CN105447502A - Transient power disturbance identification method based on S conversion and improved SVM algorithm - Google Patents
Transient power disturbance identification method based on S conversion and improved SVM algorithm Download PDFInfo
- Publication number
- CN105447502A CN105447502A CN201510741245.4A CN201510741245A CN105447502A CN 105447502 A CN105447502 A CN 105447502A CN 201510741245 A CN201510741245 A CN 201510741245A CN 105447502 A CN105447502 A CN 105447502A
- Authority
- CN
- China
- Prior art keywords
- algorithm
- transformation
- svm
- classification
- svm algorithm
- 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
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000001052 transient effect Effects 0.000 title claims abstract description 25
- 238000006243 chemical reaction Methods 0.000 title abstract 3
- 239000013598 vector Substances 0.000 claims description 35
- 230000006872 improvement Effects 0.000 claims description 17
- 238000013461 design Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 9
- 230000002123 temporal effect Effects 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 6
- 230000001105 regulatory effect Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- HUTDUHSNJYTCAR-UHFFFAOYSA-N ancymidol Chemical compound C1=CC(OC)=CC=C1C(O)(C=1C=NC=NC=1)C1CC1 HUTDUHSNJYTCAR-UHFFFAOYSA-N 0.000 claims description 3
- 230000010355 oscillation Effects 0.000 claims description 3
- 238000001228 spectrum Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 3
- 230000001737 promoting effect Effects 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 abstract 1
- 230000009466 transformation Effects 0.000 description 8
- 238000012706 support-vector machine Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000011109 contamination Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
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
- G06F18/2411—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
Abstract
The invention discloses a transient power disturbance identification method based on S conversion and an improved SVM algorithm. The method comprises the following steps: (1), carrying out processing on a disturbance signal based on improved S conversion; (2), extracting a disturbance signal characteristic; and (3) designing an SVM classifier based on a semi-supervised learning algorithm to classify samples. Compared with the previous power quality disturbance classification method, the provided method has beneficial effects: on the premise that the identification accuracy of the SVM algorithm is guaranteed, the improved semi-supervised learning algorithm is introduced into the sample with low reliability in the SVM algorithm, so that the identification accuracy of the disturbance signal can be improved; and advantages of good scientific and reasonable performances, high adaptability, and great promotional value and the like are realized.
Description
Technical field
The present invention is a kind of based on S-transformation and the transient power disturbance identification method improving SVM algorithm, is applied to Power Quality Transient disturbance automatic classification and location, equipment state on-line monitoring and assessment and power quality controlling.
Background technology
The existence of nonlinear-load, impact load and single-phase load, makes power grid environment be subject to severe contamination, and the power quality problem therefore caused also causes the attention of people day by day.Power Quality Transient disturbance automatic classification technology is the important foundation of power quality analysis and control, has great importance to the work such as transient state improvement, power electronic equipment condition monitoring, disturbance source locating.For improving the living standard of people and ensureing normal commercial production, must ensure that electric system can provide the electric power energy of high-quality.The intelligent classification of all kinds of electrical energy power quality disturbance has become the important research topic of electric system; A convenient, fast and accurate sorting algorithm can provide more high-rise application for modern intelligent electric meter and electrical network real-time monitoring system.
Conventional disturbance identification method generally comprises signal transacting and pattern-recognition 2 steps.Traditional transient disturbance method for identifying and classifying often adopts wavelet transformation, Short Time Fourier Transform etc. as signal processing means.Wavelet transformation is widely used in the feature extraction of Power Quality Disturbance owing to having good time-frequency characteristic, but the result of wavelet transformation lacks intuitive, there is spectral leakage and the easy problem such as affected by noise.And Short Time Fourier Transform exists defects such as needing selection window type and width and window width fixing, the use in power quality analysis is also restricted.S-transformation is development to Short Time Fourier Transform and wavelet transformation and succession, and its result has intuitive and not easily affected by noise.Pattern-recognition aspect, conventional method has artificial neural network, support vector machine, fuzzy classification etc.Compare additive method, support vector cassification efficiency is high, and antijamming capability is strong, has certain use value.But to the occasion of predicted vector comparatively dense, the Feasible degree of classification is not high.The occasion for the concrete occasion of application is lower to its classification results confidence level is needed to be optimized.
Summary of the invention
The object of the invention is to overcome the deficiencies in the prior art, provide a kind of scientific and reasonable, strong adaptability, antijamming capability are strong, have promotional value based on S-transformation and the transient power disturbance identification method improving SVM algorithm.
The object of the invention is to be achieved through the following technical solutions: based on S-transformation and the transient power disturbance identification method improving SVM algorithm, it comprises the following steps:
1) improvement S-transformation disturbing signal is utilized to process:
The key improving S-transformation adds regulatory factor λ in Gaussian window
m, accelerate according to the frequency distribution situation of sample signal or the width of the Gaussian window that slows down with the speed of frequency transformation.The computing formula of the S-transformation improved is:
λ in formula
mfor regulatory factor.Work as λ
mduring > 1, window width is that inverse proportion accelerates change with frequency, and temporal resolution is higher; As 0 < λ
mduring < 1, Gaussian window pace of change is slack-off, and frequency resolution improves.
2) disturbing signal feature extraction
Determine 8 kinds of feature construction proper vectors, from raw information and improvement S-transformation result of calculation, extract the required characteristic quantity of classification, each characteristic quantity implication is as follows:
F1: fundamental frequency amplitude average
F2: in fundamental frequency amplitude, amplitude is greater than the sampled point number of standard value 105%
F3: in fundamental frequency amplitude, amplitude is less than the sampled point number of standard value 95%
F4: in fundamental frequency amplitude, amplitude is less than the sampled point number of standard value 10%
F5: frequency envelope line crest number
F6: extract the average being more than or equal to 3 times of fundamental frequencies in row vector maximum value temporal envelope line
F7: temporal envelope line standard is poor
F8: the standard deviation of frequency spectrum
3) design is classified to sample based on the SVM classifier of semi-supervised learning algorithm
Classify for involved 6 kinds of disturbance design category devices, comprising S1 desired voltage signal, S2 fall temporarily voltage signal, the temporary up voltage signal of S3, S4 voltage interrupt signal, S5 transient oscillation signal and, S6 harmonic signal in short-term.The principle of design of sorter is: first classify to sample with SVM algorithm, then carry out nothing supervision with the classification of semi-supervised learning sorting algorithm arest neighbors to SVM decision function result to correct, if the classification results confidence level of SVM algorithm is higher, then accept classification results, if the classification results confidence level of SVM algorithm is lower, support vector around the nearest neighbor algorithm determination predicted vector then using improvement in certain area M, Euclidean distance value is asked to predicted vector and support vector, and using the inverse of distance as decision variable, using the mean value of the decision variable of generic effective support vector as decision function value, the decision function value of all kinds of support vectors all in predicted vector M region is compared, carrying out from big to small arranges, statistical study is carried out with the result of SVM algorithm classification, finally determine classification results.
Based on S-transformation and the transient power disturbance identification method improving SVM algorithm, first improvement S-transformation disturbing signal is utilized to process, S-transformation method not only has the ability of Short Time Fourier Transform single-frequency territory independent analysis, also there is time domain and the frequency localization characteristic of wavelet transformation, there is self-adaptation time frequency window, by the improvement to S-transformation, obtain generalized S-transform, the key improving S-transformation adds regulatory factor λ in Gaussian window
m, accelerate according to the frequency distribution situation of sample signal or the width of the Gaussian window that slows down with the speed of frequency transformation, can better analyze disturbing signal; On this basis, from raw information and improvement S-transformation result of calculation, 6 kinds of feature construction proper vectors are extracted; The SVM algorithm based on semi-supervised learning algorithm is finally adopted to carry out Classification and Identification to sample.Compared with Power Quality Disturbance Classification Method in the past, on the basis that ensure that SVM algorithm recognition accuracy, in the sample that SVM algorithm confidence level is lower, introduce the semi-supervised learning algorithm improved, the recognition accuracy of disturbing signal can be improved further, have scientific and reasonable, strong adaptability, promotional value advantages of higher.
Accompanying drawing explanation
Fig. 1 is that the embodiment of the present invention is based on the process flow diagram of S-transformation with the transient power disturbance identification method of improvement SVM algorithm.
Fig. 2 be the embodiment of the present invention based on S-transformation and improve SVM algorithm transient power disturbance identification method in improve S-transformation algorithm flow chart.
Fig. 3 be the embodiment of the present invention based on S-transformation and improve SVM algorithm transient power disturbance identification method in improve the processing flow chart of S-transformation to Power Quality Disturbance.
Fig. 4 is that the embodiment of the present invention is based on S-transformation and Classification of Transient Power Quality Disturbances process flow diagram in the transient power disturbance identification method of improvement SVM algorithm.
Embodiment
In order to make objects and advantages of the present invention clearly understand, below in conjunction with embodiment, the present invention is further elaborated.Should be appreciated that specific embodiment described herein only in order to explain the present invention, be not intended to limit the present invention
As shown in Figure 1, embodiments provide a kind of based on S-transformation and the transient power disturbance identification method improving SVM algorithm, it comprises the following steps:
1) improvement S-transformation disturbing signal is utilized to process:
The key improving S-transformation adds regulatory factor λ in Gaussian window
m, accelerate according to the frequency distribution situation of sample signal or the width of the Gaussian window that slows down with the speed of frequency transformation.The computing formula of the S-transformation improved is:
λ in formula
mfor regulatory factor.Work as λ
mduring > 1, window width is that inverse proportion accelerates change with frequency, and temporal resolution is higher; As 0 < λ
mduring < 1, Gaussian window pace of change is slack-off, and frequency resolution improves.
2) disturbing signal feature extraction
Determine 8 kinds of feature construction proper vectors, from raw information and improvement S-transformation result of calculation, extract the required characteristic quantity of classification, each characteristic quantity implication is as follows:
F1: fundamental frequency amplitude average
F2: in fundamental frequency amplitude, amplitude is greater than the sampled point number of standard value 105%
F3: in fundamental frequency amplitude, amplitude is less than the sampled point number of standard value 95%
F4: in fundamental frequency amplitude, amplitude is less than the sampled point number of standard value 10%
F5: frequency envelope line crest number
F6: extract the average being more than or equal to 3 times of fundamental frequencies in row vector maximum value temporal envelope line
F7: temporal envelope line standard is poor
F8: the standard deviation of frequency spectrum
3) design is classified to sample based on the SVM classifier of semi-supervised learning algorithm
Classify for involved 6 kinds of disturbance design category devices, comprising S1 desired voltage signal, S2 fall temporarily voltage signal, the temporary up voltage signal of S3, S4 voltage interrupt signal, S5 transient oscillation signal and, S6 harmonic signal in short-term.The principle of design of sorter is: first classify to sample with SVM algorithm, then carry out nothing supervision with the classification of semi-supervised learning sorting algorithm arest neighbors to SVM decision function result to correct, if the classification results confidence level of SVM algorithm is higher, then receive classification results, if the classification results confidence level of SVM algorithm is lower, support vector around the nearest neighbor algorithm determination predicted vector then using improvement in certain area M, Euclidean distance value is asked to predicted vector and support vector, and using the inverse of distance as decision variable, using the mean value of the decision variable of generic effective support vector as decision function value, the decision function value of all kinds of support vectors all in predicted vector M region is compared, carrying out from big to small arranges, statistical study is carried out with the result of SVM algorithm classification, finally determine classification results.
With reference to Fig. 1-Fig. 4, embodiment based on S-transformation and the transient power disturbance identification method improving SVM algorithm, comprising:
A Power Quality Disturbance builds
According to the standard of IEEE and the perturbation features of the quality of power supply, construct the signal modeling of electrical energy power quality disturbance, well characterize actual electric energy quality signal.
B utilizes S-transformation to detect transient power quality disturbance signal, comprises disturbance start/stop time, perturbation amplitude, forcing frequency etc., S-transformation to the overhaul flow chart of Power Quality Disturbance as Fig. 2.
The feature extraction of C disturbing signal
According to the module time-frequency matrixes obtained after transient power quality disturbance signal S-transformation, produce the family curve of disturbing signal S-transformation, and therefrom extract the proper vector needed for 8 kinds of feature construction classification.
D furthers investigate support vector machine and fuzzy KNN algorithm, and the two effective integration is obtained the SVM algorithm based on semi-supervised learning, and the characteristic quantity utilizing S-transformation to obtain input sorter, obtain good classifying quality, its classification process figure as shown in Figure 4.
E uses simulate signal to verify validity of the present invention
Often kind of disturbing signal emulation is generated each 500 samples, wherein often organize 300 samples as training sample, 200 samples as test sample book, and add the white noise that signal to noise ratio (S/N ratio) is 40db, 30db and 20db respectively often organizing in test disturbance, with better close to actual signal.With 300 training samples, support vector machine is trained, obtain supporting vector machine model, then 200 test sample book input supporting vector machine models, if classification results confidence level is higher, then think that support vector cassification result is correct, otherwise with k nearest neighbor algorithm, result is revised, calculate the distance of sample and all kinds of support vector of surrounding, carrying out from big to small arranges, and sample is assigned in nearest support vector machine classification.Result is as shown in table 1.
Under the different noise circumstance of table 1, two kinds of algorithm classification recognition results compare
From the statistical study of table 1, under the noise conditions of different signal to noise ratio (S/N ratio), for the recognition accuracy of desired voltage signal and 6 kinds of transient power quality disturbance signals, in the classification of method of the present invention under different noise level, accuracy rate is all higher than commonsense method, therefore, method of the present invention has good noise immunity and robustness.
The above is only the preferred embodiment of the present invention; it should be pointed out that for those skilled in the art, under the premise without departing from the principles of the invention; can also make some improvements and modifications, these improvements and modifications also should be considered as protection scope of the present invention.
Claims (1)
1., based on S-transformation and the transient power disturbance identification method improving SVM algorithm, it is characterized in that, comprise the following steps:
1) by the S-transformation that following formulae discovery improves, and improvement S-transformation disturbing signal is utilized to process;
In formula, λ
mfor regulatory factor.Work as λ
mduring > 1, window width is that inverse proportion accelerates change with frequency, and temporal resolution is higher; As 0 < λ
mduring < 1, Gaussian window pace of change is slack-off, and frequency resolution improves;
2) disturbing signal feature extraction
Determine 8 kinds of feature construction proper vectors, from raw information and improvement S-transformation result of calculation, extract the required characteristic quantity of classification, each characteristic quantity implication is as follows:
F1: fundamental frequency amplitude average;
F2: in fundamental frequency amplitude, amplitude is greater than the sampled point number of standard value 105%;
F3: in fundamental frequency amplitude, amplitude is less than the sampled point number of standard value 95%;
F4: in fundamental frequency amplitude, amplitude is less than the sampled point number of standard value 10%;
F5: frequency envelope line crest number;
F6: extract the average being more than or equal to 3 times of fundamental frequencies in row vector maximum value temporal envelope line;
F7: temporal envelope line standard is poor;
F8: the standard deviation of frequency spectrum;
3) design is classified to sample based on the SVM classifier of semi-supervised learning algorithm;
Classify for involved 6 kinds of disturbance design category devices, wherein, comprise S1 desired voltage signal, voltage signal falls in S2 temporarily, the temporary up voltage signal of S3, S4 voltage interrupt signal, S5 transient oscillation signal and S6 harmonic signal in short-term, the principle of design of sorter is: first classify to sample with SVM algorithm, then carry out nothing supervision with the classification of semi-supervised learning sorting algorithm arest neighbors to SVM decision function result to correct, if the classification results confidence level of SVM algorithm is higher, then accept classification results, if the classification results confidence level of SVM algorithm is lower, support vector around the nearest neighbor algorithm determination predicted vector then using improvement in certain area M, Euclidean distance value is asked to predicted vector and support vector, and using the inverse of distance as decision variable, using the mean value of the decision variable of generic effective support vector as decision function value, the decision function value of all kinds of support vectors all in predicted vector M region is compared, carrying out from big to small arranges, statistical study is carried out with the result of SVM algorithm classification, finally determine classification results.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510741245.4A CN105447502A (en) | 2015-11-05 | 2015-11-05 | Transient power disturbance identification method based on S conversion and improved SVM algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510741245.4A CN105447502A (en) | 2015-11-05 | 2015-11-05 | Transient power disturbance identification method based on S conversion and improved SVM algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105447502A true CN105447502A (en) | 2016-03-30 |
Family
ID=55557661
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510741245.4A Pending CN105447502A (en) | 2015-11-05 | 2015-11-05 | Transient power disturbance identification method based on S conversion and improved SVM algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105447502A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106991773A (en) * | 2017-05-16 | 2017-07-28 | 华中科技大学 | A kind of safety-protection system vibration signal recognition based on S-transformation feature extraction |
| CN107315111A (en) * | 2017-07-17 | 2017-11-03 | 浙江群力电气有限公司 | A kind of Power Quality Disturbance Classification Method and system |
| 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 |
| CN109521305A (en) * | 2018-12-29 | 2019-03-26 | 广东电网有限责任公司 | A kind of electrical energy power quality disturbance incident visualization method and device |
| CN109831802A (en) * | 2019-03-26 | 2019-05-31 | 无锡职业技术学院 | The method that prediction data packet based on support vector machines receives possibility |
| CN110222953A (en) * | 2018-12-29 | 2019-09-10 | 北京理工大学 | A kind of power quality hybrid perturbation analysis method based on deep learning |
| CN110648088A (en) * | 2019-11-26 | 2020-01-03 | 国网江西省电力有限公司电力科学研究院 | Electric energy quality disturbance source judgment method based on bird swarm algorithm and SVM |
| CN111076934A (en) * | 2019-12-24 | 2020-04-28 | 江苏大学 | Method for diagnosing potential fault of bearing based on S transformation |
| CN111368892A (en) * | 2020-02-27 | 2020-07-03 | 合肥工业大学 | Generalized S transformation and SVM electric energy quality disturbance efficient identification method |
| CN111398721A (en) * | 2020-04-14 | 2020-07-10 | 南京工程学院 | Power distribution network voltage sag source classification and identification method introducing adjustment factors |
| CN111521110A (en) * | 2020-04-26 | 2020-08-11 | 湖南工业大学 | Rotary transformer signal envelope detection method |
| CN111579881A (en) * | 2020-05-14 | 2020-08-25 | 北京航空航天大学 | Frequency domain multi-feature fusion electromagnetic emission feature vector construction method |
| CN111723684A (en) * | 2020-05-29 | 2020-09-29 | 华南理工大学 | Method for identifying transient overvoltage type in offshore wind farm |
| CN114358042A (en) * | 2021-11-29 | 2022-04-15 | 国网安徽省电力有限公司马鞍山供电公司 | Power quality signal disturbance classification method based on T-S fuzzy model |
-
2015
- 2015-11-05 CN CN201510741245.4A patent/CN105447502A/en active Pending
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106991773A (en) * | 2017-05-16 | 2017-07-28 | 华中科技大学 | A kind of safety-protection system vibration signal recognition based on S-transformation feature extraction |
| 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 |
| CN107315111A (en) * | 2017-07-17 | 2017-11-03 | 浙江群力电气有限公司 | A kind of Power Quality Disturbance Classification Method and system |
| CN109521305A (en) * | 2018-12-29 | 2019-03-26 | 广东电网有限责任公司 | A kind of electrical energy power quality disturbance incident visualization method and device |
| CN110222953A (en) * | 2018-12-29 | 2019-09-10 | 北京理工大学 | A kind of power quality hybrid perturbation analysis method based on deep learning |
| CN109831802B (en) * | 2019-03-26 | 2022-04-08 | 无锡职业技术学院 | Method for predicting data packet receiving possibility based on support vector machine |
| CN109831802A (en) * | 2019-03-26 | 2019-05-31 | 无锡职业技术学院 | The method that prediction data packet based on support vector machines receives possibility |
| CN110648088A (en) * | 2019-11-26 | 2020-01-03 | 国网江西省电力有限公司电力科学研究院 | Electric energy quality disturbance source judgment method based on bird swarm algorithm and SVM |
| CN110648088B (en) * | 2019-11-26 | 2020-04-14 | 国网江西省电力有限公司电力科学研究院 | Electric energy quality disturbance source judgment method based on bird swarm algorithm and SVM |
| CN111076934A (en) * | 2019-12-24 | 2020-04-28 | 江苏大学 | Method for diagnosing potential fault of bearing based on S transformation |
| CN111368892A (en) * | 2020-02-27 | 2020-07-03 | 合肥工业大学 | Generalized S transformation and SVM electric energy quality disturbance efficient identification method |
| CN111368892B (en) * | 2020-02-27 | 2024-01-30 | 合肥工业大学 | Electric energy quality disturbance efficient identification method for generalized S transformation and SVM |
| CN111398721A (en) * | 2020-04-14 | 2020-07-10 | 南京工程学院 | Power distribution network voltage sag source classification and identification method introducing adjustment factors |
| CN111521110B (en) * | 2020-04-26 | 2021-11-23 | 湖南工业大学 | Rotary transformer signal envelope detection method |
| CN111521110A (en) * | 2020-04-26 | 2020-08-11 | 湖南工业大学 | Rotary transformer signal envelope detection method |
| CN111579881B (en) * | 2020-05-14 | 2021-02-26 | 北京航空航天大学 | Frequency domain multi-feature fusion electromagnetic emission feature vector construction method |
| CN111579881A (en) * | 2020-05-14 | 2020-08-25 | 北京航空航天大学 | Frequency domain multi-feature fusion electromagnetic emission feature vector construction method |
| CN111723684A (en) * | 2020-05-29 | 2020-09-29 | 华南理工大学 | Method for identifying transient overvoltage type in offshore wind farm |
| CN111723684B (en) * | 2020-05-29 | 2023-07-21 | 华南理工大学 | Identification method for transient overvoltage type in offshore wind farm |
| CN114358042A (en) * | 2021-11-29 | 2022-04-15 | 国网安徽省电力有限公司马鞍山供电公司 | Power quality signal disturbance classification method based on T-S fuzzy model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105447502A (en) | Transient power disturbance identification method based on S conversion and improved SVM algorithm | |
| Zhu et al. | Wavelet-based fuzzy reasoning approach to power-quality disturbance recognition | |
| CN103743980A (en) | Power quality disturbance recognition and classification method based on PSO (Particle Swarm Optimization) for SVM (Support Vector Machine) | |
| CN103323702B (en) | Complex electric energy quality disturbance signal recognition method | |
| CN104459397B (en) | Power quality disturbance recognizing method with self-adaptation multi-resolution generalized S conversion adopted | |
| WO2019015311A1 (en) | Vibration signal support vector machine-based gil fault online monitoring system | |
| Alam et al. | An approach for assessing the effectiveness of multiple-feature-based SVM method for islanding detection of distributed generation | |
| CN104459398B (en) | A kind of quality of power supply of use Two-dimensional morphology noise reduction is combined disturbance identification method | |
| CN106548013B (en) | Utilize the voltage sag source identification method for improving incomplete S-transformation | |
| CN105572501A (en) | Power quality disturbance identification method based on SST conversion and LS-SVM | |
| CN105004939A (en) | Composite electric energy quality disturbance signal quantitative analysis method | |
| CN110007141B (en) | Resonance point detection method based on voltage and current harmonic similarity | |
| CN103018537B (en) | The Classification of Transient Power Quality Disturbances recognition methods of kurtosis is composed based on CWD | |
| CN102982347A (en) | Method for electric energy quality disturbance classification based on KL distance | |
| CN107798283A (en) | A kind of neural network failure multi classifier based on the acyclic figure of decision-directed | |
| CN110082082A (en) | A kind of GIS state identification method based on vibration signal Principal Component Analysis | |
| CN109002810A (en) | Model evaluation method, Radar Signal Recognition method and corresponding intrument | |
| Cui et al. | HVDC transmission line fault localization base on RBF neural network with wavelet packet decomposition | |
| Fan et al. | Post-fault transient stability assessment based on k-nearest neighbor algorithm with Mahalanobis distance | |
| CN109389253A (en) | A kind of frequency predication method after Power System Disturbances based on credible integrated study | |
| Zhu et al. | Complex disturbances identification: A novel PQDs decomposition and modeling method | |
| CN105550450B (en) | Electric energy quality interference source characteristic harmonic modeling method | |
| CN114236234A (en) | Electrical appliance characteristic identification method based on fundamental wave and harmonic wave mixed criterion | |
| Mishra et al. | Islanding detection of microgrid using EMD and random forest classifier | |
| CN107578016A (en) | A kind of residual current waveform automatic identifying method based on rarefaction representation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160330 |
|
| WD01 | Invention patent application deemed withdrawn after publication |