CN106778923B - Electric energy quality disturbance signal classification method and device - Google Patents
Electric energy quality disturbance signal classification method and device Download PDFInfo
- Publication number
- CN106778923B CN106778923B CN201710177945.4A CN201710177945A CN106778923B CN 106778923 B CN106778923 B CN 106778923B CN 201710177945 A CN201710177945 A CN 201710177945A CN 106778923 B CN106778923 B CN 106778923B
- Authority
- CN
- China
- Prior art keywords
- neural network
- layer
- signal
- signals
- voltage
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Abstract
The embodiment of the invention discloses a method and a device for classifying power quality disturbing signals, which are used for solving the technical problems that S transformation and a neural network cannot be organically combined in the prior art, so that the accuracy of classifying the power quality disturbing signals is poor and the stability is poor. The method provided by the embodiment of the invention comprises the following steps: selecting a normal voltage signal and seven electric energy quality disturbance signals; predefining coding categories of the normal voltage signals and the seven power quality disturbance signals, taking the normal voltage signals and the seven power quality disturbance signals as input, taking the coding categories as output, constructing a four-layer neural network based on S transformation, and training the neural network to obtain a trained neural network; and inputting the voltage signals acquired in real time into the trained neural network, and comparing the output value of the obtained neural network with the encoding category to obtain a classification result of the voltage signals.
Description
Technical Field
The invention relates to the field of power quality monitoring, in particular to a method and a device for classifying power quality disturbance signals.
Background
In recent years, with the wide application of power electronic equipment in a power grid and the large access of distributed power supplies such as photovoltaic power, wind power and the like, the problem of electric energy quality caused by the power electronic equipment is increasingly prominent. Under the conditions of precision machining and increasingly strict requirements of people on power quality in life, the power quality interference needs to be accurately classified, and then the reasons causing power quality disturbance are analyzed and corresponding treatment measures are taken.
The power quality disturbance classification comprises two steps of feature extraction and classifier classification. In the feature extraction method, the S transformation is used as the inheritance and the development of the short-time Fourier transformation and the wavelet transformation, the advantages of the short-time Fourier transformation and the wavelet transformation are combined, the high time resolution is realized in a high frequency band, the high frequency resolution is realized in a low frequency band, the processing of non-stationary signals is facilitated, and the method is widely applied to the feature extraction of the power quality disturbance. In the aspect of classifier selection, the artificial neural network is formed by interconnection of a large number of processing units, has the characteristics of self-learning, self-organization, self-adaptation and the like, and is successfully applied to classification of power quality disturbance. How to combine the advantages of the S transformation feature extraction method and the neural network classifier becomes a problem of attention of people.
In order to organically combine the advantages of the two, the traditional method is to extract the characteristic vector of the power quality disturbance signal based on S transformation, and classify the characteristic vector as the input of the network. However, it can be seen that the S transformation and the neural network are two completely independent parts in the classification process, and the S transformation and the neural network cannot be organically combined, which easily causes the problems of insufficient accuracy and poor stability of classification of the power quality disturbance signal.
Disclosure of Invention
The embodiment of the invention provides a method and a device for classifying power quality disturbing signals, and solves the technical problems that in the prior art, an S transformation and a neural network are two completely independent parts in a classification process, and the S transformation and the neural network cannot be organically combined, so that the accuracy of classification of the power quality disturbing signals is easily insufficient, and the stability is poor.
The method for classifying the power quality disturbing signals provided by the embodiment of the invention comprises the following steps:
selecting a normal voltage signal and seven electric energy quality disturbance signals, wherein the seven electric energy quality disturbance signals comprise a voltage swell signal, a voltage drop signal, a voltage interrupt signal, a transient pulse signal, a transient oscillation signal, a harmonic signal and a voltage flicker signal;
predefining coding categories of the normal voltage signals and the seven power quality disturbance signals, taking the normal voltage signals and the seven power quality disturbance signals as input, taking the coding categories as output, constructing a four-layer neural network based on S transformation, and training the neural network to obtain a trained neural network;
and inputting the voltage signals acquired in real time into the trained neural network, and comparing the output value of the obtained neural network with the encoding category to obtain a classification result of the voltage signals.
Preferably, the neural network comprises an input layer, an S-transform layer, a hidden layer and an output layer.
