CN117494591B - Wind power electric energy quality assessment method and device - Google Patents
Wind power electric energy quality assessment method and device Download PDFInfo
- Publication number
- CN117494591B CN117494591B CN202410005272.4A CN202410005272A CN117494591B CN 117494591 B CN117494591 B CN 117494591B CN 202410005272 A CN202410005272 A CN 202410005272A CN 117494591 B CN117494591 B CN 117494591B
- Authority
- CN
- China
- Prior art keywords
- layer
- electric energy
- model
- convolution
- training
- 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.)
- Active
Links
- 238000001303 quality assessment method Methods 0.000 title claims abstract description 23
- 238000013441 quality evaluation Methods 0.000 claims abstract description 73
- 238000012549 training Methods 0.000 claims abstract description 61
- 239000013598 vector Substances 0.000 claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 21
- 238000011156 evaluation Methods 0.000 claims abstract description 12
- 230000001052 transient effect Effects 0.000 claims abstract description 10
- 238000004088 simulation Methods 0.000 claims abstract description 7
- 241000283153 Cetacea Species 0.000 claims description 62
- 238000011176 pooling Methods 0.000 claims description 40
- 230000006870 function Effects 0.000 claims description 34
- 230000010355 oscillation Effects 0.000 claims description 20
- 238000004422 calculation algorithm Methods 0.000 claims description 15
- 238000013507 mapping Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 12
- 230000004913 activation Effects 0.000 claims description 8
- 210000002569 neuron Anatomy 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 description 7
- 238000005070 sampling Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000009628 steelmaking Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- 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
Abstract
The invention discloses a wind power electric energy quality assessment method and a device, wherein the wind power electric energy quality assessment method comprises the following steps: dividing a plurality of wind speed intervals according to the wind speed of a wind power plant, and building a steady-state model and a transient model through a Simulink simulation platform to obtain electric energy signals corresponding to the wind speed intervals; reconstructing and clustering electric energy signals corresponding to a plurality of wind speed intervals to obtain electric energy feature vectors; wherein the reconstructing comprises: respectively adding Gaussian white noise to electric energy signals corresponding to a plurality of wind speed intervals, compressing the electric energy signals, and converting the compressed signals into one-dimensional signals; iterative training quality assessment network by using the electric energy feature vector, and judging whether training is completed or not; if training is completed, inputting any electric energy signal into a quality evaluation network, and outputting an evaluation result; the wind power quality evaluation method can accurately and rapidly evaluate the wind power quality.
Description
Technical Field
The invention relates to the technical field of power quality analysis, in particular to a wind power quality assessment method and device.
Background
With the increasing installed capacity of wind power, a large number of nonlinear devices are connected to the grid. When these devices are operated, they generate a lot of electromagnetic interference, which has serious influence on the power grid, such as voltage fluctuation, three-phase imbalance, etc., so that the influence of wind power generation grid connection on the power quality cannot be ignored. Power Quality refers to Quality Power supply in a general sense, including voltage Quality, current Quality, power Quality, and Power Quality. It can be defined as: the content of the deviation of voltage, current or frequency which leads to the failure or the failure of the electric equipment comprises frequency deviation, voltage fluctuation and flicker, three-phase unbalance, temporary or transient overvoltage, waveform distortion (harmonic wave), voltage sag, interruption, sag, power supply continuity and the like.
The current evaluation method for the electric energy quality of the wind power plant mainly comprises probability statistics, vector algebra method, fuzzy mathematical method and the like. The principle of probability statistics and vector algebra is popular and easy to understand and has objectivity, but the calculation process is complex, the reference value is not easy to select, and the accuracy of the evaluation result is reduced. The fuzzy mathematics method quantifies qualitative indexes and solves the problems of ambiguity and uncertainty, but does not solve the problem of information repetition caused by index relevance.
Disclosure of Invention
The present invention has been made in view of the above-described problems occurring in the prior art.
In order to solve the technical problems, the invention provides the following technical scheme that: dividing a plurality of wind speed intervals according to the wind speed of a wind power plant, and building a steady-state model and a transient model through a Simulink simulation platform to obtain electric energy signals corresponding to the wind speed intervals; reconstructing and clustering electric energy signals corresponding to a plurality of wind speed intervals to obtain electric energy feature vectors; wherein the reconstructing comprises: respectively adding Gaussian white noise to electric energy signals corresponding to a plurality of wind speed intervals, compressing the electric energy signals, and converting the compressed signals into one-dimensional signals; iterative training quality assessment network by using the electric energy feature vector, and judging whether training is completed or not; if training is completed, inputting any electric energy signal into a quality evaluation network, and outputting an evaluation result.
As a preferable scheme of the wind power quality assessment method, the invention comprises the following steps: the clustering includes: step one: extracting a part of one-dimensional signals as a first data set, and randomly selecting a first clustering center of sample points from the first data set; step two: calculating Euclidean distances from other sample points in the first data set to the first clustering center, and selecting a sample point corresponding to the maximum Euclidean distance as a new clustering center; step three: extracting part of the one-dimensional signals as a second data set, and adding sample points of the second data set into a set of the first clustering center; step four: calculating Euclidean distance from a sample point of the second data set to the first clustering center, and selecting a sample point corresponding to the maximum Euclidean distance as a new clustering center; and step three and step four are circulated until the one-dimensional signal is extracted or the iteration times are reached, circulation is stopped, n clustering centers are obtained, and all sample points are divided according to the distances from each sample point to each clustering center.
As a preferable scheme of the wind power quality assessment method, the invention comprises the following steps: the quality evaluation network comprises an input layer, 3 convolution layers, 2 pooling layers, 1 depth separable convolution layer, 1 full connection layer and an output layer; wherein, the node number of the input layer is 1, and the node number of the output layer is 4; the input layer, the convolution layer, the pooling layer, the depth separable convolution layer, the full connection layer and the output layer are sequentially connected; the convolution layers comprise PW convolution with a convolution kernel size of 3*3, PW convolution with a convolution kernel size of 1*1 and DW convolution with a convolution kernel size of 3*3; the pooling layer comprises a pyramid pooling layer and a random pooling layer; the depth separable convolution layer comprises a depth convolution layer and a point-by-point convolution layer; and performing Henon mapping on the characteristics output by the depth separable convolution layer through the full connection layer, and inputting the mapping result to the output layer through a ReLU6 activation function.
As a preferable scheme of the wind power quality assessment method, the invention comprises the following steps: the judging whether training is completed comprises the following steps: dividing the electric energy feature vector into a training set and a testing set, and carrying out normalization processing on the training set; initializing a weight W and a learning rate alpha of a quality evaluation network, and constructing a loss function:
L=(W/α)[YlgY-(1-y)lg(1-y)]
wherein L is a loss function value, Y is the actual output of the quality evaluation network, and Y is the predicted output of the quality evaluation network;
judging whether the loss function value is less than 5 x 10 -7 If the training time is less than the preset time, the training is ended; otherwise, searching an optimal weight through a whale algorithm to obtain an optimal quality evaluation network;
the whale algorithm comprises: taking the initial weight W of the quality evaluation network as a whale individual, and initializing the number of whale individuals, the maximum iteration number T and the number of neurons of the quality evaluation network; randomly generating the position of the whale individual, and calculating the fitness of the whale individual; updating the position of the whale individual, calculating the fitness of the whale individual at the moment, and selecting an optimal individual according to the fitness; stopping training when the loss function value L of the quality evaluation network reaches the minimum value, and obtaining an optimal weight; wherein, the fitness of whale individual includes:
Fit=1/ L
wherein Fit is the fitness of whale individuals.
As a preferable scheme of the wind power quality assessment method, the invention comprises the following steps: comprising the following steps: the steady-state model comprises a normal voltage model, a simple harmonic model and a voltage fluctuation model, and the transient model comprises a short-time harmonic model and a voltage oscillation model; normal voltage model:
y(t)=sin(wt);
wherein y (t) is a normal voltage signal, w is fundamental wave angular frequency, and t is time;
simple harmonic model:
q(t)=sin(wt)+0.7sin(0.3wt);
wherein q (t) is a simple harmonic amplitude signal, w is fundamental wave angular frequency, and t is time;
voltage fluctuation model:
u(t)=[1+0.7sin(0.5wt)]sin(wt);
wherein u (t) is a voltage fluctuation amplitude signal, w is fundamental wave angular frequency, and t is time;
short-time harmonic model:
r(t)=sin(wt)+0.1sin(3wt)+0.3sin(5wt)+0.3sin(7wt);
wherein r (t) is a short-time harmonic amplitude signal, w is fundamental wave angular frequency, and t is time;
voltage oscillation model:
h(t)=sin(wt)+0.1e 2 sin(0.3wt);
wherein h (t) is a voltage oscillation amplitude signal, w is fundamental wave angular frequency, and t is time.
As a preferable mode of the wind power quality evaluation device according to the invention, wherein: comprising the following steps: the signal acquisition unit is configured to divide a plurality of wind speed intervals according to the wind speed of the wind power plant, and a steady-state model and a transient-state model are built through the Simulink simulation platform to obtain electric energy signals corresponding to the plurality of wind speed intervals; the signal processing unit is configured to reconstruct and cluster the electric energy signals corresponding to the wind speed intervals to obtain electric energy feature vectors; wherein the reconstructing comprises: respectively adding Gaussian white noise to electric energy signals corresponding to a plurality of wind speed intervals, compressing the electric energy signals, and converting the compressed signals into one-dimensional signals; a network training unit configured to perform iterative training of the quality assessment network using the power feature vector, and to determine whether the training is completed; and the power quality evaluation unit is configured to perform inputting any power signal into the quality evaluation network when the training of the quality evaluation network is completed and output an evaluation result.
As a preferable mode of the wind power quality evaluation device according to the invention, wherein: the signal processing unit is specifically configured to perform clustering on one-dimensional signals, and comprises: step one: extracting a part of one-dimensional signals as a first data set, and randomly selecting a first clustering center of sample points from the first data set; step two: calculating Euclidean distances from other sample points in the first data set to the first clustering center, and selecting a sample point corresponding to the maximum Euclidean distance as a new clustering center; step three: extracting part of the one-dimensional signals as a second data set, and adding sample points of the second data set into a set of the first clustering center; step four: calculating Euclidean distance from a sample point of the second data set to the first clustering center, and selecting a sample point corresponding to the maximum Euclidean distance as a new clustering center; and step three and step four are circulated until the one-dimensional signal is extracted or the iteration times are reached, circulation is stopped, n clustering centers are obtained, and all sample points are divided according to the distances from each sample point to each clustering center.
As a preferable mode of the wind power quality evaluation device according to the invention, wherein: the quality evaluation network comprises an input layer, 3 convolution layers, 2 pooling layers, 1 depth separable convolution layer, 1 full connection layer and an output layer; wherein, the node number of the input layer is 1, and the node number of the output layer is 4; the input layer, the convolution layer, the pooling layer, the depth separable convolution layer, the full connection layer and the output layer are sequentially connected; the convolution layers comprise PW convolution with a convolution kernel size of 3*3, PW convolution with a convolution kernel size of 1*1 and DW convolution with a convolution kernel size of 3*3; the pooling layer comprises a pyramid pooling layer and a random pooling layer; the depth separable convolution layer comprises a depth convolution layer and a point-by-point convolution layer; and performing Henon mapping on the characteristics output by the depth separable convolution layer through the full connection layer, and inputting the mapping result to the output layer through a ReLU6 activation function.
As a preferable mode of the wind power quality evaluation device according to the invention, wherein: the network training unit is specifically configured to perform: dividing the electric energy feature vector into a training set and a testing set, and carrying out normalization processing on the training set; initializing a weight W and a learning rate alpha of a quality evaluation network, and constructing a loss function:
L=(W/α)[YlgY-(1-y)lg(1-y)]
wherein L is a loss function value, Y is the actual output of the quality evaluation network, and Y is the predicted output of the quality evaluation network;
judging whether the loss function value is less than 5 x 10 -7 If the training time is less than the preset time, the training is ended; otherwise, searching an optimal weight through a whale algorithm to obtain an optimal quality evaluation network; the whale algorithm comprises: taking the initial weight W of the quality evaluation network as a whale individual, and initializing the number of whale individuals, the maximum iteration number T and the number of neurons of the quality evaluation network; randomly generating the position of the whale individual, and calculating the fitness of the whale individual; updating the position of the whale individual, calculating the fitness of the whale individual at the moment, and selecting an optimal individual according to the fitness; stopping training when the loss function value L of the quality evaluation network reaches the minimumTraining to obtain an optimal weight;
wherein, the fitness of whale individual includes:
Fit=1/ L
wherein Fit is the fitness of whale individuals.
As a preferable mode of the wind power quality evaluation device according to the invention, wherein: the signal acquisition unit is specifically configured to perform: the steady-state model comprises a normal voltage model, a simple harmonic model and a voltage fluctuation model, and the transient model comprises a short-time harmonic model and a voltage oscillation model;
normal voltage model:
y(t)=sin(wt);
wherein y (t) is a normal voltage signal, w is fundamental wave angular frequency, and t is time;
simple harmonic model:
q(t)=sin(wt)+0.7sin(0.3wt);
wherein q (t) is a simple harmonic amplitude signal, w is fundamental wave angular frequency, and t is time;
voltage fluctuation model:
u(t)=[1+0.7sin(0.5wt)]sin(wt);
wherein u (t) is a voltage fluctuation amplitude signal, w is fundamental wave angular frequency, and t is time;
short-time harmonic model:
r(t)=sin(wt)+0.1sin(3wt)+0.3sin(5wt)+0.3sin(7wt);
wherein r (t) is a short-time harmonic amplitude signal, w is fundamental wave angular frequency, and t is time;
voltage oscillation model:
h(t)=sin(wt)+0.1e 2 sin(0.3wt);
wherein h (t) is a voltage oscillation amplitude signal, w is fundamental wave angular frequency, and t is time
The invention has the beneficial effects that: the invention reconstructs and clusters the collected electric energy signals, so that the signals can be directly used in detection and identification of a quality evaluation network, complex pretreatment of the traditional method is avoided, and simultaneously, the accuracy is ensured and the instantaneity is improved by simplifying the neural network structure.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Wherein:
FIG. 1 is a flowchart of a wind power quality assessment method according to a first embodiment of the present invention;
fig. 2 is a schematic diagram of a training flow of a training quality evaluation network according to a first embodiment of the present invention.
Detailed Description
So that the manner in which the above recited objects, features and advantages of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
While the embodiments of the present invention have been illustrated and described in detail in the drawings, the cross-sectional view of the device structure is not to scale in the general sense for ease of illustration, and the drawings are merely exemplary and should not be construed as limiting the scope of the invention. In addition, the three-dimensional dimensions of length, width and depth should be included in actual fabrication.
Also in the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "upper, lower, inner and outer", etc. are based on the orientation or positional relationship shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the apparatus or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first, second, or third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected, and coupled" should be construed broadly in this disclosure unless otherwise specifically indicated and defined, such as: can be fixed connection, detachable connection or integral connection; it may also be a mechanical connection, an electrical connection, or a direct connection, or may be indirectly connected through an intermediate medium, or may be a communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
Example 1
Referring to fig. 1 to fig. 2, a first embodiment of the present invention provides a wind power quality evaluation method, including:
s1: dividing a plurality of wind speed intervals according to the wind speed of the wind power plant, and building a steady-state model and a transient-state model through a Simulink simulation platform to obtain electric energy signals corresponding to the wind speed intervals.
The steady-state model comprises a normal voltage model, a simple harmonic model and a voltage fluctuation model, the transient model comprises a short-time harmonic model and a voltage oscillation model, and the method is characterized in that:
(1) The normal voltage refers to that the effective value of the voltage or current is kept constant under the power frequency, and the normal voltage model is as follows:
y(t)=sin(wt);
wherein y (t) is a normal voltage signal, w is fundamental wave angular frequency, and t is time;
(2) Simple Harmonics (harmonic) are generally caused by frequent switching-off of a large number of nonlinear loads and power electronic devices, and harmonic currents generated by various low-voltage electric equipment and household appliances can be fed back into a high-voltage side from the low-voltage side, so that power grid currents are distorted, the power equipment is influenced, and equipment faults are caused. The simplified harmonic model is as follows:
q(t)=sin(wt)+0.7sin(0.3wt);
wherein q (t) is a simple harmonic amplitude signal, w is fundamental wave angular frequency, and t is time;
(3) The voltage fluctuation (Voltage Fluctuation) is caused by a drastic change in load, such as the start-up and operation of the motor, and the operation of the steelmaking furnace. The voltage fluctuation model is as follows:
u(t)=[1+0.7sin(0.5wt)]sin(wt);
wherein u (t) is a voltage fluctuation amplitude signal, w is fundamental wave angular frequency, and t is time;
(4) Short-term Harmonics (Short-term Harmonics), typically caused by a large number of nonlinear loads and frequent switching-off of power electronics. The short-term harmonic model is as follows:
r(t)=sin(wt)+0.1sin(3wt)+0.3sin(5wt)+0.3sin(7wt);
wherein r (t) is a short-time harmonic amplitude signal, w is fundamental wave angular frequency, and t is time;
(5) Voltage oscillation (Voltage Oscillations) refers to a sudden change in non-power frequency that occurs when a voltage or current is steady. The voltage oscillation model is as follows:
h(t)=sin(wt)+0.1e 2 sin(0.3wt);
wherein h (t) is a voltage oscillation amplitude signal, w is fundamental wave angular frequency, and t is time.
S2: and reconstructing and clustering the electric energy signals corresponding to the wind speed intervals to obtain electric energy feature vectors.
(1) Reconstruction
And the Gaussian white noise is respectively added to the electric energy signals corresponding to the wind speed intervals, the electric energy signals are compressed, the compressed signals are converted into one-dimensional signals, and the two-dimensional signals are converted into the one-dimensional signals, so that the redundancy is effectively reduced, and the operation speed is improved.
(2) Clustering
Step one: extracting a part of one-dimensional signals as a first data set, and randomly selecting a first clustering center of sample points from the first data set;
step two: calculating Euclidean distances from other sample points in the first data set to the first clustering center, and selecting a sample point corresponding to the maximum Euclidean distance as a new clustering center;
step three: extracting part of the one-dimensional signals as a second data set, and adding sample points of the second data set into a set of the first clustering center;
step four: calculating Euclidean distance from a sample point of the second data set to the first clustering center, and selecting a sample point corresponding to the maximum Euclidean distance as a new clustering center;
and step three and step four are circulated until the one-dimensional signal is extracted or the iteration times are reached, circulation is stopped, n clustering centers are obtained, and all sample points are divided according to the distances from each sample point to each clustering center.
Preferably, the method ensures faster convergence and effectively improves the clustering effect by optimizing the K-means++ clustering algorithm.
S2: and (3) iterating the training quality evaluation network by using the electric energy feature vector, judging whether the training is finished, inputting any electric energy signal into the quality evaluation network if the training is finished, and outputting an evaluation result.
The quality evaluation network comprises an input layer, 3 convolution layers, 2 pooling layers, 1 depth separable convolution layer, 1 full connection layer and an output layer; the number of nodes of the input layer is 1, and the evaluation result is divided into four grades of excellent, good, qualified and unqualified in consideration of the requirement of actual engineering on the power quality, so that the number of nodes of the output layer is set to be 4; the input layer, the convolution layer, the pooling layer, the depth separable convolution layer, the full connection layer and the output layer are sequentially connected.
Specifically, the convolution layer includes PW (Point-wise) convolution with a convolution kernel size of 3*3, PW convolution with a convolution kernel size of 1*1, and DW (Depth-wise) convolution with a convolution kernel size of 3*3; the input electric energy feature vector sequentially passes through three convolution layers and then is input to the pooling layer through an activation function.
The pooling layer comprises a pyramid pooling layer and a random pooling layer; the feature vector processed by the convolution layer is subjected to pooling operation through the pyramid pooling layer and the random pooling layer in sequence, wherein the random pooling is to endow the local receiving domain sampling points with probability values according to the values of the local receiving domain sampling points, and then randomly select the local receiving domain sampling points according to the values of the probability values.
The depth separable convolution layers include a depth convolution layer (Depthwise Convolutional Layer) and a point-wise convolution layer (Pointwise Convolutional Layer); where the deep convolution layer convolves each channel of the input feature with a smaller convolution kernel (e.g., 3x 3), this effectively reduces the number of parameters and provides better local feature extraction capabilities. Point-by-point convolution layer: the outputs of the deep convolutional layers were combined linearly between channels using a 1x1 convolution kernel, and the feature map size remained unchanged.
Finally, the Henon mapping is carried out on the characteristics output by the depth separable convolution layer through the full connection layer, and the mapping result is input to the output layer through the ReLU6 activation function.
Preferably, the quality evaluation network designed by the invention is lighter and more efficient in calculation by using smaller convolution kernels, and meanwhile, the expressive power of the model is maintained.
Further, the quality evaluation network is trained iteratively by using the electric energy feature vector, referring to fig. 2, the specific steps are as follows:
dividing the electric energy feature vector into a training set and a testing set, and carrying out normalization processing on the training set;
initializing a weight W and a learning rate alpha of a quality evaluation network, and constructing a loss function:
L=(W/α)[YlgY-(1-y)lg(1-y)]
wherein L is a loss function value, Y is the actual output of the quality evaluation network, and Y is the predicted output of the quality evaluation network;
judging whether the loss function value is less than 5 x 10 -7 If the training time is less than the preset time, the training is ended;
otherwise, searching an optimal weight through a whale algorithm to obtain an optimal quality evaluation network;
the whale algorithm includes: taking the initial weight W of the quality evaluation network as a whale individual, and initializing the number of whale individuals, the maximum iteration number T and the number of neurons of the quality evaluation network;
randomly generating the position of the whale individual, and calculating the fitness of the whale individual;
updating the position of the whale individual, calculating the fitness of the whale individual at the moment, and selecting an optimal individual according to the fitness;
stopping training when the loss function value L of the quality evaluation network reaches the minimum value, and obtaining an optimal weight;
wherein, the fitness of whale individual includes:
Fit=1/ L
wherein Fit is the fitness of whale individuals.
Preferably, the whale algorithm (Whale Optimization Algorithm, WOA) is simple to implement, and requires relaxed requirements on objective function conditions with less parameter control.
Example 2
This embodiment is different from the first embodiment in that a wind power quality evaluation device is provided, including,
the signal acquisition unit is configured to divide a plurality of wind speed intervals according to the wind speed of the wind power plant, and a steady-state model and a transient-state model are built through the Simulink simulation platform to obtain electric energy signals corresponding to the plurality of wind speed intervals; the signal acquisition unit is specifically configured to perform:
the steady-state model comprises a normal voltage model, a simple harmonic model and a voltage fluctuation model, and the transient model comprises a short-time harmonic model and a voltage oscillation model;
mathematical model of normal voltage:
y(t)=sin(wt);
wherein y (t) is a normal voltage signal, w is fundamental wave angular frequency, and t is time;
simple harmonic model:
q(t)=sin(wt)+0.7sin(0.3wt);
wherein q (t) is a simple harmonic amplitude signal, w is fundamental wave angular frequency, and t is time;
voltage fluctuation model:
u(t)=[1+0.7sin(0.5wt)]sin(wt);
wherein u (t) is a voltage fluctuation amplitude signal, w is fundamental wave angular frequency, and t is time;
short-time harmonic model:
r(t)=sin(wt)+0.1sin(3wt)+0.3sin(5wt)+0.3sin(7wt);
wherein r (t) is a short-time harmonic amplitude signal, w is fundamental wave angular frequency, and t is time;
voltage oscillation model:
h(t)=sin(wt)+0.1e 2 sin(0.3wt);
wherein h (t) is a voltage oscillation amplitude signal, w is fundamental wave angular frequency, and t is time.
The signal processing unit is configured to reconstruct and cluster the electric energy signals corresponding to the wind speed intervals to obtain electric energy feature vectors; wherein the reconstructing comprises: respectively adding Gaussian white noise to electric energy signals corresponding to a plurality of wind speed intervals, compressing the electric energy signals, and converting the compressed signals into one-dimensional signals;
a network training unit configured to perform iterative training of the quality assessment network using the power feature vector, and to determine whether the training is completed; specifically, the quality evaluation network comprises an input layer, 3 convolution layers, 2 pooling layers, 1 depth separable convolution layer, 1 full connection layer and an output layer; the number of nodes of the input layer is 1, and the evaluation result is divided into four grades of excellent, good, qualified and unqualified in consideration of the requirement of actual engineering on the power quality, so that the number of nodes of the output layer is set to be 4; the input layer, the convolution layer, the pooling layer, the depth separable convolution layer, the full connection layer and the output layer are sequentially connected.
Specifically, the convolution layer includes PW (Point-wise) convolution with a convolution kernel size of 3*3, PW convolution with a convolution kernel size of 1*1, and DW (Depth-wise) convolution with a convolution kernel size of 3*3; the input electric energy feature vector sequentially passes through three convolution layers and then is input to the pooling layer through an activation function.
The pooling layer comprises a pyramid pooling layer and a random pooling layer; the feature vector processed by the convolution layer is subjected to pooling operation through the pyramid pooling layer and the random pooling layer in sequence, wherein the random pooling is to endow the local receiving domain sampling points with probability values according to the values of the local receiving domain sampling points, and then randomly select the local receiving domain sampling points according to the values of the probability values.
The depth separable convolution layers include a depth convolution layer (Depthwise Convolutional Layer) and a point-wise convolution layer (Pointwise Convolutional Layer); where the deep convolution layer convolves each channel of the input feature with a smaller convolution kernel (e.g., 3x 3), this effectively reduces the number of parameters and provides better local feature extraction capabilities. Point-by-point convolution layer: the outputs of the deep convolutional layers were combined linearly between channels using a 1x1 convolution kernel, and the feature map size remained unchanged.
Finally, the Henon mapping is carried out on the characteristics output by the depth separable convolution layer through the full connection layer, and the mapping result is input to the output layer through the ReLU6 activation function.
And the power quality evaluation unit is configured to perform the steps of inputting any power signal into the quality evaluation network when the training of the quality evaluation network is completed, and outputting an evaluation result, wherein the evaluation result comprises excellent, good, qualified and unqualified.
The signal processing unit is specifically configured to perform clustering on the one-dimensional signals, and comprises:
step one: extracting a part of one-dimensional signals as a first data set, and randomly selecting a first clustering center of sample points from the first data set;
step two: calculating Euclidean distances from other sample points in the first data set to the first clustering center, and selecting a sample point corresponding to the maximum Euclidean distance as a new clustering center;
step three: extracting part of the one-dimensional signals as a second data set, and adding sample points of the second data set into a set of the first clustering center;
step four: calculating Euclidean distance from a sample point of the second data set to the first clustering center, and selecting a sample point corresponding to the maximum Euclidean distance as a new clustering center;
and step three and step four are circulated until the one-dimensional signal is extracted or the iteration times are reached, circulation is stopped, n clustering centers are obtained, and all sample points are divided according to the distances from each sample point to each clustering center.
A network training unit specifically configured to perform:
dividing the electric energy feature vector into a training set and a testing set, and carrying out normalization processing on the training set;
initializing a weight W and a learning rate alpha of a quality evaluation network, and constructing a loss function:
L=(W/α)[YlgY-(1-y)lg(1-y)]
wherein L is a loss function value, Y is the actual output of the quality evaluation network, and Y is the predicted output of the quality evaluation network;
judging whether the loss function value is less than 5 x 10 -7 If the training time is less than the preset time, the training is ended;
otherwise, searching an optimal weight through a whale algorithm to obtain an optimal quality evaluation network;
the whale algorithm includes: taking the initial weight W of the quality evaluation network as a whale individual, and initializing the number of whale individuals, the maximum iteration number T and the number of neurons of the quality evaluation network;
randomly generating the position of the whale individual, and calculating the fitness of the whale individual;
updating the position of the whale individual, calculating the fitness of the whale individual at the moment, and selecting an optimal individual according to the fitness;
stopping training when the loss function value L of the quality evaluation network reaches the minimum value, and obtaining an optimal weight;
wherein, the fitness of whale individual includes:
Fit=1/ L
wherein Fit is the fitness of whale individuals.
It should be appreciated that embodiments of the invention may be implemented or realized by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer readable memory. The methods may be implemented in a computer program using standard programming techniques, including a non-transitory computer readable storage medium configured with a computer program, where the storage medium so configured causes a computer to operate in a specific and predefined manner, in accordance with the methods and drawings described in the specific embodiments. Each program may be implemented in a high level procedural or object oriented programming language to communicate with a computer system. However, the program(s) can be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.
Furthermore, the operations of the processes described herein may be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes (or variations and/or combinations thereof) described herein may be performed under control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications), by hardware, or combinations thereof, collectively executing on one or more processors. The computer program includes a plurality of instructions executable by one or more processors.
Further, the method may be implemented in any type of computing platform operatively connected to a suitable computing platform, including, but not limited to, a personal computer, mini-computer, mainframe, workstation, network or distributed computing environment, separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, and so forth. Aspects of the invention may be implemented in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optical read and/or write storage medium, RAM, ROM, etc., such that it is readable by a programmable computer, which when read by a computer, is operable to configure and operate the computer to perform the processes described herein. Further, the machine readable code, or portions thereof, may be transmitted over a wired or wireless network. When such media includes instructions or programs that, in conjunction with a microprocessor or other data processor, implement the steps described above, the invention described herein includes these and other different types of non-transitory computer-readable storage media. The invention also includes the computer itself when programmed according to the methods and techniques of the present invention. The computer program can be applied to the input data to perform the functions described herein, thereby converting the input data to generate output data that is stored to the non-volatile memory. The output information may also be applied to one or more output devices such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including specific visual depictions of physical and tangible objects produced on a display.
As used in this application, the terms "component," "module," "system," and the like are intended to refer to a computer-related entity, either hardware, firmware, a combination of hardware and software, or software in execution. For example, the components may be, but are not limited to: a process running on a processor, an object, an executable, a thread of execution, a program, and/or a computer. By way of example, both an application running on a computing device and the computing device can be a component. One or more components may reside within a process and/or thread of execution and a component may be localized on one computer and/or distributed between two or more computers. Furthermore, these components can execute from various computer readable media having various data structures thereon. The components may communicate by way of local and/or remote processes such as in accordance with a signal having one or more data packets (e.g., data from one component interacting with another component in a local system, distributed system, and/or across a network such as the internet with other systems by way of the signal).
It should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered in the scope of the claims of the present invention.
Claims (6)
1. The wind power quality evaluation method is characterized by comprising the following steps of:
dividing a plurality of wind speed intervals according to the wind speed of a wind power plant, and building a steady-state model and a transient model through a Simulink simulation platform to obtain electric energy signals corresponding to the wind speed intervals;
reconstructing and clustering electric energy signals corresponding to a plurality of wind speed intervals to obtain electric energy feature vectors; wherein the reconstructing comprises: respectively adding Gaussian white noise to electric energy signals corresponding to a plurality of wind speed intervals, compressing the electric energy signals, and converting the compressed signals into one-dimensional signals;
iterative training quality assessment network by using the electric energy feature vector, and judging whether training is completed or not;
if training is completed, inputting any electric energy signal into a quality evaluation network, and outputting an evaluation result;
the steady-state model comprises a normal voltage model, a simple harmonic model and a voltage fluctuation model, and the transient model comprises a short-time harmonic model and a voltage oscillation model;
normal voltage model:
y(t)=sin(wt);
wherein y (t) is a normal voltage signal, w is fundamental wave angular frequency, and t is time;
simple harmonic model:
q(t)=sin(wt)+0.7sin(0.3wt);
wherein q (t) is a simple harmonic amplitude signal, w is fundamental wave angular frequency, and t is time;
voltage fluctuation model:
u(t)=[1+0.7sin(0.5wt)]sin(wt);
wherein u (t) is a voltage fluctuation amplitude signal, w is fundamental wave angular frequency, and t is time;
short-time harmonic model:
r(t)=sin(wt)+0.1sin(3wt)+0.3sin(5wt)+0.3sin(7wt);
wherein r (t) is a short-time harmonic amplitude signal, w is fundamental wave angular frequency, and t is time;
voltage oscillation model:
h(t)=sin(wt)+0.1e 2 sin(0.3wt);
wherein h (t) is a voltage oscillation amplitude signal, w is fundamental wave angular frequency, and t is time;
the judging whether training is completed comprises the following steps:
dividing the electric energy feature vector into a training set and a testing set, and carrying out normalization processing on the training set;
initializing a weight W and a learning rate alpha of a quality evaluation network, and constructing a loss function:
L=(W/α)[YlgY-(1-y)lg(1-y)]
wherein L is a loss function value, Y is the actual output of the quality evaluation network, and Y is the predicted output of the quality evaluation network;
judging whether the loss function value is less than 5 x 10 -7 If the training time is less than the preset time, the training is ended;
otherwise, searching an optimal weight through a whale algorithm to obtain an optimal quality evaluation network;
the whale algorithm comprises: taking the initial weight W of the quality evaluation network as a whale individual, and initializing the number of whale individuals, the maximum iteration number T and the number of neurons of the quality evaluation network;
randomly generating the position of the whale individual, and calculating the fitness of the whale individual;
updating the position of the whale individual, calculating the fitness of the whale individual at the moment, and selecting an optimal individual according to the fitness;
stopping training when the loss function value L of the quality evaluation network reaches the minimum value, and obtaining an optimal weight;
wherein, the fitness of whale individual includes:
Fit=1/ L
wherein Fit is the fitness of whale individuals.
2. The wind power quality assessment method of claim 1, wherein the clustering comprises:
step one: extracting a part of one-dimensional signals as a first data set, and randomly selecting a first clustering center of sample points from the first data set;
step two: calculating Euclidean distances from other sample points in the first data set to the first clustering center, and selecting a sample point corresponding to the maximum Euclidean distance as a new clustering center;
step three: extracting part of the one-dimensional signals as a second data set, and adding sample points of the second data set into a set of the first clustering center;
step four: calculating Euclidean distance from a sample point of the second data set to the first clustering center, and selecting a sample point corresponding to the maximum Euclidean distance as a new clustering center;
and step three and step four are circulated until the one-dimensional signal is extracted or the iteration times are reached, circulation is stopped, n clustering centers are obtained, and all sample points are divided according to the distances from each sample point to each clustering center.
3. The wind power quality assessment method according to claim 2, wherein the quality assessment network comprises an input layer, 3 convolution layers, 2 pooling layers, 1 depth separable convolution layer, 1 full connection layer and an output layer; wherein, the node number of the input layer is 1, and the node number of the output layer is 4; the input layer, the convolution layer, the pooling layer, the depth separable convolution layer, the full connection layer and the output layer are sequentially connected;
the convolution layers comprise PW convolution with a convolution kernel size of 3*3, PW convolution with a convolution kernel size of 1*1 and DW convolution with a convolution kernel size of 3*3;
the pooling layer comprises a pyramid pooling layer and a random pooling layer;
the depth separable convolution layer comprises a depth convolution layer and a point-by-point convolution layer;
and performing Henon mapping on the characteristics output by the depth separable convolution layer through the full connection layer, and inputting the mapping result to the output layer through a ReLU6 activation function.
4. A wind power quality assessment device, comprising:
the signal acquisition unit is configured to divide a plurality of wind speed intervals according to the wind speed of the wind power plant, and a steady-state model and a transient-state model are built through the Simulink simulation platform to obtain electric energy signals corresponding to the plurality of wind speed intervals;
the signal processing unit is configured to reconstruct and cluster the electric energy signals corresponding to the wind speed intervals to obtain electric energy feature vectors; wherein the reconstructing comprises: respectively adding Gaussian white noise to electric energy signals corresponding to a plurality of wind speed intervals, compressing the electric energy signals, and converting the compressed signals into one-dimensional signals;
a network training unit configured to perform iterative training of the quality assessment network using the power feature vector, and to determine whether the training is completed;
the power quality evaluation unit is configured to perform the steps of inputting any power signal into the quality evaluation network when the training of the quality evaluation network is completed, and outputting an evaluation result;
wherein the signal acquisition unit is specifically configured to perform:
the steady-state model comprises a normal voltage model, a simple harmonic model and a voltage fluctuation model, and the transient model comprises a short-time harmonic model and a voltage oscillation model;
normal voltage model:
y(t)=sin(wt);
wherein y (t) is a normal voltage signal, w is fundamental wave angular frequency, and t is time;
simple harmonic model:
q(t)=sin(wt)+0.7sin(0.3wt);
wherein q (t) is a simple harmonic amplitude signal, w is fundamental wave angular frequency, and t is time;
voltage fluctuation model:
u(t)=[1+0.7sin(0.5wt)]sin(wt);
wherein u (t) is a voltage fluctuation amplitude signal, w is fundamental wave angular frequency, and t is time;
short-time harmonic model:
r(t)=sin(wt)+0.1sin(3wt)+0.3sin(5wt)+0.3sin(7wt);
wherein r (t) is a short-time harmonic amplitude signal, w is fundamental wave angular frequency, and t is time;
voltage oscillation model:
h(t)=sin(wt)+0.1e 2 sin(0.3wt);
wherein h (t) is a voltage oscillation amplitude signal, w is fundamental wave angular frequency, and t is time;
the network training unit is specifically configured to perform:
dividing the electric energy feature vector into a training set and a testing set, and carrying out normalization processing on the training set;
initializing a weight W and a learning rate alpha of a quality evaluation network, and constructing a loss function:
L=(W/α)[YlgY-(1-y)lg(1-y)]
wherein L is a loss function value, Y is the actual output of the quality evaluation network, and Y is the predicted output of the quality evaluation network;
judging whether the loss function value is less than 5 x 10 -7 If the training time is less than the preset time, the training is ended;
otherwise, searching an optimal weight through a whale algorithm to obtain an optimal quality evaluation network;
the whale algorithm comprises: taking the initial weight W of the quality evaluation network as a whale individual, and initializing the number of whale individuals, the maximum iteration number T and the number of neurons of the quality evaluation network;
randomly generating the position of the whale individual, and calculating the fitness of the whale individual;
updating the position of the whale individual, calculating the fitness of the whale individual at the moment, and selecting an optimal individual according to the fitness;
stopping training when the loss function value L of the quality evaluation network reaches the minimum value, and obtaining an optimal weight;
wherein, the fitness of whale individual includes:
Fit=1/ L
wherein Fit is the fitness of whale individuals.
5. Wind power quality assessment device according to claim 4, wherein said signal processing unit is specifically configured to perform clustering of one-dimensional signals, comprising:
step one: extracting a part of one-dimensional signals as a first data set, and randomly selecting a first clustering center of sample points from the first data set;
step two: calculating Euclidean distances from other sample points in the first data set to the first clustering center, and selecting a sample point corresponding to the maximum Euclidean distance as a new clustering center;
step three: extracting part of the one-dimensional signals as a second data set, and adding sample points of the second data set into a set of the first clustering center;
step four: calculating Euclidean distance from a sample point of the second data set to the first clustering center, and selecting a sample point corresponding to the maximum Euclidean distance as a new clustering center;
and step three and step four are circulated until the one-dimensional signal is extracted or the iteration times are reached, circulation is stopped, n clustering centers are obtained, and all sample points are divided according to the distances from each sample point to each clustering center.
6. The wind power quality assessment device of claim 5, wherein the quality assessment network comprises an input layer, 3 convolution layers, 2 pooling layers, 1 depth separable convolution layer, 1 full connection layer, and an output layer; wherein, the node number of the input layer is 1, and the node number of the output layer is 4; the input layer, the convolution layer, the pooling layer, the depth separable convolution layer, the full connection layer and the output layer are sequentially connected;
the convolution layers comprise PW convolution with a convolution kernel size of 3*3, PW convolution with a convolution kernel size of 1*1 and DW convolution with a convolution kernel size of 3*3;
the pooling layer comprises a pyramid pooling layer and a random pooling layer;
the depth separable convolution layer comprises a depth convolution layer and a point-by-point convolution layer;
and performing Henon mapping on the characteristics output by the depth separable convolution layer through the full connection layer, and inputting the mapping result to the output layer through a ReLU6 activation function.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410005272.4A CN117494591B (en) | 2024-01-03 | 2024-01-03 | Wind power electric energy quality assessment method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410005272.4A CN117494591B (en) | 2024-01-03 | 2024-01-03 | Wind power electric energy quality assessment method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117494591A CN117494591A (en) | 2024-02-02 |
CN117494591B true CN117494591B (en) | 2024-03-22 |
Family
ID=89667639
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410005272.4A Active CN117494591B (en) | 2024-01-03 | 2024-01-03 | Wind power electric energy quality assessment method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117494591B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111898414A (en) * | 2020-06-16 | 2020-11-06 | 广东电网有限责任公司 | Method for improving electric energy quality disturbance signal identification effect |
CN111985825A (en) * | 2020-08-26 | 2020-11-24 | 东北大学 | Crystal face quality evaluation method for roller mill orientation instrument |
CN116405310A (en) * | 2023-04-28 | 2023-07-07 | 北京宏博知微科技有限公司 | Network data security monitoring method and system |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112653142B (en) * | 2020-12-18 | 2022-09-02 | 武汉大学 | Wind power prediction method and system for optimizing depth transform network |
-
2024
- 2024-01-03 CN CN202410005272.4A patent/CN117494591B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111898414A (en) * | 2020-06-16 | 2020-11-06 | 广东电网有限责任公司 | Method for improving electric energy quality disturbance signal identification effect |
CN111985825A (en) * | 2020-08-26 | 2020-11-24 | 东北大学 | Crystal face quality evaluation method for roller mill orientation instrument |
CN116405310A (en) * | 2023-04-28 | 2023-07-07 | 北京宏博知微科技有限公司 | Network data security monitoring method and system |
Non-Patent Citations (1)
Title |
---|
基于聚类LSTM深度学习模型的主动配电网电能质量预测;翁国庆;龚阳光;舒俊鹏;黄飞腾;;高技术通讯;20200715(07);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN117494591A (en) | 2024-02-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112651290A (en) | Hydroelectric generating set vibration trend prediction method and system | |
CN112183641B (en) | Transient frequency stability assessment method and system integrating prediction-correction deep learning | |
Ye et al. | Combined approach for short-term wind power forecasting based on wave division and Seq2Seq model using deep learning | |
Zheng et al. | Fault diagnosis of wind power converters based on compressed sensing theory and weight constrained AdaBoost-SVM | |
Guo et al. | Improved adversarial learning for fault feature generation of wind turbine gearbox | |
CN112069727A (en) | Intelligent transient stability evaluation system and method with high reliability for power system | |
Chakravorti et al. | Advanced signal processing techniques for multiclass disturbance detection and classification in microgrids | |
Wang et al. | Dynamic equivalent method of PMSG‐based wind farm for power system stability analysis | |
CN113094887B (en) | Optimization method and device for frequency-shifting electromagnetic transient simulation and electronic equipment | |
CN115422869A (en) | Load model parameter identification method, system, computer device and storage medium | |
CN117494591B (en) | Wind power electric energy quality assessment method and device | |
Zhang et al. | Fault feature extraction for planetary bearing of CRF pump in nuclear power plant based on TFDC-QPSO-optimised MOMEDA | |
CN116566061A (en) | Grid-connected inverter system stability on-line monitoring method and system | |
CN116826735A (en) | Broadband oscillation identification method and device for new energy station | |
Cho et al. | Oscillation recognition using a geometric feature extraction process based on periodic time-series approximation | |
CN116070384A (en) | Transient stability evaluation method and system based on power grid feature arrangement importance | |
CN116204771A (en) | Power system transient stability key feature selection method, device and product | |
Bing et al. | Machinery fault diagnosis method of HV circuit breaker based on EEMD and RBF neural network | |
CN115311509A (en) | Power system transient stability evaluation method and system based on imaging data driving | |
CN109066683B (en) | Static voltage stability analysis method considering harmonic influence | |
Chen et al. | The interpolation of missing wind speed data based on optimized LSSVM model | |
CN109376494B (en) | Probability power flow determination method and system based on power system | |
Xiong et al. | Application of multi-kernel relevance vector machine and data pre-processing by complementary ensemble empirical mode decomposition and mutual dimensionless in fault diagnosis | |
CN117390418B (en) | Transient stability evaluation method, system and equipment for wind power grid-connected system | |
Wang et al. | Impedance Ground Faults Detection and Classification Method for DC Microgrid |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |