CN116840765A - Voltage transformer error state evaluation method based on multivariate time sequence analysis - Google Patents
Voltage transformer error state evaluation method based on multivariate time sequence analysis Download PDFInfo
- Publication number
- CN116840765A CN116840765A CN202311112399.8A CN202311112399A CN116840765A CN 116840765 A CN116840765 A CN 116840765A CN 202311112399 A CN202311112399 A CN 202311112399A CN 116840765 A CN116840765 A CN 116840765A
- Authority
- CN
- China
- Prior art keywords
- voltage transformer
- data
- error
- data set
- reconstruction error
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 14
- 238000012300 Sequence Analysis Methods 0.000 title claims abstract description 10
- 238000005259 measurement Methods 0.000 claims abstract description 63
- 238000012549 training Methods 0.000 claims abstract description 25
- 238000000034 method Methods 0.000 claims abstract description 16
- 230000005856 abnormality Effects 0.000 claims abstract description 10
- 238000001514 detection method Methods 0.000 claims abstract description 9
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 3
- 230000006403 short-term memory Effects 0.000 claims description 3
- 230000007787 long-term memory Effects 0.000 claims description 2
- 239000011159 matrix material Substances 0.000 claims description 2
- 230000015654 memory Effects 0.000 claims description 2
- 238000005457 optimization Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims description 2
- 238000005070 sampling Methods 0.000 claims description 2
- 230000011218 segmentation Effects 0.000 claims description 2
- 238000012423 maintenance Methods 0.000 abstract description 2
- 238000012795 verification Methods 0.000 description 6
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000007774 longterm Effects 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R35/00—Testing or calibrating of apparatus covered by the other groups of this subclass
- G01R35/02—Testing or calibrating of apparatus covered by the other groups of this subclass of auxiliary devices, e.g. of instrument transformers according to prescribed transformation ratio, phase angle, or wattage rating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Power Engineering (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Testing Of Short-Circuits, Discontinuities, Leakage, Or Incorrect Line Connections (AREA)
- Measurement Of Current Or Voltage (AREA)
Abstract
The invention provides a voltage transformer error state evaluation method based on multi-element time sequence analysis, which comprises the following steps: acquiring amplitude measurement time sequence data V of a plurality of voltage transformers at the same station in normal measurement state 1 Amplitude measurement time sequence data V under unknown measurement error state 2 The method comprises the steps of carrying out a first treatment on the surface of the Dividing the time sequence data into subsequences based on a sliding window to obtain a training data set V 1 "and data set to be evaluated V 2 "; based on training dataset V 1 "training LSTM-AE model, and calculating data set V under normal measurement state using trained LSTM-AE model 1 Reconstruction error e of 1 Calculating a reconstruction error threshold value of the abnormality judgment; calculating to-be-calculatedEvaluating data set V 2 Reconstruction error e of 2 And obtaining an abnormality detection result according to the reconstruction error threshold. The invention realizes the online evaluation of the error state of the voltage transformer and effectively guides the operation and maintenance work on site.
Description
Technical Field
The invention relates to the field of online monitoring of electric power metering, in particular to a voltage transformer error evaluation method based on multivariate time sequence analysis.
Background
The voltage transformer is key measurement equipment in a high-voltage electric information detection link, and has the functions of realizing electric isolation between a high-voltage primary system and secondary equipment, converting a primary large-voltage signal into a low-voltage small signal and providing a basis for relay protection, state monitoring and electric energy metering of an electric power system. In the long-term operation process, the operation state of the voltage transformer is influenced by multiple factors to cause out-of-tolerance measurement errors, so that the safety and stability of the power system and the fairness of power trade are influenced.
According to relevant regulations, the voltage transformer needs to be periodically verified, so that the voltage transformer meets the requirement of measurement accuracy. The traditional verification method comprises offline verification and electrified verification. The offline verification method needs power system planned outage cooperation, standard voltage transformer equipment is heavy and difficult to transport, large-scale development cannot be achieved, and offline verification cannot completely reflect online operation conditions of the voltage transformer. The live verification method can realize live monitoring without power outage cooperation, but needs to be connected with a standard voltage transformer in a live state, has potential safety hazards and cannot realize long-term evaluation. Currently, a long-term online evaluation method of a voltage transformer under the condition of no power failure and no need of a standard voltage transformer is widely focused.
