CN115169704A - CVT error state prediction method and device based on increment integrated learning model - Google Patents

CVT error state prediction method and device based on increment integrated learning model Download PDF

Info

Publication number
CN115169704A
CN115169704A CN202210820650.5A CN202210820650A CN115169704A CN 115169704 A CN115169704 A CN 115169704A CN 202210820650 A CN202210820650 A CN 202210820650A CN 115169704 A CN115169704 A CN 115169704A
Authority
CN
China
Prior art keywords
cvt
model
data
base
state prediction
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.)
Pending
Application number
CN202210820650.5A
Other languages
Chinese (zh)
Inventor
张鼎衢
招景明
宋强
李经儒
冯浩洋
杨路
陈�峰
潘峰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Power Grid Co Ltd
Measurement Center of Guangdong Power Grid Co Ltd
Original Assignee
Guangdong Power Grid Co Ltd
Measurement Center of Guangdong Power Grid Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangdong Power Grid Co Ltd, Measurement Center of Guangdong Power Grid Co Ltd filed Critical Guangdong Power Grid Co Ltd
Priority to CN202210820650.5A priority Critical patent/CN115169704A/en
Publication of CN115169704A publication Critical patent/CN115169704A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/20—Ensemble learning
    • 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)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Human Resources & Organizations (AREA)
  • Mathematical Physics (AREA)
  • Economics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Tourism & Hospitality (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • General Business, Economics & Management (AREA)
  • Molecular Biology (AREA)
  • Marketing (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a CVT error state prediction method and a device based on an increment integrated learning model, wherein the method comprises the following steps: equally dividing the CVT historical data subjected to power failure verification into a plurality of data blocks, generating a corresponding number of base models according to the data blocks, and fusing the base models into a reference state prediction model; acquiring first CVT real-time data, and detecting whether concept drift occurs between the first CVT real-time data and CVT historical data; when concept drift occurs, obtaining incremental data of the first CVT real-time data relative to the CVT historical data, and generating an incremental basis model according to the incremental data; and generating an adaptive increment integrated learning model according to the increment base model and the reference state prediction model, acquiring second CVT real-time data, and performing error state prediction on the second CVT real-time data according to the adaptive increment integrated learning model. The invention improves the accuracy of CVT error state prediction.

Description

CVT error state prediction method and device based on increment integrated learning model
Technical Field
The invention relates to the technical field of CVT error state prediction, in particular to a CVT error state prediction method and device based on an increment integrated learning model.
Background
The voltage transformer is an important measuring device in an electric power system, a primary winding of the voltage transformer is connected to a high-voltage power grid, and a secondary winding of the voltage transformer is connected with devices for measurement, metering, protection and the like and is used for converting a high-voltage signal at the primary side into a low-voltage small signal for secondary equipment to use.
Long-term operation experience shows that the voltage transformer operating for several years has certain over-tolerance risk due to the increase of the service life of the voltage transformer.
The continuous operation of the out-of-tolerance voltage transformer brings huge loss to the gate metering trade settlement of the three parties, and even influences the stable operation of the power system. Therefore, in order to ensure the accuracy of metering and the safe operation of the power system, the voltage transformer with abnormal error state needs to be evaluated and replaced in time. The existing mature offline evaluation method carries out periodic offline evaluation on the voltage transformers, but the method is difficult to cover all the voltage transformers to be verified in a specified period due to the difficulty of carrying out non-fault power failure operation on a high-voltage power transmission network; and the environmental electromagnetic field during offline evaluation is different from that during online operation, so that a certain deviation exists between the evaluation result and the actual condition, and further a great amount of voltage transformers in the transformer substation are not checked for a long time and the errors are unknown.
In order to overcome the defects in the periodic off-line evaluation method, the prior art adopts an on-line evaluation method under the condition of no power failure to realize the real-time on-line monitoring of the error state of the voltage transformer. The existing online evaluation technology is to analyze and process signals acquired by each device in a power system based on a data-driven principle so as to evaluate the error state of the voltage transformer, namely, an approximate model is constructed by means of historical data, real-time data and relational data, and the real error state of the voltage transformer is represented in real time by means of a large amount of data and calculation. However, the prior art has the following defects: in terms of data, the prior art does not consider the situation that concept drift occurs in a data set, and the concept drift refers to that the concepts contained in the data set are changed, for example, phenomena such as equipment aging and sudden change of operating conditions cause the concepts contained in new and old data not to be consistent any more. Once the phenomenon of concept drift occurs in the data set, the accuracy of representing the real error state of the voltage transformer based on the data driving principle is influenced.
Disclosure of Invention
The invention provides a CVT error state prediction method and device based on an increment integrated learning model, which improve the accuracy of CVT error state prediction.
An embodiment of the invention provides a CVT error state prediction method based on an increment integrated learning model, which comprises the following steps:
equally dividing the historical CVT data subjected to power failure verification into a plurality of data blocks, generating a corresponding number of base models according to the data blocks, and fusing the base models into a reference state prediction model;
acquiring first CVT real-time data, and detecting whether concept drift occurs between the first CVT real-time data and CVT historical data;
when concept drift occurs, obtaining incremental data of the first CVT real-time data relative to the CVT historical data, and generating an incremental base model according to the incremental data;
and generating an adaptive increment integrated learning model according to the increment base model and the reference state prediction model, acquiring second CVT real-time data, and performing error state prediction on the second CVT real-time data according to the adaptive increment integrated learning model.
Further, generating a corresponding number of base models according to the plurality of data blocks, and fusing the base models into a reference state prediction model, including the following steps:
correspondingly forming k first base models by the k data blocks, and updating the k first base models into corresponding k second base models by adopting a cross verification method; wherein k is a positive integer greater than 3;
and fusing the k second base models into a reference state prediction model.
Further, for any first base model, the first base model is generated according to one data block in the k data blocks, and the other k-1 data blocks except the one data block are adopted to carry out cross validation on the first base model to obtain a corresponding second base model.
Further, after the incremental base model is used for replacing the base model with the worst classification effect in the k second base models, the incremental base model and the rest k-1 second base models are fused to obtain the self-adaptive incremental ensemble learning model.
Further, after replacing the basic model with the worst classification effect in the k first basic models with the incremental basic model, updating the remaining k-1 first basic models and the incremental basic model into corresponding k second basic models by adopting a cross validation method;
and fusing the k second base models into a reference state prediction model.
Furthermore, the incremental base model and the reference state prediction model are fused to obtain the self-adaptive incremental ensemble learning model.
Further, calculating KL divergence and a drift threshold according to the first CVT real-time data and CVT historical data;
and judging whether concept drift occurs or not according to the KL divergence and the drift threshold value.
Further, mean shift clustering is carried out on the whole CVT data set formed by the CVT historical data and the first CVT real-time data, the shift threshold value is calculated according to a formula R = D-2R, D is the average distance between cluster centers, and R is the average radius of the cluster.
Furthermore, a countermeasure neural network algorithm is adopted to conduct oversampling processing on a few types of samples in the incremental data, and the incremental base model is generated according to the incremental data after oversampling processing.
The invention provides a CVT error state prediction device based on an increment integrated learning model, which comprises a basic model generation module, a concept drift detection module, an increment basic model generation module and an error state prediction module;
the base model generation module is used for equally dividing the CVT historical data of the power failure verification into a plurality of data blocks, generating a corresponding number of base models according to the data blocks, and fusing the base models into a reference state prediction model;
the concept drift detection module is used for acquiring first CVT real-time data and detecting whether concept drift occurs between the first CVT real-time data and CVT historical data;
the increment base model generation module is used for acquiring increment data of the first CVT real-time data relative to the CVT historical data when concept drift occurs, and generating an increment base model according to the increment data;
the error state prediction module is used for generating an adaptive increment integrated learning model according to the increment base model and the reference state prediction model, acquiring real-time data of a second CVT, and performing error state prediction on the real-time data of the second CVT according to the adaptive increment integrated learning model.
The embodiment of the invention has the following beneficial effects:
the invention provides a CVT error state prediction method and device based on an increment integration learning model, which are used for detecting concept drift phenomena possibly occurring in CVT historical data and CVT real-time data, adopting an adaptive increment integration classification model according to concept drift detection results, carrying out adaptive error state evaluation on dynamic data streams, and improving the precision of an error state evaluation model and the adaptive range of the model so as to improve the precision of the CVT error state evaluation.
Drawings
Fig. 1 is a schematic flowchart of a CVT error state prediction method based on an incremental ensemble learning model according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a CVT error state prediction apparatus based on an incremental ensemble learning model according to an embodiment of the present invention.
Detailed Description
The technical solutions in the present invention will be described clearly and completely with reference to the accompanying drawings, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a CVT error state prediction method based on an incremental integrated learning model, including the following steps:
step S101: the method comprises the steps of equally dividing historical CVT data of power failure verification into a plurality of data blocks, generating base models with corresponding quantities according to the data blocks, and fusing the base models into a reference state prediction model.
As an embodiment, generating a corresponding number of base models according to the data blocks, and fusing the base models into a reference state prediction model includes the following steps:
step S11: correspondingly forming k first base models by the k data blocks, and updating the k first base models into corresponding k second base models by adopting a cross verification method; wherein k is a positive integer greater than 3. Specifically, the K first base models generate K second base models after being subjected to K times of cross check, for any one first base model, the first base model is generated according to one data block of the K data blocks, and the other K-1 data blocks except the one data block are adopted to carry out cross validation on the first base model to obtain the corresponding second base model.
Step S12: and fusing the k second base models into a reference state prediction model.
As one example, the CVT history data of the power failure verification is equally divided into k data blocks D = { D = { D } 1 ，D 2 ，D 3 ，…，D k H, where k =1,2, … …, a; a is more than or equal to 1.
D t Window data representing the historical time t, each window data being defined by:
Figure BDA0003744201230000051
then its underlying data distribution is:
Figure BDA0003744201230000052
wherein, n represents the number of samples,
Figure BDA0003744201230000053
the feature vector is represented by a vector of features,
Figure BDA0003744201230000054
class labels representing samples of the CVT. The characteristic vector of the CVT selected by the invention is the inter-group amplitude ratio difference f and the inter-group phase difference
Figure BDA0003744201230000055
CVT sample class labels are: normal, abnormal and alarm 3 state labels.
Figure BDA0003744201230000061
Figure BDA0003744201230000062
Where A, B, C represents the three phases of the CVT, i represents the group, j represents the row of the vector, V Aij Represents the magnitude of the ith group of jth row A phase CVT; conceptual drift refers to the change in the distribution of the underlying data, i.e.:
Figure BDA0003744201230000063
at time t, the goal of the integration model is to build a fit
Figure BDA0003744201230000068
Optimal model M of distribution t Thus, the first base model is generated according to equation (6):
Figure BDA0003744201230000064
updating the first base model according to a loss function (7):
Figure BDA0003744201230000065
(7) (ii) a Wherein χ (-) represents an arbitrary distribution function, E (-) represents an expectation value of a random variable, and L is a loss function, wherein k =1,2, … …, N; MSE represents the prediction value
Figure BDA0003744201230000066
And true value
Figure BDA0003744201230000067
λ is the learning parameter (initial value is 0), θ (M _ new) is the parameter of the new model, and θ (M _ orign) is the parameter of the original model.
Step S102: the method comprises the steps of acquiring first CVT real-time data and detecting whether concept drift occurs between the first CVT real-time data and CVT historical data.
Calculating a KL divergence and a drift threshold from the first CVT real-time data and CVT historical data as one of the embodiments; and judging whether concept drift occurs or not according to the KL divergence and the drift threshold value.
And performing mean shift clustering on the whole CVT data set formed by the CVT historical data and the first CVT real-time data, and calculating a shift threshold value according to a formula R = D-2R, wherein D is the average distance between cluster centers, and R is the average radius of the cluster.
Calculating the KL divergence according to equation (8):
Figure BDA0003744201230000071
wherein the CVT history data is D old The mean vector and covariance matrix are respectively mu old And η old (ii) a The first CVT real-time data is D new The mean vector and covariance matrix are respectively mu new And η new (ii) a d is the input sample dimension, preferably, d =2; tr represents the trace of the matrix; t denotes the transpose of the matrix.
Step S103: when concept drift occurs, incremental data of the first CVT real-time data relative to the CVT historical data is obtained, and an incremental base model is generated according to the incremental data.
And performing oversampling processing on a few types of samples in the incremental data by adopting an anti-neural network algorithm, and generating the incremental base model according to the oversampled incremental data.
Step S104: and generating an adaptive increment integrated learning model according to the increment base model and the reference state prediction model, acquiring second CVT real-time data, and performing error state prediction on the second CVT real-time data according to the adaptive increment integrated learning model. The error states include normal, abnormal, and alarm.
As one embodiment, after the incremental base model is substituted for the base model with the worst classification effect in the k second base models, the incremental base model and the other k-1 second base models are fused to obtain the adaptive incremental ensemble learning model.
As one embodiment, after the incremental base model is substituted for the base model with the worst classification effect in the k first base models, the other k-1 first base models and the incremental base model are updated to corresponding k second base models by adopting a cross verification method; and fusing the k second base models into a reference state prediction model.
As one embodiment, the incremental base model and the reference state prediction model are fused to obtain the adaptive incremental ensemble learning model.
And when the increased calculation of the incremental base model does not exceed the maximum memory and the limited time of the computer, obtaining the self-adaptive incremental ensemble learning model by adopting a mode of fusing the incremental base model and the reference state prediction model. And when the increased calculation of the incremental base model exceeds the maximum memory and the limited time of the computer, the incremental base model is adopted to replace the base model, and then the self-adaptive incremental integrated learning model is obtained in a fusion mode.
The method and the device provided by the invention have the advantages that the concept drift phenomenon possibly occurring in the CVT historical data and the CVT real-time data is detected, the self-adaptive increment integration classification model is adopted according to the concept drift detection result, the dynamic data stream is responded, the self-adaptive error state evaluation is carried out, the precision of the error state evaluation model and the adaptability range of the model are improved, and the accuracy of the CVT error state evaluation is further improved.
On the basis of the above embodiment of the invention, the present invention correspondingly provides an embodiment of the apparatus, as shown in fig. 2;
another embodiment of the present invention provides a CVT error state prediction apparatus based on an incremental ensemble learning model, which includes a base model generation module 101, a concept drift detection module 102, an incremental base model generation module 103, and an error state prediction module 104;
the base model generation module is used for equally dividing the historical CVT data subjected to power failure verification into a plurality of data blocks, generating a corresponding number of base models according to the data blocks, and fusing the base models into a reference state prediction model;
the concept drift detection module is used for acquiring first CVT real-time data and detecting whether concept drift occurs between the first CVT real-time data and CVT historical data;
the increment base model generation module is used for acquiring increment data of the first CVT real-time data relative to the CVT historical data when concept drift occurs, and generating an increment base model according to the increment data;
the error state prediction module is used for generating an adaptive increment integrated learning model according to the increment base model and the reference state prediction model, acquiring second CVT real-time data, and performing error state prediction on the second CVT real-time data according to the adaptive increment integrated learning model.
For convenience and brevity of description, the embodiments of the apparatus of the present invention include all the embodiments of the CVT error state prediction method embodiment based on the incremental ensemble learning model, and are not described herein again.
It should be noted that the above-described device embodiments are merely illustrative, where the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. In addition, in the drawings of the embodiment of the apparatus provided by the present invention, the connection relationship between the modules indicates that there is a communication connection therebetween, and may be specifically implemented as one or more communication buses or signal lines. One of ordinary skill in the art can understand and implement it without inventive effort.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
It will be understood by those skilled in the art that all or part of the processes of the above embodiments may be implemented by hardware related to instructions of a computer program, and the computer program may be stored in a computer readable storage medium, and when executed, may include the processes of the above embodiments. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.

Claims (10)

1. A CVT error state prediction method based on an increment integrated learning model is characterized by comprising the following steps:
equally dividing the CVT historical data subjected to power failure verification into a plurality of data blocks, generating a corresponding number of base models according to the data blocks, and fusing the base models into a reference state prediction model;
acquiring first CVT real-time data, and detecting whether concept drift occurs between the first CVT real-time data and CVT historical data;
when concept drift occurs, obtaining incremental data of the first CVT real-time data relative to the CVT historical data, and generating an incremental basis model according to the incremental data;
and generating an adaptive increment integrated learning model according to the increment base model and the reference state prediction model, acquiring second CVT real-time data, and performing error state prediction on the second CVT real-time data according to the adaptive increment integrated learning model.
2. The CVT error state prediction method according to claim 1, wherein a corresponding number of base models are generated from the plurality of data blocks, and the base models are merged into a reference state prediction model, comprising the steps of:
correspondingly forming k first base models by the k data blocks, and updating the k first base models into corresponding k second base models by adopting a cross verification method; wherein k is a positive integer greater than 3;
and fusing the k second base models into a reference state prediction model.
3. The incremental ensemble learning model-based CVT error state prediction method of claim 2, wherein for any of the first base models, the first base model is generated from one of k data blocks, and the first base model is cross-validated with the remaining k-1 data blocks except the one data block to obtain a corresponding second base model.
4. The CVT error state prediction method based on the incremental ensemble learning model of claim 3, wherein the incremental base model is substituted for a base model with the worst classification effect among the k second base models, and the incremental base model and the remaining k-1 second base models are fused to obtain the adaptive incremental ensemble learning model.
5. The CVT error state prediction method based on the incremental ensemble learning model of claim 3, wherein after the incremental base model is substituted for the base model with the worst classification effect among the k first base models, the remaining k-1 first base models and the incremental base model are updated to the corresponding k second base models by adopting a cross-validation method;
and fusing the k second base models into a reference state prediction model.
6. The incremental integrated learning model-based CVT error state prediction method of claim 3, wherein the incremental base model and the reference state prediction model are fused to obtain an adaptive incremental integrated learning model.
7. The incremental integrated learning model-based CVT error state prediction method of claim 4 or 5 or 6, wherein KL divergence and a drift threshold are calculated from the first CVT real-time data and CVT historical data;
and judging whether concept drift occurs or not according to the KL divergence and the drift threshold value.
8. The CVT error state prediction method based on the incremental ensemble learning model of claim 7, wherein the CVT data set formed by the CVT historical data and the first CVT real-time data is clustered by mean shift as a whole, the shift threshold is calculated according to a formula R = D-2R, D is an average distance between cluster centers of the clusters, and R is an average radius of the cluster centers of the clusters.
9. The CVT error state prediction method based on the incremental ensemble learning model of claim 8, wherein a countermeasure neural network algorithm is used to perform oversampling on a few types of samples in the incremental data, and the incremental base model is generated according to the oversampled incremental data.
10. A CVT error state prediction device based on an increment integrated learning model is characterized by comprising a base model generation module, a concept drift detection module, an increment base model generation module and an error state prediction module;
the base model generation module is used for equally dividing the CVT historical data of the power failure verification into a plurality of data blocks, generating a corresponding number of base models according to the data blocks, and fusing the base models into a reference state prediction model;
the concept drift detection module is used for acquiring first CVT real-time data and detecting whether concept drift occurs between the first CVT real-time data and CVT historical data;
the increment base model generation module is used for acquiring increment data of the first CVT real-time data relative to the CVT historical data when concept drift occurs, and generating an increment base model according to the increment data;
the error state prediction module is used for generating an adaptive increment integrated learning model according to the increment base model and the reference state prediction model, acquiring real-time data of a second CVT, and performing error state prediction on the real-time data of the second CVT according to the adaptive increment integrated learning model.
CN202210820650.5A 2022-07-13 2022-07-13 CVT error state prediction method and device based on increment integrated learning model Pending CN115169704A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210820650.5A CN115169704A (en) 2022-07-13 2022-07-13 CVT error state prediction method and device based on increment integrated learning model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210820650.5A CN115169704A (en) 2022-07-13 2022-07-13 CVT error state prediction method and device based on increment integrated learning model

Publications (1)

Publication Number Publication Date
CN115169704A true CN115169704A (en) 2022-10-11

Family

ID=83493908

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210820650.5A Pending CN115169704A (en) 2022-07-13 2022-07-13 CVT error state prediction method and device based on increment integrated learning model

Country Status (1)

Country Link
CN (1) CN115169704A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116029220A (en) * 2023-03-24 2023-04-28 国网福建省电力有限公司 Voltage transformer operation error assessment method, system, equipment and medium
CN116308304A (en) * 2023-05-24 2023-06-23 山东建筑大学 New energy intelligent operation and maintenance method and system based on meta learning concept drift detection

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116029220A (en) * 2023-03-24 2023-04-28 国网福建省电力有限公司 Voltage transformer operation error assessment method, system, equipment and medium
CN116308304A (en) * 2023-05-24 2023-06-23 山东建筑大学 New energy intelligent operation and maintenance method and system based on meta learning concept drift detection
CN116308304B (en) * 2023-05-24 2023-08-25 山东建筑大学 New energy intelligent operation and maintenance method and system based on meta learning concept drift detection

Similar Documents

Publication Publication Date Title
CN113496262B (en) Data-driven active power distribution network abnormal state sensing method and system
CN112202736B (en) Communication network anomaly classification method based on statistical learning and deep learning
CN115169704A (en) CVT error state prediction method and device based on increment integrated learning model
CN110728457B (en) Operation risk situation perception method considering multi-level weak links of power distribution network
CN112051481B (en) Alternating current-direct current hybrid power grid fault area diagnosis method and system based on LSTM
CN102208028B (en) Fault predicting and diagnosing method suitable for dynamic complex system
CN112731260B (en) Online evaluation method for error state of voltage transformer based on concept drift recognition
CN113702895B (en) Online quantitative evaluation method for error state of voltage transformer
CN110095744A (en) A kind of electronic mutual inductor error prediction method
CN113239132A (en) Online out-of-tolerance identification method for voltage transformer
CN116125361B (en) Voltage transformer error evaluation method, system, electronic equipment and storage medium
Mathew et al. Regression kernel for prognostics with support vector machines
CN118157132B (en) Data mining method and device for voltage monitoring system based on neural network
CN112836436A (en) Power distribution network line risk quantitative prediction method based on probability graph model
CN110443481B (en) Power distribution automation terminal state evaluation system and method based on hybrid K-nearest neighbor algorithm
CN116596301A (en) Cable multi-state variable evaluation model design method and device based on zero-order learning method
Guo et al. Power transmission risk assessment considering component condition
CN117932236A (en) Voltage transformer metering error prediction method, medium and terminal
CN107818523A (en) Power communication system data true value based on unstable frequency distribution and frequency factor study differentiates and estimating method
CN116840767A (en) Electric energy metering device overall error assessment method and device, storage medium and terminal
CN117114161A (en) Method for predicting wind deflection flashover risk of power transmission line based on meta-learning
CN115859594A (en) Health evaluation algorithm of power transformation equipment based on hierarchical analysis
Moradzadeh et al. Image processing-based data integrity attack detection in dynamic line rating forecasting applications
Huang et al. Artificial neural network enhanced by gap statistic algorithm applied for bad data detection of a power system
Bai et al. Abnormal Detection Scheme of Substation Equipment based on Intelligent Fusion Terminal

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