Method, system, equipment and medium for evaluating operation stability of DC electronic voltage transformer

Abstract

The present invention relates to a method, system, device and medium for evaluating the operating stability of a direct current electronic voltage transformer, wherein the method comprises the following steps: obtaining a secondary voltage signal, temperature data, resistance deviation, capacitance deviation and stray capacitance data of a sample voltage transformer; performing data processing on the secondary voltage signal and temperature data of the voltage transformer respectively to obtain harmonic characteristics and temperature characteristics; constructing a transformer error evaluation model, putting the data of the sample voltage transformer into a training set, training the transformer error model using the training set, and obtaining a trained transformer error evaluation model; obtaining target voltage transformer data, inputting the data into the transformer error evaluation model, obtaining an error evaluation result of the target voltage transformer to form an error evaluation sequence, calculating an error index, judging the operating stability of the transformer based on the error index, and obtaining a judgment result of the operating stability of the target voltage transformer.

Description

Technical Field

[0001] The invention relates to a method, system, equipment and medium for evaluating the operating stability of a direct current electronic voltage transformer, and belongs to the technical field of online monitoring of electric power metering. Background Art

[0002] DC electronic voltage transformers are widely used in DC transmission systems and are an important part of DC metering systems and relay protection systems. Under the current trend of digitalization of DC metering systems, DC electronic voltage transformers are gradually replacing traditional DC voltage transformers. Therefore, studying the error characteristics of DC electronic voltage transformers is of great significance to ensure the accuracy of DC metering.

[0003] The Chinese invention patent with application (patent) number CN202210072989.1 proposes a "capacitive voltage transformer stability assessment method", which constructs and obtains CVT stability state assessment indicators, establishes a CVT stability state indicator data model, and conducts stability assessment on the transformer error state. The above method has a simple error data indicator, does not mine the deep characteristics of the data, and cannot effectively assess the current operating status of the transformer. Summary of the invention

[0004] In order to solve the problems existing in the above-mentioned prior art, the present invention proposes a method, system, device and medium for evaluating the operating stability of a DC electronic voltage transformer. Firstly, the transformer error is evaluated based on parameters such as harmonics and temperature; secondly, the stability of the transformer operating state is judged based on the error evaluation result.

[0005] The technical solution of the present invention is as follows:

[0006] In one aspect, the present invention provides a method for evaluating the operating stability of a DC electronic voltage transformer, comprising the following steps:

[0007] Obtaining raw data of the sample voltage transformer, including secondary voltage signal, temperature data, resistance deviation, capacitance deviation and stray capacitance data;

[0008] Perform EEMD modal decomposition on the secondary voltage signal, obtain the DC voltage component and harmonic component based on the decomposition result, and calculate the harmonic content of each harmonic component through the DC voltage component; reconstruct the one-dimensional harmonic content sequence and temperature data respectively and convert them into two-dimensional data; perform multidimensional feature extraction on the reconstructed two-dimensional data respectively to obtain harmonic features and temperature features;

[0009] A transformer error evaluation model is constructed, and the temperature characteristics, harmonic characteristics, resistance deviation, capacitance deviation and stray capacitance data of the sample voltage transformer are put into a training set. The transformer error model is trained using the training set to obtain a trained transformer error evaluation model.

[0010] The temperature characteristics, harmonic characteristics, resistance deviation, capacitance deviation and stray capacitance data of the target voltage transformer over a period of time are obtained, and input into the trained transformer error evaluation model to obtain the error evaluation sequence of the target voltage transformer;

[0011] Evaluation indicators are calculated based on the error evaluation sequence. The evaluation indicators include fluctuation indicators, trend indicators and abnormal indicators. The operating stability of the target voltage transformer is judged based on the evaluation indicators.

[0012] Preferably, the EEMD modal decomposition is specifically as follows:

[0013]

[0014] in, , is the data length; is the number of modal decompositions; is the decomposed component, M, where is the DC voltage component, is the harmonic component, is the residual signal;

[0015] Based on the DC voltage component, the harmonic content is calculated. The specific formula is as follows:

[0016]

[0017] in, is the effective value of the DC voltage component; For the The effective value of the harmonic components, =2, 3, ... L, indicating the number of main harmonic components selected by setting the threshold;

[0018] right Reconstruct the data, convert the one-dimensional data into two-dimensional data, and extract multi-dimensional features. The specific formula is as follows:

[0019]

[0020] in, ;

[0021] Using CNN Perform multi-dimensional convolution. The specific formula is as follows:

[0022]

[0023]

[0024] in, for convolution; is the Sigmoid function; Multiply the corresponding elements; Add corresponding elements;

