CN113033077A - Direct-current transmission line fault distance measurement method based on neural network algorithm - Google Patents
Direct-current transmission line fault distance measurement method based on neural network algorithm Download PDFInfo
- Publication number
- CN113033077A CN113033077A CN202110241174.7A CN202110241174A CN113033077A CN 113033077 A CN113033077 A CN 113033077A CN 202110241174 A CN202110241174 A CN 202110241174A CN 113033077 A CN113033077 A CN 113033077A
- Authority
- CN
- China
- Prior art keywords
- current transmission
- mode
- direct current
- neural network
- line
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/085—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution lines, e.g. overhead
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
-
- 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
- G06F18/2148—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the process organisation or structure, e.g. boosting cascade
-
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/04—Power grid distribution networks
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Abstract
The application discloses a direct current transmission line fault distance measuring method based on a neural network algorithm, which comprises the following steps: constructing an extra-high voltage direct current transmission system model; obtaining line mode components and zero mode components of which the transient states are mutually independent in the extra-high voltage direct current transmission system model; obtaining the ratio of the line mode component to the zero mode component head mode maximum value in each scale; constructing an AdaBoost-Elman integrated neural network model; respectively forming a training sample set and a test data set; training the AdaBoost-Elman integrated neural network model by using the training sample set; the method comprises the steps of testing the trained AdaBoost-Elman integrated neural network model by utilizing the test data set to obtain a direct current transmission line fault distance prediction result, and comparing and analyzing the prediction result and a true value.
Description
Technical Field
The application relates to the technical field of relay protection of direct current transmission systems, in particular to a direct current transmission line fault distance measuring method based on a neural network algorithm.
Background
Direct current transmission lines are generally long, the terrain along the lines is complex, and it is very difficult to search fault points in a line patrol mode, so that the research on an accurate fault positioning method is very important for quickly removing faults and improving the stability of a power transmission system. At present, fault location of an extra-high voltage direct current transmission line mainly depends on a traveling wave fault location technology. The double-end traveling wave ranging is difficult to realize due to the fact that data communication equipment at two ends is needed and double-end synchronous sampling is required, single-end traveling wave ranging is low in cost and strong in real-time performance, but is affected by factors such as transition resistance arc characteristics and system operation modes, and under certain conditions, the second transmitting wave property is difficult to correctly identify, and the accuracy is low.
Disclosure of Invention
The application provides a direct current transmission line fault location method based on a neural network algorithm, and aims to solve the problems that in the prior art, a direct current transmission line fault single-ended traveling wave location method is difficult to identify the property of a second transmitting wave correctly and low in accuracy.
The technical scheme adopted by the application is as follows:
a direct current transmission line fault location method based on a neural network algorithm comprises the following steps:
constructing an extra-high voltage direct current transmission system model, wherein the extra-high voltage direct current transmission system model comprises the following steps: the system comprises an alternating current system model, a converter station model and a power transmission line model;
obtaining line mode components and zero mode components of which the transient states are mutually independent in the extra-high voltage direct current transmission system model;
obtaining the ratio of the line mode component to the zero mode component head mode maximum value in each scale;
constructing an AdaBoost-Elman integrated neural network model, wherein the AdaBoost-Elman integrated neural network model is used for predicting the fault distance of the direct-current transmission line according to the ratio of the line mode component to the zero mode component head mode maximum value;
selecting the line mode component and zero mode component head mode maximum value ratios in a plurality of scales under different fault positions and different transition resistances as input sample values to respectively form a training sample set and a test data set;
training the AdaBoost-Elman integrated neural network model by using the training sample set until a convergence curve meets the actual precision requirement;
and testing the trained AdaBoost-Elman integrated neural network model by using the test data set to obtain a direct current transmission line fault distance prediction result, and comparing and analyzing the prediction result with a real value.
Preferably, the constructing of the AdaBoost-Elman integrated neural network model comprises:
the Elman feedback type neural network is combined with an AdaBoost integration algorithm, and an AdaBoost-Elman integrated neural network model is constructed through matlab software.
Preferably, a carry-over layer is fused into the Elman feedback type neural network, and the carry-over layer is used for memorizing the output value of the hidden layer neuron at the previous moment, so that the network has the function of dynamic memory and can approximate to any nonlinear function with any precision.
Preferably, the obtaining line mode components and zero mode components of which the transient states are independent from each other in the model of the extra-high voltage direct current transmission system includes:
when the ground short circuit fault occurs at different positions of the transmission line and under different transition resistances in the extra-high voltage direct current transmission system model, positive and negative transient voltage signals are extracted by using a rectification side or inversion side measuring element;
and carrying out phase-mode transformation decoupling on the positive and negative transient voltage signals to obtain mutually independent linear-mode components and zero-mode components.
Preferably, the obtaining of the ratio of the head mode maximum of the line mode component and the zero mode component in each scale includes:
performing multi-scale wavelet decomposition on the positive and negative transient voltage line modulus components and the zero modulus component;
and solving the ratio of the line mode component to the zero mode component head mode maximum value in each scale.
Preferably, the obtaining of the ratio of the head mode maximum of the line mode component and the zero mode component in each scale includes:
and obtaining an approximate formula between the ratio of the maximum value of the head wave mode of the transient voltage line mode component and the zero mode component of the extra-high voltage direct current transmission system model and the fault distance according to the modulus transmission function of the extra-high voltage direct current transmission line.
Preferably, the modulus transfer function of the extra-high voltage direct current transmission line is as follows:
wherein A isj(omega) is the direct current transmission line mode transfer function, Uj1(j ω) is a high-frequency component, U, detected at the installation point of the distance measuring devicej(j ω) is a high frequency component, γ, of the point where the fault occursjThe direct current transmission line mode attenuation coefficient is shown, and x is the length between a fault occurrence point and a mounting point of the ranging device.
Preferably, the obtaining of an approximate formula between a ratio of a transient voltage line mode component to a zero mode component head mode maximum of the model of the ultra-high voltage direct current transmission system and a fault distance according to the modulus transmission function of the ultra-high voltage direct current transmission line includes:
deducing the relation between the modulus attenuation characteristic and the fault distance x according to the modulus transmission function formula (1) of the extra-high voltage direct current transmission line:
wherein alpha is1Attenuation coefficient of line mode, alpha0Attenuation coefficient of zero mode, U1(jω)、U0(j omega) is a line mode component, a zero mode component, U, detected by the installation point of the distance measuring deviced1(jω)、Ud0(j omega) is a line mode component and a zero mode component of a fault occurrence point without line attenuation;
the approximate formula between the ratio of the maximum value of the head mode of the transient voltage line mode component and the zero mode component and the fault distance obtained by the formulas (2) and (3) is as follows:
under the same fault
Is a constant value, as shown in equation (4)
The fault distance x is in a nonlinear relation;
and constructing the AdaBoost-Elman integrated neural network model according to an approximate formula between the maximum value ratio of the line mode component and the zero mode component head mode and the fault distance.
The technical scheme of the application has the following beneficial effects:
the fault location method for the extra-high voltage direct current transmission line based on the AdaBoost-Elman integrated neural network algorithm can solve the problem that the location precision is not high in the fault location process of the extra-high voltage direct current transmission line, in addition, the repeatability of a computer is fully utilized, a strong predictor is constructed by the Adaboost integrated algorithm, and the prediction precision and the generalization capability are improved. The method comprises the steps of establishing an extra-high voltage direct-current power transmission system model by utilizing PSCAD/EMTDC simulation software, carrying out massive simulation on ground short circuit faults at different fault positions and under different transition resistances, obtaining enough training sample sets and testing data sets, training and testing an AdaBoost-Elman integrated neural network on the basis, and verifying effectiveness, feasibility and reliability of an AdaBoost-Elman integrated algorithm in the application of extra-high voltage direct-current power transmission system line fault distance measurement.
Drawings
In order to more clearly explain the technical solution of the present application, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious to those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flow chart of a direct current transmission line fault location method based on a neural network algorithm according to the present application;
FIG. 2 is a +/-800 kV extra-high voltage direct-current transmission simulation model in the application;
fig. 3 is a diagram showing the construction of the Elman feedback neural network according to the present application.
Detailed Description
Reference will now be made in detail to embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following examples do not represent all embodiments consistent with the present application. But merely as exemplifications of systems and methods consistent with certain aspects of the application, as recited in the claims.
Referring to fig. 1, a flow chart of a method for measuring a distance between direct current transmission line faults based on a neural network algorithm is shown.
The application provides a direct current transmission line fault distance measurement method based on a neural network algorithm, which comprises the following steps:
constructing an extra-high voltage direct current transmission system model, wherein the extra-high voltage direct current transmission system model comprises the following steps: an alternating current system model, a converter station model and a power transmission line model, which are +/-800 kV ultrahigh voltage direct current transmission simulation models as shown in figure 2;
obtaining line mode components and zero mode components of which the transient states are mutually independent in the extra-high voltage direct current transmission system model;
obtaining the ratio of the line mode component to the zero mode component head mode maximum value in each scale;
constructing an AdaBoost-Elman integrated neural network model, wherein the AdaBoost-Elman integrated neural network model is used for predicting the fault distance of the direct-current transmission line according to the ratio of the line mode component to the zero mode component head mode maximum value;
selecting the line mode component and zero mode component head mode maximum value ratios in a plurality of scales under different fault positions and different transition resistances as input sample values to respectively form a training sample set and a test data set;
training the AdaBoost-Elman integrated neural network model by using the training sample set until a convergence curve meets the actual precision requirement;
and testing the trained AdaBoost-Elman integrated neural network model by using the test data set to obtain a direct current transmission line fault distance prediction result, and comparing and analyzing the prediction result with a real value.
As shown in fig. 1, selecting a line mode component and zero mode component head mode maximum ratio in the k1, k2 and k3 scales as input sample values to respectively form a training sample set and a test data set; training the AdaBoost-Elman integrated neural network model by using the training sample set until a convergence curve meets the precision requirement; and testing the trained AdaBoost-Elman integrated neural network model by using the test data set, and comparing and analyzing a predicted value and a real value.
The construction of the AdaBoost-Elman integrated neural network model comprises the following steps:
the Elman feedback type neural network is combined with an AdaBoost integration algorithm, and an AdaBoost-Elman integrated neural network model is constructed through matlab software.
As shown in fig. 3, a carry-over layer is merged into the Elman feedback neural network, and the carry-over layer is used for memorizing the output value of the hidden layer neuron at the previous moment, so that the network has a dynamic memory function and can approximate to any nonlinear function with any precision. The AdaBoost integration algorithm completes the learning task by constructing a plurality of weak predictors and integrating the weak predictors into a strong predictor through a certain combination strategy. The dynamic memory function of the Elman neural network is combined with the AdaBoost integration algorithm, so that the integrated strong predictor has high prediction precision and strong generalization capability. Compared with the existing method, the extra-high voltage direct current transmission line fault location method based on the AdaBoost-Elman integrated neural network algorithm has the advantages of being high in prediction accuracy, strong in generalization capability, high in convergence speed and the like.
The obtaining of the line mode component and the zero mode component of which the transient states are mutually independent in the model of the extra-high voltage direct current transmission system includes:
when the ground short circuit fault occurs at different positions of the transmission line and under different transition resistances in the extra-high voltage direct current transmission system model, positive and negative transient voltage signals are extracted by using a rectification side or inversion side measuring element;
and carrying out phase-mode transformation decoupling on the positive and negative transient voltage signals to obtain mutually independent linear-mode components and zero-mode components.
The solving of the ratio of the line mode component to the zero mode component head mode maximum in each scale comprises:
performing multi-scale wavelet decomposition on the positive and negative transient voltage line modulus components and the zero modulus component;
and solving the ratio of the line mode component to the zero mode component head mode maximum value in each scale. The ratio of the line mode component to the zero mode component head mode maximum value is increased nonlinearly along with the increase of the fault distance, is only related to the fault distance and is not related to the fault resistance, and is not influenced by the fault intensity.
The step of solving the ratio of the line mode component to the zero mode component head mode maximum value in each scale comprises the following steps:
and obtaining an approximate formula between the ratio of the maximum value of the head wave mode of the transient voltage line mode component and the zero mode component of the extra-high voltage direct current transmission system model and the fault distance according to the modulus transmission function of the extra-high voltage direct current transmission line.
The modulus transmission function of the extra-high voltage direct current transmission line is as follows:
wherein A isj(omega) is the direct current transmission line mode transfer function, Uj1(j ω) is a high-frequency component, U, detected at the installation point of the distance measuring devicej(j ω) is a high frequency component, γ, of the point where the fault occursjThe direct current transmission line mode attenuation coefficient is shown, and x is the length between a fault occurrence point and a mounting point of the ranging device.
The method for obtaining the approximate formula between the ratio of the transient voltage line mode component of the model of the extra-high voltage direct current transmission system to the maximum value of the head mode of the zero mode component of the model of the extra-high voltage direct current transmission system and the fault distance according to the modulus transmission function of the extra-high voltage direct current transmission line comprises the following steps:
deducing the relation between the modulus attenuation characteristic and the fault distance x according to the modulus transmission function formula (1) of the extra-high voltage direct current transmission line:
wherein alpha is1Attenuation coefficient of line mode, alpha0Attenuation coefficient of zero mode, U1(jω)、U0(j omega) is a line mode component, a zero mode component, U, detected by the installation point of the distance measuring deviced1(jω)、Ud0(j omega) is a line mode component and a zero mode component of a fault occurrence point without line attenuation;
the approximate formula between the ratio of the maximum value of the head mode of the transient voltage line mode component and the zero mode component and the fault distance obtained by the formulas (2) and (3) is as follows:
under the same fault
Is a constant value, as shown in equation (4)
The fault distance x is in a nonlinear relation;
and constructing the AdaBoost-Elman integrated neural network model according to an approximate formula between the maximum value ratio of the line mode component and the zero mode component head mode and the fault distance.
The extra-high voltage direct current transmission line fault location method based on the AdaBoost-Elman integrated neural network algorithm can solve the problem that the location precision is not high in the extra-high voltage direct current transmission line fault location process, in addition, the repeatability of a computer is fully utilized, a strong predictor is constructed by the Adaboost integrated algorithm, and the prediction precision and the generalization capability are improved. The method comprises the steps of establishing an extra-high voltage direct-current power transmission system model by utilizing PSCAD/EMTDC simulation software, carrying out massive simulation on ground short circuit faults at different fault positions and under different transition resistances, obtaining enough training sample sets and testing data sets, training and testing an AdaBoost-Elman integrated neural network on the basis, and verifying effectiveness, feasibility and reliability of an AdaBoost-Elman integrated algorithm in the application of extra-high voltage direct-current power transmission system line fault distance measurement.
The embodiments provided in the present application are only a few examples of the general concept of the present application, and do not limit the scope of the present application. Any other embodiments extended according to the scheme of the present application without inventive efforts will be within the scope of protection of the present application for a person skilled in the art.
Claims (8)
1. A direct current transmission line fault location method based on a neural network algorithm is characterized by comprising the following steps:
constructing an extra-high voltage direct current transmission system model, wherein the extra-high voltage direct current transmission system model comprises the following steps: the system comprises an alternating current system model, a converter station model and a power transmission line model;
obtaining line mode components and zero mode components of which the transient states are mutually independent in the extra-high voltage direct current transmission system model;
obtaining the ratio of the line mode component to the zero mode component head mode maximum value in each scale;
constructing an AdaBoost-Elman integrated neural network model, wherein the AdaBoost-Elman integrated neural network model is used for predicting the fault distance of the direct-current transmission line according to the ratio of the line mode component to the zero mode component head mode maximum value;
selecting the line mode component and zero mode component head mode maximum value ratios in a plurality of scales under different fault positions and different transition resistances as input sample values to respectively form a training sample set and a test data set;
training the AdaBoost-Elman integrated neural network model by using the training sample set until a convergence curve meets the actual precision requirement;
and testing the trained AdaBoost-Elman integrated neural network model by using the test data set to obtain a direct current transmission line fault distance prediction result, and comparing and analyzing the prediction result with a real value.
2. The method for fault location of the direct current transmission line based on the neural network algorithm as claimed in claim 1, wherein the constructing of the AdaBoost-Elman integrated neural network model comprises:
the Elman feedback type neural network is combined with an AdaBoost integration algorithm, and an AdaBoost-Elman integrated neural network model is constructed through matlab software.
3. The method for fault location of the direct current transmission line based on the neural network algorithm as claimed in claim 2, wherein a adapting layer is integrated into the Elman feedback type neural network, and the adapting layer is used for memorizing the output value of the hidden layer neuron at the previous moment, so that the network has a dynamic memory function and can approximate to any nonlinear function with any precision.
4. The method according to claim 1, wherein the obtaining of the line-mode component and the zero-mode component of the ultra-high voltage direct current transmission system model, in which the transient states are independent from each other, comprises:
when the ground short circuit fault occurs at different positions of the transmission line and under different transition resistances in the extra-high voltage direct current transmission system model, positive and negative transient voltage signals are extracted by using a rectification side or inversion side measuring element;
and carrying out phase-mode transformation decoupling on the positive and negative transient voltage signals to obtain mutually independent linear-mode components and zero-mode components.
5. The method of claim 4, wherein the step of obtaining the ratio of the line-mode component to the zero-mode component head-mode maximum in each scale comprises:
performing multi-scale wavelet decomposition on the positive and negative transient voltage line modulus components and the zero modulus component;
and solving the ratio of the line mode component to the zero mode component head mode maximum value in each scale.
6. The method of claim 5, wherein the step of obtaining the ratio of the line-mode component to the zero-mode component head-mode maximum in each scale comprises the following steps:
and obtaining an approximate formula between the ratio of the maximum value of the head wave mode of the transient voltage line mode component and the zero mode component of the extra-high voltage direct current transmission system model and the fault distance according to the modulus transmission function of the extra-high voltage direct current transmission line.
7. The direct current transmission line fault location method based on the neural network algorithm of claim 6, wherein the modulus transmission function of the extra-high voltage direct current transmission line is as follows:
wherein A isj(omega) is the direct current transmission line mode transfer function, Uj1(j ω) is a high-frequency component, U, detected at the installation point of the distance measuring devicej(j ω) is a high frequency component, γ, of the point where the fault occursjThe direct current transmission line mode attenuation coefficient is shown, and x is the length between a fault occurrence point and a mounting point of the ranging device.
8. The method for fault location of the direct current transmission line based on the neural network algorithm of claim 7, wherein the step of obtaining an approximate formula between a ratio of a head mode maximum value of a transient voltage line mode component and a zero mode component of the model of the extra-high voltage direct current transmission system and a fault distance according to a modulus transmission function of the extra-high voltage direct current transmission line comprises the following steps:
deducing the relation between the modulus attenuation characteristic and the fault distance x according to the modulus transmission function formula (1) of the extra-high voltage direct current transmission line:
wherein alpha is1Attenuation coefficient of line mode, alpha0Attenuation coefficient of zero mode, U1(jω)、U0(j omega) is a line mode component, a zero mode component, U, detected by the installation point of the distance measuring deviced1(jω)、Ud0(j omega) is a line mode component and a zero mode component of a fault occurrence point without line attenuation;
the approximate formula between the ratio of the maximum value of the head mode of the transient voltage line mode component and the zero mode component and the fault distance obtained by the formulas (2) and (3) is as follows:
under the same fault
Is a constant value, as shown in equation (4)
The fault distance x is in a nonlinear relation;
and constructing the AdaBoost-Elman integrated neural network model according to an approximate formula between the maximum value ratio of the line mode component and the zero mode component head mode and the fault distance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110241174.7A CN113033077A (en) | 2021-03-04 | 2021-03-04 | Direct-current transmission line fault distance measurement method based on neural network algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110241174.7A CN113033077A (en) | 2021-03-04 | 2021-03-04 | Direct-current transmission line fault distance measurement method based on neural network algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113033077A true CN113033077A (en) | 2021-06-25 |
Family
ID=76467784
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110241174.7A Pending CN113033077A (en) | 2021-03-04 | 2021-03-04 | Direct-current transmission line fault distance measurement method based on neural network algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113033077A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113392589A (en) * | 2021-06-30 | 2021-09-14 | 云南电网有限责任公司电力科学研究院 | High-voltage direct-current converter station fault analysis method and system based on convolutional neural network |
| CN113466624A (en) * | 2021-06-30 | 2021-10-01 | 云南电网有限责任公司电力科学研究院 | Method and system for detecting fault area of multi-terminal hybrid direct-current transmission line |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103852692A (en) * | 2014-03-12 | 2014-06-11 | 昆明理工大学 | Ultra-high-voltage direct-current transmission line neural network double end fault location method based on high frequency amount attenuation characteristic |
| CN105223466A (en) * | 2015-09-24 | 2016-01-06 | 昆明理工大学 | A kind of extra high voltage direct current transmission line method of single end distance measurement utilizing modulus maximum ratio |
| CN106096637A (en) * | 2016-06-06 | 2016-11-09 | 浙江大学 | Molten iron silicon content Forecasting Methodology based on the strong predictor of Elman Adaboost |
| CN109239533A (en) * | 2018-11-16 | 2019-01-18 | 国网山东省电力公司电力科学研究院 | A kind of Fault Locating Method of the extra high voltage direct current transmission line based on artificial neural network |
| EP3460496A1 (en) * | 2017-09-26 | 2019-03-27 | Siemens Aktiengesellschaft | A method and apparatus for automatic localization of a fault |
| CN110470937A (en) * | 2019-07-15 | 2019-11-19 | 昆明理工大学 | Based on FEEMD Sample Entropy+neural network HVDC transmission system line fault and commutation failure method for diagnosing faults |
| CN110609215A (en) * | 2019-11-01 | 2019-12-24 | 云南电网有限责任公司电力科学研究院 | Flexible direct-current transmission line fault detection method and system based on transient current |
-
2021
- 2021-03-04 CN CN202110241174.7A patent/CN113033077A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103852692A (en) * | 2014-03-12 | 2014-06-11 | 昆明理工大学 | Ultra-high-voltage direct-current transmission line neural network double end fault location method based on high frequency amount attenuation characteristic |
| CN105223466A (en) * | 2015-09-24 | 2016-01-06 | 昆明理工大学 | A kind of extra high voltage direct current transmission line method of single end distance measurement utilizing modulus maximum ratio |
| CN106096637A (en) * | 2016-06-06 | 2016-11-09 | 浙江大学 | Molten iron silicon content Forecasting Methodology based on the strong predictor of Elman Adaboost |
| EP3460496A1 (en) * | 2017-09-26 | 2019-03-27 | Siemens Aktiengesellschaft | A method and apparatus for automatic localization of a fault |
| CN109239533A (en) * | 2018-11-16 | 2019-01-18 | 国网山东省电力公司电力科学研究院 | A kind of Fault Locating Method of the extra high voltage direct current transmission line based on artificial neural network |
| CN110470937A (en) * | 2019-07-15 | 2019-11-19 | 昆明理工大学 | Based on FEEMD Sample Entropy+neural network HVDC transmission system line fault and commutation failure method for diagnosing faults |
| CN110609215A (en) * | 2019-11-01 | 2019-12-24 | 云南电网有限责任公司电力科学研究院 | Flexible direct-current transmission line fault detection method and system based on transient current |
Non-Patent Citations (4)
| Title |
|---|
| SAMI EKICI等: "A transmission line fault locator based on Elman recurrent networks", 《APPLIED SOFT COMPUTING》 * |
| 刘晶 等: "基于PSO-ENN算法的高压直流输电线路故障测距", 《高压电器》 * |
| 杨鸿雁 等: "基于经验模态分解与Elman神经网络的永富直流换相失败故障诊断方法", 《电子测量技术》 * |
| 王燕武: "基于ESMD的特高压直流输电线路暂态保护与故障测距", 《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113392589A (en) * | 2021-06-30 | 2021-09-14 | 云南电网有限责任公司电力科学研究院 | High-voltage direct-current converter station fault analysis method and system based on convolutional neural network |
| CN113466624A (en) * | 2021-06-30 | 2021-10-01 | 云南电网有限责任公司电力科学研究院 | Method and system for detecting fault area of multi-terminal hybrid direct-current transmission line |
| CN113392589B (en) * | 2021-06-30 | 2022-09-27 | 云南电网有限责任公司电力科学研究院 | High-voltage direct-current converter station fault analysis method and system based on convolutional neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tong et al. | Detection and classification of transmission line transient faults based on graph convolutional neural network | |
| CN102087332B (en) | Direct current (DC) travelling wave fault location method based on wave velocity optimization | |
| CN105223466B (en) | It is a kind of using modulus maximum than extra high voltage direct current transmission line method of single end distance measurement | |
| CN113033077A (en) | Direct-current transmission line fault distance measurement method based on neural network algorithm | |
| CN109521330B (en) | Power transmission line fault traveling wave distance measurement method based on ARIMA wave head prediction | |
| WO2024045962A1 (en) | Protection method and system for high-voltage direct-current circuit | |
| CN110161375B (en) | High-voltage direct-current transmission line calculation model based on distributed resistance parameters | |
| Khaleghi et al. | Single-phase fault location in four-circuit transmission lines based on wavelet analysis using anfis | |
| CN113884818B (en) | Method for accurately estimating arrival time of fault traveling wave of power distribution network based on LSTM | |
| CN117272913A (en) | Integrated circuit layout design system and method | |
| Ye et al. | Single pole‐to‐ground fault location method for mmc‐hvdc system using wavelet decomposition and dbn | |
| CN115201563A (en) | Multi-harmonic source positioning method and system based on joint entropy | |
| CN113189513B (en) | Ripple-based redundant power supply current sharing state identification method | |
| Wang et al. | Balanced truncation for time-delay systems via approximate Gramians | |
| Zhang et al. | Detection of single-phase-to-ground faults in distribution networks based on Gramian Angular Field and Improved Convolutional Neural Networks | |
| CN107505534B (en) | Distribution network fault genetic search positioning method | |
| CN111766470A (en) | Fault positioning method and system for high-voltage direct-current transmission line and direct-current transmission line | |
| CN112946425A (en) | Fault positioning method for mining travelling wave time-frequency domain characteristics by utilizing deep learning | |
| CN111950125A (en) | Method and system for judging fault type and position of direct-current cable | |
| CN111460367A (en) | Algorithm for solving unbalanced data leakage of halogen conveying pipeline based on S transformation/WGAN | |
| CN115130505A (en) | FOCS fault diagnosis method based on improved residual shrinkage network | |
| Bohórquez et al. | One-ended fault location method based on machine learning models | |
| Wijaya et al. | Review of transmission line fault location using travelling wave method | |
| CN115494341A (en) | Power distribution network fault location method and system based on IELM-VMD algorithm | |
| CN115630296A (en) | LSTM-based fault detection method for extra-high voltage multi-terminal hybrid direct-current transmission line |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210625 |