CN113569464A - Wind turbine generator oscillation mode prediction method and device based on deep learning network and multi-task learning strategy - Google Patents
Wind turbine generator oscillation mode prediction method and device based on deep learning network and multi-task learning strategy Download PDFInfo
- Publication number
- CN113569464A CN113569464A CN202110686343.8A CN202110686343A CN113569464A CN 113569464 A CN113569464 A CN 113569464A CN 202110686343 A CN202110686343 A CN 202110686343A CN 113569464 A CN113569464 A CN 113569464A
- Authority
- CN
- China
- Prior art keywords
- oscillation mode
- data
- network
- output power
- turbine generator
- 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
- 230000010355 oscillation Effects 0.000 title claims abstract description 126
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000013135 deep learning Methods 0.000 title claims abstract description 36
- 230000006870 function Effects 0.000 claims description 28
- 210000002569 neuron Anatomy 0.000 claims description 25
- 238000012549 training Methods 0.000 claims description 19
- 238000000605 extraction Methods 0.000 claims description 15
- 230000004913 activation Effects 0.000 claims description 12
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 238000000354 decomposition reaction Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 8
- 230000007246 mechanism Effects 0.000 claims description 7
- 230000009467 reduction Effects 0.000 claims description 7
- 238000013500 data storage Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000010248 power generation Methods 0.000 abstract description 5
- 238000003062 neural network model Methods 0.000 abstract description 3
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 4
- 229910052799 carbon Inorganic materials 0.000 description 4
- 238000010276 construction Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 230000003993 interaction Effects 0.000 description 3
- 238000006386 neutralization reaction Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 239000002803 fossil fuel Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
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
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
-
- 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
- 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
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
- F05B—INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
- F05B2270/00—Control
- F05B2270/30—Control parameters, e.g. input parameters
- F05B2270/32—Wind speeds
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
- F05B—INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
- F05B2270/00—Control
- F05B2270/30—Control parameters, e.g. input parameters
- F05B2270/335—Output power or torque
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
- F05B—INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
- F05B2270/00—Control
- F05B2270/30—Control parameters, e.g. input parameters
- F05B2270/337—Electrical grid status parameters, e.g. voltage, frequency or power demand
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/06—Wind turbines or wind farms
-
- 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
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B10/00—Integration of renewable energy sources in buildings
- Y02B10/30—Wind power
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Public Health (AREA)
- Mathematical Physics (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- Water Supply & Treatment (AREA)
- Sustainable Energy (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Primary Health Care (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Chemical & Material Sciences (AREA)
- Sustainable Development (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
Abstract
The invention belongs to the technical field of renewable energy power generation, and discloses a wind turbine generator oscillation mode prediction method based on a deep learning network and a multi-task learning strategy, which comprises the following steps: acquiring output power, voltage and wind speed data of the wind turbine generator during actual operation; segmenting the collected wind turbine generator output power, voltage and wind speed data; analyzing oscillation modes contained in the data segment by using a Pony algorithm; extracting characteristics of the output power data by using a denoising autoencoder, and solving a wind speed average value and a voltage average value of a data section to obtain output power, wind speed and voltage characteristics; and constructing a multi-task learning network to predict the oscillation mode. The embodiment of the invention applies the deep learning method to the field of wind power system oscillation mode prediction for the first time, predicts the oscillation mode of the wind turbine generator based on wind turbine generator operation big data and a multi-task learning neural network model, and provides reference for wind power system operation safety analysis.
Description
Technical Field
The invention belongs to the technical field of renewable energy power generation, and particularly relates to a wind turbine generator oscillation mode prediction method and device based on a deep learning network and a multi-task learning strategy.
Background
In order to deal with the threat brought by global warming, China proposes the strategy of 'carbon peak reaching and carbon neutralization', strives not to increase the carbon emission before 2030 years and achieve the aim of carbon neutralization before 2060 yearsAnd (4) marking. Combustion of fossil fuels to produce CO2Therefore, the conventional power system is gradually transformed into a high-proportion renewable energy power system, and new energy represented by wind energy is started to be connected into a power grid in a large scale. Compared with the traditional fossil energy power generation mode, the wind energy has the advantages of cleanness, high efficiency, reproducibility and the like, but the output of the wind energy has strong uncertainty, and the oscillation problem can be caused when the wind energy is connected with a power grid in a grid mode. With the continuous improvement of wind power permeability, the interaction problem between the wind turbine generator and the power grid is paid more and more attention.