Disclosure of Invention
Aiming at the technical problems existing in the prior art, the invention provides a voltage transformer error state evaluation method based on multi-element time sequence analysis, which comprises the following steps:
s100: acquisition ofAmplitude measurement time sequence data V obtained under normal measurement state of multiple voltage transformers at same site 1 Amplitude measurement time sequence data V under unknown measurement error state 2 Normalizing the obtained amplitude measurement time sequence data;
s200: dividing the normalized amplitude measurement time sequence data into subsequences based on a sliding window, thereby obtaining a training data set V 1 "and data set to be evaluated V 2 "；
S300: based on training dataset V 1 "training LSTM-AE model, and calculating amplitude measurement data set V in normal measurement state using trained LSTM-AE model 1 Reconstruction error e of 1 Calculating a reconstruction error threshold value of the abnormality judgment;
s400: computing a data set V to be evaluated 2 Reconstruction error e of 2 And obtaining an abnormality detection result according to the reconstruction error threshold.
According to the voltage transformer error state assessment method based on multi-element time sequence analysis, time and space information of the time sequence measurement data of the multi-voltage transformer with real physical association is used as input, and the LSTM-AE model is used for mining the data, so that the data information extraction capability is improved, the voltage transformer error state on-line assessment is realized, and the on-site operation and maintenance work is effectively guided.
Drawings
FIG. 1 is a flow chart of a voltage transformer error state evaluation method based on multivariate time sequence analysis;
FIG. 2 is a schematic structural diagram of the LSTM-AE model.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention. In addition, the technical features of each embodiment or the single embodiment provided by the invention can be combined with each other at will to form a feasible technical scheme, and the combination is not limited by the sequence of steps and/or the structural composition mode, but is necessarily based on the fact that a person of ordinary skill in the art can realize the combination, and when the technical scheme is contradictory or can not realize, the combination of the technical scheme is not considered to exist and is not within the protection scope of the invention claimed.
Fig. 1 is a flowchart of a voltage transformer error state evaluation method based on multivariate time sequence analysis, provided by the invention, as shown in fig. 1, the method comprises:
s100: acquiring amplitude measurement time sequence data V obtained under normal measurement state of multiple voltage transformers at the same station 1 Amplitude measurement time sequence data V under unknown measurement error state 2 And normalizing the obtained amplitude measurement time sequence data.
It is understood that S100 mainly includes two steps:
(1) Raw data is acquired. Acquiring amplitude measurement time sequence data of a plurality of voltage transformers associated with real topology at the same site，/>M is the number of voltage transformers considered by the method, n is the sampling length of the time series, wherein +.>And the vector which is formed by the measurement data of the m voltage transformers at the nth moment is represented, and m and n are positive integers. Amplitude measurement time sequence data obtained by the voltage transformer in a normal measurement state and amplitude measurement time sequence data obtained by the voltage transformer in an unknown measurement error state are respectively recorded as V 1 and V2 。
(2) And (5) normalizing the data Min-Max. Processing the original data by using a Min-Max normalization formula to obtainNormalized V 1' and V2 '。
。
S200: dividing the normalized amplitude measurement time sequence data into subsequences based on a sliding window, thereby obtaining a training data set V 1 "and data set to be evaluated V 2 "。
It can be understood that step S100 obtains normalized time series data by setting the sliding window sizeDividing the amplitude measurement time series data into sub-sequences to obtain a data set +.>Wherein each subsequence->The matrix is formed by m voltage transformer measurement data containing win moments.
The normalized amplitude measurement time sequence data V are respectively subjected to sliding window 1 ' and amplitude measurement timing data V 2 ' segmentation, normal data subsequences make up the training dataset V 1 ", the data set V to be evaluated consisting of data subsequences under unknown measurement error condition 2 "。
S300: based on training dataset V 1 "training LSTM-AE model, and calculating amplitude measurement data set V in normal measurement state using trained LSTM-AE model 1 Reconstruction error e of 1 And calculating a reconstruction error threshold of the anomaly judgment.
It can be understood that the LSTM-AE model is a self-encoder model which is composed of Long Short-Term Memory neural network (LSTM) as a basic unit, and the structural schematic diagram of the LSTM-AE model is shown in FIG. 2.