[0025] Use attention mechanism to focus on features , , The specific steps for fusion are as follows:

[0026] The features to be input , , Perform element-by-element multiplication to remove redundant information. The specific formula is as follows:

[0027]

[0028] The features to be input , , Perform element-by-element addition to integrate complementary information. The specific formula is as follows:

[0029]

[0030] Will and Perform splicing to generate fusion features , the specific formula is as follows:

[0031]

[0032] in, It is a channel splicing operation;

[0033] Use the coordinate attention mechanism to input , , The features are further extracted to obtain multimodal features:

[0034]

[0035] in, is the coordinate attention operation;

[0036] The attention mechanism is enhanced , , Features and Fusion The features are concatenated to obtain the final fusion features. , as shown below:

[0037]

[0038] Using CNN-LSTM to fusion features Perform feature extraction:

[0039]

[0040] in, It is a harmonic characteristic.

[0041] Preferably, the calculation of the evaluation index comprises the following steps:

[0042] Calculate the theoretical impact of harmonics and temperature on the error as follows:

[0043] Calculate the theoretical effect of harmonics on the error:

[0044]

[0045]

[0046]

[0047] in, The frequency of existence is The ratio difference of the mutual inductor when the harmonic is is an imaginary unit; is the ratio difference of the transformer when the influence of harmonics is not considered; is the resistance of the high voltage arm; is the capacitance of the high voltage arm; is the resistance of the low voltage arm; is the capacitance of the low voltage arm; It is the high voltage resistor of the secondary voltage divider; It is the low voltage resistor of the secondary voltage divider; is the equivalent input resistance of the remote module; ;

[0048] Calculate the theoretical effect of temperature change on the error:

[0049]

[0050] in, ; ; is the transformer resistance affected by temperature; is the capacitance value of the transformer affected by temperature;

[0051]

[0052]

[0053]

[0054] in, is the temperature change; is the temperature coefficient of the voltage divider resistor; is the temperature coefficient of the remote module resistance; is the temperature coefficient of the voltage divider capacitor;

[0055] The error evaluation results of the target voltage transformer for a period of time are obtained to form an error evaluation sequence. Harmonic and temperature effects are separated based on the error evaluation sequence, as shown in the following formula:

[0056]

[0057] in, is the error evaluation sequence;

[0058] based on Calculate the fluctuation index, trend index, and abnormal index of the error at the current time t. Divide into different interval blocks according to J size:

[0059] The volatility indicators are as follows:

[0060]

[0061] in, is the fluctuation of error within the error length of 2J; For the The error evaluation result data value of each point; is the mean value of the error result data of any two data blocks within the length of 2J;

[0062] The trend indicators are as follows:

[0063]

[0064]

[0065]

[0066] in, is the difference between the mean of the current J error values ​​and the mean of the previous J error values; is the difference between the maximum value of the current J error values ​​and the mean value of the previous J error values; is the error evaluation result data value of the vth point;

[0067] The abnormal indicator is defined as , represents the number of times exceeding the abnormal threshold line within the 2J range;

[0068] The upper and lower limits of the threshold line are set as shown in the following formula:

[0069]

[0070]

[0071] in, is the upper limit of the threshold line; is the lower limit of the threshold line;

[0072]

[0073]

[0074] in, is the mean of the current 2J errors; is the standard deviation of the current 2J errors; To adjust the parameters.

[0075] Preferably, the method for judging the operating stability of the target voltage transformer based on the evaluation index is specifically:

[0076] Construct the scoring function for each evaluation indicator:

[0077]

[0078]

[0079]

[0080]

[0081] in, , , Set the thresholds respectively; For the current error value The scoring function is set; is the stability scoring function of the volatility index; Scoring function for stability of trend indicator; is the stability scoring function of the anomaly indicator;

[0082] Compare and analyze the above four indicators and assign weights to them respectively. , , complete the transformer stability score, the specific formula is as follows:

[0083]

[0084] The calculated value of Q is matched to the following four operating states: stable [80, 100], slightly unstable [50, 80), moderately unstable [30, 50), and severely unstable [0, 30), to obtain the stable operating state of the transformer.

