CN102087311A - Method for improving measurement accuracy of power mutual inductor - Google Patents
Method for improving measurement accuracy of power mutual inductor Download PDFInfo
- Publication number
- CN102087311A CN102087311A CN 201010598866 CN201010598866A CN102087311A CN 102087311 A CN102087311 A CN 102087311A CN 201010598866 CN201010598866 CN 201010598866 CN 201010598866 A CN201010598866 A CN 201010598866A CN 102087311 A CN102087311 A CN 102087311A
- Authority
- CN
- China
- Prior art keywords
- inductor
- mutual
- signal
- electric power
- power mutual
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000005259 measurement Methods 0.000 title claims abstract description 10
- 238000013528 artificial neural network Methods 0.000 claims abstract description 20
- 230000003044 adaptive effect Effects 0.000 claims abstract description 7
- 230000006870 function Effects 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 12
- 238000003062 neural network model Methods 0.000 claims description 11
- 238000010606 normalization Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000007423 decrease Effects 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 abstract 1
- 238000012544 monitoring process Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000013011 mating Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Landscapes
- Measurement Of Resistance Or Impedance (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a method for improving the measurement accuracy of a power mutual inductor. The method comprises the following steps of: establishing a system model based on a fuzzy neural network; preprocessing a signal acquired by a power mutual inductor; and sending the preprocessed signal into a trained and learned adaptive fuzzy neural network system for calibrating to obtain a calibrated signal of the power mutual inductor. In the invention, a power mutual inductor measurement signal with a higher accuracy can be obtained by adopting an ordinary power mutual inductor, thereby the accuracy of the measurement system including the power mutual inductor is improved, and the cost of the system is reduced.
Description
Technical field
The present invention relates to the electric power mutual-inductor measuring technique of electronic industrial technology, particularly a kind of method that improves the electric power mutual-inductor measuring accuracy.
Background technology
Electric current on the line of electric force and leakage current are of paramount importance parameters in the systems such as electric power monitoring, load prediction and fire hazard monitoring, in existing some electric fire monitoring system, directly compare and judge whether to carry out electric fire alarm with current value or leakage current value and pre-set threshold.Usually electric current and leakage current value collect by electric power mutual-inductor on the line of electric force, and the measured value of electric power mutual-inductor is subjected to the influence of factors such as itself and the position relation of line of electric force, on-the-spot electromagnetic environment.In addition, material that common electric power mutual-inductor uses and manufacturing process etc. also can make its electric current or leakage current measurement value and actual value directly have deviation, and precision is not high, and then cause the performance index of these systems to reduce.The electric current of common electric power mutual-inductor or leakage current measurement value and the direct deviation of actual value are non-linear, be subjected to the influence of installation site, environment temperature and electromagnetic environment etc. simultaneously, can't be described with explicit mathematical formulae, and in application, the site environment parameter is constantly to change, and can not set up complete data set for all possible ambient conditions and parameter area.Must consider the signal value of current transformer collection to be carried out the data adjustment, make it, and then handle and application lays the foundation for follow-up data near actual value with nonlinear signal processing technology.
?
Summary of the invention
In order to solve the problems of the technologies described above, the invention provides a kind of method that can effectively improve the electric power mutual-inductor measuring accuracy.
The technical scheme of stating that the present invention solves the problems of the technologies described above may further comprise the steps:
1) foundation is based on the system model of fuzzy neural network;
2) signal to the electric power mutual-inductor collection carries out pre-service;
3) pretreated signal is sent in the good Adaptive Fuzzy Neural-network system of training study and carried out calibration process, obtain electric power mutual-inductor calibration measurement signal.
Further, described step 1) foundation based on the concrete grammar step of the system model of fuzzy neural network is:
1) gathers training sample, common mutual inductor and precision standard mutual inductor are installed in the same tested line of electric force measurement environment, guarantee the position consistency of two mutual inductors and tested line of electric force, and produce site environment parameters such as temperature, power frequency magnetic field by the environmental baseline generator, the signal that electric power mutual-inductor is gathered through A/D conversion and pre-service after as the training sample of system model;
2) set up fuzzy neural network model, the network of fuzzy neural network model is made up of input layer, the definite layer of fuzzy membership function, relevance grade computation layer, normalization computation layer and output layer;
3) set up the fuzzy neural network model structure, utilize the gradient decline learning algorithm of self-adaptation momentum decoupling zero to adjust the fuzzy membership function parameter, utilize least square method to adjust the output layer link weight coefficients.
Further, described step 2) the pretreated basic skills of acquired signal is any of the in limited time method of average, normalization smoothing method, MMSE method and RLS method.
Technique effect of the present invention is: the present invention utilizes common mutual inductor and the measuring-signal of precision standard mutual inductor under the same test environment training sample as neural network, set up the Adaptive Fuzzy Neural-network system with this, utilize the measuring-signal of Adaptive Fuzzy Neural-network system calibration electric power mutual-inductor, improve the measuring accuracy of common electric power mutual-inductor greatly, in guaranteed performance, effectively reduced system cost.
Below in conjunction with the drawings and specific embodiments invention is described in further detail.
Description of drawings
Fig. 1 is the electric power mutual-inductor calibrating patterns synoptic diagram among the present invention.
Fig. 2 is the structure of fuzzy neural network figure among the present invention.
Embodiment
As shown in Figure 1, be the common electric power mutual-inductor image data calibrating patterns that the present invention sets up, this model comprises following three partial contents:
1, sets up based on fuzzy neural network model.
Foundation is based on fuzzy neural network model, comprises that mainly data acquisition, model structure, model parameter determine.
Common mutual inductor and precision standard mutual inductor are installed in the same tested line of electric force measurement environment, guarantee the position consistency of two mutual inductors and tested line of electric force simultaneously, produce simultaneously site environment parameters such as temperature, power frequency magnetic field by the environmental baseline generator, through after A/D conversion and the pre-service as the training sample of fuzzy neural network.
Fuzzy neural network model comprises following five layers, and its structure is referring to Fig. 2:
Input layer d, each node directly link to each other with pretreated signals of process such as the environment parameter of gathering, common electric power mutual-inductor acquired signal, send into down one deck.
Fuzzy membership function is determined layer e, each node is represented a linguistic variable value, be used to calculate and respectively import the membership function that component belongs to each linguistic variable value fuzzy set, used membership function can be Gauss's membership function, double-flanged end Gauss membership function, bell membership function etc.
Relevance grade computation layer f, each node represent a fuzzy rule, are used for mating the fuzzy rule former piece, calculate the relevance grade of every rule.
Normalization computation layer g realizes that data normalization calculates.
Output layer h realizes that fuzzy sharpening calculates, i.e. solving result.
The model hybrid learning algorithm: learning process is mainly used in the weighting parameter of adjusting connecting line between each node layer of fuzzy neural network.Parameter adjustment is made up of two parts:
Fuzzy membership function is determined the center and the width of membership function in the layer in the network, and they and output are nonlinear relationships;
The link weight coefficients of output layer, they and output are linear relationships.According to parameter and output relation, adopt the learning algorithm of similar BP neural network, adopt the gradient decline learning algorithm of self-adaptation momentum decoupling zero to adjust the fuzzy membership function parameter respectively, adjust the output layer link weight coefficients with least square method.The input sample of training fuzzy neural network is the signal parameter that input layer connects in the system model, the signal parameter that output sample is gathered for the precision standard mutual inductor.
2, the signal with the electric power mutual-inductor collection carries out pre-service.
The influence that handled by electric power mutual-inductor manufacturing process, neighbourhood noise (thunder and lightning, environment temperature etc.), circuit thermonoise (electron device intrinsic noise, electromagnetic interference (EMI) etc.) and follow-up A/D etc., the twinkling signal saltus step may appear, be that measured signal also can exist vibration behind mutual inductor continuous acquisition signal digitalized when constant and changes, for improving the stability of signal, need before carrying out follow-up data, carry out pre-service, make signal keep stable, basic skills comprises the method for average, normalization smoothing method, MMSE method, RLS method etc. in limited time.
3, pretreated signal is sent in the good Adaptive Fuzzy Neural-network system of training study and carried out calibration process.
With the collection in worksite signal is input, and good Adaptive Fuzzy Neural-network is handled to send into training study, and output is the mutual inductor acquired signal after the calibration, can be directly used in the electric power monitoring or the electric fire monitoring system that give threshold value.
Provide better embodiment of the present invention below, and described in detail, enable to understand better function of the present invention, characteristics.
The example that is calibrated to the common electric power mutual-inductor that is applied to electric fire monitoring system illustrates sensor calibrating method of the present invention.
Signalization is gathered environment, the data that obtain comprise the environment parameter that the signal, temperature sensor, power frequency magnetic field sensor of common electrical power mutual inductor collection etc. collects etc., the input layer that is directly connected to fuzzy neural network as shown in Figure 2 after these data process pre-service is as the input sample, and pre-service adopts the mean value of simply asking a continuous acquisition M sample to replace the data of single collection.
The input value of the input layer d correspondence of fuzzy neural network is designated as
Fuzzy membership function determines that layer e uses Gaussian function
As membership function, wherein
With
Center and the width of representing membership function respectively.
Relevance grade computation layer f adopts to connect and takes advantage of solving method to calculate relevance grade, promptly
Normalization computation layer g realizes normalization calculating, promptly
Output layer h calculates the output result, promptly
, wherein
Link weight coefficients value for output layer.
When learning, adopts fuzzy neural network model the adjustment of gradient descent method
With
, the Error Calculation formula is
Wherein
EBe a square type error function,
N p Be the learning sample number,
y t Be the acquired signal data of common electric power mutual-inductor,
Be the acquired signal data of precision standard mutual inductor, the parameter adjustment formula is
Wherein
tBe the study iterations,
Be the study step-length.
Adopt least square method adjustment output link weight coefficients, formula is
Wherein
W t Be of link weight coefficients to be adjusted
tIndividual row vector,
Be of relevance grade normalized vector
tIndividual row vector,
S t Be covariance matrix,
Be training output data vector
Y kIndividual row vector.
After modelling is good, the signal of common electric power mutual-inductor b collection and the site environment parameter of collection are handled the acquired signal data after output is very calibrated through sending into fuzzy neural network model after the pre-service.
Above-described; it only is preferred embodiment of the present invention; be not in order to limiting scope of the present invention, promptly every simple, equivalence of doing according to the claims and the description of the present patent application changes and modifies, and all falls into the claim protection domain of patent of the present invention.
Claims (3)
1. a method that improves the electric power mutual-inductor measuring accuracy is characterized in that, may further comprise the steps:
1) foundation is based on the system model of fuzzy neural network;
2) signal to the electric power mutual-inductor collection carries out pre-service;
3) pretreated signal is sent in the good Adaptive Fuzzy Neural-network system of training study and carried out calibration process, obtain calibrating back electric power mutual-inductor measuring-signal.
2. the method for raising electric power mutual-inductor measuring accuracy according to claim 1 is characterized in that, the concrete grammar step that described step 1) is set up based on the system model of fuzzy neural network is:
1) gathers training sample, common mutual inductor and precision standard mutual inductor are installed in the same tested line of electric force measurement environment, guarantee the position consistency of two mutual inductors and tested line of electric force, and produce site environment parameters such as temperature, power frequency magnetic field by the environmental baseline generator, the signal that electric power mutual-inductor is gathered through A/D conversion and pre-service after as the training sample of system model;
2) set up fuzzy neural network model, the network of fuzzy neural network model is made up of input layer, the definite layer of fuzzy membership function, relevance grade computation layer, normalization computation layer and output layer;
3) set up the fuzzy neural network model structure, utilize the gradient decline learning algorithm of self-adaptation momentum decoupling zero to adjust the fuzzy membership function parameter, utilize least square method to adjust the output layer link weight coefficients.
3. the method for raising electric power mutual-inductor measuring accuracy according to claim 1 is characterized in that, described step 2) the pretreated basic skills of acquired signal is any of the in limited time method of average, normalization smoothing method, MMSE method and RLS method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010598866 CN102087311B (en) | 2010-12-21 | 2010-12-21 | Method for improving measurement accuracy of power mutual inductor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010598866 CN102087311B (en) | 2010-12-21 | 2010-12-21 | Method for improving measurement accuracy of power mutual inductor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102087311A true CN102087311A (en) | 2011-06-08 |
| CN102087311B CN102087311B (en) | 2013-03-06 |
Family
ID=44099205
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201010598866 Active CN102087311B (en) | 2010-12-21 | 2010-12-21 | Method for improving measurement accuracy of power mutual inductor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102087311B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103853786A (en) * | 2012-12-06 | 2014-06-11 | 中国电信股份有限公司 | Method and system for optimizing database parameters |
| CN104215279A (en) * | 2014-09-18 | 2014-12-17 | 贵州电力试验研究院 | Online environment monitoring system and environment monitoring method |
| CN106783435A (en) * | 2017-02-14 | 2017-05-31 | 河北农业大学 | Leakage protector and leakage protection method thereof |
| CN108088469A (en) * | 2017-11-14 | 2018-05-29 | 中国航空工业集团公司西安飞机设计研究所 | A kind of long endurance airplane inertial navigation error compensation method |
| CN109799379A (en) * | 2019-01-11 | 2019-05-24 | 厦门南鹏物联科技有限公司 | Method for measuring charged, charging detection device and socket |
| CN112368717A (en) * | 2018-07-03 | 2021-02-12 | 松下知识产权经营株式会社 | Calculation processing system, sensor system, calculation processing method, and program |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1141097A (en) * | 1994-01-06 | 1997-01-22 | 施耐德电器公司 | Device for differentially protecting a power transformer |
| US6247003B1 (en) * | 1998-08-13 | 2001-06-12 | Mcgraw-Edison Company | Current transformer saturation correction using artificial neural networks |