Preferably, the output of the neural network is specifically:
wherein x (K) is the kth input value of the network input layer, and the upper bound K of the summation item where x (K) is located is the number of nodes of the network input layer; w is a
jiIs the connection weight, w, of the S transform layer node j and the hidden layer node i
jiThe upper bound J of the summation item is the node number of the S conversion layer; w is a
ipA connection weight, w, for the hidden layer node i and the output layer node p
ipThe upper bound I of the summation item is the node number of the hidden layer; o is
pThe subscript p is the number of nodes of the output layer; h (k, m)
j,n
j) A basis function adopted for the S transformation layer of the network; m is
jAnd n
jIs a position factor; sigma (-) is a transfer function adopted by a network hidden layer and an output layer, and is a sigmoid function.
Preferably, the basis function H (k, m)
j,n
j) The calculation is carried out through a first formula, wherein the first formula specifically comprises the following steps:
preferably, the training of the neural network is training of the neural network by a BP algorithm.
The embodiment of the invention provides a power quality disturbing signal classification device, which comprises:
the selection module is used for selecting a normal voltage signal and seven electric energy quality disturbance signals, wherein the seven electric energy quality disturbance signals comprise a voltage swell signal, a voltage break signal, a transient pulse signal, a transient oscillation signal, a harmonic signal and a voltage flicker signal;
the building module is used for predefining coding types of the normal voltage signals and the seven electric energy quality disturbance signals, taking the normal voltage signals and the seven electric energy quality disturbance signals as input, taking the coding types as output, building a four-layer neural network based on S transformation, and training the neural network to obtain a trained neural network;
and the input comparison module is used for inputting the voltage signals acquired in real time into the trained neural network, and comparing the obtained output value of the neural network with the encoding category to obtain the classification result of the voltage signals.
According to the technical scheme, the embodiment of the invention has the following advantages:
the embodiment of the invention provides a method and a device for classifying power quality disturbance signals, which comprise the following steps: selecting a normal voltage signal and seven electric energy quality disturbance signals, wherein the seven electric energy quality disturbance signals comprise a voltage swell signal, a voltage drop signal, a voltage interrupt signal, a transient pulse signal, a transient oscillation signal, a harmonic signal and a voltage flicker signal; predefining coding categories of the normal voltage signals and the seven power quality disturbance signals, taking the normal voltage signals and the seven power quality disturbance signals as input, taking the coding categories as output, constructing a four-layer neural network based on S transformation, and training the neural network to obtain a trained neural network; the voltage signal acquired in real time is input into the trained neural network, and the obtained output value of the neural network is compared with the code category to obtain the classification result of the voltage signal.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.
Fig. 1 is a schematic flow chart of a method for classifying a power quality disturbance signal according to an embodiment of the present invention;
FIG. 2(a) is a waveform diagram of a normal voltage signal according to an embodiment of the present invention;
FIG. 2(b) is a waveform diagram of a voltage swell signal according to an embodiment of the present invention;
FIG. 2(c) is a waveform diagram of a slump signal according to an embodiment of the present invention;
FIG. 2(d) is a waveform diagram of a voltage interrupt signal according to an embodiment of the present invention;
FIG. 2(e) is a waveform diagram of a transient pulse signal according to an embodiment of the present invention;
FIG. 2(f) is a waveform diagram of a transient oscillation signal according to an embodiment of the present invention;
FIG. 2(g) is a waveform diagram of a harmonic signal provided by an embodiment of the present invention;
FIG. 2(h) is a waveform diagram of a voltage flicker signal according to an embodiment of the present invention;
fig. 3 is a topology structure diagram of a four-layer neural network based on S transformation according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a classification result of a power quality disturbance signal after a neural network is adopted according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an apparatus for classifying a power quality disturbing signal according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a method and a device for classifying power quality disturbing signals, which are used for solving the technical problems that in the prior art, an S transformation and a neural network are two completely independent parts in a classification process, and the S transformation and the neural network cannot be organically combined, so that the accuracy of classification of the power quality disturbing signals is easily insufficient, and the stability is poor.
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the embodiments described below are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a method for classifying a power quality disturbance signal according to an embodiment of the present invention includes:
101. selecting a normal voltage signal and seven electric energy quality disturbance signals, wherein the seven electric energy quality disturbance signals comprise a voltage swell signal, a voltage drop signal, a voltage interrupt signal, a transient pulse signal, a transient oscillation signal, a harmonic signal and a voltage flicker signal;
first, a normal voltage signal and seven power quality disturbance signals are selected, as shown in fig. 2(a) to 2(h), which are a normal voltage signal, a voltage swell signal, a voltage interrupt signal, a transient pulse signal, a transient oscillation signal, a harmonic signal, and a voltage flicker signal, respectively.