[0085] On the other hand, the present invention also provides a DC electronic voltage transformer operation stability evaluation system, comprising:

[0086] The data processing module obtains the original data of the sample voltage transformer, including the secondary voltage signal, temperature data, resistance deviation, capacitance deviation and stray capacitance data; performs EEMD modal decomposition on the secondary voltage signal, obtains the DC voltage component and the harmonic component based on the decomposition result, and calculates the harmonic content of each harmonic component through the DC voltage component; reconstructs the one-dimensional harmonic content sequence and temperature data respectively and converts them into two-dimensional data; performs multi-dimensional feature extraction on the reconstructed two-dimensional data to obtain harmonic features and temperature features;

[0087] The error evaluation module constructs a transformer error evaluation model, puts the temperature characteristics, harmonic characteristics, resistance deviation, capacitance deviation and stray capacitance data of the sample voltage transformer into a training set, and uses the training set to train the transformer error model to obtain a trained transformer error evaluation model;

[0088] The stability judgment module obtains the temperature characteristics, harmonic characteristics, resistance deviation, capacitance deviation and stray capacitance data of the target voltage transformer over a period of time, and inputs them into the trained transformer error evaluation model to obtain the error evaluation sequence of the target voltage transformer; the evaluation indicators are calculated based on the error evaluation sequence, and the evaluation indicators include fluctuation indicators, trend indicators, and abnormal indicators, and the operating stability of the target voltage transformer is judged based on the evaluation indicators.

[0089] Preferably, the EEMD modal decomposition is specifically as follows:

[0090]

[0091] in, , is the data length; is the number of modal decompositions; is the decomposed component, M, where is the DC voltage component, is the harmonic component, is the residual signal;

[0092] Based on the DC voltage component, the harmonic content is calculated. The specific formula is as follows:

[0093]

[0094] in, is the effective value of the DC voltage component; For the The effective value of the harmonic components, =2, 3, ... L, indicating the number of main harmonic components selected by setting the threshold;

[0095] right Reconstruct the data, convert the one-dimensional data into two-dimensional data, and extract multi-dimensional features. The specific formula is as follows:

[0096]

[0097] in, ;

[0098] Using CNN Perform multi-dimensional convolution. The specific formula is as follows:

[0099]

[0100]

[0101] in, for convolution; is the Sigmoid function; Multiply the corresponding elements; Add corresponding elements;

[0102] Use attention mechanism to focus on features , , The specific steps for fusion are as follows:

[0103] The features to be input , , Perform element-by-element multiplication to remove redundant information. The specific formula is as follows:

[0104]

[0105] The features to be input , , Perform element-by-element addition to integrate complementary information. The specific formula is as follows:

[0106]

[0107] Will and Perform splicing to generate fusion features , the specific formula is as follows:

[0108]

[0109] in, It is a channel splicing operation;

[0110] Use the coordinate attention mechanism to input , , The features are further extracted to obtain multimodal features:

[0111]

[0112] in, is the coordinate attention operation;

[0113] The attention mechanism is enhanced , , Features and Fusion The features are concatenated to obtain the final fusion features. , as shown below:

[0114]

[0115] Using CNN-LSTM to fusion features Perform feature extraction:

[0116]

[0117] in, It is a harmonic characteristic.

[0118] Preferably, the calculation of the evaluation index comprises the following steps:

[0119] Calculate the theoretical impact of harmonics and temperature on the error as follows:

[0120] Calculate the theoretical effect of harmonics on the error:

[0121]

[0122]

[0123]

[0124] in, The frequency of existence is The ratio difference of the mutual inductor when the harmonic is is an imaginary unit; is the ratio difference of the transformer when the influence of harmonics is not considered; is the resistance of the high voltage arm; is the capacitance of the high voltage arm; is the resistance of the low voltage arm; is the capacitance of the low voltage arm; It is the high voltage resistor of the secondary voltage divider; It is the low voltage resistor of the secondary voltage divider; is the equivalent input resistance of the remote module; ;

[0125] Calculate the theoretical effect of temperature change on the error:

[0126]

[0127] in, ; ; is the transformer resistance affected by temperature; is the capacitance value of the transformer affected by temperature;

[0128]

[0129]

[0130]

[0131] in, is the temperature change; is the temperature coefficient of the voltage divider resistor; is the temperature coefficient of the remote module resistance; is the temperature coefficient of the voltage divider capacitor;

[0132] The error evaluation results of the target voltage transformer for a period of time are obtained to form an error evaluation sequence. Harmonic and temperature effects are separated based on the error evaluation sequence, as shown in the following formula:

[0133]

[0134] in, is the error evaluation sequence;

[0135] based on Calculate the fluctuation index, trend index, and abnormal index of the error at the current time t. Divide into different interval blocks according to J size:

[0136] The volatility indicators are as follows:

[0137]

[0138] in, is the fluctuation of error within the error length of 2J; For the The error evaluation result data value of each point; is the mean value of the error result data of any two data blocks within the length of 2J;

[0139] The trend indicators are as follows:

[0140]

[0141]

[0142]

[0143] in, is the difference between the mean of the current J error values ​​and the mean of the previous J error values; is the difference between the maximum value of the current J error values ​​and the mean value of the previous J error values; is the error evaluation result data value of the vth point;

[0144] The abnormal indicator is defined as , represents the number of times exceeding the abnormal threshold line within the 2J range;

[0145] The upper and lower limits of the threshold line are set as shown in the following formula:

[0146]

[0147]

[0148] in, is the upper limit of the threshold line; is the lower limit of the threshold line;

[0149]

[0150]

[0151] in, is the mean of the current 2J errors; is the standard deviation of the current 2J errors; To adjust the parameters.

