CN117967529A - Control system and method for dehumidifying equipment of offshore wind turbine based on Internet of things - Google Patents
Control system and method for dehumidifying equipment of offshore wind turbine based on Internet of things Download PDFInfo
- Publication number
- CN117967529A CN117967529A CN202211292793.XA CN202211292793A CN117967529A CN 117967529 A CN117967529 A CN 117967529A CN 202211292793 A CN202211292793 A CN 202211292793A CN 117967529 A CN117967529 A CN 117967529A
- Authority
- CN
- China
- Prior art keywords
- humidity
- matrix
- power
- corrected
- wind turbine
- 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
- 238000000034 method Methods 0.000 title claims description 25
- 239000011159 matrix material Substances 0.000 claims abstract description 237
- 238000007791 dehumidification Methods 0.000 claims abstract description 26
- 238000012937 correction Methods 0.000 claims abstract description 24
- 238000000605 extraction Methods 0.000 claims abstract description 20
- 230000004043 responsiveness Effects 0.000 claims abstract description 19
- 230000004044 response Effects 0.000 claims abstract description 11
- 239000013598 vector Substances 0.000 claims description 63
- 238000013527 convolutional neural network Methods 0.000 claims description 35
- 238000010586 diagram Methods 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 6
- 238000011176 pooling Methods 0.000 claims description 6
- 238000012546 transfer Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 230000006855 networking Effects 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 17
- 230000008447 perception Effects 0.000 description 8
- 230000002776 aggregation Effects 0.000 description 6
- 238000004220 aggregation Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 5
- 230000006698 induction Effects 0.000 description 5
- 238000005260 corrosion Methods 0.000 description 4
- 230000007797 corrosion Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 239000002184 metal Substances 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 102100033620 Calponin-1 Human genes 0.000 description 1
- 102100033591 Calponin-2 Human genes 0.000 description 1
- 101000945318 Homo sapiens Calponin-1 Proteins 0.000 description 1
- 101000945403 Homo sapiens Calponin-2 Proteins 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000009833 condensation Methods 0.000 description 1
- 230000005494 condensation Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
Classifications
-
- 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
- F03D80/00—Details, components or accessories not provided for in groups F03D1/00 - F03D17/00
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01D—SEPARATION
- B01D53/00—Separation of gases or vapours; Recovering vapours of volatile solvents from gases; Chemical or biological purification of waste gases, e.g. engine exhaust gases, smoke, fumes, flue gases, aerosols
- B01D53/26—Drying gases or vapours
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63B—SHIPS OR OTHER WATERBORNE VESSELS; EQUIPMENT FOR SHIPPING
- B63B35/00—Vessels or similar floating structures specially adapted for specific purposes and not otherwise provided for
- B63B35/44—Floating buildings, stores, drilling platforms, or workshops, e.g. carrying water-oil separating devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63B—SHIPS OR OTHER WATERBORNE VESSELS; EQUIPMENT FOR SHIPPING
- B63B35/00—Vessels or similar floating structures specially adapted for specific purposes and not otherwise provided for
- B63B35/44—Floating buildings, stores, drilling platforms, or workshops, e.g. carrying water-oil separating devices
- B63B2035/4433—Floating structures carrying electric power plants
- B63B2035/446—Floating structures carrying electric power plants for converting wind energy into electric energy
-
- 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
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/70—Wind energy
- Y02E10/72—Wind turbines with rotation axis in wind direction
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Mechanical Engineering (AREA)
- Combustion & Propulsion (AREA)
- Structural Engineering (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Architecture (AREA)
- Civil Engineering (AREA)
- Oil, Petroleum & Natural Gas (AREA)
- General Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Ocean & Marine Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- General Engineering & Computer Science (AREA)
- Drying Of Gases (AREA)
Abstract
The invention provides a control system of dehumidifying equipment based on an offshore wind turbine, which comprises: the acquisition module is used for acquiring the humidity value and the working power value; the structuring module is used for arranging the humidity value and the working power value into a humidity input matrix and a power input matrix; the characteristic extraction module is used for extracting the humidity characteristic matrix and the power characteristic matrix through the two matrixes; the correction module is used for correcting the characteristic values of the two characteristic matrixes to obtain a corrected humidity characteristic matrix and a corrected power characteristic matrix; the responsiveness estimation module is used for calculating responsiveness estimation of the corrected power characteristic matrix relative to the corrected humidity characteristic matrix; and the control result generation module is used for passing the response estimation through the classifier to obtain a classification result, and the result is used for indicating whether the working power combination of the dehumidifier is reasonable or not. Based on the above, the working mode combination of a plurality of dehumidifiers of the offshore wind turbine can be intelligently controlled, and the dehumidification effect is optimized so as to ensure the normal operation of the offshore wind turbine.
Description
Technical Field
The invention relates to the field of intelligent dehumidification control of offshore fans, in particular to a control system and a method of dehumidification equipment of an offshore fan based on the Internet of things.
Background
The offshore wind turbine works in a high-humidity and high-salt environment for a long time. The metal equipment and facilities in the fan are easy to corrode. In general, the critical point of the relative humidity of metal corrosion is 45% -50%, corrosion occurs beyond the limit, the corrosion speed is increased along with the increase of the relative humidity, and once condensation occurs on steel, the corrosion process is more rapid.
At present, wind field fans are distributed and dispersed, and each fan is provided with a plurality of dehumidifiers according to different conditions. In the existing working mode of the dehumidifier, the dehumidifier is started in a fixed power mode, and if the dehumidification effect of one dehumidifier cannot meet the application requirement, a plurality of dehumidifiers are started.
The dehumidification efficiency and effect of the working mode are relatively low, and the dehumidification effect is better when the dehumidifier with a relatively close initial position is started because the humidity of the unused position in the application scene is different in the real application scene. Therefore, an optimized control system of the dehumidifying equipment of the offshore wind turbine is expected to intelligently control the operation mode combination of a plurality of dehumidifiers of the offshore wind turbine, thereby optimizing the dehumidifying effect and ensuring the normal operation of the offshore wind turbine.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems in the related art to some extent.
Therefore, a first object of the present invention is to provide a control system for a dehumidifying apparatus of an offshore wind turbine based on the internet of things, which can intelligently control the operation mode combination of a plurality of dehumidifiers of the offshore wind turbine, thereby optimizing the dehumidifying effect and ensuring the normal operation of the offshore wind turbine.
To achieve the above object, according to a first aspect of the present application, there is provided a control system of a dehumidifying apparatus of an offshore wind turbine based on the internet of things, comprising:
the acquisition module is used for acquiring a plurality of groups of humidity values acquired by a plurality of humidity sensors in the offshore wind turbine at a plurality of preset time points and a plurality of groups of working power values of a plurality of dehumidifiers at the plurality of preset time points;
the structuring module is used for arranging the multiple groups of humidity values into a humidity input matrix according to a humidity sample dimension and a time dimension and arranging the multiple groups of working power values into a power input matrix according to a power sample dimension and a time dimension;
the time sequence associated feature extraction module is used for extracting a humidity feature matrix and a power feature matrix through the humidity input matrix and the power input matrix;
The correction module is used for correcting the characteristic values of all the row vectors in the humidity characteristic matrix and the power characteristic matrix respectively to obtain a corrected humidity characteristic matrix and a corrected power characteristic matrix;
The responsiveness estimation module is used for calculating responsiveness estimation of the corrected power characteristic matrix relative to the corrected humidity characteristic matrix to obtain a classification characteristic matrix;
And the control result generation module is used for passing the classification characteristic matrix through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the combination of the working powers of the plurality of dehumidifiers at the current time point is reasonable or not.
Optionally, in an embodiment of the present application, the structuring module further includes:
The humidity time dimension arrangement sub-module is used for respectively arranging the plurality of groups of humidity values into row vectors according to the time dimension to obtain a plurality of humidity row vectors; and
And the humidity sample dimension arrangement sub-module is used for arranging the plurality of humidity row vectors into the humidity input matrix according to the humidity sample dimension.
Optionally, in an embodiment of the present application, the structuring module further includes:
The power time dimension arrangement sub-module is used for respectively arranging the plurality of groups of working power values into row vectors according to the time dimension to obtain a plurality of power row vectors; and
And the power sample dimension arrangement sub-module is used for arranging the plurality of power row vectors into the power input matrix according to the power sample dimension.
Optionally, in an embodiment of the present application, the timing related feature extraction module further includes: each layer of the first convolutional neural network performs input data in forward transfer of the layer:
carrying out convolution processing on input data to obtain a convolution characteristic diagram;
Carrying out local channel dimension-based mean pooling on the convolution feature map to obtain a pooled feature map; and
Non-linear activation is carried out on the pooled feature map so as to obtain an activated feature map;
The output of the last layer of the first convolutional neural network is the humidity characteristic matrix, and the input of the first layer of the first convolutional neural network is the humidity input matrix.
Optionally, in an embodiment of the present application, the timing related feature extraction module further includes: each layer of the second convolutional neural network performs input data in forward transfer of the layer:
carrying out convolution processing on input data to obtain a convolution characteristic diagram;
Carrying out local channel dimension-based mean pooling on the convolution feature map to obtain a pooled feature map; and
Non-linear activation is carried out on the pooled feature map so as to obtain an activated feature map;
The output of the last layer of the second convolutional neural network is the power characteristic matrix, and the input of the first layer of the second convolutional neural network is the power input matrix.
Optionally, in an embodiment of the present application, the correction module further includes: respectively carrying out eigenvalue correction on each row vector in the humidity characteristic matrix by using a formula (1) to obtain the corrected humidity characteristic matrix;
wherein, the formula (1) is:
Wherein B 1' represents the corrected humidity characteristic matrix, B 1 represents the individual row vectors in the humidity characteristic matrix, Indicating the inverse of the mean value of all eigenvalues of each row vector in the humidity eigenvector matrix, and as such, indicates multiplication by location.
Optionally, in an embodiment of the present application, the correction module further includes: respectively carrying out eigenvalue correction on each row vector in the power eigenvalue matrix by using a formula (2) to obtain a corrected power eigenvalue matrix;
Wherein, the formula (2) is:
Wherein B 2' represents the corrected power matrix, V 2 represents the individual row vectors in the power feature matrix, Indicating the inverse of the mean value of all eigenvalues of each row vector in the power eigenvector matrix, as indicated by the dot product by location.
Optionally, in an embodiment of the present application, the responsiveness estimation module further includes: calculating a responsiveness estimate of the corrected power feature matrix relative to the corrected humidity feature matrix using equation (3) to obtain the classification feature matrix;
Wherein, the formula (3) is:
M1＝M*M2
Wherein M 1 represents the corrected power feature matrix, M 2 represents the corrected humidity feature matrix, and M represents the classification feature matrix.
Optionally, in an embodiment of the present application, the control result generating module further includes: the classifier processes the classification feature matrix with formula (4) to generate a classification result, wherein formula (4) is: softmax { (W n,Bn)：...：(W1,B1) |project (F) }, where Project (F) represents the projection of the classification feature matrix as a vector, W 1 to W n are weight matrices for each fully connected layer, and B 1 to B n represent bias matrices for each fully connected layer.
To achieve the above object, according to a second aspect of the present application, a method for controlling a dehumidifying apparatus of an offshore wind turbine based on the internet of things, includes:
acquiring a plurality of sets of humidity values acquired at a plurality of preset time points by a plurality of humidity sensors deployed in an offshore wind turbine and a plurality of sets of working power values of a plurality of dehumidifiers at the plurality of preset time points;
arranging the multiple groups of humidity values into a humidity input matrix according to a humidity sample dimension and a time dimension, and arranging the multiple groups of working power values into a power input matrix according to a power sample dimension and a time dimension;
Extracting a humidity power matrix and a power characteristic matrix through the humidity input matrix and the power input matrix;
Respectively carrying out eigenvalue correction on each row vector in the humidity characteristic matrix and the power characteristic matrix to obtain a corrected humidity characteristic matrix and a corrected power characteristic matrix;
calculating the response estimation of the corrected power characteristic matrix relative to the corrected humidity characteristic matrix to obtain a classification characteristic matrix; and
And the classification feature matrix passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the combination of the working powers of the plurality of dehumidifiers at the current time point is reasonable.
In summary, according to the control system and the method for the dehumidification device of the offshore wind turbine based on the internet of things provided by the application, based on the acquired humidity values and the working power values, dynamic implicit association feature extraction is respectively carried out on the humidity values of a plurality of positions of the offshore wind turbine and the working power values of a plurality of dehumidifiers in the time dimension, and the obtained feature matrix is subjected to phase-aware position-wise aggregation along the vector of the time dimension, so that inductive bias possibly caused when the subsequent classification feature matrix carries out real-value classification tasks without position attribute is compensated in a multi-layer perception mode, and the classification accuracy of the classification feature matrix is enhanced. Based on the above, the working mode combination of a plurality of dehumidifiers of the offshore wind turbine can be intelligently controlled, so that the dehumidification effect is optimized, and the normal operation of the offshore wind turbine is ensured.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing embodiments of the present application in more detail with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and together with the embodiments of the application, and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.
Fig. 1 is an application scenario diagram of a control system of a dehumidifying apparatus of an offshore wind turbine based on the internet of things provided by an embodiment of the present application;
Fig. 2a is a block diagram of a control system of a dehumidifying apparatus of an offshore wind turbine based on the internet of things according to an embodiment of the present application;
fig. 2b is a block diagram of a control method of a dehumidifying apparatus of an offshore wind turbine based on the internet of things according to an embodiment of the present application;
fig. 2c is a block diagram of another control method of a dehumidifying apparatus of an offshore wind turbine based on the internet of things according to an embodiment of the present application;
fig. 3 is a flow chart of a control method of a dehumidifying device of an offshore wind turbine based on the internet of things according to an embodiment of the present application;
fig. 4 is a schematic diagram of a control method of a dehumidifying apparatus of an offshore wind turbine based on the internet of things according to an embodiment of the present application.
Detailed Description
Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
Fig. 1 is an application scenario diagram of a control system of a dehumidifying apparatus of an offshore wind turbine based on the internet of things provided by an embodiment of the present application. As shown in fig. 1, in this application scenario, first, a plurality of sets of humidity values are acquired at a plurality of predetermined time points by a plurality of humidity sensors (e.g., T as illustrated in fig. 1) disposed within an offshore wind turbine (e.g., F as illustrated in fig. 1), and a plurality of sets of operating power values of a plurality of dehumidifiers (e.g., D as illustrated in fig. 1) at a plurality of predetermined time points are acquired by a power detector (e.g., P as illustrated in fig. 1). Then, the obtained plurality of sets of humidity values collected at the plurality of predetermined time points and the plurality of sets of operating power values of the plurality of dehumidifiers at the plurality of predetermined time points are input into a server (for example, a cloud server S as illustrated in fig. 1) in which a control algorithm of the dehumidifying apparatus of the internet-of-things-based offshore wind turbine is deployed, wherein the server is capable of processing the plurality of sets of humidity values collected at the plurality of predetermined time points and the plurality of sets of operating power values of the plurality of dehumidifiers at the plurality of predetermined time points with the control algorithm of the dehumidifying apparatus of the internet-of-things-based offshore wind turbine to generate a classification result indicating whether a combination of operating powers of the plurality of dehumidifiers at the current time point is reasonable.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Fig. 2a is a block diagram of a control system of a dehumidifying apparatus of an offshore wind turbine based on the internet of things according to an embodiment of the present application. As shown in fig. 2a, a control system 200 of a dehumidifying apparatus of an offshore wind turbine based on the internet of things according to an embodiment of the present application includes:
A humidity data acquisition module 201, configured to acquire a plurality of sets of humidity values acquired at a plurality of predetermined time points by a plurality of humidity sensors deployed in an offshore wind turbine and a plurality of sets of working power values of a plurality of dehumidifiers at the plurality of predetermined time points;
A data structuring module 202, configured to arrange a plurality of sets of humidity values into a humidity input matrix according to a humidity sample dimension and a time dimension, and a plurality of sets of working power values into a power input matrix according to a power sample dimension and a time dimension;
The time sequence associated feature extraction module 203 is configured to pass the humidity input matrix and the power input matrix through a first convolutional neural network and a second convolutional neural network serving as feature extractors to obtain a power feature matrix;
The correction module 204 is configured to perform eigenvalue correction on each row vector in the humidity eigenvalue matrix and the power eigenvalue matrix to obtain a corrected humidity eigenvalue matrix and a corrected power eigenvalue matrix;
a responsiveness estimation module 205, configured to calculate responsiveness estimation of the corrected power feature matrix relative to the corrected humidity feature matrix to obtain a classification feature matrix;
The control result generating module 206 is configured to pass the classification feature matrix through a classifier to obtain a classification result, where the classification result is used to indicate whether the combination of the working powers of the plurality of dehumidifiers at the current time point is reasonable.
The humidity data acquisition module 201 is configured to acquire a plurality of sets of humidity values acquired at a plurality of predetermined time points by a plurality of humidity sensors disposed in the offshore wind turbine and a plurality of sets of working power values of a plurality of dehumidifiers at a plurality of predetermined time points. In the embodiment of the application, because the humidity of each position of the offshore wind turbine may be different in an actual application scene, the power values of the plurality of humidity sensors need to be dynamically adjusted accordingly according to the dynamic change characteristics of the humidity values of the different positions, so that the dehumidification effect is better.
And a structuring module 202 for arranging the plurality of sets of humidity values into a humidity input matrix according to a humidity sample dimension and a time dimension and the plurality of sets of working power values into a power input matrix according to a power sample dimension and a time dimension. The dynamic associated characteristic information of a plurality of sets of humidity values and a plurality of sets of working power values in time sequence can be fully mined. In the embodiment of the application, the correlation matrix of humidity and working power and time can be respectively constructed, a plurality of groups of humidity values are arranged into a humidity input matrix according to the dimension of a humidity sample and the dimension of time, and a plurality of groups of working power values are arranged into a power input matrix according to the dimension of a power sample and the dimension of time. Specifically, in the embodiment of the present application, for convenience of explanation, please refer to fig. 2b and fig. 2c, and fig. 2b is a schematic diagram of a data structure module of a control system of an offshore wind turbine dehumidification device according to an embodiment of the present application. As shown in fig. 2b, the data structuring module 202 further comprises: a humidity time dimension arrangement sub-module 2021 for respectively arranging a plurality of sets of humidity values into row vectors according to a time dimension to obtain a plurality of humidity row vectors, and a humidity sample dimension arrangement sub-module 2022 for arranging the plurality of humidity row vectors into a humidity input matrix according to a humidity sample dimension. Fig. 2c is a schematic diagram of a data structure module of another control system for a dehumidifying apparatus of an offshore wind turbine according to an embodiment of the present application. As shown in fig. 2c, the data structuring module 202 further comprises: a power time dimension arrangement sub-module 2023, configured to arrange multiple sets of working power values into row vectors according to a time dimension respectively to obtain multiple power row vectors; and a power sample dimension arrangement sub-module 2024 for arranging the plurality of power row vectors into a power input matrix in a power sample dimension.
And a time sequence correlation feature extraction module 203, configured to pass the humidity input matrix and the power input matrix through a first convolutional neural network and a second convolutional neural network as feature extractors, respectively, so as to obtain a power feature matrix. It should be noted that, in the embodiment of the present application, since the convolutional neural network model has excellent performance in terms of implicit associated feature extraction, the convolutional neural network serving as the feature extractor is further used to perform feature mining of deep association on the humidity input matrix and the power input matrix, respectively, so as to obtain a humidity feature matrix with humidity dynamic implicit associated feature information in a time sequence dimension and a power feature matrix with power dynamic implicit associated feature information in a time sequence dimension. Specifically, in the embodiment of the present application, the timing related feature extraction module 203 further includes: each layer of the first convolutional neural network performs on input data in forward transfer of the layer: carrying out convolution processing on input data to obtain a convolution characteristic diagram; carrying out local channel dimension-based mean pooling on the convolution feature map to obtain a pooled feature map; performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the first convolutional neural network is a humidity characteristic matrix, and the input of the first layer of the first convolutional neural network is a humidity input matrix. More specifically, in the embodiment of the present application, the timing related feature extraction module 203 further includes: each layer of the second convolutional neural network performs the following steps on input data in forward transfer of the layer: carrying out convolution processing on input data to obtain a convolution characteristic diagram; carrying out local channel dimension-based mean pooling on the convolution feature map to obtain a pooled feature map; performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the second convolutional neural network is a power characteristic matrix, and the input of the first layer of the second convolutional neural network is a power input matrix.
And a correction module 204, configured to perform eigenvalue correction on each row vector in the humidity eigenvector and the power eigenvector to obtain a corrected humidity eigenvector and a corrected power eigenvector. It should be noted that, for both the power feature matrix and the humidity feature matrix, since the source data thereof has periodic features in the time dimension, this results in the feature matrix having a phase response with respect to periodicity between the distributions of feature values in the time dimension after feature extraction. In addition, when the classification feature matrix is classified by the classifier, the classification feature matrix is projected into a linear feature vector, so that the classification problem is independent of the position of the feature matrix, which leads to loss of phase response information and influences the classification accuracy. Thus, after the power and humidity feature matrices are obtained, it is necessary to perform a phase-aware per-position aggregation of its vectors (e.g., row vectors) along the time dimension. The phase perception representation of the aggregated vector introduces the real-value-imaginary value representation of the amplitude-phase, and the vector is spliced and unfolded according to the position based on the principle of the Euler formula, so that the induction bias possibly caused when the subsequent classification feature matrix performs the real-value classification task without the position attribute is compensated in a multi-layer perception mode, and the classification accuracy of the classification feature matrix is enhanced. Specifically, in the embodiment of the present application, the correction module 204 further includes: respectively correcting the characteristic values of each row vector in the humidity characteristic matrix by using a formula (1) to obtain a corrected humidity characteristic matrix;
wherein, formula (1) is:
Where V 1 represents the individual row vectors in the wetness characteristic matrix, Indicating the inverse of the mean value of all eigenvalues of each row vector in the humidity eigenvector, and by-position point multiplication.
Specifically, in the embodiment of the present application, the correction module further includes: respectively correcting the eigenvalues of each row vector in the power eigenvector by using a formula (2) to obtain a corrected power eigenvector;
wherein, formula (2) is:
Wherein B 2' represents the corrected power matrix, V 2 represents the individual row vectors in the power feature matrix, Indicating the inverse of the mean value of all eigenvalues of each row vector in the power eigenvector, and by-position point multiplication.
And a responsiveness estimation module 205, configured to calculate a responsiveness estimate of the corrected power feature matrix relative to the corrected humidity feature matrix to obtain a classification feature matrix. It should be noted that the dynamic implicit correlation feature due to the working power may be regarded as a responsive feature to the dynamic implicit correlation feature of humidity in the high-dimensional feature space. In order to enable the fused classification feature matrix to accurately classify, the responsiveness estimation of the corrected power feature matrix relative to the corrected humidity feature matrix is further calculated to obtain the classification feature matrix. Specifically, in the embodiment of the present application, the responsiveness estimation module 205 is further configured to: calculating the response estimation of the corrected power characteristic matrix relative to the corrected humidity characteristic matrix by using a formula (3) to obtain a classification characteristic matrix;
wherein, formula (3) is:
M1＝M*M2
Where M 1 represents the corrected power feature matrix, M 2 represents the corrected humidity feature matrix, and M represents the classification feature matrix.
And a control result generating module 206, configured to pass the classification feature matrix through a classifier to obtain a classification result, where the classification result may be used to indicate whether the combination of the working powers of the plurality of dehumidifiers at the current time point is reasonable. That is, in the embodiment of the present application, the classification feature matrix is further passed through the classifier to obtain a classification result for indicating whether the combination of the working powers of the plurality of dehumidifiers at the current time point is reasonable. Specifically, in the embodiment of the present application, the classifier may process the classification feature matrix according to formula (4) to generate a classification result, where formula (4) is: softmax { (W n,Bn)：...：(W1,B1) |project (F) }, where Project (F) represents projection of the classification feature matrix as a vector, W 1 to W n are weight matrices of each layer of fully connected layers, and B 1 to B n represent bias matrices of each layer of fully connected layers.
In summary, in the control system 200 of the offshore wind turbine dehumidification device based on the internet of things provided by the application, the plurality of groups of humidity values and the power values of the plurality of dehumidifiers are collected by the collection module 201, the humidity values and the working power values are used as input data to form an input matrix by the structuring module 202, and then the respective characteristic information is extracted and processed by the time sequence association characteristic extraction module 203, the correction module 204 and the responsiveness estimation module 205 to classify the characteristic matrix in a high-dimensional space, and then the classifier is used to analyze the classified characteristic matrix to judge whether the working power combination of the plurality of dehumidifiers at the current time point is reasonable or not so as to optimize the dehumidification effect of the plurality of dehumidifiers. Based on the method, the system collects the humidity value and the working power value, performs dynamic implicit association feature extraction on the humidity value and the working power value in the time dimension through a convolutional neural network model based on deep learning, and performs phase-aware position-based aggregation on the obtained feature matrix along the vector of the time dimension, so that induction bias possibly caused when a subsequent classification feature matrix performs a real-value classification task without position attribute is compensated in a multi-layer perception mode, and classification accuracy of the classification feature matrix is enhanced. The working modes of the plurality of dehumidifiers for intelligently controlling the offshore wind turbine are combined, so that the dehumidification effect is optimized, and the normal operation of the offshore wind turbine is ensured.
In addition, the control system 200 of the dehumidifying apparatus of an offshore wind turbine based on the internet of things according to the embodiment of the application may be implemented in various terminal apparatuses, for example, a server or the like of a control algorithm of the dehumidifying apparatus of an offshore wind turbine based on the internet of things. In one example, the control system 200 of the dehumidifying apparatus of an offshore wind turbine based on the internet of things according to an embodiment of the present application may be integrated into the terminal apparatus as one software module and/or hardware module. For example, the control system 200 of the dehumidifying apparatus of an offshore wind turbine based on the internet of things may be a software module in the operating system of the terminal apparatus, or may be an application developed for the terminal apparatus; of course, the control system 200 of the dehumidifying apparatus of the offshore wind turbine based on the internet of things can be one of a plurality of hardware modules of the terminal apparatus.
Alternatively, in another example, the control system 200 of the dehumidifying apparatus of the internet of things-based offshore wind turbine and the terminal apparatus may be separate apparatuses, and the control system 200 of the dehumidifying apparatus of the internet of things-based offshore wind turbine may be connected to the terminal apparatus through a wired and/or wireless network and transmit the interactive information according to an agreed data format.
Fig. 3 illustrates a flowchart of a control method of a dehumidifying apparatus of an offshore wind turbine based on the internet of things. As shown in fig. 3, a control method of a dehumidifying apparatus of an offshore wind turbine based on internet of things according to an embodiment of the present application includes the steps of:
S301, acquiring a plurality of sets of humidity values acquired at a plurality of preset time points by a plurality of humidity sensors deployed in the offshore wind turbine and a plurality of sets of working power values of a plurality of dehumidifiers at a plurality of preset time points.
S302, arranging a plurality of groups of humidity values into a humidity input matrix according to a humidity sample dimension and a time dimension, and arranging a plurality of groups of working power values into a power input matrix according to a power sample dimension and a time dimension.
And S303, passing the humidity input matrix and the power input matrix through a first convolutional neural network and a second convolutional neural network which are feature extractors to obtain a power feature matrix.
S304, respectively carrying out eigenvalue correction on each row vector in the humidity eigenvector and the power eigenvector to obtain a corrected humidity eigenvector and a corrected power eigenvector.
S305, calculating the response estimation of the corrected power characteristic matrix relative to the corrected humidity characteristic matrix to obtain a classification characteristic matrix.
S306, the classification feature matrix is passed through a classifier to obtain a classification result, and the classification result is used for indicating whether the combination of the working powers of the plurality of dehumidifiers at the current time point is reasonable.
It should be noted that, the foregoing explanation of the embodiment of the control system of the offshore wind turbine dehumidification device based on the internet of things is also applicable to the method of the embodiment, and reference may be made to the related description of the foregoing embodiment, which is not repeated herein.
In summary, according to the control method of the dehumidification device of the offshore wind turbine based on the internet of things provided by the application, the multiple groups of humidity values collected by the multiple humidity sensors in the offshore wind turbine and the power values of the multiple dehumidifiers are used as input data to respectively extract the respective characteristic information and process the respective characteristic information to classify the characteristic matrixes in the high-dimensional space, and then the classifier is used for analyzing the classifying characteristic matrixes so as to judge whether the working power combination of the multiple dehumidifiers at the current time point is reasonable or not, so that the dehumidification effect of the multiple dehumidifiers is optimized. Based on the method, humidity values and working power values can be collected first, dynamic implicit association feature extraction is carried out on the humidity values and the working power values in the time dimension respectively through a convolutional neural network model based on deep learning, and the obtained feature matrix is subjected to phase-aware position-based aggregation along the vector of the time dimension, so that induction bias possibly caused when a subsequent classification feature matrix carries out real-value classification task without position attribute is compensated in a multi-layer perception mode, and classification accuracy of the classification feature matrix is enhanced. The working modes of the plurality of dehumidifiers for intelligently controlling the offshore wind turbine are combined, so that the dehumidification effect is optimized, and the normal operation of the offshore wind turbine is ensured.
Fig. 4 illustrates an architecture diagram of a control method of a dehumidifying apparatus of an offshore wind turbine based on the internet of things according to an embodiment of the present application. As shown in fig. 4, in a network architecture of a control method of a dehumidifying apparatus of an offshore wind turbine based on the internet of things, first, a plurality of obtained sets of humidity values (e.g., P1 as illustrated in fig. 4) are arranged as a humidity input matrix (e.g., M1 as illustrated in fig. 4) in a humidity sample dimension and a time dimension; next, the obtained sets of operating power values (e.g., P2 as illustrated in fig. 4) are arranged in a power sample dimension and a time dimension into a power input matrix (e.g., M2 as illustrated in fig. 4); then, passing the wetness input matrix through a first convolutional neural network (e.g., CNN1 as illustrated in fig. 4) as a feature extractor to obtain a wetness feature matrix (e.g., MF1 as illustrated in fig. 4); next, the power input matrix is passed through a second convolutional neural network (e.g., CNN2 as illustrated in fig. 4) as a feature extractor to obtain a power feature matrix (e.g., MF2 as illustrated in fig. 4); then, performing eigenvalue correction on each row vector in the humidity eigenvector to obtain a corrected humidity eigenvector (for example, MF3 as illustrated in fig. 4); then, performing eigenvalue correction on each row vector in the power eigenvector to obtain a corrected power eigenvector (e.g., MF4 as illustrated in fig. 4); then, calculating a responsiveness estimate of the corrected power feature matrix relative to the corrected humidity feature matrix to obtain a classification feature matrix (e.g., MF as illustrated in fig. 4); and finally, passing the classification feature matrix through a classifier (for example, the classifier as illustrated in fig. 4) to obtain a classification result, wherein the classification result is used for indicating whether the combination of the working powers of the plurality of dehumidifiers at the current time point is reasonable.
Specifically, in step S301, a plurality of sets of humidity values acquired at a plurality of predetermined time points by a plurality of humidity sensors disposed in the offshore wind turbine and a plurality of sets of operation power values of a plurality of dehumidifiers at a plurality of predetermined time points are acquired. It should be understood that, in practical application, the humidity of each position of the offshore wind turbine is different, so in the technical scheme of the application, the power values of the plurality of humidity sensors need to be dynamically adjusted correspondingly according to the dynamic change characteristics of the humidity values of different positions, so that the dehumidification effect is better. That is, a plurality of sets of humidity values collected by a plurality of humidity sensors in the offshore wind turbine and power values of a plurality of dehumidifiers are used as input data to extract characteristic distribution representations of respective characteristic information in a high-dimensional space respectively, and then a classifier is used for classifying and judging whether working power combinations of the plurality of dehumidifiers at the current time point are reasonable or not so as to optimize the dehumidification effect of the plurality of dehumidifiers.
In step S302, a plurality of sets of humidity values are arranged as a humidity input matrix in a humidity sample dimension and a time dimension and a plurality of sets of operating power values are arranged as a power input matrix in a power sample dimension and a time dimension. It should be understood that, in order to fully mine dynamic association characteristic information of multiple sets of humidity values and multiple sets of working power values in time sequence, in the technical scheme of the application, firstly, association matrixes of humidity and working power and time are required to be respectively constructed.
In step S303, the humidity input matrix and the power input matrix are passed through a first convolutional neural network and a second convolutional neural network as feature extractors to obtain a power feature matrix. It should be understood that, considering that the convolutional neural network model has excellent performance in terms of implicit associated feature extraction, in the technical solution of the present application, the convolutional neural network serving as a feature extractor is further used to perform feature mining of deep association on the humidity input matrix and the power input matrix, respectively, so as to obtain a humidity feature matrix with humidity dynamic implicit associated feature information in a time sequence dimension and a power feature matrix with power dynamic implicit associated feature information in a time sequence dimension.
In step S304, feature value correction is performed on each row vector in the humidity feature matrix and the power feature matrix, so as to obtain a corrected humidity feature matrix and a corrected power feature matrix. It should be appreciated that for both the power and humidity signature matrices, since the source data has periodic signatures in the time dimension, this results in a signature matrix having a phase response relative to periodicity between the distribution of signature values along the time dimension after the signature extraction. On the other hand, when the classification feature matrix is classified by the classifier, the classification feature matrix is projected into a linear feature vector, so that the classification problem is independent of the position of the feature matrix, which leads to loss of phase response information and influences the classification accuracy. Therefore, in the technical scheme of the application, after the power characteristic matrix and the humidity characteristic matrix are obtained, the vectors (for example, row vectors) along the time dimension are further subjected to phase-aware position-by-position aggregation. That is, the phase perception representation of the aggregated vector introduces the real-value-imaginary-value representation of the amplitude-phase, and the vector is spliced and unfolded according to the position based on the principle of the Euler formula, so that the induction bias possibly caused when the subsequent classification feature matrix performs the real-value classification task without the position attribute is compensated in the form of multi-layer perception, and the classification accuracy of the classification feature matrix is enhanced.
In steps S305 and S306, the responsiveness estimation of the corrected power feature matrix with respect to the corrected humidity feature matrix is calculated to obtain a classification feature matrix, and the classification feature matrix is passed through a classifier to obtain a classification result, where the classification result is used to indicate whether the combination of the working powers of the plurality of dehumidifiers at the current time point is reasonable. It should be understood that, considering that the dynamic change implicit correlation feature of the working power can be regarded as the response feature of the dynamic implicit correlation feature of the humidity in the high-dimensional feature space, in the technical scheme of the application, in order to enable the fused classification feature matrix to accurately classify, the response estimation of the corrected power feature matrix relative to the corrected humidity feature matrix is further calculated to obtain the classification feature matrix. And further, the classification feature matrix passes through a classifier to obtain a classification result for indicating whether the combination of the working powers of the plurality of dehumidifiers at the current time point is reasonable.
In summary, the control method of the dehumidifying equipment of the offshore wind turbine based on the Internet of things is explained, which is used for respectively carrying out dynamic implicit association feature extraction on humidity values of a plurality of positions of the offshore wind turbine and working power values of a plurality of dehumidifiers in a time dimension through a convolutional neural network model based on deep learning, and carrying out phase-aware position-based aggregation on vectors of the obtained feature matrix along the time dimension, so that induction bias possibly caused when a subsequent classification feature matrix carries out real-value classification task without position attribute is compensated in a multi-layer perception mode, and classification accuracy of the classification feature matrix is enhanced. Thus, the working mode combination of a plurality of dehumidifiers of the offshore wind turbine can be intelligently controlled, so that the dehumidification effect is optimized, and the normal operation of the offshore wind turbine is ensured.
The basic principles of the present application have been described above in connection with specific embodiments, but it should be noted that the advantages, benefits, effects, etc. mentioned in the present application are merely examples and not intended to be limiting, and these advantages, benefits, effects, etc. are not to be construed as necessarily possessed by the various embodiments of the application. Furthermore, the specific details disclosed herein are for purposes of illustration and understanding only, and are not intended to be limiting, as the application is not necessarily limited to practice with the above described specific details.
The block diagrams of the devices, apparatuses, devices, systems referred to in the present application are only illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be made in the manner shown in the block diagrams. As will be appreciated by one of skill in the art, the devices, apparatuses, devices, systems may be connected, arranged, configured in any manner. Words such as "including," "comprising," "having," and the like are words of openness and mean "including but not limited to," and are used interchangeably therewith. The terms "or" and "as used herein refer to and are used interchangeably with the term" and/or "unless the context clearly indicates otherwise. The term "such as" as used herein refers to, and is used interchangeably with, the phrase "such as, but not limited to.
It is also noted that in the apparatus, devices and methods of the present application, the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present application.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit embodiments of the application to the form disclosed herein. Although a number of example aspects and embodiments have been discussed above, a person of ordinary skill in the art will recognize certain variations, modifications, alterations, additions, and subcombinations thereof.
Claims (10)
1. Control system of dehumidification equipment of marine fan based on thing networking, its characterized in that includes:
the acquisition module is used for acquiring a plurality of groups of humidity values acquired by a plurality of humidity sensors in the offshore wind turbine at a plurality of preset time points and a plurality of groups of working power values of a plurality of dehumidifiers at the plurality of preset time points;
the structuring module is used for arranging the multiple groups of humidity values into a humidity input matrix according to a humidity sample dimension and a time dimension and arranging the multiple groups of working power values into a power input matrix according to a power sample dimension and a time dimension;
the time sequence associated feature extraction module is used for extracting a humidity feature matrix and a power feature matrix through the humidity input matrix and the power input matrix;
The correction module is used for correcting the characteristic values of all the row vectors in the humidity characteristic matrix and the power characteristic matrix respectively to obtain a corrected humidity characteristic matrix and a corrected power characteristic matrix;
The responsiveness estimation module is used for calculating responsiveness estimation of the corrected power characteristic matrix relative to the corrected humidity characteristic matrix to obtain a classification characteristic matrix;
And the control result generation module is used for passing the classification characteristic matrix through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the combination of the working powers of the plurality of dehumidifiers at the current time point is reasonable or not.
2. The control system of an internet of things based offshore wind turbine dehumidification device of claim 1, wherein the structuring module further comprises:
The humidity time dimension arrangement sub-module is used for respectively arranging the plurality of groups of humidity values into row vectors according to the time dimension to obtain a plurality of humidity row vectors; and
And the humidity sample dimension arrangement sub-module is used for arranging the plurality of humidity row vectors into the humidity input matrix according to the humidity sample dimension.
3. The control system of an internet of things based offshore wind turbine dehumidification device of claim 2, wherein the structuring module further comprises:
The power time dimension arrangement sub-module is used for respectively arranging the plurality of groups of working power values into row vectors according to the time dimension to obtain a plurality of power row vectors; and
And the power sample dimension arrangement sub-module is used for arranging the plurality of power row vectors into the power input matrix according to the power sample dimension.
4. The control system of a dehumidifying device of an offshore wind turbine based on the internet of things as claimed in claim 3, wherein the time-series-associated feature extraction module further comprises: each layer of the first convolutional neural network performs input data in forward transfer of the layer:
carrying out convolution processing on input data to obtain a convolution characteristic diagram;
Carrying out local channel dimension-based mean pooling on the convolution feature map to obtain a pooled feature map; and
Non-linear activation is carried out on the pooled feature map so as to obtain an activated feature map;
The output of the last layer of the first convolutional neural network is the humidity characteristic matrix, and the input of the first layer of the first convolutional neural network is the humidity input matrix.
5. The control system of a dehumidifying device of an offshore wind turbine based on the internet of things as claimed in claim 4, wherein the time-series-associated feature extraction module further comprises: each layer of the second convolutional neural network performs input data in forward transfer of the layer:
carrying out convolution processing on input data to obtain a convolution characteristic diagram;
Carrying out local channel dimension-based mean pooling on the convolution feature map to obtain a pooled feature map; and
Non-linear activation is carried out on the pooled feature map so as to obtain an activated feature map;
The output of the last layer of the second convolutional neural network is the power characteristic matrix, and the input of the first layer of the second convolutional neural network is the power input matrix.
6. The control system of an internet of things-based offshore wind turbine dehumidification device of claim 5, wherein the correction module further comprises: respectively carrying out eigenvalue correction on each row vector in the humidity characteristic matrix by using a formula (1) to obtain the corrected humidity characteristic matrix;
wherein, the formula (1) is:
Wherein V 1' represents the corrected humidity characteristic matrix, V 1 represents each row vector in the humidity characteristic matrix, Indicating the inverse of the mean value of all eigenvalues of each row vector in the humidity eigenvector matrix, and as such, indicates multiplication by location.
7. The control system of an internet of things-based offshore wind turbine dehumidification device of claim 6, wherein the correction module further comprises: respectively carrying out eigenvalue correction on each row vector in the power eigenvalue matrix by using a formula (2) to obtain a corrected power eigenvalue matrix;
Wherein, the formula (2) is:
Where V 2' represents the corrected power matrix, V 2 represents the individual row vectors in the power feature matrix, Indicating the inverse of the mean value of all eigenvalues of each row vector in the power eigenvector matrix, as indicated by the dot product by location.
8. The control system of an internet of things-based offshore wind turbine dehumidification device of claim 7, wherein the responsiveness estimation module further comprises: calculating a responsiveness estimate of the corrected power feature matrix relative to the corrected humidity feature matrix using equation (3) to obtain the classification feature matrix;
Wherein, the formula (3) is:
M1＝M*M2
Wherein M 1 represents the corrected power feature matrix, M 2 represents the corrected humidity feature matrix, and M represents the classification feature matrix.
9. The control system of a dehumidifying device of an offshore wind turbine based on the internet of things of claim 8, wherein the control result generating module further comprises: the classifier processes the classification feature matrix with formula (4) to generate a classification result, wherein formula (4) is: softmax { (W n,Bn):…:(W1,B1) |project (F) }, where Project (F) represents the projection of the classification feature matrix as a vector, W 1 to W n are weight matrices for each fully connected layer, and B 1 to B n represent bias matrices for each fully connected layer.
10. The control method of the dehumidifying equipment of the offshore wind turbine based on the Internet of things is characterized by comprising the following steps of:
acquiring a plurality of sets of humidity values acquired at a plurality of preset time points by a plurality of humidity sensors deployed in an offshore wind turbine and a plurality of sets of working power values of a plurality of dehumidifiers at the plurality of preset time points;
arranging the multiple groups of humidity values into a humidity input matrix according to a humidity sample dimension and a time dimension, and arranging the multiple groups of working power values into a power input matrix according to a power sample dimension and a time dimension;
Extracting a humidity power matrix and a power characteristic matrix through the humidity input matrix and the power input matrix;
Respectively carrying out eigenvalue correction on each row vector in the humidity characteristic matrix and the power characteristic matrix to obtain a corrected humidity characteristic matrix and a corrected power characteristic matrix;
calculating the response estimation of the corrected power characteristic matrix relative to the corrected humidity characteristic matrix to obtain a classification characteristic matrix; and
And the classification feature matrix passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the combination of the working powers of the plurality of dehumidifiers at the current time point is reasonable.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211292793.XA CN117967529A (en) | 2022-10-21 | 2022-10-21 | Control system and method for dehumidifying equipment of offshore wind turbine based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211292793.XA CN117967529A (en) | 2022-10-21 | 2022-10-21 | Control system and method for dehumidifying equipment of offshore wind turbine based on Internet of things |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117967529A true CN117967529A (en) | 2024-05-03 |
Family
ID=90844661
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211292793.XA Pending CN117967529A (en) | 2022-10-21 | 2022-10-21 | Control system and method for dehumidifying equipment of offshore wind turbine based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117967529A (en) |
-
2022
- 2022-10-21 CN CN202211292793.XA patent/CN117967529A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111414987B (en) | Training method and training device of neural network and electronic equipment | |
| CN109462521B (en) | Network flow abnormity detection method suitable for source network load interaction industrial control system | |
| CN115013298B (en) | Real-time performance online monitoring system and monitoring method of sewage pump | |
| CN115357065B (en) | Remote intelligent dehumidification control system and method for offshore wind turbine | |
| CN115328228B (en) | High-frequency switching power supply | |
| CN108204341A (en) | Method and device for identifying operating state of wind power plant | |
| CN115481677A (en) | Intelligent control system and method for hoisting blade of offshore wind turbine | |
| CN116934304A (en) | Intelligent power distribution room equipment operation maintenance management system and method thereof | |
| CN115456047A (en) | Offshore wind turbine structure state monitoring system and method based on artificial intelligence | |
| CN116844088A (en) | Online dust remover control system and method thereof | |
| CN116577464A (en) | Intelligent monitoring system and method for atmospheric pollution | |
| CN114627369A (en) | Environment monitoring system, method and computer device thereof | |
| CN111798518A (en) | Mechanical arm posture detection method, device and equipment and computer storage medium | |
| Zoltowski et al. | Sparsity-promoting optimal control of spatially-invariant systems | |
| CN117967529A (en) | Control system and method for dehumidifying equipment of offshore wind turbine based on Internet of things | |
| CN116827685B (en) | Dynamic defense strategy method of micro-service system based on deep reinforcement learning | |
| CN108459585B (en) | Power station fan fault diagnosis method based on sparse local embedded deep convolutional network | |
| CN115617636A (en) | Distributed performance test system | |
| CN115456259A (en) | Wind power plant site selection optimization system and method based on mesoscale data | |
| CN115419556A (en) | Land fan defect detection system and method | |
| WO2018142694A1 (en) | Feature amount generation device, feature amount generation method, and program | |
| CN115788793A (en) | Global monitoring and early warning method and system thereof | |
| US20190146469A1 (en) | System and method for facilitating comprehensive control data for a device | |
| US20230177393A1 (en) | Machine learning apparatus, machine learning system, machine learning method, and program | |
| CN113393453A (en) | Method, apparatus, device, medium and product for detecting self-bursting insulators |
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 |