Research shows that the oscillation caused by the interaction between the wind turbine generator and the power grid is generally active power oscillation, and the oscillation can be divided into different oscillation modes according to the frequency, such as low-frequency oscillation, synchronous control interaction (SSCI), subsynchronous oscillation (SSO), subsynchronous oscillation (SSR), and the like. Different oscillation mechanisms of different oscillation modes are different, and different suppression measures need to be taken according to different oscillation mode categories, so that accurate prediction of the oscillation modes is necessary. The traditional method generally analyzes the oscillation mode category through a physical modeling and simulation mode, however, because the cause of the oscillation mode of the wind turbine generator is complex, the influence of factors such as voltage and wind speed on the oscillation mode is difficult to be considered comprehensively during physical modeling, and accurate prediction of the oscillation mode is difficult to realize.
Disclosure of Invention
The embodiment of the invention provides a wind turbine generator oscillation mode prediction method and device based on a deep learning network and a multi-task learning strategy, and aims to solve the problem that the influence of factors such as voltage and wind speed on an oscillation mode is difficult to take into full consideration during physical modeling in the prior art. The following presents a simplified summary in order to provide a basic understanding of some aspects of the disclosed embodiments. This summary is not an extensive overview and is intended to neither identify key/critical elements nor delineate the scope of such embodiments. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is presented later.
According to the first aspect of the embodiment of the invention, a wind turbine generator oscillation mode prediction method based on a deep learning network and a multi-task learning strategy is provided.
In one embodiment, a wind turbine generator oscillation mode prediction method based on a deep learning network and a multitask learning strategy comprises the following steps:
step S1, acquiring output power, voltage and wind speed data of the wind turbine generator during actual operation;
step S2, segmenting the collected wind turbine generator output power, voltage and wind speed data;
step S3, analyzing the oscillation mode contained in the data segment by using a Pony algorithm;
step S4, extracting the characteristics of the output power data by using a denoising autoencoder, and solving the wind speed average value and the voltage average value of the data segment to obtain the characteristics of the output power, the wind speed and the voltage;
and step S5, constructing a multitask learning network to predict the oscillation mode.
Optionally, in step S2, the output power, voltage and wind speed data are segmented at time intervals T.
Optionally, in the step S3, a Pony algorithm is used to perform signal decomposition on each output power data segment, so as to obtain an oscillation mode included in each output power data segment.
Optionally, in step S3, the rule of correspondence between the signal decomposition result of the output power data segment and the oscillation mode is as follows:
optionally, in step S4, the method further includes a step of constructing a denoising self-encoder, including: and taking each section of output power data as the input and the output of the denoising autoencoder, training the autoencoder, and learning the significant features in the output power data by using the denoising autoencoder.
Optionally, the denoising self-encoder is of a three-layer network structure, and includes an encoding layer, a hidden layer, and a decoding layer, the number of neurons in the encoding layer is the same as that in the decoding layer, the number of neurons in the middle hidden layer is far smaller than that in the encoding layer and that in the decoding layer, the loss function is a mean square error function, the activation function is Relu, and the optimizer is Adam.
Optionally, the step of constructing a multitask learning network includes: taking the oscillation mode category in the step S3 as a prediction task, taking the output power, wind speed and voltage characteristics of the previous section of data as the input characteristics of the network, taking the oscillation mode of the next section of data as a label, and performing network training by using all data; and then inputting the output power, the wind speed and the voltage characteristics of the current data segment into the trained multi-task learning network, thereby predicting the oscillation mode category of the next data segment.
Optionally, the multitask learning network adopts a four-layer network structure, the first two layers are parameter sharing layers, and the parameter sharing is realized through a hard sharing mechanism;
the third layer is a subtask learning layer and is realized by adopting a full-connection neural network;
the fourth layer is an output layer and is realized by adopting a fully-connected neural network, and the number of neurons is 1.
Optionally, in the multi-task learning network, the non-output layer activation function is Relu, the output layer activation function is Sigmoid, the loss function is an average absolute error function, the optimizer is Adam, and the initial learning rate of the network is 0.01.
According to a second aspect of the embodiment of the invention, a wind turbine generator oscillation mode prediction device based on a deep learning network and a multi-task learning strategy is provided.
In one embodiment, the wind turbine generator oscillation mode prediction apparatus based on the deep learning network and the multitask learning strategy includes:
the system comprises an original data and oscillation mode acquisition module, a data storage module and a data processing module, wherein the original data and oscillation mode acquisition module is used for acquiring output power, voltage and wind speed data of a wind turbine generator set during operation, and segmenting the data to obtain an oscillation mode category contained in each segment of data;
the data feature extraction module is used for constructing a denoising autoencoder to perform feature extraction on the power data to obtain power features after dimensionality reduction, and solving the average value of wind speed and voltage in each segment of data to obtain wind speed and voltage average value features;
and the oscillation mode prediction module is used for constructing a multi-task learning network, training the network by using the characteristic data obtained by the data characteristic extraction module and further performing oscillation mode prediction by using the trained network.
Optionally, the original data and oscillation mode obtaining module performs signal decomposition on each output power data segment by using a Pony algorithm to obtain an oscillation mode included in each output power data segment, and a rule of correspondence between a signal decomposition result of the output power data segment and the oscillation mode is shown in the following table:
signal frequency range/Hz | Mode of oscillation/Hz | Class of oscillation modes |
[0.1—1.8] | 0.1~1.8 | 1 |
[1.82—2.02] | 1.92 | 2 |
[4.17—4.57] | 4.37 | 3 |
[11.91—12.91] | 12.41 | 4 |
[22.4—23.6] | 23 | 5 |
[44.57—46.17] | 45.37 | 6 |
[77.5—80.5] | 79 | 7 |
Optionally, the data feature extraction module constructs a denoising autoencoder, including: and taking each section of output power data as the input and the output of the denoising autoencoder, training the autoencoder, and learning the significant features in the output power data by using the denoising autoencoder.
Optionally, the data feature extraction module inputs the output power data into a trained denoising autoencoder, extracts the output of the middle hidden layer, and obtains the power feature after dimensionality reduction; and solving the wind speed mean value and the voltage mean value of each data segment, and inputting the wind speed mean value and the voltage mean value into a trained denoising autoencoder to obtain the characteristics of the wind speed mean value and the voltage mean value.
Optionally, the oscillation mode prediction module constructs a multitask learning network, including: taking the oscillation mode category as a prediction task, taking the output power, wind speed and voltage characteristics of the previous section of data as the input characteristics of the network, taking the oscillation mode of the next section of data as a label, and performing network training by using all data; and then inputting the output power, the wind speed and the voltage characteristics of the current data segment into the trained multi-task learning network, thereby predicting the oscillation mode category of the next data segment.
Optionally, the multitask learning network adopts a four-layer network structure, the first two layers are parameter sharing layers, and the parameter sharing is realized through a hard sharing mechanism; the third layer is a subtask learning layer and is realized by adopting a full-connection neural network; the fourth layer is an output layer and is realized by adopting a fully-connected neural network, and the number of neurons is 1.
According to a third aspect of embodiments of the present invention, there is provided a computer apparatus.
In some embodiments, the computer device comprises a memory storing a computer program and a processor implementing the steps of the above method when executing the computer program.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
the deep learning method is applied to the field of wind power system oscillation mode prediction for the first time, the wind power generation set oscillation mode is predicted based on wind power generation set operation big data and a multi-task learning neural network model, the influence of factors such as voltage and wind speed on the oscillation mode is comprehensively considered, accurate prediction of the oscillation mode is achieved, the problems that a traditional physical modeling method is complex in model and difficult to accurately model are solved, and reference is provided for wind power system operation safety analysis.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
FIG. 1 is a flow diagram illustrating a method for wind turbine oscillation mode prediction based on a deep learning network and a multi-task learning strategy according to an exemplary embodiment;
FIG. 2 is a schematic structural diagram illustrating a wind turbine generator oscillation mode prediction device based on a deep learning network and a multitask learning strategy according to an exemplary embodiment;
FIG. 3 is a schematic diagram illustrating the structure of a computer device according to an example embodiment.
Detailed Description
The following description and the drawings sufficiently illustrate specific embodiments herein to enable those skilled in the art to practice them. Portions and features of some embodiments may be included in or substituted for those of others. The scope of the embodiments herein includes the full ambit of the claims, as well as all available equivalents of the claims. The terms "first," "second," and the like, herein are used solely to distinguish one element from another without requiring or implying any actual such relationship or order between such elements. In practice, a first element can also be referred to as a second element, and vice versa. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a structure, apparatus, or device that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such structure, apparatus, or device. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a structure, device or apparatus that comprises the element. The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The terms "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like herein, as used herein, are defined as orientations or positional relationships based on the orientation or positional relationship shown in the drawings, and are used for convenience in describing and simplifying the description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus should not be construed as limiting the present invention. In the description herein, unless otherwise specified and limited, the terms "mounted," "connected," and "connected" are to be construed broadly, and may include, for example, mechanical or electrical connections, communications between two elements, direct connections, and indirect connections via intermediary media, where the specific meaning of the terms is understood by those skilled in the art as appropriate.
Herein, the term "plurality" means two or more, unless otherwise specified.
Herein, the character "/" indicates that the preceding and following objects are in an "or" relationship. For example, A/B represents: a or B.
Herein, the term "and/or" is an associative relationship describing objects, meaning that three relationships may exist. For example, a and/or B, represents: a or B, or A and B.
Fig. 1 shows an embodiment of a wind turbine generator oscillation mode prediction method based on a deep learning network and a multi-task learning strategy according to the present invention.
In this embodiment, the wind turbine generator oscillation mode prediction method based on the deep learning network and the multitask learning strategy includes:
step S1, collecting output power, voltage and wind speed data of the wind turbine generator during actual operation by taking M as sampling frequency;
step S2, segmenting the collected wind turbine generator output power, voltage and wind speed data;
step S3, analyzing the oscillation mode contained in the data segment by using a Pony algorithm;
step S4, extracting the characteristics of the output power data by using a denoising autoencoder, and solving the wind speed average value and the voltage average value of the data segment to obtain the characteristics of the output power, the wind speed and the voltage;
and step S5, constructing a multitask learning network to predict the oscillation mode.
The embodiment of the invention applies the deep learning method to the field of wind power system oscillation mode prediction, predicts the oscillation mode of a wind turbine generator based on wind turbine generator operation big data and a multitask learning neural network model, comprehensively considers the influence of factors such as voltage and wind speed on the oscillation mode, realizes accurate prediction of the oscillation mode, overcomes the problems of complex model and difficulty in accurate modeling of the traditional physical modeling method, and provides reference for wind power system operation safety analysis.
Alternatively, in the above step S1, the sampling frequency M is generally greater than or equal to 100 Hz.
In one embodiment, in step S2, the output power, voltage and wind speed data are segmented at time intervals T.
Alternatively, the time interval T is typically 10 s.
In one embodiment, in step S3, a Pony algorithm is used to perform signal decomposition on each output power data segment, so as to obtain an oscillation mode included in each output power data segment.
In one embodiment, in step S3, the rule of correspondence between the signal decomposition result of the output power data segment and the oscillation mode is as follows:
TABLE 1
Signal frequency range/Hz | Mode of oscillation/Hz | Class of oscillation modes |
[0.1—1.8] | 0.1~1.8 | 1 |
[1.82—2.02] | 1.92 | 2 |
[4.17—4.57] | 4.37 | 3 |
[11.91—12.91] | 12.41 | 4 |
[22.4—23.6] | 23 | 5 |
[44.57—46.17] | 45.37 | 6 |
[77.5—80.5] | 79 | 7 |
In an embodiment, the step S4 includes a step of constructing a denoising autoencoder, including: and taking each section of output power data as the input and the output of the denoising autoencoder, training the autoencoder, and learning the significant features in the output power data by using the denoising autoencoder.
In one embodiment, the denoising self-encoder is a three-layer network structure, which includes an encoding layer, a hiding layer and a decoding layer, and the number of neurons in the encoding layer and the number of neurons in the decoding layer are the same, the number of neurons in the middle hiding layer is much smaller than the number of neurons in the encoding layer and the number of neurons in the decoding layer (for example, the number of neurons in the encoding layer and the decoding layer is 256, the number of neurons in the middle hiding layer is 10), the loss function is a mean square error function, the activation function is Relu, and the optimizer is Adam.
Optionally, the construction and training of the denoising self-encoder both use a keras deep learning toolkit in python programming language.
In one embodiment, the output power data is input into the trained denoising autoencoder in the embodiment, and the output of the middle hidden layer is extracted to obtain the power characteristic after dimension reduction; and solving the wind speed mean value and the voltage mean value of each data segment, and inputting the wind speed mean value and the voltage mean value into the trained denoising autoencoder in the embodiment to obtain the characteristics of the wind speed mean value and the voltage mean value.
In one embodiment, the step of constructing a multitask learning network comprises: taking the oscillation mode category in the step S3 as a prediction task, taking the output power, wind speed and voltage characteristics of the previous section of data as the input characteristics of the network, taking the oscillation mode of the next section of data as a label, and performing network training by using all data; and then inputting the output power, the wind speed and the voltage characteristics of the current data segment into the trained multi-task learning network, thereby predicting the oscillation mode category of the next data segment.
In one embodiment, the multi-task learning network adopts a four-layer network structure, the first two layers are parameter sharing layers, and the parameter sharing layer is realized through a hard sharing mechanism; the third layer is a subtask learning layer and is realized by adopting a full-connection neural network; the fourth layer is an output layer and is realized by adopting a fully-connected neural network, and the number of neurons is 1. Optionally, in the multi-task learning network model, the non-output layer activation function is Relu, the output layer activation function is Sigmoid, the loss function is an average absolute error function, the optimizer is Adam, and the network initial learning rate is 0.01.
In one embodiment, the multitask learning network tag is set by setting an existing oscillation mode category to be 1 and setting an absent oscillation mode category to be 0.
Optionally, the construction and training of the multitask learning network use a keras deep learning toolkit in python programming language.
In another embodiment, as shown in fig. 2, the present invention further provides a wind turbine generator oscillation mode prediction apparatus based on a deep learning network and a multitask learning strategy, including:
the system comprises an original data and oscillation mode acquisition module, a data storage module and a data processing module, wherein the original data and oscillation mode acquisition module is used for acquiring output power, voltage and wind speed data of a wind turbine generator set during operation, and segmenting the data to obtain an oscillation mode category contained in each segment of data;
the data feature extraction module is used for constructing a denoising autoencoder to perform feature extraction on the power data to obtain power features after dimensionality reduction, and solving the average value of wind speed and voltage in each segment of data to obtain wind speed and voltage average value features;
and the oscillation mode prediction module is used for constructing a multi-task learning network, training the network by using the characteristic data obtained by the data characteristic extraction module and further performing oscillation mode prediction by using the trained network.
In one embodiment, the raw data and oscillation mode obtaining module collects output power, voltage and wind speed data of the wind turbine generator during actual operation by using M as a sampling frequency.
Alternatively, the sampling frequency M is typically greater than or equal to 100 Hz.
In one embodiment, the raw data and oscillation mode acquisition module segments the output power, voltage and wind speed data at time intervals T.
Alternatively, the time interval T is typically 10 s.
In an embodiment, the raw data and oscillation mode obtaining module performs signal decomposition on each output power data segment by using a Pony algorithm to obtain an oscillation mode included in each output power data segment.
In an embodiment, the rule of correspondence between the signal decomposition result of the output power data segment obtained by the raw data and oscillation mode obtaining module and the oscillation mode is shown in the following table:
TABLE 1
In one embodiment, the data feature extraction module constructs a denoising autoencoder, including: and taking each section of output power data as the input and the output of the denoising autoencoder, training the autoencoder, and learning the significant features in the output power data by using the denoising autoencoder.
In one embodiment, the denoising self-encoder is a three-layer network structure, which includes an encoding layer, a hiding layer and a decoding layer, and the number of neurons in the encoding layer and the number of neurons in the decoding layer are the same, the number of neurons in the middle hiding layer is much smaller than the number of neurons in the encoding layer and the number of neurons in the decoding layer (for example, the number of neurons in the encoding layer and the decoding layer is 256, the number of neurons in the middle hiding layer is 10), the loss function is a mean square error function, the activation function is Relu, and the optimizer is Adam.
Optionally, the construction and training of the denoising self-encoder both use a keras deep learning toolkit in python programming language.
In one embodiment, the data feature extraction module inputs the output power data into the trained denoising autoencoder in the embodiment, extracts the output of the middle hidden layer, and obtains the power feature after dimensionality reduction; and solving the wind speed mean value and the voltage mean value of each data segment, and inputting the wind speed mean value and the voltage mean value into the trained denoising autoencoder in the embodiment to obtain the characteristics of the wind speed mean value and the voltage mean value.
In one embodiment, the oscillation mode prediction module constructs a multitask learning network, including: taking the oscillation mode category as a prediction task, taking the output power, wind speed and voltage characteristics of the previous section of data as the input characteristics of the network, taking the oscillation mode of the next section of data as a label, and performing network training by using all data; and then inputting the output power, the wind speed and the voltage characteristics of the current data segment into the trained multi-task learning network, thereby predicting the oscillation mode category of the next data segment.
In one embodiment, the multi-task learning network model adopts a four-layer network structure, the first two layers are parameter sharing layers, and the parameter sharing layer is realized through a hard sharing mechanism; the third layer is a subtask learning layer and is realized by adopting a full-connection neural network; the fourth layer is an output layer and is realized by adopting a fully-connected neural network, and the number of neurons is 1. Optionally, in the multi-task learning network model, the non-output layer activation function is Relu, the output layer activation function is Sigmoid, the loss function is an average absolute error function, the optimizer is Adam, and the network initial learning rate is 0.01.
In one embodiment, the above-mentioned setting method of the multitask learning network model tag is that the existing oscillation mode category is set to 1, and the non-existing oscillation mode category is set to 0.
Optionally, the construction and training of the multitask learning network model both use a keras deep learning toolkit in python programming language.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 3. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing static information and dynamic information data. The network interface of the computer device is used for communicating with an external terminal through a network connection. Which computer program is executed by a processor to carry out the steps in the above-described method embodiments.
Those skilled in the art will appreciate that the configuration shown in fig. 3 is a block diagram of only a portion of the configuration associated with aspects of the present invention and is not intended to limit the computing devices to which aspects of the present invention may be applied, and that a particular computing device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the above method embodiments when executing the computer program.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The present invention is not limited to the structures that have been described above and shown in the drawings, and various modifications and changes can be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.
Claims (16)
1. A wind turbine generator oscillation mode prediction method based on a deep learning network and a multi-task learning strategy is characterized by comprising the following steps:
step S1, acquiring output power, voltage and wind speed data of the wind turbine generator during actual operation;
step S2, segmenting the collected wind turbine generator output power, voltage and wind speed data;
step S3, analyzing the oscillation mode contained in the data segment by using a Pony algorithm;
step S4, extracting the characteristics of the output power data by using a denoising autoencoder, and solving the wind speed average value and the voltage average value of the data segment to obtain the characteristics of the output power, the wind speed and the voltage;
and step S5, constructing a multitask learning network to predict the oscillation mode.
2. The wind turbine generator oscillation mode prediction method based on the deep learning network and the multi-task learning strategy as claimed in claim 1,
in step S2, the output power, voltage and wind speed data are segmented at time intervals T.
3. The wind turbine generator oscillation mode prediction method based on the deep learning network and the multi-task learning strategy as claimed in claim 1,
in the step S3, a Pony algorithm is used to perform signal decomposition on each output power data segment, so as to obtain an oscillation mode included in each output power data segment.
4. The wind turbine generator oscillation mode prediction method based on the deep learning network and the multi-task learning strategy as claimed in claim 3,
in step S3, the rule of correspondence between the signal decomposition result of the output power data segment and the oscillation mode is shown in the following table:
5. the wind turbine generator oscillation mode prediction method based on the deep learning network and the multi-task learning strategy as claimed in claim 1,
in step S4, the method further includes a step of constructing a denoising autoencoder, including: and taking each section of output power data as the input and the output of the denoising autoencoder, training the autoencoder, and learning the significant features in the output power data by using the denoising autoencoder.
6. The wind turbine generator oscillation mode prediction method based on the deep learning network and the multi-task learning strategy as claimed in claim 5,
the denoising self-encoder is of a three-layer network structure and comprises a coding layer, a hiding layer and a decoding layer, the number of neurons of the coding layer is consistent with that of neurons of the decoding layer, the number of neurons of the middle hiding layer is far smaller than that of the coding layer and that of the decoding layer, a loss function is a mean square error function, an activation function is Relu, and an optimizer is Adam.
7. The wind turbine generator oscillation mode prediction method based on the deep learning network and the multi-task learning strategy as claimed in claim 1,
the step of constructing the multitask learning network comprises the following steps: taking the oscillation mode category in the step S3 as a prediction task, taking the output power, wind speed and voltage characteristics of the previous section of data as the input characteristics of the network, taking the oscillation mode of the next section of data as a label, and performing network training by using all data; and then inputting the output power, the wind speed and the voltage characteristics of the current data segment into the trained multi-task learning network, thereby predicting the oscillation mode category of the next data segment.
8. The wind turbine generator oscillation mode prediction method based on the deep learning network and the multi-task learning strategy as claimed in claim 7,
the multi-task learning network adopts a four-layer network structure, the first two layers are parameter sharing layers and are realized through a hard sharing mechanism;
the third layer is a subtask learning layer and is realized by adopting a full-connection neural network;
the fourth layer is an output layer and is realized by adopting a fully-connected neural network, and the number of neurons is 1.
9. The wind turbine generator oscillation mode prediction method based on the deep learning network and the multi-task learning strategy as claimed in claim 8,
in the multi-task learning network, a non-output layer activation function is Relu, an output layer activation function is Sigmoid, a loss function is an average absolute error function, an optimizer is Adam, and the initial learning rate of the network is 0.01.
10. The utility model provides a wind turbine generator system oscillation mode prediction device based on deep learning network and multitask learning strategy which characterized in that includes:
the system comprises an original data and oscillation mode acquisition module, a data storage module and a data processing module, wherein the original data and oscillation mode acquisition module is used for acquiring output power, voltage and wind speed data of a wind turbine generator set during operation, and segmenting the data to obtain an oscillation mode category contained in each segment of data;
the data feature extraction module is used for constructing a denoising autoencoder to perform feature extraction on the power data to obtain power features after dimensionality reduction, and solving the average value of wind speed and voltage in each segment of data to obtain wind speed and voltage average value features;
and the oscillation mode prediction module is used for constructing a multi-task learning network, training the network by using the characteristic data obtained by the data characteristic extraction module and further performing oscillation mode prediction by using the trained network.
11. The wind turbine generator oscillation mode prediction device based on the deep learning network and the multitask learning strategy as claimed in claim 10,
the original data and oscillation mode acquisition module adopts a Pony algorithm to carry out signal decomposition on each section of output power data section to obtain the oscillation mode contained in each section of output power data section, and the corresponding rule of the signal decomposition result of the output power data section and the oscillation mode is shown in the following table:
12. the wind turbine generator oscillation mode prediction device based on the deep learning network and the multitask learning strategy as claimed in claim 10,
the data feature extraction module constructs a denoising autoencoder, and comprises: and taking each section of output power data as the input and the output of the denoising autoencoder, training the autoencoder, and learning the significant features in the output power data by using the denoising autoencoder.
13. The wind turbine generator oscillation mode prediction device based on the deep learning network and the multitask learning strategy as claimed in claim 12,
the data feature extraction module inputs output power data into a trained denoising autoencoder, extracts the output of an intermediate hidden layer and obtains power features after dimension reduction; and solving the wind speed mean value and the voltage mean value of each data segment, and inputting the wind speed mean value and the voltage mean value into a trained denoising autoencoder to obtain the characteristics of the wind speed mean value and the voltage mean value.
14. The wind turbine generator oscillation mode prediction device based on the deep learning network and the multitask learning strategy as claimed in claim 10,
the oscillation mode prediction module constructs a multitask learning network, and comprises the following steps: taking the oscillation mode category as a prediction task, taking the output power, wind speed and voltage characteristics of the previous section of data as the input characteristics of the network, taking the oscillation mode of the next section of data as a label, and performing network training by using all data; and then inputting the output power, the wind speed and the voltage characteristics of the current data segment into the trained multi-task learning network, thereby predicting the oscillation mode category of the next data segment.
15. The wind turbine generator oscillation mode prediction device based on the deep learning network and the multitask learning strategy as claimed in claim 14,
the multi-task learning network adopts a four-layer network structure, the first two layers are parameter sharing layers and are realized through a hard sharing mechanism; the third layer is a subtask learning layer and is realized by adopting a full-connection neural network; the fourth layer is an output layer and is realized by adopting a fully-connected neural network, and the number of neurons is 1.
16. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the method of any one of claims 1 to 9 when executing the computer program.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110686343.8A CN113569464A (en) | 2021-06-21 | 2021-06-21 | Wind turbine generator oscillation mode prediction method and device based on deep learning network and multi-task learning strategy |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110686343.8A CN113569464A (en) | 2021-06-21 | 2021-06-21 | Wind turbine generator oscillation mode prediction method and device based on deep learning network and multi-task learning strategy |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113569464A true CN113569464A (en) | 2021-10-29 |
Family
ID=78162408
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110686343.8A Pending CN113569464A (en) | 2021-06-21 | 2021-06-21 | Wind turbine generator oscillation mode prediction method and device based on deep learning network and multi-task learning strategy |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113569464A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117272022A (en) * | 2023-09-19 | 2023-12-22 | 小谷粒(广州)母婴用品有限公司 | Detection method of MEMS oscillator |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108089095A (en) * | 2017-12-05 | 2018-05-29 | 广东电网有限责任公司电力科学研究院 | A kind of electricity grid oscillating parameter prediction method and device |
CN110474716A (en) * | 2019-08-14 | 2019-11-19 | 安徽大学 | The method for building up of SCMA codec models based on noise reduction self-encoding encoder |
CN110490215A (en) * | 2018-05-14 | 2019-11-22 | 中国电力科学研究院有限公司 | A kind of modal identification method and system of wind power plant-power grid interaction |
CN111160268A (en) * | 2019-12-30 | 2020-05-15 | 北京化工大学 | Multi-angle SAR target recognition method based on multi-task learning |
US20200310520A1 (en) * | 2019-03-29 | 2020-10-01 | Micron Technology, Inc. | Predictive power management |
CN111769575A (en) * | 2020-07-15 | 2020-10-13 | 华北电力大学 | Fan parameter optimization oscillation suppression system and method based on modal stability domain |
CN111950726A (en) * | 2020-07-09 | 2020-11-17 | 华为技术有限公司 | Decision method based on multi-task learning, decision model training method and device |
CN112183368A (en) * | 2020-09-29 | 2021-01-05 | 国网四川省电力公司经济技术研究院 | LSTM-based quick identification method for low-frequency oscillation modal characteristics of power system |
CN112307677A (en) * | 2020-11-05 | 2021-02-02 | 浙江大学 | Power grid oscillation mode evaluation and safety active early warning method based on deep learning |
CN112329535A (en) * | 2020-09-29 | 2021-02-05 | 国网四川省电力公司经济技术研究院 | CNN-based quick identification method for low-frequency oscillation modal characteristics of power system |
-
2021
- 2021-06-21 CN CN202110686343.8A patent/CN113569464A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108089095A (en) * | 2017-12-05 | 2018-05-29 | 广东电网有限责任公司电力科学研究院 | A kind of electricity grid oscillating parameter prediction method and device |