[0152] Preferably, the method for judging the operating stability of the target voltage transformer based on the evaluation index is specifically:

[0153] Construct the scoring function for each evaluation indicator:

[0154]

[0155]

[0156]

[0157]

[0158] in, , , Set the thresholds respectively; For the current error value The scoring function is set; is the stability scoring function of the volatility index; Scoring function for stability of trend indicator; is the stability scoring function of the anomaly indicator;

[0159] Compare and analyze the above four indicators and assign weights to them respectively. , , complete the transformer stability score, the specific formula is as follows:

[0160]

[0161] The calculated value of Q is matched to the following four operating states: stable [80, 100], slightly unstable [50, 80), moderately unstable [30, 50), and severely unstable [0, 30), to obtain the stable operating state of the transformer.

[0162] On the other hand, the present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for evaluating the operating stability of a DC electronic voltage transformer as described in any embodiment of the present invention is implemented.

[0163] On the other hand, the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method for evaluating the operating stability of a DC electronic voltage transformer as described in any embodiment of the present invention is implemented.

[0164] The present invention has the following beneficial effects:

[0165] 1. The present invention uses multi-dimensional convolution to extract features from harmonic data, and uses coordinate attention to complete the fusion of features of different dimensions, thereby achieving deep and accurate extraction of feature data;

[0166] 2. Based on the error results, the present invention further constructs a stability evaluation index to realize the judgment of the stable state of the mutual inductor. BRIEF DESCRIPTION OF THE DRAWINGS

[0167] Figure 1 A schematic diagram of a method flow chart of an embodiment of the present invention;

[0168] Figure 2 A schematic diagram of multi-dimensional convolution shown in an embodiment of the present invention;

[0169] Figure 3 Schematic diagram of a mutual inductor error evaluation result according to an embodiment of the present invention. DETAILED DESCRIPTION

[0170] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0171] It should be understood that the step numbers used in this document are only for convenience of description and are not intended to limit the order in which the steps are executed.

[0172] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0173] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0174] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.

[0175] Embodiment 1:

[0176] See also Figure 1-3 This embodiment provides a method for evaluating the operating stability of a DC electronic voltage transformer, comprising the following steps:

[0177] S10, obtaining the original data of the sample voltage transformer, including secondary voltage signal, temperature data, resistance deviation, capacitance deviation and stray capacitance data; performing EEMD modal decomposition on the secondary voltage signal, obtaining DC voltage component and harmonic component based on the decomposition result, and calculating the harmonic content of each harmonic component through the DC voltage component; reconstructing the one-dimensional harmonic content sequence and temperature data respectively, and converting them into two-dimensional data; performing multidimensional feature extraction on the reconstructed two-dimensional data respectively, and obtaining harmonic features and temperature features;

[0178] S20, constructing a transformer error evaluation model, putting the temperature characteristics, harmonic characteristics, resistance deviation, capacitance deviation and stray capacitance data of the sample voltage transformer into a training set, and using the training set to train the transformer error model to obtain a trained transformer error evaluation model;

[0179] S30. Obtain temperature characteristics, harmonic characteristics, resistance deviation, capacitance deviation and stray capacitance data of the target voltage transformer over a period of time, and input them into a trained transformer error evaluation model to obtain an error evaluation sequence of the target voltage transformer; calculate evaluation indicators based on the error evaluation sequence, the evaluation indicators including fluctuation indicators, trend indicators and abnormality indicators, and judge the operating stability of the target voltage transformer based on the evaluation indicators.