The LSTM-AE model is composed of an encoder and a decoder which are both composed of a plurality of layers of long-term and short-term memory neural networks. The input data of the LSTM-AE model is the subsequence data obtained in S200Output data of LSTM-AE model is reconstruction subsequence of input data +.>。
The encoder first inputs dataPerforming dimension reduction coding:
；
decoder for dimension reduced coded dataAnd (4) decoding reconstruction:
；
wherein and />Is a corresponding function of the encoder and decoder, and d < m.
Using training data set V obtained under normal measurement conditions 1 "training LSTM-AE model, the loss function (reconstruction error) of LSTM-AE model training is mean square error (MSE, mean Square Error), the mathematical expression is as follows:
；
wherein ,Vsub To input a subsequence, V sub ' is the reconstructed sub-sequence of the output,for the amplitude of the ith moment of the ith voltage transformer, +.>Reconstructing the amplitude value of the ith voltage transformer at the jth moment in the subsequence;
the parameters of the encoder and decoder are trained using an optimization method to minimize the loss function.
Subsequently, based on the trained LSTM-AE model, a training data set V is obtained 1 "corresponding reconstruction error sequence，e 1 For training data set V 1 "each subsequence V sub The sequence of errors is reconstructed and the sequence of errors is reconstructed,indicate->Reconstructing a mean square error of the subsequence;
from the reconstructed error sequence e 1 Calculating a reconstruction error thresholdWherein quatile 95% represents the calculated reconstruction error sequence e 1 Is a 95% quantile of k is a threshold coefficient. The invention adopts quantiles to increase the resistance to individual extrema and adopts threshold coefficients for changing the severity of anomaly judgment.
S400: computing a data set V to be evaluated 2 Reconstruction error e of 2 And obtaining an abnormality detection result according to the reconstruction error threshold.
As an embodiment, in S400, a data set V to be evaluated is calculated 2 Reconstruction error e of 2 And obtaining an abnormality detection result according to the reconstruction error threshold, including:
to-be-evaluated data set V 2 Inputting each subsequence in the' to a trained LSTM-AE model to obtain a corresponding sequenceReconstructing error sequences，/>Representing a reconstructed mean square error of the ith sub-sequence; if->Reconstruction error threshold, then data set V to be evaluated 2 The ith subsequence in "is determined to be abnormal, whereas the ith subsequence is determined to be normal.
It will be appreciated that for the data set V to be evaluated 2 And (3) inputting each subsequence into the trained LSTM-AE model, calculating the reconstruction error of each subsequence, comparing the reconstruction error with a reconstruction error threshold, judging that the subsequence is abnormal if the reconstruction error is larger than the reconstruction error threshold, and judging that the subsequence is normal if the reconstruction error is smaller than the reconstruction error threshold.
For an abnormal error sub-sequence, it is necessary to locate the abnormal voltage transformers, and therefore, for a sub-sequence determined to be abnormal, calculate the individual reconstruction error for each voltage transformer in the sub-sequence; and obtaining the abnormal possibility or degree of each voltage transformer according to the independent reconstruction error of each voltage transformer. The greater the individual reconstruction error of each voltage transformer, the greater the likelihood or degree of anomaly of the voltage transformer. Wherein calculating the individual reconstruction error for each voltage transformer in the subsequence comprises:
；
wherein ,for the original amplitude of the ith voltage transformer, < +.>The amplitude value of the ith voltage transformer after being reconstructed by the LSTM-AE model is +.>For the amplitude of the ith voltage transformer at the jth moment,/th>And (5) reconstructing the amplitude value of the ith voltage transformer after the LSTM-AE model is carried out at the jth moment.
The voltage transformer error state evaluation method based on the multi-element time sequence analysis provided by the embodiment of the invention has the following beneficial effects:
1. the time sequence measurement data of the multi-voltage transformer with the physical association is taken as input, and the LSTM-AE (long-short-term memory neural network self-encoder) is used for mining the time and space information of the data, so that the data information extraction capability is improved;
2. the model reconstruction mean square error is used as an anomaly score to realize anomaly detection, so that the anomalies of the voltage transformer can be successfully identified and positioned, and the online continuous monitoring of the voltage transformer is realized.
In the foregoing embodiments, the descriptions of the embodiments are focused on, and for those portions of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (9)
1. The voltage transformer error state evaluation method based on the multivariate time sequence analysis is characterized by comprising the following steps of:
s100: acquiring amplitude measurement time sequence data V obtained under normal measurement state of multiple voltage transformers at the same station 1 Amplitude measurement time sequence data V under unknown measurement error state 2 Normalizing the obtained amplitude measurement time sequence data;
s200: dividing the normalized amplitude measurement time sequence data into subsequences based on a sliding window, thereby obtaining a training data set V 1 "and data set to be evaluated V 2 "；
S300: based on training dataset V 1 Training a self-encoder LSTM-AE model of a long-term and short-term memory neural network, and calculating an amplitude measurement data set V in a normal measurement state by using the trained LSTM-AE model 1 Reconstruction error e of 1 Calculating a reconstruction error threshold value of the abnormality judgment;
s400: computing a data set V to be evaluated 2 Reconstruction error e of 2 And obtaining an abnormality detection result according to the reconstruction error threshold.
2. The voltage transformer error state evaluation method according to claim 1, wherein the S100 comprises:
acquiring amplitude measurement time sequence data of a plurality of voltage transformers associated with real topology at the same site，/>M is the number of voltage transformers, n is the sampling length of the time series, wherein +.>The vector formed by the measurement data of m voltage transformers at the nth moment is represented, and m and n are positive integers;
respectively acquiring amplitude measurement time sequence data V obtained by a plurality of voltage transformers in a normal measurement state 1 And amplitude measurement obtained under unknown measurement error stateTime-series data V 2 ；
Amplitude measurement time series data V are respectively measured by using Min-Max normalization formula 1 And amplitude measurement timing data V 2 Normalization processing is carried out to obtain normalized amplitude measurement time sequence data V 1 ' and amplitude measurement timing data V 2 '。
3. The voltage transformer error state evaluation method according to claim 1, wherein S200 comprises:
dividing the amplitude measurement time sequence data into subsequences by setting the value of the sliding window size win to obtain a data setWherein each subsequence->Namely, a matrix consisting of m voltage transformer measurement data at win moments;
the normalized amplitude measurement time sequence data V are respectively subjected to sliding window 1 ' and amplitude measurement timing data V 2 ' segmentation, normal data subsequences make up the training dataset V 1 ", the data set V to be evaluated consisting of data subsequences under unknown measurement error condition 2 "。
4. The method of claim 3, wherein the LSTM-AE model in S300 includes an encoder and a decoder, each of which is composed of a multi-layer long-short-term memory neural network, and the training data set V is based on 1 "training LSTM-AE model, comprising:
training data set V 1 "subsequence V of sub Inputting into LSTM-AE model, outputting reconstruction subsequence V sub ’。
5. The method for evaluating the error state of a voltage transformer according to claim 4, wherein the loss function, i.e. the reconstruction error, of the LSTM-AE model is a mean square error, and the expression is:
；
wherein ,Vsub To input a subsequence, V sub ' is the reconstructed sub-sequence of the output,for the amplitude of the ith moment of the ith voltage transformer, +.>Reconstructing the amplitude value of the ith voltage transformer at the jth moment in the subsequence;
and (3) minimizing a loss function by using an optimization method, training to obtain parameters of an encoder and a decoder, and obtaining a trained LSTM-AE model.
6. The method according to claim 5, wherein in S300, the magnitude measurement data set V in the normal measurement state is calculated using the trained LSTM-AE model 1 Reconstruction error e of 1 Calculating a reconstruction error threshold for anomaly determination, comprising:
based on the trained LSTM-AE model, a training data set V is obtained 1 "corresponding reconstruction error sequence，e 1 For training data set V 1 "each subsequence V sub The sequence of errors is reconstructed and the sequence of errors is reconstructed,indicate->Reconstructing a mean square error of the subsequence;
from the reconstructed error sequence e 1 Calculating a reconstruction error thresholdWherein quatile 95% represents the calculated reconstruction error sequence e 1 Is a 95% quantile of k is a threshold coefficient.
7. The method according to claim 5, wherein in S400, a data set V to be evaluated is calculated 2 Reconstruction error e of 2 And obtaining an abnormality detection result according to the reconstruction error threshold, including:
to-be-evaluated data set V 2 Inputting each subsequence in the' to a trained LSTM-AE model to obtain a corresponding reconstruction error sequence，/>Representing a reconstructed mean square error of the ith sub-sequence;
if it isReconstruction error threshold, then data set V to be evaluated 2 The ith subsequence in "is determined to be abnormal, whereas the ith subsequence is determined to be normal.