CN110490215A (en) * | 2018-05-14 | 2019-11-22 | 中国电力科学研究院有限公司 | A kind of modal identification method and system of wind power plant-power grid interaction |
US20200310520A1 (en) * | 2019-03-29 | 2020-10-01 | Micron Technology, Inc. | Predictive power management |
CN110474716A (en) * | 2019-08-14 | 2019-11-19 | 安徽大学 | The method for building up of SCMA codec models based on noise reduction self-encoding encoder |
CN111160268A (en) * | 2019-12-30 | 2020-05-15 | 北京化工大学 | Multi-angle SAR target recognition method based on multi-task learning |
CN111950726A (en) * | 2020-07-09 | 2020-11-17 | 华为技术有限公司 | Decision method based on multi-task learning, decision model training method and device |
CN111769575A (en) * | 2020-07-15 | 2020-10-13 | 华北电力大学 | Fan parameter optimization oscillation suppression system and method based on modal stability domain |
CN112183368A (en) * | 2020-09-29 | 2021-01-05 | 国网四川省电力公司经济技术研究院 | LSTM-based quick identification method for low-frequency oscillation modal characteristics of power system |
CN112329535A (en) * | 2020-09-29 | 2021-02-05 | 国网四川省电力公司经济技术研究院 | CNN-based quick identification method for low-frequency oscillation modal characteristics of power system |
CN112307677A (en) * | 2020-11-05 | 2021-02-02 | 浙江大学 | Power grid oscillation mode evaluation and safety active early warning method based on deep learning |
Non-Patent Citations (5)
Title |
---|
刘忠雨: "《深入浅出图神经网络:GNN原理解析》", 31 January 2020, 机械工业出版社, pages: 69 * |
史佳琪;谭涛;郭经;刘阳;张建华;: "基于深度结构多任务学习的园区型综合能源***多元负荷预测", 电网技术, no. 03 * |
孙庆凯: "基于LSTM 和多任务学习的综合能源***多元负荷预测", 《电力***自动化》, vol. 45, no. 5, pages 63 - 69 * |
苗洁蓉: "基于大数据技术的新能源并网***状态认知与振荡识别", 工程科技Ⅱ辑, pages 33 - 51 * |
贾文娟, 张煜东: "自编码器理论与方法综述", 计算机***应用, vol. 27, no. 5, pages 1 - 9 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117272022A (en) * | 2023-09-19 | 2023-12-22 | 小谷粒(广州)母婴用品有限公司 | Detection method of MEMS oscillator |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Yu et al. | LSTM-EFG for wind power forecasting based on sequential correlation features | |
CN110941928A (en) | Rolling bearing residual life prediction method based on dropout-SAE and Bi-LSTM | |
CN112365885B (en) | Training method and device of wake-up model and computer equipment | |
CN114201920A (en) | Laser cutting numerical control system fault diagnosis method based on digital twinning and deep transfer learning | |
CN111369299A (en) | Method, device and equipment for identification and computer readable storage medium | |
CN111832838B (en) | Method for predicting short-term wind power generation output power | |
CN112330078B (en) | Power consumption prediction method and device, computer equipment and storage medium | |
CN113449919B (en) | Power consumption prediction method and system based on feature and trend perception | |
CN111725802B (en) | Method for judging transient stability of alternating current-direct current hybrid power grid based on deep neural network | |
CN115983494A (en) | Short-term wind power prediction method and system for newly-built small-sample wind power plant | |
CN117556369A (en) | Power theft detection method and system for dynamically generated residual error graph convolution neural network | |
CN116485049A (en) | Electric energy metering error prediction and optimization system based on artificial intelligence | |
CN113569464A (en) | Wind turbine generator oscillation mode prediction method and device based on deep learning network and multi-task learning strategy | |
EP1939796A2 (en) | Data processing apparatus, data processing method data processing program and computer readable medium | |
CN116388232B (en) | Wind power frequency modulation integrated inertia control method, system, electronic equipment and storage medium | |
CN113469013A (en) | Motor fault prediction method and system based on transfer learning and time sequence | |
CN113344243A (en) | Wind speed prediction method and system for optimizing ELM based on improved Harris eagle algorithm | |
CN115630316A (en) | Ultrashort-term wind speed prediction method based on improved long-term and short-term memory network | |
CN114861977A (en) | Distillation integration mode perception algorithm and system for unbalanced power data | |
Lu et al. | Anomaly Recognition Method for Massive Data of Power Internet of Things Based on Bayesian Belief Network | |
CN113572152B (en) | Wind turbine generator oscillation mode and influence factor correlation analysis method based on FP-growth | |
CN116863277B (en) | RPA-combined multimedia data detection method and device and computer equipment | |
CN117977677A (en) | MIWOA-based inverter control parameter identification method and MIWOA-based inverter control parameter identification system | |
CN117748516A (en) | Double-fed fan grid-connected transient voltage stability assessment method and system | |
CN115953019A (en) | Method and system suitable for predicting disturbance risk degree of regional power grid |
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 |