[0180] As a preferred implementation of this embodiment, in steps S10-S30, the EEMD modal decomposition is specifically as follows:

[0181]

[0182] in, , is the data length; is the number of modal decompositions; is the decomposed component, M, where is the DC voltage component, is the harmonic component, is the residual signal;

[0183] Based on the DC voltage component, the harmonic content is calculated. The specific formula is as follows:

[0184]

[0185] in, is the effective value of the DC voltage component; For the The effective value of the harmonic components, =2, 3, ... L, indicating the number of main harmonic components selected by setting the threshold;

[0186] right Reconstruct the data, convert the one-dimensional data into two-dimensional data, and extract multi-dimensional features. The specific formula is as follows:

[0187]

[0188] in, ;

[0189] Using CNN Perform multi-dimensional convolution. The specific formula is as follows:

[0190]

[0191]

[0192] in, for convolution; is the Sigmoid function; Multiply the corresponding elements; Add corresponding elements;

[0193] Use attention mechanism to focus on features , , The specific steps for fusion are as follows:

[0194] The features to be input , , Perform element-by-element multiplication to remove redundant information. The specific formula is as follows:

[0195]

[0196] The features to be input , , Perform element-by-element addition to integrate complementary information. The specific formula is as follows:

[0197]

[0198] Will and Perform splicing to generate fusion features , the specific formula is as follows:

[0199]

[0200] in, It is a channel splicing operation;

[0201] Use the coordinate attention mechanism to input , , The features are further extracted to obtain multimodal features:

[0202]

[0203] in, is the coordinate attention operation;

[0204] The attention mechanism is enhanced , , Features and Fusion The features are concatenated to obtain the final fusion features. , as shown below:

[0205]

[0206] Using CNN-LSTM to fusion features Perform feature extraction:

[0207]

[0208] in, It is a harmonic characteristic.

[0209] As a preferred implementation of this embodiment, the calculation of the evaluation index includes the following steps:

[0210] Calculate the theoretical impact of harmonics and temperature on the error as follows:

[0211] Theoretical impact of harmonics on error:

[0212]

[0213]

[0214]

[0215] in, The frequency of existence is The ratio difference of the mutual inductor when the harmonic is is an imaginary unit; is the ratio difference of the transformer when the influence of harmonics is not considered; is the resistance of the high voltage arm; is the capacitance of the high voltage arm; is the resistance of the low voltage arm; is the capacitance of the low voltage arm; It is the high voltage resistor of the secondary voltage divider; It is the low voltage resistor of the secondary voltage divider; is the equivalent input resistance of the remote module; ;

[0216] Calculate the theoretical effect of temperature change on the error:

[0217]

[0218] in, ; ; is the transformer resistance affected by temperature; is the capacitance value of the transformer affected by temperature;

[0219]

[0220]

[0221]

[0222] in, is the temperature change; is the temperature coefficient of the voltage divider resistor; is the temperature coefficient of the remote module resistance; is the temperature coefficient of the voltage divider capacitor;

[0223] The error evaluation results of the target voltage transformer for a period of time are obtained to form an error evaluation sequence. Harmonic and temperature effects are separated based on the error evaluation sequence, as shown in the following formula:

[0224]

[0225] in, is the error evaluation sequence;

[0226] based on Calculate the fluctuation index, trend index, and abnormal index of the error at the current time t. Divide into different interval blocks according to J size:

[0227] The volatility indicators are as follows:

[0228]

[0229] in, is the fluctuation of error within the error length of 2J; For the The error evaluation result data value of each point; is the mean value of the error result data of any two data blocks within the length of 2J;

[0230] The trend indicators are as follows:

[0231]

[0232]

[0233]

[0234] in, is the difference between the mean of the current J error values ​​and the mean of the previous J error values; is the difference between the maximum value of the current J error values ​​and the mean value of the previous J error values; is the error evaluation result data value of the vth point;

[0235] The abnormal indicator is defined as , represents the number of times exceeding the abnormal threshold line within the 2J range;

[0236] The upper and lower limits of the threshold line are set as shown in the following formula:

[0237]

[0238]

[0239] in, is the upper limit of the threshold line; is the lower limit of the threshold line;

[0240]

[0241]

[0242] in, is the mean of the current 2J errors; is the standard deviation of the current 2J errors; To adjust the parameters.

[0243] Stability scores are as follows:

[0244]

[0245]

[0246]

[0247]

[0248] in, , , Set the thresholds respectively; For the current error value The scoring function is set; is the stability scoring function of the volatility index; Scoring function for stability of trend indicator; is the stability scoring function of the anomaly indicator;

[0249] The above four indicators can be compared and analyzed by using the analytic hierarchy process, subjective weighting, objective weighting and other methods, and weights can be assigned respectively. , , complete the transformer stability score, the specific formula is as follows:

[0250]

[0251] The calculated value of Q is matched to the following four operating states: stable [80, 100], slightly unstable [50, 80), moderately unstable [30, 50), and severely unstable [0, 30), to obtain the stable operating state of the transformer.

[0252] Based on the error test results of the DC voltage transformer, the error evaluation model is constructed using the method proposed in this application. The comparison between the actual transformer error and the model evaluation results is shown in the following table:

[0253]

[0254] Based on the error evaluation results of a certain transformer at different times, the error operation stability is judged:

[0255]

[0256] Embodiment 2:

[0257] This embodiment provides a DC electronic voltage transformer operation stability assessment system, including:

[0258] The data processing module obtains the original data of the sample voltage transformer, including the secondary voltage signal, temperature data, resistance deviation, capacitance deviation and stray capacitance data; performs EEMD modal decomposition on the secondary voltage signal, obtains the DC voltage component and the harmonic component based on the decomposition result, and calculates the harmonic content of each harmonic component through the DC voltage component; reconstructs the one-dimensional harmonic content sequence and temperature data respectively and converts them into two-dimensional data; performs multidimensional feature extraction on the reconstructed two-dimensional data respectively to obtain harmonic features and temperature features; this module is used to implement the function of step S10 in the above-mentioned implementation one, and will not be described in detail;

[0259] An error evaluation module is used to construct a transformer error evaluation model, and the temperature characteristics, harmonic characteristics, resistance deviation, capacitance deviation and stray capacitance data of the sample voltage transformer are put into a training set, and the transformer error model is trained using the training set to obtain a trained transformer error evaluation model; this module is used to implement the function of step S20 in the above implementation, and the specific details are not repeated here;

[0260] The stability judgment module obtains the temperature characteristics, harmonic characteristics, resistance deviation, capacitance deviation and stray capacitance data of the target voltage transformer over a period of time, and inputs them into the trained transformer error evaluation model to obtain the error evaluation sequence of the target voltage transformer; the evaluation indicators are calculated based on the error evaluation sequence, and the evaluation indicators include fluctuation indicators, trend indicators, and abnormality indicators, and the operating stability of the target voltage transformer is judged based on the evaluation indicators; this module is used to implement the function of step S30 in the above-mentioned implementation one, and the details will not be repeated here.

[0261] Embodiment three:

[0262] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, a method for evaluating the operating stability of a DC electronic voltage transformer as described in any embodiment of the present invention is implemented.

[0263] Embodiment 4:

[0264] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, a method for evaluating the operating stability of a DC electronic voltage transformer as described in any embodiment of the present invention is implemented.

[0265] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0266] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0267] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0268] In several embodiments provided in the present application, if any function 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, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk, and other media that can store program codes.

[0269] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for evaluating the operating stability of a DC electronic voltage transformer, characterized in that: The following steps are involved: Obtaining raw data of the sample voltage transformer, including secondary voltage signal, temperature data, resistance deviation, capacitance deviation and stray capacitance data; Perform EEMD modal decomposition on the secondary voltage signal, obtain the DC voltage component and harmonic component based on the decomposition result, and calculate the harmonic content of each harmonic component through the DC voltage component; reconstruct the one-dimensional harmonic content sequence and temperature data respectively and convert them into two-dimensional data; perform multidimensional feature extraction on the reconstructed two-dimensional data respectively to obtain harmonic features and temperature features; A transformer error evaluation model is constructed, and the temperature characteristics, harmonic characteristics, resistance deviation, capacitance deviation and stray capacitance data of the sample voltage transformer are put into a training set. The transformer error model is trained using the training set to obtain a trained transformer error evaluation model. The temperature characteristics, harmonic characteristics, resistance deviation, capacitance deviation and stray capacitance data of the target voltage transformer over a period of time are obtained, and input into the trained transformer error evaluation model to obtain the error evaluation sequence of the target voltage transformer; Calculate evaluation indicators based on the error evaluation sequence, the evaluation indicators include fluctuation indicators, trend indicators, and abnormal indicators, and judge the operating stability of the target voltage transformer based on the evaluation indicators; The calculation of the evaluation index comprises the following steps: Calculate the theoretical impact of harmonics and temperature on the error as follows: Calculate the theoretical effect of harmonics on the error: in, The frequency of existence is The ratio difference of the mutual inductor when the harmonic is is an imaginary unit; is the ratio difference of the transformer when the influence of harmonics is not considered; is the resistance of the high voltage arm; is the capacitance of the high voltage arm; is the resistance of the low voltage arm; is the capacitance of the low voltage arm; It is the high voltage resistor of the secondary voltage divider; It is the low voltage resistor of the secondary voltage divider; is the equivalent input resistance of the remote module; ; Calculate the theoretical effect of temperature change on the error: in, ; ; is the transformer resistance affected by temperature; is the capacitance value of the transformer affected by temperature; in, is the temperature change; is the temperature coefficient of the voltage divider resistor; is the temperature coefficient of the remote module resistance; is the temperature coefficient of the voltage divider capacitor; The error evaluation results of the target voltage transformer for a period of time are obtained to form an error evaluation sequence. Harmonic and temperature effects are separated based on the error evaluation sequence, as shown in the following formula: in, is the error evaluation sequence; based on Calculate the fluctuation index, trend index, and abnormal index of the error at the current time t. according to Size is divided into different interval blocks: The volatility indicators are as follows: in, is the fluctuation of error within the error length of 2J; For the The error evaluation result data value of each point; is the mean value of the error result data of any two data blocks within the length of 2J; The trend indicators are as follows: in, is the difference between the mean of the current J error values ​​and the mean of the previous J error values; is the difference between the maximum value of the current J error values ​​and the mean value of the previous J error values; is the error evaluation result data value of the vth point; The abnormal indicator is defined as , represents the number of times exceeding the abnormal threshold line within the 2J range; The upper and lower limits of the threshold line are set as shown in the following formula: in, is the upper limit of the threshold line; is the lower limit of the threshold line; in, is the mean of the current 2J errors; is the standard deviation of the current 2J errors; To adjust the parameters.

2. A method for evaluating the operating stability of a DC electronic voltage transformer according to claim 1, characterized in that: The EEMD modal decomposition is specifically as follows: in, , is the data length; is the number of modal decompositions; is the decomposed component, M ,in, is the DC voltage component, is the harmonic component, is the residual signal; Based on the DC voltage component, the harmonic content is calculated. The specific formula is as follows: in, is the effective value of the DC voltage component; For the The effective value of the harmonic components, =2, 3, ... L, indicating the number of main harmonic components selected by setting the threshold; right Reconstruct the data, convert the one-dimensional data into two-dimensional data, and extract multi-dimensional features. The specific formula is as follows: in, ; Using CNN Perform multi-dimensional convolution. The specific formula is as follows: ； in, for convolution; is the Sigmoid function; Multiply the corresponding elements; Add corresponding elements; Use attention mechanism to focus on features , , The specific steps for fusion are as follows: The features to be input , , Perform element-by-element multiplication to remove redundant information. The specific formula is as follows: The features to be input , , Perform element-by-element addition to integrate complementary information. The specific formula is as follows: Will and Perform splicing to generate fusion features , the specific formula is as follows: in, It is a channel splicing operation; Use the coordinate attention mechanism to input , , The features are further extracted to obtain multimodal features: in, is the coordinate attention operation; The attention mechanism is enhanced , , Features and Fusion The features are concatenated to obtain the final fusion features. , as shown below: Using CNN-LSTM to fusion features Perform feature extraction: in, It is a harmonic characteristic.

3. A method for evaluating the operating stability of a DC electronic voltage transformer according to claim 1, characterized in that: The method for judging the operating stability of the target voltage transformer based on the evaluation index is specifically as follows: Construct the scoring function for each evaluation indicator: in, , , Set the thresholds respectively; For the current error value The scoring function is set; is the stability scoring function of the volatility index; Scoring function for stability of trend indicator; is the stability scoring function of the anomaly indicator; Compare and analyze the above four indicators and assign weights to them respectively. , , complete the transformer stability score, the specific formula is as follows: The calculated value of Q is matched to the following four operating states: stable [80, 100], slightly unstable [50, 80), moderately unstable [30, 50), and severely unstable [0, 30), to obtain the stable operating state of the transformer.

4. A DC electronic voltage transformer operation stability evaluation system, characterized in that: include: A data processing module is used to obtain raw data of the sample voltage transformer, including secondary voltage signal, temperature data, resistance deviation, capacitance deviation and stray capacitance data; Perform EEMD modal decomposition on the secondary voltage signal, obtain the DC voltage component and harmonic component based on the decomposition result, and calculate the harmonic content of each harmonic component through the DC voltage component; reconstruct the one-dimensional harmonic content sequence and temperature data respectively and convert them into two-dimensional data; perform multidimensional feature extraction on the reconstructed two-dimensional data respectively to obtain harmonic features and temperature features; The error evaluation module constructs a transformer error evaluation model, puts the temperature characteristics, harmonic characteristics, resistance deviation, capacitance deviation and stray capacitance data of the sample voltage transformer into a training set, and uses the training set to train the transformer error model to obtain a trained transformer error evaluation model; The stability judgment module obtains the temperature characteristics, harmonic characteristics, resistance deviation, capacitance deviation and stray capacitance data of the target voltage transformer over a period of time, and inputs them into the trained transformer error evaluation model to obtain the error evaluation sequence of the target voltage transformer; the evaluation indicators are calculated based on the error evaluation sequence, and the evaluation indicators include fluctuation indicators, trend indicators and abnormal indicators, and the operating stability of the target voltage transformer is judged based on the evaluation indicators; The calculation of the evaluation index comprises the following steps: Calculate the theoretical impact of harmonics and temperature on the error as follows: Calculate the theoretical effect of harmonics on the error: in, The frequency of existence is The ratio difference of the mutual inductor when the harmonic is is an imaginary unit; is the ratio difference of the transformer when the influence of harmonics is not considered; is the resistance of the high voltage arm; is the capacitance of the high voltage arm; is the resistance of the low voltage arm; is the capacitance of the low voltage arm; It is the high voltage resistor of the secondary voltage divider; It is the low voltage resistor of the secondary voltage divider; is the equivalent input resistance of the remote module; ; Calculate the theoretical effect of temperature change on the error: in, ; ; is the transformer resistance affected by temperature; is the capacitance value of the transformer affected by temperature; in, is the temperature change; is the temperature coefficient of the voltage divider resistor; is the temperature coefficient of the remote module resistance; is the temperature coefficient of the voltage divider capacitor; The error evaluation results of the target voltage transformer for a period of time are obtained to form an error evaluation sequence. Harmonic and temperature effects are separated based on the error evaluation sequence, as shown in the following formula: in, is the error evaluation sequence; based on Calculate the fluctuation index, trend index, and abnormal index of the error at the current time t. according to Size is divided into different interval blocks: The volatility indicators are as follows: in, is the fluctuation of error within the error length of 2J; For the The error evaluation result data value of each point; is the mean value of the error result data of any two data blocks within the length of 2J; The trend indicators are as follows: in, is the difference between the mean of the current J error values ​​and the mean of the previous J error values; is the difference between the maximum value of the current J error values ​​and the mean value of the previous J error values; is the error evaluation result data value of the vth point; The abnormal indicator is defined as , represents the number of times exceeding the abnormal threshold line within the 2J range; The upper and lower limits of the threshold line are set as shown in the following formula: in, is the upper limit of the threshold line; is the lower limit of the threshold line; in, is the mean of the current 2J errors; is the standard deviation of the current 2J errors; To adjust the parameters.

5. A DC electronic voltage transformer operation stability evaluation system according to claim 4, characterized in that: The EEMD modal decomposition is specifically as follows: in, , is the data length; is the number of modal decompositions; is the decomposed component, M ,in, is the DC voltage component, is the harmonic component, is the residual signal; Based on the DC voltage component, the harmonic content is calculated. The specific formula is as follows: in, is the effective value of the DC voltage component; For the The effective value of the harmonic components, =2, 3, ... L, indicating the number of main harmonic components selected by setting the threshold; right Reconstruct the data, convert the one-dimensional data into two-dimensional data, and extract multi-dimensional features. The specific formula is as follows: in, ; Using CNN Perform multi-dimensional convolution. The specific formula is as follows: ； in, for convolution; is the Sigmoid function; Multiply the corresponding elements; Add corresponding elements; Use attention mechanism to focus on features , , The specific steps for fusion are as follows: The features to be input , , Perform element-by-element multiplication to remove redundant information. The specific formula is as follows: The features to be input , , Perform element-by-element addition to integrate complementary information. The specific formula is as follows: Will and Perform splicing to generate fusion features , the specific formula is as follows: in, It is a channel splicing operation; Use the coordinate attention mechanism to input , , The features are further extracted to obtain multimodal features: in, is the coordinate attention operation; The attention mechanism is enhanced , , Features and Fusion The features are concatenated to obtain the final fusion features. , as shown below: Using CNN-LSTM to fusion features Perform feature extraction: in, It is a harmonic characteristic.

6. A DC electronic voltage transformer operation stability evaluation system according to claim 4, characterized in that: The method for judging the operating stability of the target voltage transformer based on the evaluation index is specifically as follows: Construct the scoring function for each evaluation indicator: in, , , Set the thresholds respectively; For the current error value The scoring function is set; is the stability scoring function of the volatility index; Scoring function for stability of trend indicator; is the stability scoring function of the anomaly indicator; Compare and analyze the above four indicators and assign weights to them respectively. , , complete the transformer stability score, the specific formula is as follows: The calculated value of Q is matched to the following four operating states: stable [80, 100], slightly unstable [50, 80), moderately unstable [30, 50), and severely unstable [0, 30), to obtain the stable operating state of the transformer.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method for evaluating the operating stability of a DC electronic voltage transformer as described in any one of claims 1 to 3 is implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, a method for evaluating the operating stability of a DC electronic voltage transformer as claimed in any one of claims 1 to 3 is implemented.

Images