102. Predefining coding categories of the normal voltage signals and the seven power quality disturbance signals, taking the normal voltage signals and the seven power quality disturbance signals as input, taking the coding categories as output, constructing a four-layer neural network based on S transformation, and training the neural network to obtain a trained neural network;
then, the normal voltage signal and seven power quality disturbance signals are predefined and coded, such as 000, 001, 010, 011, 100, 101, 110, 111, which respectively represent the normal voltage signal, the voltage swell signal, the voltage break signal, the transient pulse signal, the transient oscillation signal, the harmonic signal, and the voltage flicker signal. And then, taking the normal voltage signal and seven electric energy quality disturbance signals as input, taking the coding type as output, constructing a four-layer neural network based on S transformation, and training the neural network by adopting a BP algorithm to obtain the trained neural network. The neural network comprises an input layer, an S conversion layer, a hidden layer and an output layer; and the output of the neural network is specifically
Wherein x (K) is the kth input value of the network input layer, and the upper bound K of the summation item where x (K) is located is the number of nodes of the network input layer; w is a
jiIs the connection weight, w, of the S transform layer node j and the hidden layer node i
jiThe upper bound J of the summation item is the node number of the S conversion layer; w is a
ipA connection weight, w, for the hidden layer node i and the output layer node p
ipThe upper bound I of the summation item is the node number of the hidden layer; o is
pThe subscript p is the number of nodes of the output layer; h (k, m)
j,n
j) A basis function adopted for the S transformation layer of the network; m is
jAnd n
jIs a position factor; sigma (-) is a transfer function adopted by a network hidden layer and an output layer, and is a sigmoid function.
Further, the basis functions H (k, m)
j,n
j) The calculation is carried out through a first formula, wherein the first formula specifically comprises the following steps:
FIG. 3 is a diagram of a four-layer neural network topology based on S transformation, as shown in FIG. 3, wherein Z is
jIs the jth output value of the S transform layer, Y
iFor the ith output value of the hidden layer, S (Σ) represents the pair-sum modulo.
103. And inputting the voltage signals acquired in real time into the trained neural network, and comparing the output value of the obtained neural network with the encoding category to obtain a classification result of the voltage signals.
And finally, inputting the voltage signals acquired in real time into the trained neural network, and comparing the output value of the obtained neural network with the encoding type to obtain the classification result of the voltage signals. For example, the output values of the neural network are 000, 111, and 110, and the classification result of the voltage signal can be obtained by comparing the three output values with the encoding categories: normal voltage signal, voltage flicker signal, harmonic signal. Please refer to fig. 4, which is a schematic diagram of a classification result of a power quality disturbing signal after a neural network is adopted.
In order to describe the method for classifying the power quality disturbing signal provided by the embodiment of the present invention in detail, a power quality disturbing signal classifying device provided by the embodiment of the present invention will be described in detail below.
Referring to fig. 5, an apparatus for classifying a power quality disturbing signal according to an embodiment of the present invention includes:
the selection module 201 is configured to select a normal voltage signal and seven power quality disturbance signals, where the seven power quality disturbance signals include a voltage swell signal, a voltage break signal, a transient pulse signal, a transient oscillation signal, a harmonic signal, and a voltage flicker signal;
the building module 202 is configured to predefine coding types of the normal voltage signal and the seven power quality disturbance signals, construct a four-layer neural network based on S transformation with the normal voltage signal and the seven power quality disturbance signals as inputs and the coding types as outputs, and train the neural network to obtain a trained neural network;
and the input comparison module 203 is used for inputting the voltage signals acquired in real time into the trained neural network, and comparing the obtained output value of the neural network with the encoding category to obtain the classification result of the voltage signals.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (4)
1. A method for classifying power quality disturbance signals is characterized by comprising the following steps:
selecting a normal voltage signal and seven electric energy quality disturbance signals, wherein the seven electric energy quality disturbance signals comprise a voltage swell signal, a voltage drop signal, a voltage interrupt signal, a transient pulse signal, a transient oscillation signal, a harmonic signal and a voltage flicker signal;
carrying out predefined coding classification on the normal voltage signal and the seven electric energy quality disturbing signals, taking the normal voltage signal and the seven electric energy quality disturbing signals as input, taking the coding classification as output, constructing a four-layer neural network based on S transformation, and training the neural network to obtain a trained neural network;
inputting the voltage signals acquired in real time into the trained neural network, and comparing the obtained output value of the neural network with the coding type to obtain a classification result of the voltage signals;
the neural network comprises an input layer, an S conversion layer, a hidden layer and an output layer, and the output of the neural network is
Wherein x (K) is the kth input value of the network input layer, and the upper bound K of the summation item where x (K) is located is the number of nodes of the network input layer; w is a
jiIs the connection weight, w, of the S transform layer node j and the hidden layer node i
jiIs at the position ofThe upper bound J of the sum term is the number of nodes of the S conversion layer; w is a
ipA connection weight, w, for the hidden layer node i and the output layer node p
ipThe upper bound I of the summation item is the node number of the hidden layer; o is
pThe subscript p is the number of nodes of the output layer; h (k, m)
j,n
j) A basis function adopted for the S transformation layer of the network; m is
jAnd n
jIs a position factor; sigma (-) is a transfer function adopted by a network hidden layer and an output layer, and is a sigmoid function.
