CN114285038B - APF resonance prediction method based on voting perceptron - Google Patents
APF resonance prediction method based on voting perceptron Download PDFInfo
- Publication number
- CN114285038B CN114285038B CN202111399708.5A CN202111399708A CN114285038B CN 114285038 B CN114285038 B CN 114285038B CN 202111399708 A CN202111399708 A CN 202111399708A CN 114285038 B CN114285038 B CN 114285038B
- Authority
- CN
- China
- Prior art keywords
- apf
- resonance
- current
- power grid
- phase
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 22
- 239000013598 vector Substances 0.000 claims abstract description 21
- 230000006870 function Effects 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims abstract description 9
- 239000000284 extract Substances 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000004422 calculation algorithm Methods 0.000 description 9
- 230000001629 suppression Effects 0.000 description 5
- 238000013461 design Methods 0.000 description 3
- 239000002245 particle Substances 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000001010 compromised effect Effects 0.000 description 1
- 238000013016 damping Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/20—Active power filtering [APF]
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides an APF resonance prediction method based on a voting sensor, which comprises the following steps: collecting waveform data of grid voltage and load current before and after APF resonance; determining a characteristic value of a training sample for APF resonance prediction; constructing a classification criterion of the feature vector and the perceptron; selecting a loss function and a parameter learning method of a sensor; iteratively calculating a weight vector of the sensor; the learned sensor classification criteria are used in the resonance judgment of the APF. Compared with the prior art, the method can accurately predict the resonance of the APF according to some characteristics of the voltage and the load current in the power grid, and the shutdown operation is performed on the APF in advance, so that the bad influence of the resonance of the APF and the load on the power grid is avoided.
Description
Technical Field
The invention relates to the technical field of power electronics and neural networks, in particular to an APF resonance prediction method based on a voting sensor.
Background
The active filter (APF) is connected in parallel in the power grid and is equivalent to a controllable reactive and harmonic current source, the reactive current and the harmonic current of the active filter can quickly change along with the change of the load reactive current and the harmonic current, the reactive power and the harmonic wave required by the power grid system are automatically compensated, the dynamic reactive compensation is realized on the reactive power and the harmonic wave of the power grid, and the active filter belongs to an important component of a Flexible Alternating Current Transmission System (FACTS).
Due to the fact that the load characteristic of the power grid is complex, the APF can resonate with a special load in practical application. APFs have serious consequences once they resonate in the grid. Light weight results in load protection for the plant, and heavy weight burns out the transformer or load.
Patent document CN112994004a (application number: CN 202011580570.4) discloses a hybrid active filter resonance suppression strategy taking control delay into consideration, and the hybrid active filter applied to high-voltage direct-current transmission is taken as a research object, and belongs to a novel resonance suppression method. However, the impedance characteristic of the hybrid active filter is complex, resonance risks are easy to generate, and in addition, the hybrid active filter may present negative impedance characteristics due to calculation delay and sampling delay, so that the stability of an ac/dc system is greatly compromised. Therefore, the invention analyzes the influence of digital delay on the system stability by establishing an impedance model, designs a self-adaptive resonance suppression strategy based on a least mean square algorithm, adopts a design thought of feedforward compensation, utilizes the waveform of the predicted next moment to eliminate the phase lag caused by controlling delay, not only can improve the impedance characteristic of a filter, but also can self-adaptively adjust a prediction matrix, so that the method can be applied to the condition of working conditions and circuit parameter change.
Patent document CN106253279a (application number: CN 201610712875.3) discloses an algorithm for rapidly extracting current harmonic components on the grid side and performing suppression, and by performing detection contrast judgment, resonance between the active filter and the grid is effectively suppressed. The anti-resonance control algorithm applied to the active filter detects load current in real time, extracts harmonic components in the load current through a sliding window DFT algorithm, provides current reference for a control module, and achieves the harmonic suppression function of the active filter. The invention can protect equipment under the condition of weak power grid damping, prevent the equipment from being damaged by resonance, and simultaneously can rapidly extract harmonic components of resonance current, and the internal module rapidly responds, thereby achieving the purpose of resonance inhibition.
Patent document CN103378595a (application number: CN201210105400. X) discloses a method for optimally configuring parameters of a parallel hybrid active filter (shunt hybrid act ive power fi lter, SHAPF) by using a relation between capacitance reactive compensation power and series-parallel resonance frequency as a constraint condition, and an improved particle swarm optimization algorithm (improved particle swarm optimization, IPSO) is adopted, and a time-varying nonlinear trigonometric function method is proposed to control the parameters according to the relation between the parameter speed and inertia factor of the particle swarm algorithm, so that the convergence speed of the algorithm is accelerated, and the local optimum is prevented from being trapped. Simulation verification is carried out by Matlab, the parameter design of SHAPF is optimized, and the filter effect is good. In the example application, resonance is effectively avoided, and the method has certain engineering application value.
The prior art proposes an algorithm that can suppress resonance under specific load or specific power grid conditions, but APF has a large load in the practical application, and once resonance occurs, serious consequences can occur. The invention aims to provide an APF resonance prediction method based on a voting sensor, which accurately predicts that an APF will resonate according to some characteristics of voltage and load current in a power grid, and performs shutdown operation on the APF in advance so as to avoid bad influence of the APF and the load resonance on the power grid.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide an APF resonance prediction method and system based on a voting sensor. The method is convenient to accurately predict the resonance risk of the APF running in the power grid, and the APF is shut down before resonance occurs, so that the safe and reliable running of the power grid is ensured.
In order to achieve the above purpose, the invention adopts the following technical scheme:
the invention predicts APF resonance by adopting a neural network of a perceptron algorithm, and comprises the following steps:
step 1: collecting waveform data of grid voltage and load current before and after APF current suddenly increases
APF resonance typically occurs when the output current increases suddenly, but APF output current increases do not necessarily resonate. The method comprises the steps of designing a data acquisition function in APF equipment, storing waveform data of grid voltage and load current before and after the output current is increased in flash memory in the APF equipment once the output current of the APF suddenly becomes large, and uploading the data to a server through GPRS.
Step 2: characteristic values of training samples for APF resonance prediction are determined. The APF resonates in the power grid usually because of the operation of a special load in the power grid, and the special load operation that can cause the APF to resonate usually causes a change in the phase of the current and voltage in the power grid, or causes abrupt changes in the voltage or current of the power grid, and may also generate spike voltages or surge currents in the voltage or current of the power grid. The eigenvalues of the selected training samples are:
1. APF resonance or sudden increase of current in the three-phase mains voltage phase change maximum value in the previous mains cycle;
2. APF resonance or sudden increase of current phase change maximum value of three-phase grid current in the previous mains supply period;
3. APF resonance or sudden increase of current in the three-phase grid voltage slope maximum in the previous mains cycle;
4. APF resonance or sudden increase of current in the three-phase grid current slope maximum in the previous mains cycle;
5. APF resonance or sudden increase of current in the three-phase mains voltage maximum in the previous mains cycle;
6. APF resonance or sudden increase in current in the three-phase grid current maximum in the previous mains cycle;
n groups of resonance data are selected from the data of the server, the characteristic values are extracted, then N groups of data with suddenly increased current but not resonance are selected, the characteristic values are extracted, and a training set of 2N samples is obtained. phva= { phva (1) ,phva (2) ,phva (3) ,…,phva (2N) Wherein phva (1) For APF resonance or current extracted from the first group of data suddenly increasing the maximum value of phase change of A-phase power grid voltage in the previous mains supply period, phva (2N) And (3) the maximum value of the phase change of the voltage of the phase A power grid in the previous mains supply period is suddenly increased for the APF resonance or the current extracted from the 2N group data. phvb and phvc and so on, are B, C phase grid voltage phase change maxima, respectively.
phia＝{phia (1) ,phia (2) ,phia (3) ,…,phia (2N) Wherein phia (1) For APF resonance or abrupt current increase of extracted from the first set of data, the maximum value of the phase change of the A-phase network current in the previous mains cycle, phia (2N) And (3) the maximum value of the phase change of the phase A power grid current in the previous mains supply period is suddenly increased for APF resonance or current extracted from the 2N group data. phib and phic and so on, are B, C phase grid current phase change maximum values respectively.
sva＝{sva (1) ,sva (2) ,sva (3) ,…,sva (2N) Sva therein (1) For APF resonance or abrupt current increase in the first set of data, the maximum value of the A-phase grid voltage slope in the previous mains cycle is sva (2N) And (3) the APF resonance or current extracted from the 2N group data is suddenly increased to the maximum value of the voltage slope of the phase A power grid in the previous mains supply period. svb and svc, and so on, are B, C phase grid voltage slope maximum values, respectively.
sia＝{sia (1) ,sia (2) ,sia (3) ,…,sia (2N) (where sia) (1) For APF resonance or current abrupt increase of the first group of data, the maximum value of the A phase power grid current slope in the previous mains supply period, sia (2N) And (3) the APF resonance or current extracted from the 2N group data is suddenly increased to the maximum value of the current slope of the phase A power grid in the previous mains supply period. And SIb and sic and the like are B, C phase grid current slope maximum values respectively.
vpa＝{vpa (1) ,vpa (2) ,vpa (3) ,…,vpa (2N) Vpa therein (1) For the extracted APF resonance or current in the first set of data suddenly increasing the maximum value of the a-phase mains voltage in the previous mains cycle vpa (2N) The APF resonance or current extracted from the 2N group data suddenly increases the maximum value of the a-phase grid voltage in the previous mains cycle. vpb and vpc, respectively, are the maximum values of B, C phase mains voltage.
ipa＝{ipa (1) ,ipa (2) ,ipa (3) ,…,ipa (2N) Wherein ipa (1) For APF resonance or sudden increase of current extracted from the first set of data to maximum value of A-phase grid current in previous mains cycle vpa (2N) The APF resonance or current extracted from the 2N group data suddenly increases the maximum value of the a-phase grid current in the previous mains cycle. vpb and vpc, respectively, are the maximum values of B, C phase grid currents.
y＝{y (1) ,y (2) ,y (3) ,…,y (2N) Class labels are stored in y (resonance is defined as 1 and non-resonance is defined as-1). y is (1) Class label, y, whether or not resonating for the first set of data (2N) A class label for whether group 2N data is resonant.
Step 3: building vector X (n) ＝[phva (n) ,phvb (n) ,phvc (n) ,phia (n) ,phib (n) ,phic (n) ,sva (n) ,svb (n) ,svc (n) ,sia (n) ,sib (n) ,sic (n) ,vpa (n) ,vpb (n) ,vpc (n) ,ipa (n) ,ipb (n) ,ipc (n) ] T
In step 2, there are 2N sets of data, so 2N vectors X can be constructed from the 2N sets of data (n) (n＝1，2，3，…,2N)。
Constructing classification criteria of the perceptrons:
wherein ω= [ ω1, ω2, ω3, …, ω18] T Is the weight vector of the perceptron, X (n) Is a feature value extracted from a set of data needed to predict whether an APF will resonate,is the predicted outcome (++>Will resonate, < >>Will not resonate
Step 4: initializing a weight vector omega 0 ，ω 0 Is the initial value of ω.
Step 5: handle omega k-1 And X in step 2 (k) Substituting the result into the formula (1) to obtain the kth prediction result
Step 6: calculating the difference between model predictions and real tags ifSample prediction error, if->The sample prediction is correct. The following formula is chosen as the loss function:
L(ω；X,y)＝max(0,-yω T X)
if it isThen->I.e. sample misprediction, then the loss functionIf->Then->Then the sample prediction is correct, then the loss function L (ω k-1 ；X (k) ,y (k) )＝0。
Step 7: updating weight vector omega k A random gradient descent is used, and the gradient of each update is:
step 8: repeating the iteration for 2N times to calculate omega k (k＝1，2，3，…,2N)；
Step 9: calculating omega k Average value of (2)
UsingWeight orientation as used in APF productsThe amount is substituted into the formula (1) to predict whether the APF will resonate.
Step 10: when APF is running, the sliding window extracts X= [ phva, phvb, phvc, phia, phib, phic, sva, svb, svc, sia, sic, vpa, vpb, vpc, ipa, ipb, ipc within 20ms] T Substituting X into (2) to calculateIf->The APF is immediately turned off to avoid resonance.
Drawings
Other features, objects and advantages of the present invention will become more apparent upon reading of the detailed description of non-limiting embodiments, given with reference to the accompanying drawings in which:
FIG. 1 is a waveform of three-phase grid voltage before and after resonance occurs;
fig. 2 is a waveform of three-phase grid current before and after resonance occurs.
Fig. 3 is a flowchart of an APF resonance prediction method.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the present invention, but are not intended to limit the invention in any way. It should be noted that variations and modifications could be made by those skilled in the art without departing from the inventive concept. These are all within the scope of the present invention.
According to the APF resonance prediction method based on the voting sensor provided by the invention, as shown in fig. 1-2, the APF resonance prediction method comprises the following steps:
step 1: collecting waveform data of grid voltage and load current before and after APF current suddenly increases
APF resonance typically occurs when the output current increases suddenly, but APF output current increases do not necessarily resonate. The method comprises the steps of designing a data acquisition function in APF equipment, storing waveform data of grid voltage and load current before and after the output current is increased in flash memory in the APF equipment once the output current of the APF suddenly becomes large, and uploading the data to a server through GPRS.
Step 2: characteristic values of training samples for APF resonance prediction are determined. The APF resonates in the power grid usually because of the operation of a special load in the power grid, and the special load operation that can cause the APF to resonate usually causes a change in the phase of the current and voltage in the power grid, or causes abrupt changes in the voltage or current of the power grid, and may also generate spike voltages or surge currents in the voltage or current of the power grid. The eigenvalues of the selected training samples are:
1. APF resonance or sudden increase of current in the three-phase mains voltage phase change maximum value in the previous mains cycle;
2. APF resonance or sudden increase of current phase change maximum value of three-phase grid current in the previous mains supply period;
3. APF resonance or sudden increase of current in the three-phase grid voltage slope maximum in the previous mains cycle;
4. APF resonance or sudden increase of current in the three-phase grid current slope maximum in the previous mains cycle;
5. APF resonance or sudden increase of current in the three-phase mains voltage maximum in the previous mains cycle;
6. APF resonance or sudden increase in current in the three-phase grid current maximum in the previous mains cycle;
1000 sets of resonance data are selected from the data of the server, the characteristic values are extracted, 1000 sets of current suddenly increased but not resonating data are selected, the characteristic values are extracted, and a training set of 2000 samples is obtained. phva= { phva (1) ,phva (2) ,phva (3) ,…,phva (2000) Wherein phva (1) For APF resonance or current extracted from the first group of data suddenly increasing the maximum value of phase change of A-phase power grid voltage in the previous mains supply period, phva (2000) The maximum value of the phase change of the A-phase power grid voltage in the previous mains supply period is suddenly increased for the APF resonance or the current extracted from the 2000 th group of data. phvb and phvc and so on, are B, C phase grid voltage phase change maxima, respectively.
phia＝{phia (1) ,phia (2) ,phia (3) ,…,phia (2000) Wherein phia (1) For APF resonance or abrupt current increase of extracted from the first set of data, the maximum value of the phase change of the A-phase network current in the previous mains cycle, phia (2000) The maximum value of the phase change of the phase A power grid current in the previous mains supply period is suddenly increased for the APF resonance or the current extracted from the 2000 th group of data. phib and phic and so on, are B, C phase grid current phase change maximum values respectively.
sva＝{sva (1) ,sva (2) ,sva (3) ,…,sva (2000) Sva therein (1) For APF resonance or abrupt current increase in the first set of data, the maximum value of the A-phase grid voltage slope in the previous mains cycle is sva (2000) The APF resonance or current extracted from the 2000 th set of data is suddenly increased by the maximum value of the a-phase grid voltage slope in the previous mains cycle. svb and svc, and so on, are B, C phase grid voltage slope maximum values, respectively.
sia＝{sia (1) ,sia (2) ,sia (3) ,…,sia (2000) (where sia) (1) For APF resonance or current abrupt increase of the first group of data, the maximum value of the A phase power grid current slope in the previous mains supply period, sia (2000) The maximum value of the current slope of the A-phase power grid in the previous mains cycle is suddenly increased for the APF resonance or current extracted from the 2000 th group of data. And SIb and sic and the like are B, C phase grid current slope maximum values respectively.
vpa＝{vpa (1) ,vpa (2) ,vpa (3) ,…,vpa (2000) Vpa therein (1) For the extracted APF resonance or current in the first set of data suddenly increasing the maximum value of the a-phase mains voltage in the previous mains cycle vpa (2000) For the highest A-phase network voltage in the previous mains cycle of APF resonance or current abrupt increase extracted from group 2000 dataLarge value. vpb and vpc, respectively, are the maximum values of B, C phase mains voltage.
ipa＝{ipa (1) ,ipa (2) ,ipa (3) ,…,ipa (2000) Wherein ipa (1) For APF resonance or sudden increase of current extracted from the first set of data to maximum value of A-phase grid current in previous mains cycle vpa (2000) The APF resonance or current extracted for group 2000 data suddenly increases the maximum value of the phase a grid current in the previous mains cycle. vpb and vpc, respectively, are the maximum values of B, C phase grid currents.
y＝{y (1) ,y (2) ,y (3) ,…,y (2000) Class labels are stored in y (resonance is defined as 1 and non-resonance is defined as-1). y is (1) Class label, y, whether or not resonating for the first set of data (2000) A class label for whether group 2000 data is resonant.
Step 3: building vector X (n) ＝[phva (n) ,phvb (n) ,phvc (n) ,phia (n) ,phib (n) ,phic (n) ,sva (n) ,svb (n) ,svc (n) ,sia (n) ,sib (n) ,sic (n) ,vpa (n) ,vpb (n) ,vpc (n) ,ipa (n) ,ipb (n) ,ipc (n) ] T ；
2000 sets of data are available in step 2, then 2N vectors X can be constructed from these 2N sets of data (n) (n＝1，2，3，…,2000)。
Constructing classification criteria of the perceptrons:
wherein ω= [ ω1, ω2, ω3, …, ω18] T Is the weight vector of the perceptron, X (n) Is a feature value extracted from a set of data needed to predict whether an APF will resonate,is the predicted outcome (++>Will resonate, < >>Will not resonate).
Step 4: initializing a weight vector omega 0 ≡0 (all zero vector), ω 0 Is the initial value of ω.
Step 5: handle omega k-1 And X in step 2 (k) Substituting the result into the formula (1) to obtain the kth prediction result
Step 6: calculating the difference between model predictions and real tags ifSample prediction error, if->The sample prediction is correct. The following formula is chosen as the loss function:
L(ω；X,y)＝max(0,-yω T X)
if it isThen->I.e. sample misprediction, then the loss functionIf->Then->Then the sample prediction is correct, then the lossLoss function L (omega) k-1 ；X (k) ,y (k) )＝0。
Step 7: updating weight vector omega k Adopts random gradient descent, and the gradient of each update is that
Step 8: repeating the steps 5-7, iterating 2000 times, and calculating omega k (k＝1，2，3，…,2000)
Step 9: calculating omega k Average value of (2)
UsingAs a weight vector used in the APF product, the formula (1) is substituted to predict whether the APF will resonate.
Step 10: when APF is running, the sliding window extracts X= [ phva, phvb, phvc, phia, phib, phic, sva, svb, svc, sia, sic, vpa, vpb, vpc, ipa, ipb, ipc within 20ms] T Substituting X into (2) to calculateIf->The APF is immediately turned off to avoid resonance.
The foregoing describes specific embodiments of the present invention. It is to be understood that the invention is not limited to the particular embodiments described above, and that various changes or modifications may be made by those skilled in the art within the scope of the appended claims without affecting the spirit of the invention.
Claims (1)
1. An APF resonance prediction method based on a voting sensor, comprising:
step 1: collecting waveform data of grid voltage and load current before and after APF current suddenly increases;
step 2: determining a characteristic value of a training sample for APF resonance prediction;
step 3: constructing a vector X and a classification criterion of a sensor;
step 4: initializing a weight vector;
step 5: calculating a prediction result;
step 6: calculating the difference between the model prediction and the real label;
step 7: updating the weight vector;
step 8: repeating the steps 5 to 7;
step 9: calculating the average value of the weight vectors to obtain a resonance classification criterion required by the APF;
step 10: when the APF operates, the sliding window extracts the characteristic vector within 20ms, and the characteristic vector is substituted into the classification criterion obtained by the previous calculation to judge whether resonance occurs or not;
in the step 1:
the method comprises the steps of designing a data acquisition function in APF equipment, storing waveform data of grid voltage and load current before and after the output current is increased in flash memory in the APF equipment once the output current of the APF suddenly becomes large, and uploading the data to a server through GPRS;
in the step 2:
the feature values of the selected training samples are: the method comprises the steps that APF resonance or current suddenly increases the three-phase power grid voltage phase change maximum value in a previous mains supply period, APF resonance or current suddenly increases the three-phase power grid current phase change maximum value in the previous mains supply period, APF resonance or current suddenly increases the three-phase power grid voltage slope maximum value in the previous mains supply period, APF resonance or current suddenly increases the three-phase power grid voltage maximum value in the previous mains supply period, and APF resonance or current suddenly increases the three-phase power grid current maximum value in the previous mains supply period; in the step 3:
constructing classification criteria of the perceptrons:
wherein ω= [ ω1, ω2, ω3, …, ω18] T Is the weight vector of the perceptron, X (n) Is a feature value extracted from a set of data needed to predict whether an APF will resonate,is the predicted outcome, ->Will resonate, < >>Will not resonate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111399708.5A CN114285038B (en) | 2021-11-24 | 2021-11-24 | APF resonance prediction method based on voting perceptron |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111399708.5A CN114285038B (en) | 2021-11-24 | 2021-11-24 | APF resonance prediction method based on voting perceptron |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114285038A CN114285038A (en) | 2022-04-05 |
| CN114285038B true CN114285038B (en) | 2023-10-31 |
Family
ID=80869862
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111399708.5A Active CN114285038B (en) | 2021-11-24 | 2021-11-24 | APF resonance prediction method based on voting perceptron |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114285038B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106253279A (en) * | 2016-08-23 | 2016-12-21 | 南京亚派科技股份有限公司 | A kind of anti-resonance control algolithm being applied to active filter |
| CN112217213A (en) * | 2020-10-24 | 2021-01-12 | 青岛鼎信通讯股份有限公司 | Resonance point real-time calculation method based on APF device |
| CN112448392A (en) * | 2020-11-09 | 2021-03-05 | 广西电网有限责任公司电力科学研究院 | Regional power grid harmonic treatment method and device based on complex-valued neural network |
-
2021
- 2021-11-24 CN CN202111399708.5A patent/CN114285038B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106253279A (en) * | 2016-08-23 | 2016-12-21 | 南京亚派科技股份有限公司 | A kind of anti-resonance control algolithm being applied to active filter |
| CN112217213A (en) * | 2020-10-24 | 2021-01-12 | 青岛鼎信通讯股份有限公司 | Resonance point real-time calculation method based on APF device |
| CN112448392A (en) * | 2020-11-09 | 2021-03-05 | 广西电网有限责任公司电力科学研究院 | Regional power grid harmonic treatment method and device based on complex-valued neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114285038A (en) | 2022-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lopez-Garcia et al. | Artificial neural networks in microgrids: A review | |
| Yang et al. | Energy reshaping based passive fractional-order PID control design and implementation of a grid-connected PV inverter for MPPT using grouped grey wolf optimizer | |
| Long et al. | Gradient descent optimization based parameter identification for FCS-MPC control of LCL-type grid connected converter | |
| Gupta et al. | Fuzzy logic controlled shunt active power filter for reactive power compensation and harmonic elimination | |
| Tsang et al. | Model based rapid maximum power point tracking for photovoltaic systems | |
| CN106849082B (en) | Harmonic control method of unified power quality regulator with photovoltaic distribution network | |
| CN111740575B (en) | An Adaptive Identification Method of Inverter Model Parameters Based on Steepest Descent Method | |
| Wang et al. | DC fault detection and classification approach of MMC-HVDC based on convolutional neural network | |
| CN115632394A (en) | Photovoltaic power station transient model construction and parameter identification method based on PPO algorithm | |
| Tan et al. | Intelligent controlled dynamic voltage restorer for improving transient voltage quality | |
| Priyadarshi et al. | An experimental performance verification of continuous mixed P‐norm based adaptive asymmetrical fuzzy logic controller for single stage photovoltaic grid integration | |
| CN114285038B (en) | APF resonance prediction method based on voting perceptron | |
| Chen et al. | Adaptive PI gain control to realize sinusoidal ripple current charging | |
| Selva Santhose Kumar et al. | Z-source inverter fed induction motor drive control using particle swarm optimization recurrent neural network | |
| CN107123991B (en) | Dynamic voltage restorer control method and device based on fuzzy particle swarm algorithm | |
| Shah et al. | Power quality improvement using ultra capacitor based dynamic voltage restorer with real twisting sliding mode control | |
| Liu et al. | Model predictive control of permanent magnet synchronous motor based on parameter identification and dead time compensation | |
| Ma et al. | Model reference adaptive fuzzy control of a shunt active power filter | |
| Sujith et al. | Implementation of psoann optimized PI control algorithm for shunt active filter | |
| Joshi et al. | Backpropagation and particle swarm optimization based neural network for power quality improvement in grid connected systems | |
| Wen et al. | Equivalent Modeling Based on Long Short-term Memory Neural Network for Virtual Synchronous Generator | |
| CN110518625A (en) | A kind of gird-connected inverter DC component suppressing method of variable learning rate BP-PID control | |
| Jia et al. | Voltage fluctuation based monitoring scheme of submodule capacitors in modular multilevel converter | |
| Singh et al. | AI-enhanced power quality management in distribution systems: implementing a dual-phase UPQC control with adaptive neural networks and optimized PI controllers | |
| Janggi et al. | Artificial neural network controller for single-phase active power filter |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |