeled samples in the pre-training set.

[0093] Use the labeled samples in the optimization set to tune the entire network through the back propagation algorithm to make the network performance close to the global optimum; save the trained network and test its diagnostic performance with the data samples in the test set;

[0094] The fault analysis model is optimized according to the computing power index of the system operation equipment, the system operation time index and the system accuracy index to realize fault analysis and prediction.

[0095] It should be noted that the present invention overcomes the problem of incompleteness caused by simplification by adopting multi-dimensional input data; during data preprocessing, on the basis of conventional amplification, filtering, and conversion operations, the empirical mode decomposition method is used for noise reduction, which more effectively improves the signal-to-noise ratio, and after noise reduction, feature extraction is performed using wavelet transform, and the signal is decomposed by selecting appropriate wavelet basis functions, reconstructing coefficients to determine the frequency band and performing power spectrum analysis to accurately extract features; the input data is quantified using credibility scoring, and an evaluation model is constructed by combining the four evaluation indicators of completeness, accuracy, correctness, and effectiveness to more comprehensively evaluate the credibility of the data and further improve the accuracy of fault detection; a comprehensive data analysis framework is constructed and a data quality scoring system is introduced. By real-time collection of equipment operation data and environmental parameters, combined with historical maintenance records, big data mining technology is used to comprehensively analyze data consistency, accuracy, and completeness, quantify data credibility, ensure the reliability of the digital twin model, effectively detect equipment status, and improve fault prediction accuracy, providing strong support for intelligent management and operation and maintenance of power grids.

[0096] Example 2

[0097] The above embodiment is a schematic scheme of a method for credible assessment of digital twin data of power grid equipment. It should be noted that the technical scheme of the credible assessment system of digital twin data of power grid equipment and the technical scheme of the credible assessment method of digital twin data of power grid equipment mentioned above belong to the same concept. The details of the technical scheme of the credible assessment system of digital twin data of power grid equipment in this embodiment that are not described in detail can all be referred to the description of the technical scheme of the credible assessment method of digital twin data of power grid equipment mentioned above.

[0098] In this embodiment, a power grid equipment digital twin data trust evaluation system includes:

[0099] The data acquisition and processing module is used to acquire the data of the power transmission and transformation equipment, pre-process the data, and perform feature extraction based on the pre-processed data;

[0100] The evaluation module is used to define the evaluation indicators and the corresponding weights of each indicator according to the data characteristics of the power transmission and transformation equipment, and to build an evaluation model to quantitatively evaluate the input data quality of the digital twin model;

[0101] The fault prediction module is used to establish a power transmission and transformation equipment fault diagnosis model based on the data after quantitative evaluation, and to perform fault analysis and prediction based on the power transmission and transformation equipment fault diagnosis model.

[0102] This embodiment also provides an electronic device, which is applicable to the case of a method for credible assessment of digital twin data of power grid equipment, including:

[0103] Memory and processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the trusted assessment method of digital twin data of power grid equipment as proposed in the above embodiment.

[0104] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for implementing the trusted assessment of digital twin data of power grid equipment proposed in the above embodiment is implemented.

[0105] The storage medium proposed in this embodiment and the method for implementing trusted assessment of digital twin data of power grid equipment proposed in the above embodiment belong to the same inventive concept. For technical details not fully described in this embodiment, please refer to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0106] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ReadOnly, Memory, ROM), random access memory (RandomAccess Memory, RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform the methods of various embodiments of the present invention.

[0107] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for credible assessment of digital twin data of power grid equipment, characterized in that: include: Acquire power transmission and transformation equipment data, preprocess the data, and perform feature extraction based on the preprocessed data; According to the data characteristics of power transmission and transformation equipment, the evaluation indicators and the corresponding weights of each indicator are defined, and a power transmission and transformation equipment input data quality evaluation model is constructed to quantitatively evaluate the input data quality of the digital twin model; A power transmission and transformation equipment fault diagnosis model is established based on the quantitatively evaluated data, and fault analysis and prediction is performed based on the power transmission and transformation equipment fault diagnosis model.

2. The method for credible assessment of digital twin data of power grid equipment according to claim 1, characterized in that: The data preprocessing includes: using empirical mode decomposition method to perform signal denoising; The eigenmode function is expressed as: Where N is the total number of data points, E min (i) represents the upper envelope defined by the local maximum at time point i, E max (i) represents the lower envelope defined by the local minimum at time point i; Assume that the original signal is x(t), use cubic spline interpolation to determine the maximum and minimum values, obtain the upper and lower envelopes, and calculate the average value of the envelope, denoted as m1. The average value of the envelope taken from the original signal is expressed as: h1=x(t)-m1 If the difference h1 satisfies the eigenmode function, then h1 = c1. If not, then h1 = x(t). Repeat the calculation to obtain m. 11 , and calculate h 11 =h1-m 11 .

3. The method for credible assessment of digital twin data of power grid equipment according to claim 2, characterized in that: Also includes: If the eigenmode function is not satisfied, repeat the iteration k times until the requirement is met, and record the obtained signal as c1=h 1k , where h 1k =h 1(k-1) -m 1k ; Separate c1 from x(t) and we get r1=x(t)-c n , taking r1(t) as the signal to be decomposed, repeat the iterative process to obtain the second component c2 that meets the requirements of the eigenmode function. After n iterations, n components will be obtained; n eigenmode components and one r n get:

4. The method for credible assessment of digital twin data of power grid equipment according to claim 3, characterized in that: Extracting features based on the preprocessed data includes: decomposing the signal based on a wavelet basis function to obtain decomposition coefficients; The decomposition coefficients are reconstructed to extract signal details within a single frequency band and determine the frequency bands in which the signal is concentrated, and power spectrum analysis is performed on the signal for feature extraction.

5. The method for credible assessment of digital twin data of power grid equipment according to claim 4, characterized in that: According to the characteristics of power transmission and transformation equipment data, the evaluation indicators and the corresponding weights of each indicator are defined, and the power transmission and transformation equipment input data quality evaluation model is constructed to quantitatively evaluate the input data quality of the digital twin model. According to the characteristics of power transmission and transformation equipment data, completeness, accuracy, correctness and effectiveness are selected as evaluation indicators, and the weights are determined according to the expert scores. The calculation is as follows: Among them, l max represents the maximum eigenvalue in the judgment matrix, and n represents the number of evaluation indicators; The consistency judgment result is P. If P=0, the evaluation setting is reasonable and the weight is valid. If P<0.1, the expected consistency level is achieved. If P>0.1, the weight is invalid and needs to be redivided. After defining each indicator and its corresponding weight, data mining technology is introduced to calculate and construct a quality assessment model for input data of power transmission and transformation equipment.

6. The method for credible assessment of digital twin data of power grid equipment according to claim 5, characterized in that: Also includes: When multidimensional data mining is performed, outlier mining is performed in combination with the relationship between various indicators. If the results calculated by the formula are inconsistent, they are considered as abnormal data. When calculating, it is assumed that the input dependent variable indicator is y and the independent variable indicator is x, where x is a set of power transmission and transformation equipment data, expressed as x = {x1, x2, x3, ..., x n }, and combine the prediction method to calculate the residual: in, represents the predicted value; Solve the deviation degree A sequence: Combined with the deviation tolerance to detect the deviation degree sequence, the tolerance parameter T is set. When T=0, the input data quality assessment model of the power transmission and transformation equipment is used to detect whether the measured value is consistent with the predicted value to judge the quality of the power grid data; when T≠0, the model is used to detect the deviation between the actual value and the predicted value acceptable to the user.

7. The method for credible assessment of digital twin data of power grid equipment according to claim 6, characterized in that: Based on the data after quantitative evaluation, a fault diagnosis model for power transmission and transformation equipment is established. Fault analysis and prediction based on the fault diagnosis model for power transmission and transformation equipment include: Select sample data and feature variables, standardize the sample data, and divide it into pre-training set, optimization set and test set according to a fixed ratio; Encode the fault type and status of power transmission and transformation equipment; A transformer fault diagnosis model based on a deep belief network is established, and the model parameters are initialized to random values. The shallow restricted Boltzmann machine layer of the model is pre-trained layer by layer using unlabeled samples in the pre-training set. Use the labeled samples in the optimization set to tune the entire network through the back propagation algorithm to make the network performance close to the global optimum; save the trained network and test its diagnostic performance with the data samples in the test set; The fault analysis model is optimized according to the computing power index of the system operation equipment, the system operation time index and the system accuracy index to realize fault analysis and prediction.

8. A power grid equipment digital twin data trust evaluation system, characterized in that: include: A data acquisition and processing module, used to acquire data of power transmission and transformation equipment, pre-process the data, and perform feature extraction based on the pre-processed data; The evaluation module is used to define the evaluation indicators and the corresponding weights of each indicator according to the data characteristics of the power transmission and transformation equipment, and to build an evaluation model to quantitatively evaluate the input data quality of the digital twin model; The fault prediction module is used to establish a power transmission and transformation equipment fault diagnosis model based on the quantitatively evaluated data, and to perform fault analysis and prediction based on the power transmission and transformation equipment fault diagnosis model.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method for trustworthy assessment of digital twin data of power grid equipment described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the method for trustworthy assessment of digital twin data of power grid equipment as described in any one of claims 1 to 7.

Images