| CN101226162A (en) * | 2008-02-18 | 2008-07-23 | 重庆大学 | Intelligent method for inhibiting gas-sensitive sensor decussation sensitivity |
-
2010
- 2010-12-21 CN CN 201010598866 patent/CN102087311B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1141097A (en) * | 1994-01-06 | 1997-01-22 | 施耐德电器公司 | Device for differentially protecting a power transformer |
| US6247003B1 (en) * | 1998-08-13 | 2001-06-12 | Mcgraw-Edison Company | Current transformer saturation correction using artificial neural networks |
| CN101226162A (en) * | 2008-02-18 | 2008-07-23 | 重庆大学 | Intelligent method for inhibiting gas-sensitive sensor decussation sensitivity |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103853786A (en) * | 2012-12-06 | 2014-06-11 | 中国电信股份有限公司 | Method and system for optimizing database parameters |
| CN103853786B (en) * | 2012-12-06 | 2017-07-07 | 中国电信股份有限公司 | The optimization method and system of database parameter |
| CN104215279A (en) * | 2014-09-18 | 2014-12-17 | 贵州电力试验研究院 | Online environment monitoring system and environment monitoring method |
| CN106783435A (en) * | 2017-02-14 | 2017-05-31 | 河北农业大学 | Leakage protector and leakage protection method thereof |
| CN106783435B (en) * | 2017-02-14 | 2018-08-14 | 河北农业大学 | Leakage protector and leakage protection method thereof |
| CN108088469A (en) * | 2017-11-14 | 2018-05-29 | 中国航空工业集团公司西安飞机设计研究所 | A kind of long endurance airplane inertial navigation error compensation method |
| CN112368717A (en) * | 2018-07-03 | 2021-02-12 | 松下知识产权经营株式会社 | Calculation processing system, sensor system, calculation processing method, and program |
| CN109799379A (en) * | 2019-01-11 | 2019-05-24 | 厦门南鹏物联科技有限公司 | Method for measuring charged, charging detection device and socket |
| CN109799379B (en) * | 2019-01-11 | 2022-01-11 | 厦门南鹏物联科技有限公司 | Charging detection method, charging detection device and socket |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102087311B (en) | 2013-03-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103728535B (en) | A kind of extra-high-voltage direct-current transmission line fault location based on wavelet transformation transient state energy spectrum | |
| CN102087311B (en) | Method for improving measurement accuracy of power mutual inductor | |
| CN104280612B (en) | Distributed harmonic source identification method based on single-frequency current transmission characteristics | |
| Jiang et al. | Stochastic subspace identification‐based approach for tracking inter‐area oscillatory modes in bulk power system utilising synchrophasor measurements | |
| Ayyagari | Artificial neural network based fault location for transmission lines | |
| CN107565553A (en) | A kind of power distribution network robust dynamic state estimator method based on UKF | |
| CN105098763A (en) | Transient voltage stable on-line assessment method based on WAMS and EMS | |
| CN111461922A (en) | Transformer hot spot temperature real-time prediction method based on extreme learning machine | |
| CN110414412A (en) | The multiple disturbance precise recognition method of the Wide Area Power based on big data analysis and device | |
| CN105719094A (en) | State evaluation method of power transmission equipment | |
| CN105471110B (en) | A kind of low frequency oscillation mode layer detection method of electric system noise-like signal | |
| CN107014519A (en) | BOTDR temperature, strain fast separating process in a kind of intelligent grid icing monitoring | |
| Wang et al. | Dynamic equivalent method of PMSG‐based wind farm for power system stability analysis | |
| CN106372440B (en) | A kind of adaptive robust state estimation method of the power distribution network of parallel computation and device | |
| CN106228033B (en) | Three-core cable conductor temperature real-time computing technique based on RBF neural | |
| CN108764550A (en) | Lightning Warning method and system based on transmission line information data | |
| CN113162002B (en) | DC traveling wave protection method and system considering broadband measurement link | |
| CN117394311B (en) | Power distribution network toughness assessment and emergency control method based on multi-source information fusion | |
| Wang et al. | Application of multiattention mechanism in power system branch parameter identification | |
| CN108092272A (en) | A kind of voltage stabilization on-line monitoring method based on the Kalman filtering that fades | |
| CN111864741B (en) | Quantitative analysis method and system for influence of line parameter errors on power distribution | |
| CN107069710B (en) | Power system state estimation method considering new energy space-time correlation | |
| Li et al. | Dynamic equivalent modeling for power converter based on LSTM neural network in wide operating range | |
| CN105139092B (en) | A kind of high robust transmission line parameter method of estimation based on multi-period PMU | |
| Yan et al. | Application of random matrix model in multiple abnormal sources detection and location based on PMU monitoring data in distribution network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20170927 Address after: 410000, A385 building, headquarter building, Changsha Electric Power Software Park, 39 Gaoxin Road, Changsha, Hunan Patentee after: Hunan Lin Ze Technology Development Co. Ltd. Address before: 410002 blue Landmark 1305, Jiefang West Road, Furong district, Hunan, Changsha, 136 Patentee before: Peng Haoming |
|
| TR01 | Transfer of patent right |