8. The method according to claim 7, wherein in S400, a data set V to be evaluated is calculated 2 Reconstruction error e of 2 And obtaining an abnormality detection result according to the reconstruction error threshold value, further comprising:
for the subsequences determined to be abnormal, calculating an individual reconstruction error for each voltage transformer in the subsequence;
and obtaining the abnormal possibility or degree of each voltage transformer according to the independent reconstruction error of each voltage transformer.
9. The method of claim 8, wherein calculating the individual reconstruction errors for each voltage transformer in the subsequence comprises:
；
wherein ,for the original amplitude of the ith voltage transformer, < +.>The amplitude value of the ith voltage transformer after being reconstructed by the LSTM-AE model is +.>For the amplitude of the ith voltage transformer at the jth moment,/th>And (5) reconstructing the amplitude value of the ith voltage transformer after the LSTM-AE model is carried out at the jth moment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311112399.8A CN116840765B (en) | 2023-08-31 | 2023-08-31 | Voltage transformer error state evaluation method based on multivariate time sequence analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311112399.8A CN116840765B (en) | 2023-08-31 | 2023-08-31 | Voltage transformer error state evaluation method based on multivariate time sequence analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116840765A true CN116840765A (en) | 2023-10-03 |
| CN116840765B CN116840765B (en) | 2023-11-07 |
Family
ID=88172855
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311112399.8A Active CN116840765B (en) | 2023-08-31 | 2023-08-31 | Voltage transformer error state evaluation method based on multivariate time sequence analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116840765B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117272055A (en) * | 2023-11-23 | 2023-12-22 | 国网山西省电力公司营销服务中心 | Electric energy meter abnormality detection method and device based on filtering enhancement self-encoder |
| CN117972537A (en) * | 2024-04-02 | 2024-05-03 | 国网山东省电力公司营销服务中心(计量中心) | Voltage transformer metering state evaluation method and system based on wide area measurement |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1991019342A1 (en) * | 1990-06-01 | 1991-12-12 | Siemens Aktiengesellschaft | Process for testing devices |
| GB202013593D0 (en) * | 2020-08-28 | 2020-10-14 | Kovacevic Uros | Real time live line measurement of metrological properties of current transformers |
| CN113702895A (en) * | 2021-10-28 | 2021-11-26 | 华中科技大学 | Online quantitative evaluation method for error state of voltage transformer |
| WO2022021726A1 (en) * | 2020-07-29 | 2022-02-03 | 国网上海市电力公司 | Pmu-based power system state estimation performance evaluation method |
| CN114460521A (en) * | 2021-12-24 | 2022-05-10 | 广东电网有限责任公司 | Current transformer error state discrimination method and device, terminal equipment and medium |
| KR20230016423A (en) * | 2021-07-26 | 2023-02-02 | 주식회사 남전사 | Portable error correction apparatus for power meter |
| CN115932702A (en) * | 2023-03-14 | 2023-04-07 | 武汉格蓝若智能技术股份有限公司 | Voltage transformer online operation calibration method and device based on virtual standard device |
| CN116049629A (en) * | 2023-03-29 | 2023-05-02 | 国网福建省电力有限公司 | Voltage transformer error state prediction method, system, equipment and medium |
| US20230155381A1 (en) * | 2020-11-19 | 2023-05-18 | State Grid Blockchain Technology (beijing) Co., Ltd. | Blockchain-based electricity charge settlement method and system for energy storage station |
| CN116341796A (en) * | 2023-05-29 | 2023-06-27 | 山东国研自动化有限公司 | Energy consumption monitoring and evaluating system and method |
-
2023
- 2023-08-31 CN CN202311112399.8A patent/CN116840765B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1991019342A1 (en) * | 1990-06-01 | 1991-12-12 | Siemens Aktiengesellschaft | Process for testing devices |
| WO2022021726A1 (en) * | 2020-07-29 | 2022-02-03 | 国网上海市电力公司 | Pmu-based power system state estimation performance evaluation method |
| GB202013593D0 (en) * | 2020-08-28 | 2020-10-14 | Kovacevic Uros | Real time live line measurement of metrological properties of current transformers |
| US20230155381A1 (en) * | 2020-11-19 | 2023-05-18 | State Grid Blockchain Technology (beijing) Co., Ltd. | Blockchain-based electricity charge settlement method and system for energy storage station |
| KR20230016423A (en) * | 2021-07-26 | 2023-02-02 | 주식회사 남전사 | Portable error correction apparatus for power meter |
| CN113702895A (en) * | 2021-10-28 | 2021-11-26 | 华中科技大学 | Online quantitative evaluation method for error state of voltage transformer |
| CN114460521A (en) * | 2021-12-24 | 2022-05-10 | 广东电网有限责任公司 | Current transformer error state discrimination method and device, terminal equipment and medium |
| CN115932702A (en) * | 2023-03-14 | 2023-04-07 | 武汉格蓝若智能技术股份有限公司 | Voltage transformer online operation calibration method and device based on virtual standard device |
| CN116049629A (en) * | 2023-03-29 | 2023-05-02 | 国网福建省电力有限公司 | Voltage transformer error state prediction method, system, equipment and medium |
| CN116341796A (en) * | 2023-05-29 | 2023-06-27 | 山东国研自动化有限公司 | Energy consumption monitoring and evaluating system and method |
Non-Patent Citations (1)
| Title |
|---|
| 陈文中等: "基于循环神经网络的一种在线辅助 ＣＶＴ电压误差测量方法", 《东华大学学报（自然科学版）》, vol. 46, no. 1, pages 53 - 57 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117272055A (en) * | 2023-11-23 | 2023-12-22 | 国网山西省电力公司营销服务中心 | Electric energy meter abnormality detection method and device based on filtering enhancement self-encoder |
| CN117272055B (en) * | 2023-11-23 | 2024-02-06 | 国网山西省电力公司营销服务中心 | Electric energy meter abnormality detection method and device based on filtering enhancement self-encoder |
| CN117972537A (en) * | 2024-04-02 | 2024-05-03 | 国网山东省电力公司营销服务中心(计量中心) | Voltage transformer metering state evaluation method and system based on wide area measurement |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116840765B (en) | 2023-11-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116840765B (en) | Voltage transformer error state evaluation method based on multivariate time sequence analysis | |
| CN109492193B (en) | Abnormal network data generation and prediction method based on deep machine learning model | |
| CN108491404B (en) | State estimation bad data identification method based on BP neural network | |
| CN106251059B (en) | Cable state evaluation method based on probabilistic neural network algorithm | |
| CN110334866B (en) | Power equipment fault probability prediction method and system considering insulation defect type and fault correlation | |
| CN114169237B (en) | Power cable joint temperature abnormality early warning method combining EEMD-LSTM and isolated forest algorithm | |
| CN103745119A (en) | Oil-immersed transformer fault diagnosis method based on fault probability distribution model | |
| CN117421687A (en) | Method for monitoring running state of digital power ring main unit | |
| CN115563563A (en) | Fault diagnosis method and device based on transformer oil chromatographic analysis | |
| CN112904810B (en) | Process industry nonlinear process monitoring method based on effective feature selection | |
| CN109100429A (en) | A kind of oil dissolved gas prediction technique of combined prediction residual GM | |
| CN112731260A (en) | Online evaluation method for error state of voltage transformer based on concept drift recognition | |
| CN112070322A (en) | High-voltage cable line running state prediction method based on long-short term memory network | |
| CN116431966A (en) | Reactor core temperature anomaly detection method of incremental characteristic decoupling self-encoder | |
| CN112069666A (en) | Power grid short-term reliability evaluation method based on probabilistic power flow method | |
| CN115081331A (en) | Wind turbine generator running state abnormity detection method based on state parameter reconstruction error | |
| CN115017828A (en) | Power cable fault identification method and system based on bidirectional long-short-time memory network | |
| Shutenko et al. | Correction of the maximum permissible values of the oil acidity by the minimum risk method | |
| CN114581699A (en) | Transformer state evaluation method based on deep learning model in consideration of multi-source information | |
| CN114266201A (en) | Self-attention elevator trapping prediction method based on deep learning | |
| CN105741184B (en) | Transformer state evaluation method and device | |
| CN116029165A (en) | Power cable reliability analysis method and system considering lightning influence | |
| CN115906520A (en) | Low-voltage transformer health degree evaluation method based on Mahalanobis distance and self-encoder | |
| CN116029295A (en) | Electric power text entity extraction method, defect positioning method and fault diagnosis method | |
| CN115184734A (en) | Power grid line fault detection method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |