CN112232386A - Voltage sag severity prediction method based on support vector machine - Google Patents
Voltage sag severity prediction method based on support vector machine Download PDFInfo
- Publication number
- CN112232386A CN112232386A CN202011037249.1A CN202011037249A CN112232386A CN 112232386 A CN112232386 A CN 112232386A CN 202011037249 A CN202011037249 A CN 202011037249A CN 112232386 A CN112232386 A CN 112232386A
- Authority
- CN
- China
- Prior art keywords
- data
- voltage sag
- model
- support vector
- vector machine
- 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
- 238000012706 support-vector machine Methods 0.000 title claims abstract description 58
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000012544 monitoring process Methods 0.000 claims abstract description 31
- 238000012549 training Methods 0.000 claims description 55
- 238000012360 testing method Methods 0.000 claims description 42
- 230000006870 function Effects 0.000 claims description 34
- 238000004364 calculation method Methods 0.000 claims description 10
- 239000013598 vector Substances 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 9
- 230000009977 dual effect Effects 0.000 claims description 6
- 238000012806 monitoring device Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 150000001875 compounds Chemical class 0.000 claims description 3
- 239000006185 dispersion Substances 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000000691 measurement method Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013506 data mapping Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000013058 risk prediction model Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/82—Energy audits or management systems therefor
Abstract
The invention relates to a voltage sag severity prediction method based on a support vector machine, which is characterized in that a voltage sag severity prediction model based on the support vector machine is established, historical voltage sag monitoring data are analyzed by using the model to predict the severity of voltage sag at a certain time, and the function of predicting the severity of voltage sag is realized to reduce the economic loss caused by voltage sag.
Description
Technical Field
The invention relates to the field of power systems, in particular to a voltage sag severity prediction method based on a support vector machine.
Background
In order to realize safer, more reliable and more accurate production work of enterprises and related equipment, higher requirements on the quality of electric energy are also provided in the current rapidly-developed electric power system. The problem of voltage sag affects the quality of electric energy to a great extent, the occurrence of voltage sag can cause the working state of equipment to change, and the quality of products is affected finally, so that users suffer great economic loss, and especially in some high-tech industries, the loss caused by voltage sag is more serious.
At present, the prediction and evaluation of the severity of voltage sag mainly comprises an actual measurement method and an analog simulation method, wherein the actual measurement method is used for evaluating the severity by monitoring all indexes in an all-around manner by using related equipment, and the method has the advantages of complex and various required equipment, higher requirement on the equipment, higher cost and lower economy and is not suitable for enterprise users. The simulation method sets faults based on statistics and probability principles to carry out prediction and evaluation on the severity of voltage sag, and the method has the advantages of long calculation time, complex calculation and large influence of fault information under a complex large power grid, so that the accuracy of obtained results is not high, and the method is not suitable for the current complex and large-scale power system network.
Disclosure of Invention
In view of the above, the present invention aims to provide a method for predicting the severity of voltage sag based on a support vector machine, which establishes a model for predicting the severity of voltage sag based on the support vector machine, and predicts the severity of voltage sag at a certain time by analyzing historical monitoring data of voltage sag by using the model, so as to predict the severity of voltage sag.
The invention is realized by adopting the following scheme: a voltage sag severity prediction method based on a support vector machine comprises the following steps:
step S1: measuring and collecting historical voltage sag monitoring data recorded by the power quality monitoring device, and dividing the historical voltage sag monitoring data into training data and testing data, wherein the proportion of the training data to the testing data is 8: 2, training data is used for training and learning the support vector machine model, and test data is used for testing and verifying the support vector machine model;
step S2: normalizing the voltage sag historical monitoring data to be between [0 and 1] by adopting dispersion standardization, and using the normalized voltage sag historical monitoring data as input data for predicting the severity of voltage sag, and meanwhile, using the severity of voltage sag of a node to be evaluated in a power grid as output data and storing the input data and the output data;
step S3: selecting a Support Vector Machine (SVM) type: an RBF function is selected as a kernel function to construct a support vector machine model;
step S4: training a support vector machine model by using the normalized voltage sag historical monitoring data, and learning by using the normalized voltage sag historical monitoring data as a training sample input; judging whether the model learning is finished or not, if the termination criterion is smaller than a preset value of tolerable deviation, finishing the model learning, if so, executing the step S5, otherwise, continuing the model learning;
step S5: inputting test data to test the model, and adjusting and optimizing a punishment parameter C, an insensitive loss parameter epsilon and a gamma value of the model according to the error magnitude and the variation trend of the output result of the training data and the test data to obtain a voltage sag severity prediction model based on a support vector machine;
step S6: after the parameters are adjusted and optimized, the current known data is input into the model for predicting the severity of voltage sag based on the support vector machine obtained in step S5, the trained function for predicting the severity of voltage sag of the model is used, and the model for predicting the severity of voltage sag based on the support vector machine is used to process and analyze the data, so that the severity of voltage sag of a certain node is obtained, and a user can know the voltage sag according to the obtained result.
Further, the voltage sag history monitoring data comprises a residual voltage amplitude, a duration, a voltage level, a monitoring position and an operation mode of the voltage sag.
Further, the specific content of step S3 is:
sample set for support vector machine { (X)1,y1),(X2,y2)…(Xn,yn)},Xi=1,2…nAs an input vector, yiIs an output vector, and the corresponding relation is:
in the formula (I), the compound is shown in the specification,representing the corresponding vector after mapping X to a high-dimensional space;
the dual problem is obtained according to Lagrange dual theory as follows:
the RBF function has small influence on the complexity of the model in the calculation process and has nonlinear characteristics and fitting capacity, so the RBF function is adopted as a kernel function of the support vector machine;
after the data normalization and kernel function establishment are completed, step S4 is performed.
Further, the specific content of adjusting and optimizing the penalty parameter C, the insensitive loss parameter epsilon, and the gamma value of the model in step S5 is as follows:
while adding the relaxation variable xii,i=1…nThen, the model introduces the fault tolerance to the data, and the objective function and the constraint condition among the support vector machines become:
c is a punishment coefficient, the large value C has high fitting degree on training data, overfitting is easy to occur, the generalization capability is poor, the small value C has under-fitting, the fitness on the training data is not high, therefore, the value C needs to be adjusted according to the output result and the error of the training data and the test data, when the error of the result obtained by the training data is small, the error of the result obtained by the test data is large, the difference between the accuracy of the training result and the accuracy of the test result is more than 15%, the value C is considered to be reduced, and when the error of the result obtained by the training data is more than an error allowable value, the value C is increased, and finally, a reasonable value C is obtained; determining a reasonable epsilon value through the repeated calculation result of the training data and the test data, wherein the epsilon value is selected differently according to different data volumes; the gamma value is a parameter carried after an RBF function is selected as a kernel function, and has the following relationship:
After the training data, the test data result and the error analysis are repeatedly carried out, the gamma value is adjusted according to the error magnitude and the change trend, when the training result precision is high, the test data result precision is low, the difference between the accuracy rates of the training data result precision and the test data result precision is larger than 15%, the gamma value needs to be adjusted to be small, and when the training result error is larger than the error allowable range, the gamma value is increased, so that the accuracy and the efficiency of the model are improved.
Compared with the prior art, the invention has the following beneficial effects:
the invention can predict and evaluate the severity of a certain voltage sag. The method comprises the steps of utilizing data in the existing power quality monitoring device of the power system, constructing a voltage sag severity prediction model based on a support vector machine on the basis of the support vector machine, and realizing the function of predicting the voltage sag severity. Meanwhile, the existing power quality monitoring device in the power system is utilized, the multiple devices in the real measurement method are not needed, the economy is improved, the complex calculation of the simulation method is avoided, and the prediction and evaluation on the severity of the voltage sag can be accurately, economically and rapidly carried out.
Drawings
FIG. 1 is a flow chart of a method according to an embodiment of the present invention.