2. The method according to claim 1, wherein the basis functions H (k, m) are
j,n
j) The method comprises the following steps of obtaining through a first formula, wherein the first formula specifically comprises the following steps:
3. the method according to claim 1, wherein the training of the neural network is training of the neural network by a BP algorithm.
4. An apparatus for classifying a power quality disturbing signal, comprising:
the selection module is used for selecting a normal voltage signal and seven electric energy quality disturbance signals, wherein the seven electric energy quality disturbance signals comprise a voltage swell signal, a voltage break signal, a transient pulse signal, a transient oscillation signal, a harmonic signal and a voltage flicker signal;
a building module, configured to perform predefined coding types on the normal voltage signal and the seven power quality disturbance signals, take the normal voltage signal and the seven power quality disturbance signals as inputs, take the coding types as outputs, build a four-layer neural network based on S transform, train the neural network, and obtain a trained neural network, where the neural network packet includesComprises an input layer, an S transformation layer, a hidden layer and an output layer, wherein the output of the neural network is
Wherein x (K) is the kth input value of the network input layer, and the upper bound K of the summation item where x (K) is located is the number of nodes of the network input layer; w is a
jiIs the connection weight, w, of the S transform layer node j and the hidden layer node i
jiThe upper bound J of the summation item is the node number of the S conversion layer; w is a
ipA connection weight, w, for the hidden layer node i and the output layer node p
ipThe upper bound I of the summation item is the node number of the hidden layer; o is
pThe subscript p is the number of nodes of the output layer; h (k, m)
j,n
j) A basis function adopted for the S transformation layer of the network; m is
jAnd n
jIs a position factor; sigma (-) is a transfer function adopted by the network hidden layer and the output layer, and is a sigmoid function;
and the input comparison module is used for inputting the voltage signals acquired in real time into the trained neural network, and comparing the obtained output value of the neural network with the coding type to obtain a classification result of the voltage signals.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710177945.4A CN106778923B (en) | 2017-03-23 | 2017-03-23 | Electric energy quality disturbance signal classification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710177945.4A CN106778923B (en) | 2017-03-23 | 2017-03-23 | Electric energy quality disturbance signal classification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106778923A CN106778923A (en) | 2017-05-31 |
| CN106778923B true CN106778923B (en) | 2020-02-11 |
Family
ID=58966666
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710177945.4A Active CN106778923B (en) | 2017-03-23 | 2017-03-23 | Electric energy quality disturbance signal classification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106778923B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107392090A (en) * | 2017-06-05 | 2017-11-24 | 国网新疆电力公司经济技术研究院 | Optimize Classification of Power Quality Disturbances device ELM method |
| CN107817400A (en) * | 2017-10-23 | 2018-03-20 | 国家电网公司 | A kind of power equipment data processing equipment and method |
| CN108288039A (en) * | 2018-01-25 | 2018-07-17 | 浙江群力电气有限公司 | Voltage swell and electrical energy power quality disturbance recognition methods, device and the equipment temporarily dropped |
| CN108562811B (en) * | 2018-03-12 | 2020-05-22 | 西安理工大学 | Bidirectional long-short term memory-based complex power quality disturbance analysis method |
| CN108664923A (en) * | 2018-05-10 | 2018-10-16 | 长沙理工大学 | Voltage disturbance Modulation recognition method and system based on LMD and machine learning classification |
| CN108664950A (en) * | 2018-05-22 | 2018-10-16 | 天津大学 | A kind of electrical energy power quality disturbance identification and sorting technique based on deep learning |
| CN108921285B (en) * | 2018-06-22 | 2021-05-25 | 西安理工大学 | Bidirectional gate control cyclic neural network-based classification method for power quality disturbance |
| CN109324250A (en) * | 2018-11-29 | 2019-02-12 | 广东电网有限责任公司 | A kind of Power Quality Disturbance recognition methods |
| CN110728195B (en) * | 2019-09-18 | 2022-04-01 | 武汉大学 | Power quality disturbance detection method based on YOLO algorithm |
| CN111191548B (en) * | 2019-12-23 | 2024-01-23 | 广东电网有限责任公司 | Discharge signal identification method and identification system based on S transformation |
| CN110989363B (en) * | 2019-12-27 | 2022-01-25 | 广东电网有限责任公司电力科学研究院 | Electric energy quality control method and device based on deep learning |
| 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 |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105447464A (en) * | 2015-11-23 | 2016-03-30 | 广东工业大学 | Electric energy quality disturbance recognition and classification method based on PSO |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9116716B2 (en) * | 2012-06-24 | 2015-08-25 | Veerai Bharatia | Systems and methods for declarative applications |
-
2017
- 2017-03-23 CN CN201710177945.4A patent/CN106778923B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105447464A (en) * | 2015-11-23 | 2016-03-30 | 广东工业大学 | Electric energy quality disturbance recognition and classification method based on PSO |
Non-Patent Citations (2)
| Title |
|---|
| 基于S变换和弹性神经网络的电能质量扰动分类;赵强强等;《西安理工大学学报》;20101231;第26卷(第04期);第468-472页 * |
| 时间序列小波神经网络在故障测距中的应用;张兆宁等;《中国电机工程学报》;20010630;第21卷(第06期);第66-71页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106778923A (en) | 2017-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106778923B (en) | Electric energy quality disturbance signal classification method and device | |
| Manimala et al. | Optimization techniques for improving power quality data mining using wavelet packet based support vector machine | |
| Kaewarsa et al. | Recognition of power quality events by using multiwavelet-based neural networks | |
| CN110738010A (en) | Wind power plant short-term wind speed prediction method integrated with deep learning model | |
| Wang et al. | Classification of power quality events using optimal time-frequency representations-part 1: Theory | |
| Dou et al. | Hybrid model for renewable energy and loads prediction based on data mining and variational mode decomposition | |
| Ahmadipour et al. | Islanding detection technique using Slantlet Transform and Ridgelet Probabilistic Neural Network in grid-connected photovoltaic system | |
| CN110083940A (en) | A kind of short-term wind speed forecasting method based on SSA-HMD-CNNSVM model | |
| Ijaz et al. | Classification of power quality disturbances using Wavelet Transform and Optimized ANN | |
| CN114781435B (en) | Power electronic circuit fault diagnosis method based on improved Harris eagle optimization algorithm optimization variation modal decomposition | |
| Mohammadi et al. | Detection and classification of multiple power quality disturbances based on temporal deep learning | |
| Dong et al. | Short-term wind-speed forecasting based on multiscale mathematical morphological decomposition, K-means clustering, and stacked denoising autoencoders | |
| CN113093058A (en) | NPC three-level inverter open-circuit fault diagnosis method | |
| Shukla et al. | Power quality disturbances classification based on Gramian angular summation field method and convolutional neural networks | |
| Fu et al. | Powercog: A practical method for recognizing power quality disturbances accurately in a noisy environment | |
| Guo et al. | A data-enhanced high impedance fault detection method under imbalanced sample scenarios in distribution networks | |
| Hussein et al. | Multi-step-ahead chaotic time series prediction using coevolutionary recurrent neural networks | |
| Liu et al. | Fault diagnosis of rolling bearing combining improved AWSGMD-CP and ACO-ELM model | |
| Abubakar et al. | High-Precision Identification of Power Quality Disturbances Based on Discrete Orthogonal S-Transforms and Compressed Neural Network Methods | |
| Saini et al. | Power quality events classification using MWT and MLP | |
| Jia et al. | Partial discharge pattern recognition using variable predictive model‐based class discrimination with kernel partial least squares regression | |
| Sykora et al. | Artificial Neural Networks in Educational Process | |
| CN111191548B (en) | Discharge signal identification method and identification system based on S transformation | |
| Zhu et al. | Wind power prediction based on the chaos theory and the GABP neural network | |
| Xu et al. | Effective context inconsistency elimination algorithm based on feedback and reliability distribution for IOV |
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 |