CN105447464A - Electric energy quality disturbance recognition and classification method based on PSO - Google Patents
Electric energy quality disturbance recognition and classification method based on PSO Download PDFInfo
- Publication number
- CN105447464A CN105447464A CN201510822400.5A CN201510822400A CN105447464A CN 105447464 A CN105447464 A CN 105447464A CN 201510822400 A CN201510822400 A CN 201510822400A CN 105447464 A CN105447464 A CN 105447464A
- Authority
- CN
- China
- Prior art keywords
- signal
- classification
- pso
- quality disturbance
- electric energy
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- 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
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides an electric energy quality disturbance recognition and classification method based on a PSO, and the method achieves detection and positioning of a disturbance signal through employing complex wavelet transform, and effectively extracts a dynamic electric energy quality disturbance feature vector. After the optimization of an SVM parameter is completed through the PSO algorithm, the method carries out the automatic recognition and classification of the electric energy quality disturbance according to an extracted feature signal. The method can effectively improve the training speed and classification accuracy of the detection and classification of the electric energy quality disturbance. The complex wavelet transform can iron out the defect that the conventional real wavelet transform just can achieve the analysis of the amplitude-frequency of a signal, and can achieve the analysis of the amplitude-frequency and phase-frequency features of the signal, and also can provide a plurality of types of composite information. The method can accurately recognize the most common dynamic disturbance signals in a power system. Compared with a conventional method for recognizing an interference signal through a neural network, the method is accurate and reliable in recognition, and is higher in accuracy.
Description
Technical field
The present invention relates to electric power quality analytical technology research field, more specifically, relate to a kind of electrical energy power quality disturbance recognition and classification method based on PSO.
Background technology
The quality of power supply (PowerQuality, PQ) problem has caused the extensive concern of power industry worker.Along with industrial control field is on the increase to non-linear, system integrating, the nonlinear-load capacity such as future development and the medium-and-large-sized rectifying installation of system, frequency control equipment such as extensive, many mains supplies quality of power supply causes severe contamination, have a strong impact on electric power enterprise to power the quality of electric energy, to the accurate recognition and classification of electrical energy power quality disturbance, it is the prerequisite ensureing power grid security economical operation and improve power supply quality.
In recent years, method for power quality analysis employing is substantially all the method based on digital signal processing and artificial intelligence, namely first adopt the digital signal processing instruments such as Fourier transform, Short Time Fourier Transform, wavelet transformation, dq conversion to detect and feature extraction electrical energy power quality disturbance, then adopt the artificial intelligence approach such as artificial neural network, expert system to classify to electrical energy power quality disturbance.Shortcoming based on the method for expert system is that the knowledge of electrical energy power quality disturbance extracts more difficult realization, and along with the increase of electrical energy power quality disturbance kind, expert system easily produces shot array problem; Although artificial neural network is widely applied in a lot of field, but its self there is larger defect, there is local optimum problem in such as algorithm, algorithm exists over-fitting and poor fitting problem, convergence is poor, the training time is longer, limited reliability etc.
The identification of Power Quality Disturbance and the problems such as the main extraction of research characteristic vector, the optimization of SVM classifier of classifying in electrical network.Current academic research field, mostly utilize the characteristic of the multiresolution analysis of wavelet transformation, time-frequency screen diverse location has different resolution, the disturbances location of the quality of power supply, the determination etc. of disturbance duration is realized by amplitude characteristic, but disturbing signal not only phase-frequency characteristic is various, and phase place is also very important, extract phase information, new thought and new technology will be provided to the research analyzing undesired signal in electrical network.In addition, in present stage, for electrical energy power quality disturbance recognition and classification structure SVM classifier in Selecting parameter, be all given parameter, and do not find the best approach to carry out optimizing to parameter.
Summary of the invention
The invention provides a kind of electrical energy power quality disturbance recognition and classification method based on PSO, after the method is optimized SVM parameter by PSO algorithm, to Dynamic Power Quality Disturbances, automatic recognition and classification is carried out according to the characteristic signal extracted to it, effectively can improve training speed and the classification accuracy of duration power quality disturbances and classification.
In order to reach above-mentioned technique effect, technical scheme of the present invention is as follows:
Based on an electrical energy power quality disturbance recognition and classification method of PSO, comprise the following steps:
A, the signal model of foundation containing common dynamic disturbances signal, complex wavelet transform is adopted to extract disturbing signal from input voltage signal, adopt the Db4 complex wavelets of Mallat fast wavelet algorithm to carry out multiple dimensioned Phase information decomposition to disturbing signal by structure, obtain Phase information coefficient; Wherein, common dynamic disturbances signal comprises voltage swells signal, voltage dip signal, temporary voltage look-at-me, transient state pulse signal and transient oscillation signal;
B, according to the real part of Phase information coefficient and imaginary part, calculate and extract the simple of disturbing signal and composite information;
C, multiple dimensioned Phase information decomposition is carried out to disturbing signal after, choose the proper vector that the composite information that constructs in the energy on each layer, mean value, standard deviation, disturbance duration and step b forms disturbing signal;
D, first utilize the SVM of PSO optimizing optimal parameter, structure multistage clustering svm classifier tree, secondly proper vector and classification corresponding to proper vector are inputted this classification tree to carry out training and obtain training sample, then utilize training sample to classify to the test sample book comprising above-mentioned common dynamic disturbances signal, finally obtain and corresponding classification results required by exporting.
Further, in described step b, the simple information obtained through complex wavelet transform comprises real part, imaginary part, amplitude and phase place, comprises imaginary part and phase place compound, real part and phase place compound and amplitude and phase place compound according to the composite information of these simple information structure dynamic disturbances signal.
Further, described common dynamic disturbances signal comprises voltage swells signal, voltage dip signal, temporary voltage look-at-me, transient state pulse signal and transient oscillation signal.
Compared with prior art, the beneficial effect of technical solution of the present invention is:
The present invention adopts complex wavelet transform to carry out detection and positioning to disturbing signal, the proper vector of effective extraction Dynamic Power Quality Disturbances, after SVM parameter being optimized by PSO algorithm, to Dynamic Power Quality Disturbances, automatic recognition and classification is carried out according to the characteristic signal extracted to it, effectively can improve training speed and the classification accuracy of duration power quality disturbances and classification.Complex wavelet transform can make up real Wavelet transformation in the past can only the shortcoming of analytic signal amplitude-frequency, can the simultaneously amplitude-frequency of analytic signal and phase-frequency characteristic multiple composite information can be provided, modal several dynamic disturbances signal in electric system can be identified more accurately, compared with the methods such as traditional neural network recognization undesired signal, the method identification accurately and reliably and accuracy rate is higher.
Accompanying drawing explanation
Fig. 1 is the electrical energy power quality disturbance recognition methods block diagram based on the SVM of PSO optimization in the present invention;
Fig. 2 is disturbed depth and sorting technique particular flow sheet in Fig. 1;
Fig. 3 is the schematic diagram of Dynamic Power Quality Disturbances multistage clustering svm classifier tree;
Fig. 4 is PSO optimizing result figure in Fig. 1;
Fig. 5 is the Classification of Power Quality Disturbances result figure based on the SVM of PSO optimization in the present invention, there is shown the classification results in voltage swells process of the test;
Fig. 6 is traditional BP neural network training curve figure, there is shown the training curve in voltage swells process of the test;
Fig. 7 is BP neural network classification results figure, there is shown the classification results in voltage swells process of the test.
Embodiment
Accompanying drawing, only for exemplary illustration, can not be interpreted as the restriction to this patent;
In order to better the present embodiment is described, some parts of accompanying drawing have omission, zoom in or out, and do not represent the size of actual product;
To those skilled in the art, in accompanying drawing, some known features and explanation thereof may be omitted is understandable.
Below in conjunction with drawings and Examples, technical scheme of the present invention is described further.
Embodiment 1
As shown in Fig. 1 to 7, a kind of electrical energy power quality disturbance recognition and classification method based on PSO, comprises the following steps:
A, the signal model of foundation containing common dynamic disturbances signal, common disturbing signal comprises voltage swells signal, voltage dip signal, temporary voltage look-at-me, transient state pulse signal and transient oscillation signal five kinds, and table 1 shows the model of five kinds of common dynamic disturbances signals and corresponding optimum configurations.
The common dynamic disturbances signal model of five kinds, table 1 table 1
Complex wavelet transform is adopted to extract disturbing signal from input voltage signal, adopt the Db4 complex wavelets of Mallat fast wavelet algorithm to carry out multiple dimensioned Phase information decomposition to disturbing signal by structure, obtain the structural information of disturbing signal on each frequency band and Phase information coefficient.Wherein, as follows to the specific practice of disturbing signal extraction:
If f (t) is the input voltage signal containing disturbing signal, input voltage signal f (t) is carried out continuous complex wavelet conversion and inverse transformation obtains:
In formula, wave function ψ (t) is continuous wavelet, represents the complex conjugate of ψ (t), a is contraction-expansion factor, b is shift factor, and for avoiding the signal energy reconstructed during complex wavelet transform to shift, converting input voltage signal f (t) to analytic signal is:
z(t)=f(t)+jH[f(t)]
In formula, the Hilbert that H [f (t)] is f (t) converts, namely
B, through the simple information of complex wavelet transform be real part WTR, imaginary part WTI, amplitude WTM and phase place WTPH, composite information according to these simple information structuring dynamic disturbances signals: imaginary part and phase place compound WTIPH, real part and phase place compound WTRPH, amplitude and phase place compound WTMPH, is beneficial to and increases the ability that complex wavelet transform extracts feeble signal.The specific practice calculating the composite information extracting disturbing signal is as follows:
Then according to simple information structure composite information, expression formula is as follows:
WTIPH=WTI·WTPH
WTRPH=WTR·WTPH
WTMPH=WTM·WTPH
WTRIPH=WTR·WTI·WTPH
Because the waveform of disturbing signal is not only relevant with its amplitude characteristic, and relevant with phase-frequency characteristic, so the effect of complex wavelet translation not only depends on the amplitude characteristic of Phase information, depend on its phase-frequency characteristic simultaneously.Through complex wavelet transform structure composite signal, can to the amplitude-frequency of signal and phase-frequency characteristic comprehensive evaluation, analytical effect is better.
The proper vector of c, extraction disturbing signal
After multiple dimensioned Phase information decomposition is carried out to disturbing signal, choose the proper vector T that the composite information constructed in the energy on each layer, mean value, standard deviation and disturbance duration and step b forms disturbing signal, the specific practice extracting perturbation features vector step is:
Choose the proper vector that the composite information constructed in the energy on each yardstick, mean value, standard deviation and disturbance duration and step b forms disturbing signal, be expressed as: T=(K
w, K
av, K
δ, K
t, K
wT)
Wherein, K
wfor the energy on each yardstick, K
avfor the mean value of each yardstick, K
δfor the standard deviation of each yardstick, K
tfor the disturbance duration of each yardstick, K
wTfor the composite information on each yardstick of constructing in step b.
The svm classifier identification of d, PSO Optimal Parameters
First the SVM of PSO optimizing optimal parameter is utilized, structure multistage clustering svm classifier tree, secondly proper vector and classification corresponding to proper vector are inputted this classification tree to carry out training and obtain training sample, then utilize training sample to classify to test sample book, finally obtain and classification results required by exporting.
Choosing of d1, kernel function
RBF kernel function is selected in this invention, and expression formula is:
K(x-x
c)=exp(g||x-x
c||
2)
Wherein x
cfor kernel function center, g is adjustable parameter, the radial effect scope of control function.
D2, Selecting parameter
Choosing of penalty factor c and g has larger impact to classification results.This invention utilizes PSO to optimize SVM parametric technique, and the optimized parameter obtained is (c, g)=(8.2645,13.5708)
Table 2PSO optimizing parametric results
Test 1 | Test 2 | Test 3 | Test 4 | Test 5 | |
c | 10.2 | 12.92 | 11.084 | 8.2645 | 11.4 |
g | 12.78 | 12.67 | 16.34 | 13.56 | 15.4 |
Classification accuracy (%) | 98.1 | 98.1 | 98.1 | 99.24 | 98 |
Program runtime t (s) | 99.7 | 100.8 | 100.3 | 100.1 | 95.2 |
The structure of d3, multistage clustering svm classifier tree
This invention is by constructing 4 two class SVM sub-classifiers,, these two class SVM sub-classifiers form a tree structure, adopt the many five kinds of Dynamic Signals of multistage clustering SVM algorithm realization to classify, largely can reduce the possibility that sample mistake is divided, the accuracy rate improving classification also reduces computing time.
D4, Classification and Identification
Obvious to the feature difference of these five kinds of dynamic disturbances signal extractions, and there is very strong noiseproof feature.The SVM of PSO Optimal Parameters has very high small-sample learning ability, and model Generalization Ability is strong, is applicable to the identification of dynamic disturbances signal.
By MATLAB software to five kinds of common dynamic disturbances signal Modling model as table 2, wherein sample frequency is 1.6kHz, and disturbing signal fundamental frequency is 50Hz, r (t) is white noise, and signal to noise ratio (S/N ratio) is 20dB.Divide sample matrix equally two groups at random, one group is training sample, and one group is test sample book, tests common five kinds of dynamic disturbance signals.The inventive method is adopted to carry out Classification and Identification to five kinds of Dynamic Signals.
Table 3 the inventive method classification results
Undesired signal type | Voltage swells | Voltage dip | Brief interruption | Transient state pulse | Transient oscillation |
Training accuracy rate (%) | 100 | 100 | 100 | 100 | 100 |
Test accuracy rate (%) | 100 | 100 | 100 | 100 | 100 |
Table 4BP neural network classification results
Undesired signal type | Voltage swells | Voltage dip | Brief interruption | Transient state pulse | Transient oscillation |
Classification accuracy (%) | 97.2 | 94.2 | 92.3 | 91.4 | 92.1 |
From form above, the inventive method has very high discrimination to five kinds of common interference signals.
The corresponding same or analogous parts of same or analogous label;
Describe in accompanying drawing position relationship for only for exemplary illustration, the restriction to this patent can not be interpreted as;
Obviously, the above embodiment of the present invention is only for example of the present invention is clearly described, and is not the restriction to embodiments of the present invention.For those of ordinary skill in the field, can also make other changes in different forms on the basis of the above description.Here exhaustive without the need to also giving all embodiments.All any amendments done within the spirit and principles in the present invention, equivalent to replace and improvement etc., within the protection domain that all should be included in the claims in the present invention.
Claims (3)
1., based on an electrical energy power quality disturbance recognition and classification method of PSO, it is characterized in that, comprise the following steps:
A, the signal model of foundation containing common dynamic disturbances signal, complex wavelet transform is adopted to extract disturbing signal from input voltage signal, adopt the Db4 complex wavelets of Mallat fast wavelet algorithm to carry out multiple dimensioned Phase information decomposition to disturbing signal by structure, obtain Phase information coefficient;
B, according to the real part of Phase information coefficient and imaginary part, calculate and extract the simple of disturbing signal and composite information;
C, multiple dimensioned Phase information decomposition is carried out to disturbing signal after, choose the proper vector that the composite information that constructs in the energy on each layer, mean value, standard deviation, disturbance duration and step b forms disturbing signal;
D, first utilize the SVM of PSO optimizing optimal parameter, structure multistage clustering svm classifier tree, secondly proper vector and classification corresponding to proper vector are inputted this classification tree to carry out training and obtain training sample, then utilize training sample to classify to the test sample book comprising above-mentioned common dynamic disturbances signal, finally obtain and corresponding classification results required by exporting.
2. the electrical energy power quality disturbance recognition and classification method based on PSO according to claim 1, it is characterized in that, in described step b, the simple information obtained through complex wavelet transform comprises real part, imaginary part, amplitude and phase place, comprises imaginary part and phase place compound, real part and phase place compound and amplitude and phase place compound according to the composite information of these simple information structure dynamic disturbances signal.
3. the electrical energy power quality disturbance recognition and classification method based on PSO according to claim 1, it is characterized in that, described common dynamic disturbances signal comprises voltage swells signal, voltage dip signal, temporary voltage look-at-me, transient state pulse signal and transient oscillation signal.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510822400.5A CN105447464A (en) | 2015-11-23 | 2015-11-23 | Electric energy quality disturbance recognition and classification method based on PSO |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510822400.5A CN105447464A (en) | 2015-11-23 | 2015-11-23 | Electric energy quality disturbance recognition and classification method based on PSO |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105447464A true CN105447464A (en) | 2016-03-30 |
Family
ID=55557624
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510822400.5A Pending CN105447464A (en) | 2015-11-23 | 2015-11-23 | Electric energy quality disturbance recognition and classification method based on PSO |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105447464A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106778923A (en) * | 2017-03-23 | 2017-05-31 | 广东电网有限责任公司珠海供电局 | A kind of Power Quality Disturbance sorting technique and device |
CN106908661A (en) * | 2017-02-20 | 2017-06-30 | 国网江西省电力公司电力科学研究院 | Electric signal disturbance identification method and device under a kind of exceptional operating conditions |
CN106970278A (en) * | 2017-03-28 | 2017-07-21 | 北京印刷学院 | Electrical energy power quality disturbance recognition methods based on fitting Lifting Wavelet and mean analysis |
CN107123987A (en) * | 2017-05-11 | 2017-09-01 | 华东交通大学 | Electrical energy power quality disturbance recognition methods based on on-line training weighed SVM |
CN107462785A (en) * | 2017-06-14 | 2017-12-12 | 郑州轻工业学院 | The more disturbing signal classifying identification methods of the quality of power supply based on GA SVM |
CN108197073A (en) * | 2018-02-09 | 2018-06-22 | 国网江苏省电力有限公司电力科学研究院 | A kind of improved electric vehicle rechargeable electrical energy signature analysis method |
CN108629087A (en) * | 2018-04-13 | 2018-10-09 | 广州供电局有限公司 | Disturbance event model building method, device and disturbance event recognition methods, device |
CN108805204A (en) * | 2018-06-12 | 2018-11-13 | 东北大学 | Electrical energy power quality disturbance analytical equipment based on deep neural network and its application method |
CN113361427A (en) * | 2021-06-11 | 2021-09-07 | 温州大学 | WT and GA-PNN based composite power quality disturbance classification method |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101339208A (en) * | 2008-08-12 | 2009-01-07 | 中国矿业大学 | Voltage quality monitoring and perturb automatic classification method based on analysis in time-domain |
CN102063626A (en) * | 2010-12-29 | 2011-05-18 | 吉林大学 | Power quality disturbance mode discrimination method |
CN102288843A (en) * | 2011-05-16 | 2011-12-21 | 湖南大学 | Power quality disturbance signal detection method |
CN102323480A (en) * | 2011-05-19 | 2012-01-18 | 西南交通大学 | A kind of power quality analysis method based on the Hilbert-Huang conversion |
CN102750543A (en) * | 2012-05-31 | 2012-10-24 | 西南交通大学 | Transient state power quality disturbance classification recognition method based on BUD spectrum kurtosis |
CN103488996A (en) * | 2013-09-05 | 2014-01-01 | 国家电网公司 | Power quality disturbing signal classifying method based on wavelet domain statistics |
CN103743980A (en) * | 2014-01-14 | 2014-04-23 | 山东科技大学 | Power quality disturbance recognition and classification method based on PSO (Particle Swarm Optimization) for SVM (Support Vector Machine) |
-
2015
- 2015-11-23 CN CN201510822400.5A patent/CN105447464A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101339208A (en) * | 2008-08-12 | 2009-01-07 | 中国矿业大学 | Voltage quality monitoring and perturb automatic classification method based on analysis in time-domain |
CN102063626A (en) * | 2010-12-29 | 2011-05-18 | 吉林大学 | Power quality disturbance mode discrimination method |
CN102288843A (en) * | 2011-05-16 | 2011-12-21 | 湖南大学 | Power quality disturbance signal detection method |
CN102323480A (en) * | 2011-05-19 | 2012-01-18 | 西南交通大学 | A kind of power quality analysis method based on the Hilbert-Huang conversion |
CN102750543A (en) * | 2012-05-31 | 2012-10-24 | 西南交通大学 | Transient state power quality disturbance classification recognition method based on BUD spectrum kurtosis |
CN103488996A (en) * | 2013-09-05 | 2014-01-01 | 国家电网公司 | Power quality disturbing signal classifying method based on wavelet domain statistics |
CN103743980A (en) * | 2014-01-14 | 2014-04-23 | 山东科技大学 | Power quality disturbance recognition and classification method based on PSO (Particle Swarm Optimization) for SVM (Support Vector Machine) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106908661A (en) * | 2017-02-20 | 2017-06-30 | 国网江西省电力公司电力科学研究院 | Electric signal disturbance identification method and device under a kind of exceptional operating conditions |
CN106778923A (en) * | 2017-03-23 | 2017-05-31 | 广东电网有限责任公司珠海供电局 | A kind of Power Quality Disturbance sorting technique and device |
CN106778923B (en) * | 2017-03-23 | 2020-02-11 | 广东电网有限责任公司珠海供电局 | Electric energy quality disturbance signal classification method and device |
CN106970278B (en) * | 2017-03-28 | 2019-04-16 | 北京印刷学院 | Electrical energy power quality disturbance recognition methods based on fitting Lifting Wavelet and mean analysis |
CN106970278A (en) * | 2017-03-28 | 2017-07-21 | 北京印刷学院 | Electrical energy power quality disturbance recognition methods based on fitting Lifting Wavelet and mean analysis |
CN107123987A (en) * | 2017-05-11 | 2017-09-01 | 华东交通大学 | Electrical energy power quality disturbance recognition methods based on on-line training weighed SVM |
CN107462785A (en) * | 2017-06-14 | 2017-12-12 | 郑州轻工业学院 | The more disturbing signal classifying identification methods of the quality of power supply based on GA SVM |
CN108197073A (en) * | 2018-02-09 | 2018-06-22 | 国网江苏省电力有限公司电力科学研究院 | A kind of improved electric vehicle rechargeable electrical energy signature analysis method |
CN108197073B (en) * | 2018-02-09 | 2021-05-14 | 国网江苏省电力有限公司电力科学研究院 | Improved electric vehicle charging electric energy signal characteristic analysis method |
CN108629087A (en) * | 2018-04-13 | 2018-10-09 | 广州供电局有限公司 | Disturbance event model building method, device and disturbance event recognition methods, device |
CN108805204A (en) * | 2018-06-12 | 2018-11-13 | 东北大学 | Electrical energy power quality disturbance analytical equipment based on deep neural network and its application method |
CN113361427A (en) * | 2021-06-11 | 2021-09-07 | 温州大学 | WT and GA-PNN based composite power quality disturbance classification method |
CN113361427B (en) * | 2021-06-11 | 2024-03-15 | 温州大学 | Composite electric energy quality disturbance classification method based on WT and GA-PNN |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105447464A (en) | Electric energy quality disturbance recognition and classification method based on PSO | |
CN103743980A (en) | Power quality disturbance recognition and classification method based on PSO (Particle Swarm Optimization) for SVM (Support Vector Machine) | |
Liu et al. | Complex power quality disturbances classification via curvelet transform and deep learning | |
CN103076547B (en) | Method for identifying GIS (Gas Insulated Switchgear) local discharge fault type mode based on support vector machines | |
CN108573225B (en) | Partial discharge signal pattern recognition method and system | |
Lazzaretti et al. | Novelty detection and multi-class classification in power distribution voltage waveforms | |
CN101832471B (en) | Signal identification and classification method | |
CN107462785B (en) | The more disturbing signal classifying identification methods of power quality based on GA-SVM | |
CN103728551B (en) | A kind of analog-circuit fault diagnosis method based on cascade integrated classifier | |
CN105004498A (en) | Vibration fault diagnosis method of hydroelectric generating set | |
CN105572501A (en) | Power quality disturbance identification method based on SST conversion and LS-SVM | |
CN106548013B (en) | Utilize the voltage sag source identification method for improving incomplete S-transformation | |
Motlagh et al. | Power quality disturbances recognition using adaptive chirp mode pursuit and grasshopper optimized support vector machines | |
CN112881942B (en) | Abnormal current diagnosis method and system based on wavelet decomposition and empirical mode decomposition | |
CN103149514B (en) | Method for identifying multi-insulated defect mode in GIS (gas insulated switchgear) | |
CN107830996B (en) | Fault diagnosis method for aircraft control surface system | |
CN104036289A (en) | Hyperspectral image classification method based on spatial and spectral features and sparse representation | |
CN101980298A (en) | Multi-agent genetic clustering algorithm-based image segmentation method | |
CN103412557A (en) | Industrial fault detection and diagnostic method suitable for nonlinear process on-line monitoring | |
CN104535905A (en) | Partial discharge diagnosis method based on naive bayesian classification | |
CN110702966B (en) | Fault arc detection method, device and system based on probabilistic neural network | |
CN104966161A (en) | Electric energy quality recording data calculating analysis method based on Gaussian mixture model | |
CN103413134A (en) | Ground moving target micro-tremor signal characteristic extraction based on sparse decomposition | |
CN104156628A (en) | Ship radiation signal recognition method based on multi-kernel learning and discriminant analysis | |
CN103528820B (en) | A kind of Fault Diagnosis of Roller Bearings based on distance evaluation factor potential-energy function |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160330 |
|
WD01 | Invention patent application deemed withdrawn after publication |