Detailed Description
The invention is further explained below with reference to the drawings and the embodiments.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
As shown in fig. 1, the present embodiment provides a method for predicting the severity of voltage sag based on a support vector machine, which includes the following steps:
step S1: measuring and collecting historical voltage sag monitoring data recorded by the power quality monitoring device, and dividing the historical voltage sag monitoring data into training data and testing data, wherein the proportion of the training data to the testing data is 8: 2, when the data volume is large, the proportion can be properly adjusted, the training data is used for training and learning the support vector machine model, and the test data is used for testing and verifying the support vector machine model;
step S2: normalizing the voltage sag historical monitoring data to be between [0 and 1] by adopting dispersion standardization, and using the normalized voltage sag historical monitoring data as input data for predicting the severity of voltage sag, and meanwhile, using the severity of voltage sag of a node to be evaluated in a power grid as output data and storing the input data and the output data;
step S3: selecting a Support Vector Machine (SVM) type: the RBF function has nonlinearity, so that the complexity of the model cannot be changed due to parameter adjustment in the calculation process, and the RBF-based SVM algorithm has excellent fitting capability in the past research, so that the RBF function is selected as a kernel function to construct a support vector machine model;
step S4: training a support vector machine model by using the normalized voltage sag historical monitoring data, and learning by using the normalized voltage sag historical monitoring data as a training sample input; judging whether the model learning is finished or not, if the termination criterion is smaller than a preset value of tolerable deviation, finishing the model learning, if so, executing the step S5, otherwise, continuing the model learning; in this embodiment, the preset value of the tolerable deviation is 0.001;
step S5: inputting test data to test the model, and adjusting and optimizing a punishment parameter C, an insensitive loss parameter epsilon and a gamma value of the model according to the error magnitude and the variation trend of the output result of the training data and the test data to obtain a voltage sag severity prediction model based on a support vector machine;
step S6: after the parameters are adjusted and optimized, the current known data is input into the model for predicting the severity of voltage sag based on the support vector machine obtained in step S5, the trained function for predicting the severity of voltage sag of the model is used, and the model for predicting the severity of voltage sag based on the support vector machine is used to process and analyze the data, so that the severity of voltage sag of a certain node is obtained, and a user can know the voltage sag according to the obtained result.
In this embodiment, the voltage sag history monitoring data includes a residual voltage amplitude, a duration, a voltage level, a monitoring location, and an operation mode of the voltage sag.
In this embodiment, the specific content of step S3 is:
sample set for support vector machine { (X)1,y1),(X2,y2)…(Xn,yn)},Xi=1,2…nAs an input vector, yiIs an output vector, and the corresponding relation is:
in the formula (I), the compound is shown in the specification,representing the corresponding vector after mapping X to a high-dimensional space;
the dual problem is obtained according to Lagrange dual theory as follows:
the RBF function has small influence on the complexity of the model in the calculation process and has nonlinear characteristics and fitting capacity, so the RBF function is adopted as a kernel function of the support vector machine;
after the data normalization and kernel function establishment are completed, step S4 is performed.
In this embodiment, the specific content of adjusting and optimizing the penalty parameter C, the insensitive loss parameter epsilon, and the gamma value of the model in step S5 is as follows:
while adding the relaxation variable xii,i=1…nThen, the model introduces the fault tolerance to the data, and the objective function and the constraint condition among the support vector machines become:
c is a punishment coefficient, the large value C has high fitting data to the training data, overfitting is easy to occur, the generalization capability is poor, the small value C has under-fitting, the fitness to the training data is not high, therefore, the value C needs to be adjusted according to the output result and the error of the training data and the test data, when the error of the result obtained by the training data is small, the error of the result obtained by the test data is large, the difference between the accuracy of the training result and the accuracy of the test result is more than 15%, the value C is considered to be reduced, and when the error of the result obtained by the training data is more than an error allowable value, the value C is increased, and finally, a reasonable value C is obtained; the introduction of the insensitive loss parameter epsilon can ignore the deviation of the true value within a certain degree, a reasonable epsilon value is determined through the result of repeated calculation of training data and test data, and the selection of the epsilon value is different according to the difference of data quantity; the gamma value is a parameter carried after an RBF function is selected as a kernel function, and has the following relationship:
The size of the gamma value influences the distribution condition of data mapping to a new feature space, the gamma value is too large, the sigma value is small, the Gaussian radial basis function is narrow, the data prediction accuracy is high, but the adaptability to unknown samples is not high, the data is overfitted, the gamma value is too small, the obtained results are opposite, meanwhile, the gamma value has certain influence on the number of support vectors, and further the speed of data training and prediction is influenced, therefore, after the training data, the test data result and the error analysis are repeatedly carried out, the gamma value is adjusted according to the error size and the change trend, when the training result accuracy is high, the test data result accuracy is low, the difference between the accuracy of the training data and the accuracy of the test data result is more than 15%, the gamma value needs to be adjusted to be reduced, and when the error of the training result is more than the error allowable range, the gamma value is increased, so that the accuracy and efficiency of the model are improved.
Preferably, in this embodiment, the support vector machine is used as a model basis to analyze and process data, so as to exert its advantages and predict the severity of voltage sag. A Support Vector Machine (SVM) is an important Machine learning method. Even under the condition of a small number of samples, the SVM can neutralize the complexity of the model and has certain new sample adaptability so as to obtain better popularization capability, and is suitable for solving the problem of data fitting prediction.
Preferably, the embodiment:
(1) predicting the severity of a certain voltage sag by using historical voltage sag monitoring data;
(2) the function of predicting the severity of the voltage sag is realized by taking a support vector machine as a model building foundation;
(3) the historical monitoring data of the voltage sag are analyzed and processed through the support vector machine, the severity of the voltage sag at a certain time is obtained through prediction, and a basis is provided for prevention and treatment of the voltage sag.
Preferably, in this embodiment, the historical monitoring data of the voltage sag of the power quality monitoring device is collected, and these data are used as data support for predicting the severity of the voltage sag, and are stored in a centralized manner as input data for predicting the severity of the voltage sag. And then, establishing a voltage sag risk prediction model based on the support vector machine, wherein the model is based on the support vector machine and is learned through the voltage sag historical monitoring data, the model is continuously optimized and adjusted in the learning process, and after the learning is finished, the voltage sag severity prediction model based on the support vector machine is obtained, namely the voltage sag severity prediction can be carried out by inputting related data.
The above description is only a preferred embodiment of the present invention, and all equivalent changes and modifications made in accordance with the claims of the present invention should be covered by the present invention.
Claims (4)
1. A voltage sag severity prediction method based on a support vector machine is characterized by comprising the following steps: the method comprises the following steps:
step S1: measuring and collecting historical voltage sag monitoring data recorded by the power quality monitoring device, and dividing the historical voltage sag monitoring data into training data and testing data, wherein the proportion of the training data to the testing data is 8: 2, training data is used for training and learning the support vector machine model, and test data is used for testing and verifying the support vector machine model;
step S2: normalizing the voltage sag historical monitoring data to be between [0 and 1] by adopting dispersion standardization, and using the normalized voltage sag historical monitoring data as input data for predicting the severity of voltage sag, and meanwhile, using the severity of voltage sag of a node to be evaluated in a power grid as output data and storing the input data and the output data;
step S3: selecting a Support Vector Machine (SVM) type: an RBF function is selected as a kernel function to construct a support vector machine model;
step S4: training a support vector machine model by using the normalized voltage sag historical monitoring data, and learning by using the normalized voltage sag historical monitoring data as a training sample input; judging whether the model learning is finished or not, if the termination criterion is smaller than a preset value of tolerable deviation, finishing the model learning, if so, executing the step S5, otherwise, continuing the model learning;
step S5: inputting test data to test the model, and adjusting and optimizing a punishment parameter C, an insensitive loss parameter epsilon and a gamma value of the model according to the error magnitude and the variation trend of the output result of the training data and the test data to obtain a voltage sag severity prediction model based on a support vector machine;
step S6: after the parameters are adjusted and optimized, the current known data is input into the model for predicting the severity of voltage sag based on the support vector machine obtained in step S5, the trained function for predicting the severity of voltage sag of the model is used, and the model for predicting the severity of voltage sag based on the support vector machine is used to process and analyze the data, so that the severity of voltage sag of a certain node is obtained, and a user can know the voltage sag according to the obtained result.
2. The method according to claim 1, wherein the method comprises: the historical monitoring data of the voltage sag comprise the residual voltage amplitude, the duration, the voltage level, the monitoring position and the operation mode of the voltage sag.
3. The method according to claim 1, wherein the method comprises: the specific content of step S3 is:
sample set for support vector machine { (X)1,y1),(X2,y2)…(Xn,yn)},Xi=1,2…nAs an input vector, yiIs an output vector, and the corresponding relation is:
in the formula (I), the compound is shown in the specification,representing the corresponding vector after mapping X to a high-dimensional space;
the dual problem is obtained according to Lagrange dual theory as follows:
the RBF function has small influence on the complexity of the model in the calculation process and has nonlinear characteristics and fitting capacity, so the RBF function is adopted as a kernel function of the support vector machine;
4. The method according to claim 1, wherein the method comprises: the specific contents of adjusting and optimizing the penalty parameter C, the insensitive loss parameter epsilon and the gamma value of the model in step S5 are as follows:
while adding the relaxation variable xii,i=1…nThen, the model introduces the fault tolerance to the data, and the objective function and the constraint condition among the support vector machines become:
c is a punishment coefficient, the large value C has high fitting degree on training data, overfitting is easy to occur, the generalization capability is poor, the small value C has under-fitting, the fitness on the training data is not high, therefore, the value C needs to be adjusted according to the output result and the error of the training data and the test data, when the error of the result obtained by the training data is small, the error of the result obtained by the test data is large, the difference between the accuracy of the training result and the accuracy of the test result is more than 15%, the value C is considered to be reduced, and when the error of the result obtained by the training data is more than an error allowable value, the value C is increased, and finally, a reasonable value C is obtained; determining a reasonable epsilon value through the repeated calculation result of the training data and the test data, wherein the epsilon value is selected differently according to different data volumes; the gamma value is a parameter carried after an RBF function is selected as a kernel function, and has the following relationship:
After the training data, the test data result and the error analysis are repeatedly carried out, the gamma value is adjusted according to the error magnitude and the change trend, when the training result precision is high, the test data result precision is low, the difference between the accuracy rates of the training data result precision and the test data result precision is larger than 15%, the gamma value needs to be adjusted to be small, and when the training result error is larger than the error allowable range, the gamma value is increased, so that the accuracy and the efficiency of the model are improved.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011037249.1A CN112232386B (en) | 2020-09-27 | 2020-09-27 | Voltage sag severity prediction method based on support vector machine |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011037249.1A CN112232386B (en) | 2020-09-27 | 2020-09-27 | Voltage sag severity prediction method based on support vector machine |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112232386A true CN112232386A (en) | 2021-01-15 |
CN112232386B CN112232386B (en) | 2024-03-15 |
Family
ID=74120270
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011037249.1A Active CN112232386B (en) | 2020-09-27 | 2020-09-27 | Voltage sag severity prediction method based on support vector machine |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112232386B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113919162A (en) * | 2021-10-15 | 2022-01-11 | 福州大学 | Voltage sag risk early warning method based on simulation and multi-source measured data fusion |
CN115469154A (en) * | 2022-11-02 | 2022-12-13 | 国网信息通信产业集团有限公司 | Voltage sag duration type prediction method and system and prediction terminal |
WO2023284731A1 (en) * | 2021-07-13 | 2023-01-19 | 中兴通讯股份有限公司 | Parameter setting method and apparatus, and electronic device and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105548862A (en) * | 2016-01-25 | 2016-05-04 | 合肥工业大学 | Simulation circuit fault diagnosis method on the basis of generalized multi-nuclear support vector machine |
CN107123987A (en) * | 2017-05-11 | 2017-09-01 | 华东交通大学 | Electrical energy power quality disturbance recognition methods based on on-line training weighed SVM |
CN108564204A (en) * | 2018-03-23 | 2018-09-21 | 西安理工大学 | Least square method supporting vector machine power predicating method based on maximal correlation entropy criterion |
CN109470985A (en) * | 2018-06-19 | 2019-03-15 | 国网浙江省电力有限公司湖州供电公司 | A kind of voltage sag source identification methods based on more resolution singular value decompositions |
WO2019202494A1 (en) * | 2018-04-16 | 2019-10-24 | Ashish Sharma | A system and a method for predicting failure risk of appliances |
US20200271720A1 (en) * | 2020-05-09 | 2020-08-27 | Hefei University Of Technology | Method for diagnosing analog circuit fault based on vector-valued regularized kernel function approximation |
-
2020
- 2020-09-27 CN CN202011037249.1A patent/CN112232386B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105548862A (en) * | 2016-01-25 | 2016-05-04 | 合肥工业大学 | Simulation circuit fault diagnosis method on the basis of generalized multi-nuclear support vector machine |
CN107123987A (en) * | 2017-05-11 | 2017-09-01 | 华东交通大学 | Electrical energy power quality disturbance recognition methods based on on-line training weighed SVM |
CN108564204A (en) * | 2018-03-23 | 2018-09-21 | 西安理工大学 | Least square method supporting vector machine power predicating method based on maximal correlation entropy criterion |
WO2019202494A1 (en) * | 2018-04-16 | 2019-10-24 | Ashish Sharma | A system and a method for predicting failure risk of appliances |
CN109470985A (en) * | 2018-06-19 | 2019-03-15 | 国网浙江省电力有限公司湖州供电公司 | A kind of voltage sag source identification methods based on more resolution singular value decompositions |
US20200271720A1 (en) * | 2020-05-09 | 2020-08-27 | Hefei University Of Technology | Method for diagnosing analog circuit fault based on vector-valued regularized kernel function approximation |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2023284731A1 (en) * | 2021-07-13 | 2023-01-19 | 中兴通讯股份有限公司 | Parameter setting method and apparatus, and electronic device and storage medium |
CN113919162A (en) * | 2021-10-15 | 2022-01-11 | 福州大学 | Voltage sag risk early warning method based on simulation and multi-source measured data fusion |
CN115469154A (en) * | 2022-11-02 | 2022-12-13 | 国网信息通信产业集团有限公司 | Voltage sag duration type prediction method and system and prediction terminal |
Also Published As
Publication number | Publication date |
---|---|
CN112232386B (en) | 2024-03-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112232386B (en) | Voltage sag severity prediction method based on support vector machine | |
CN109409628B (en) | Acquisition terminal manufacturer evaluation method based on metering big data clustering model | |
CN110874685A (en) | Intelligent electric energy meter running state distinguishing method and system based on neural network | |
CN113917334B (en) | Battery health state estimation method based on evolution LSTM self-encoder | |
CN101863088A (en) | Method for forecasting Mooney viscosity in rubber mixing process | |
CN101726451A (en) | Method for measuring viscosity index of internal combustion engine oil | |
CN109033513A (en) | Method for diagnosing fault of power transformer and diagnosing fault of power transformer device | |
CN105868164A (en) | Soft measurement modeling method based on monitored linear dynamic system model | |
CN111950205A (en) | Lithium battery SOH prediction method based on FWA optimization extreme learning machine | |
CN111695452A (en) | Parallel reactor internal aging degree evaluation method based on RBF neural network | |
CN114583767B (en) | Data-driven wind power plant frequency modulation response characteristic modeling method and system | |
CN104866679A (en) | Mechanical characteristic prediction method of switching device | |
CN105471624A (en) | Comprehensive evaluation method for access of communication equipment to terminal communication access network | |
CN111832703A (en) | Sampling interval perception long-short term memory network-based process manufacturing industry irregular sampling dynamic sequence modeling method | |
CN103344740A (en) | Online soft measuring method of glutamate product concentration based on multi-input wiener model | |
CN103279030A (en) | Bayesian framework-based dynamic soft measurement modeling method and device | |
CN113722898A (en) | Durability evaluation method and device for fuel cell stack | |
CN112014757A (en) | Battery SOH estimation method integrating capacity increment analysis and genetic wavelet neural network | |
CN111985091A (en) | Rapid safety correction method for power system containing UPFC | |
CN116662925A (en) | Industrial process soft measurement method based on weighted sparse neural network | |
CN115577856A (en) | Method and system for predicting construction cost and controlling balance of power transformation project | |
Zhao et al. | Lithium-ion battery state-of-health estimation method using isobaric energy analysis and pso-lstm | |
CN116702629B (en) | Power system transient stability evaluation method with migration capability | |
CN106341837A (en) | Inferior quality telephone traffic proportion value prediction method and device | |
CN117174899B (en) | Preparation method of carbon fluoride anode material |
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 |