CN112968516B - Parallel UPS system state feedback control method based on neural network - Google Patents
Parallel UPS system state feedback control method based on neural network Download PDFInfo
- Publication number
- CN112968516B CN112968516B CN202110194518.3A CN202110194518A CN112968516B CN 112968516 B CN112968516 B CN 112968516B CN 202110194518 A CN202110194518 A CN 202110194518A CN 112968516 B CN112968516 B CN 112968516B
- Authority
- CN
- China
- Prior art keywords
- neural network
- formula
- parallel ups
- ups system
- inverter
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 55
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000013461 design Methods 0.000 claims abstract description 6
- 239000011159 matrix material Substances 0.000 claims description 11
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 4
- 230000003247 decreasing effect Effects 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 230000001537 neural effect Effects 0.000 claims 1
- 238000004088 simulation Methods 0.000 abstract description 11
- 238000011160 research Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000002401 inhibitory effect Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J9/00—Circuit arrangements for emergency or stand-by power supply, e.g. for emergency lighting
- H02J9/04—Circuit arrangements for emergency or stand-by power supply, e.g. for emergency lighting in which the distribution system is disconnected from the normal source and connected to a standby source
- H02J9/06—Circuit arrangements for emergency or stand-by power supply, e.g. for emergency lighting in which the distribution system is disconnected from the normal source and connected to a standby source with automatic change-over, e.g. UPS systems
- H02J9/062—Circuit arrangements for emergency or stand-by power supply, e.g. for emergency lighting in which the distribution system is disconnected from the normal source and connected to a standby source with automatic change-over, e.g. UPS systems for AC powered loads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
Abstract
The invention is applicable to the technical field of parallel UPS systems, and provides a state feedback control method of a parallel UPS system based on a neural network, which comprises the following steps: establishing a state space model of the parallel UPS system; state feedback tracking control design of completely known system dynamics; and carrying out parallel UPS system parameter identification based on the neural network. The invention provides a parallel UPS system state feedback control method based on a neural network, which strictly proves the convergence of an identification error, and through simulation research, the identification capability of the neural network and the performance and effectiveness of the proposed control algorithm are proved for the first time.
Description
Technical Field
The invention belongs to the technical field of parallel UPS systems, and particularly relates to a state feedback control method of a parallel UPS system based on a neural network.
Background
Parallel UPS systems have many advantages, but their effective control is challenging. These challenges are due to dynamic loading conditions and the interaction of multiple converters. In order to achieve effective control of the parallel UPS system, it is mainly achieved by two control objectives. The first goal is to adjust the output voltage to perfect sinusoidal nonlinearities and rapidly changing load conditions. A second challenge is to minimize the circulating current between the converters.
However, both of the above control objectives have a common disadvantage in that they require precise system parameters (resistance, capacitance, inductance, etc.). This also explains why existing control methods always consider using the same parallel inverter. In fact, the system parameters tend to fluctuate due to the effects of heating, aging, and the like. Thus, for parallel UPS systems with more system parameters, a more complex and efficient system identifier is needed.
Currently, neural Network (NN) systems based on training or learning have been developed for decades, but have not been applied much in the field of power electronics. This may be due to the large gap between theoretical control techniques and physical applications.
Therefore, the invention provides a parallel UPS system state feedback control method based on a neural network.
Disclosure of Invention
In view of the above-mentioned drawbacks of the prior art, the present invention is to provide a parallel UPS system status feedback control method based on a neural network.
In order to achieve the above object, the present invention provides a parallel UPS system, including n inverters arranged in parallel, the output ends of the n inverters are respectively connected to one LC filter, each LC filter is connected to an ac bus, and each inverter is connected to a centralized voltage and load sharing controller.
Another object of the embodiments of the present invention is to provide a parallel UPS system status feedback control method based on a neural network, including the following steps:
establishing a state space model of the parallel UPS system;
state feedback tracking control design of completely known system dynamics;
and carrying out parallel UPS system parameter identification based on the neural network.
As another preferable scheme of the embodiment of the invention, the method for establishing the state space model of the parallel UPS system comprises the following steps:
the control input U (t) of the system is a set of voltage references for each inverter, expressed as equation (1):
wherein ,vj An input voltage of the jth inverter is represented, and n represents the total number of inverters;
the state variable X (t) of the system is the output voltage v of the parallel inverter o And the output current i of the inverter j Expressed as formula (2):
wherein ,ij The output current of the jth inverter is obtained, and n is the total number of inverters;
state space model of system
For a continuous time linear system, expressed as formula (3):
wherein ：
wherein ,Lj Output inductance of output filter of jth inverter, C j The capacitance of the output filter for the jth inverter, r j An output resistor of the output filter for the j-th inverter; d (t) represents a compensation coefficient.
As another preferred scheme of the embodiment of the invention, based on a state space system model, an ideal state track X of the system * (t) is represented by formula (4):
wherein ,
representing the output voltage reference, i * Representing the output current reference.
As another preferred scheme of the embodiment of the invention, the state feedback tracking control design for carrying out the completely known system dynamics comprises the following steps:
the tracking error is defined as E (t) =x (t) -X * (t) the tracking error dynamics formula obtainable from equation (3), expressed as equation (5):
according to equation (5), the stable tracking control equation is expressed as equation (6):
U(t)＝U e (t)+U D (t)+U des (t) (6)
wherein ,
for ensuring convergence of tracking error->
To estimate a state vector; u (U) D (t)＝-M 1 D(t)；U des (t)＝-M 2 X * (t)；K,M 1 and M2 For controlling the gain matrix;
substituting formula (6) into formula (5) to obtain formula (9)
wherein 
Is a state estimation error; and selecting proper K through pole allocation, so that all characteristic values of (A-BK) are negative, and the tracking error is converged to zero.
As another preferred embodiment of the present invention, K, M 1 and M2 For controlling the gain matrix, the requirements of the matrix are formula (7), formula (8):
BU D (t)＝-BM 1 D(t)＝-D(t) (7)
as another preferred embodiment of the present invention, it is ensured that
The speed of convergence to zero is much faster than the speed of convergence of E (t) to zero.
As another preferable scheme of the embodiment of the invention, the neural network-based parallel UPS system parameter identification comprises the following steps:
formula (3) discrete system dynamics with sampling interval Ts is rewritten as formula (10):
X[k+1]＝A d X[k]+B d U[k]+D[k] (10)
wherein ,
discrete system dynamics (10) are represented on an omega tight set as formula (11) with a neural network
X[k+1]＝W A X[k]+ε A [k]+W B U[k]+ε B [k]+D[k]
＝W s σ s [k]+ε s [k]+D[k] (11)
wherein ,
is an input vector; />
The target weight matrix; epsilon s [k]＝ε A [k]+ε B [k]Reconstructing an error for the neural network; d [ k ]]Is a measurable load current;
using the neural network identifier, the state of the system at k estimates a model pattern, expressed as equation (12):
the error equation is identified as:
wherein ,
estimating an error for the neural network weight; definition of e [ k+1 ]]＝αe[k]And 0 < α < 1 is the decreasing gradient of the error e, yielding formula (14):
update law of neural network weight
Represented by formula (15):
wherein ,
σ s [k] T to activate function sigma s [k]Is a pseudo-inverse of (a).
As another preferable scheme of the embodiment of the invention, the upper bound of the weight of the target neural network is W s ||≤W sM Wherein is W sM A positive constant; the upper bound of the neural network activation function and the reconstruction error is ||sigma s [k]||≤σ sM And |ε s [k]||≤ε sM ，σ sM and εsM Is a positive constant.
The beneficial effects of the invention are as follows: the invention provides a parallel UPS system state feedback control method based on a neural network, which strictly proves the convergence of an identification error, and the identification capability of the neural network and the performance and the effectiveness of the proposed control algorithm are proved for the first time through Matlab simulation research.
Drawings
FIG. 1 is a topology of n inverters in a parallel UPS system;
FIG. 2 is a state feedback control block diagram of a parallel UPS system;
FIG. 3 is a waveform of simulation results of Experimental example 1;
fig. 4 is a waveform of the simulation result of experimental example 2.
In FIG. 1, i Load (t) is the load current; v ij * Is the input voltage reference value of the jth inverter.
Detailed Description
The invention is further illustrated by the following examples in conjunction with the accompanying drawings:
example 1
The embodiment provides a parallel UPS system state feedback control method based on a neural network, which comprises the following steps:
1. establishing a state space model of the parallel UPS system, comprising the following steps:
the control input U (t) of the system is a set of voltage references for each inverter, expressed as equation (1):
wherein ,vj An input voltage of the jth inverter is represented, and n represents the total number of inverters;
the state variable X (t) of the system is the output voltage v of the parallel inverter o And the output current i of the inverter j Expressed as formula (2):
wherein ,ij The output current of the jth inverter is obtained, and n is the total number of inverters;
state space model of system
For a continuous time linear system, expressed as formula (3):
wherein ：
wherein ,Lj Output inductance of output filter of jth inverter, C j The capacitance of the output filter for the jth inverter, r j An output resistor of the output filter for the j-th inverter; d (t) represents a compensation coefficient;
based on the state space system model, an ideal state track X of the system can be given * (t) expressed as formula (4):
wherein ,
representing the output voltage reference, i * Representing the output current reference.
Thus, the control targets include:
1) Tracking the output voltage of the parallel inverter to an output voltage reference value, wherein the output voltage reference value is a sine function of time;
2) Tracking an output current of the inverter to an output current reference value, the output current reference value being calculated from the uniformly shared load current and charging current;
3) And canceling the system circulation current.
2. A state feedback tracking control design of completely known system dynamics is performed, comprising the following steps:
the tracking error is defined as E (t) =x (t) -X * (t) the tracking error dynamics formula obtainable from equation (3), expressed as equation (5):
according to equation (5), the stable tracking control equation is expressed as equation (6):
U(t)＝U e (t)+U D (t)+U des (t) (6)
wherein ,
for ensuring convergence of tracking error->
To estimate a state vector; u (U) D (t)＝-M 1 D (t) for removing the interference term; u (U) des (t)＝-M 2 X * (t) for canceling the remaining interference term; k, M 1 and M2 For controlling the gain matrix, the requirements of the matrix are formula (7), formula (8):
BU D (t)＝-BM 1 D(t)＝-D(t) (7)
substituting formula (6) into formula (5) to obtain formula (9)
wherein 
Is a state estimation error; selecting proper K through pole allocation, so that all characteristic values of (A-BK) are negative, and the tracking error is converged to zero; in addition, guarantee->
The speed of convergence to zero is much faster than the speed of convergence of E (t) to zero, +.>
Can be ignored.
3. Based on neural network, carrying out on-line identification of the parameters of the parallel UPS system, comprising the following steps:
the discrete system dynamics of formula (3) with a sampling interval of Ts can be rewritten as formula (10):
X[k+1]＝A d X[k]+B d U[k]+D[k] (10)
wherein ,
discrete system dynamics formula (10) can be represented as formula (11) on a omega tight set using a Neural Network (NN)
X[k+1]＝W A X[k]+ε A [k]+W B U[k]+ε B [k]+D[k]
＝W s σ s [k]+ε s [k]+D[k] (11)
wherein ,
is an input vector (activation function of NN);
the target weight matrix; epsilon s [k]＝ε A [k]+ε B [k]Reconstructing an error for NN; d [ k ]]Is a measurable load current; further, assume that the upper bound of the target NN weight is ||w s ||≤W sM Wherein is W sM A positive constant, assuming that the upper bound of NN activation function and reconstruction error is ||σ s [k]||≤σ sM And |ε s [k]||≤ε sM ，σ sM and εsM Is a positive constant;
using a Neural Network (NN) identifier, the state of the system at k estimates a model form, expressed as equation (12):
the error equation is identified as:
wherein ,
estimating an error for the NN weight; definition of e [ k+1 ]]＝αe[k]And 0 < α < 1 is the decreasing gradient of the error e, yielding formula (14):
parameter recognition, i.e. updating rules of weights of neural network identifiers
Represented by formula (15):
wherein ,
σ s [k] T to activate function sigma s [k]Is a pseudo-inverse of (a).
Therefore, after learning the system dynamics through the designed neural network identifier, the state feedback tracking control can be applied to the system dynamics. A block diagram of the status feedback control of a parallel UPS system is shown in fig. 2. Obtaining a state space model of the parallel UPS system through the method (3)
Based on a state space model of the system, an ideal state track X of the system can be given * (t). According to X * The state feedback tracking control of the completely known system dynamics is carried out on the (t) and the X (t) to obtain a formula (9), and proper K is selected through pole allocation in the formula (9), so that all characteristic values of the (A-BK) are negative, and the tracking error is converged to zero; in addition, guarantee->
The speed of convergence to zero is much faster than the speed of convergence of E (t) to zero, +.>
Can be ignored. From a and B in formula (9), the discrete system dynamics of formula (3) sampling interval Ts can be rewritten as formula (10): calculating the recognition error formula of formula (13) by using a Neural Network (NN) recognizer, and obtaining the update rule of the weight value of the network recognizer according to the deduction of formulas (1) - (14)>
Expressed as equation (15), equation (15) becomes a control signal for the parallel UPS system.
Example 2
On the basis of embodiment 1, the parallel UPS system includes n inverters arranged in parallel, the output ends of the n inverters are respectively connected with one LC filter, each LC filter is connected with an ac bus, and each inverter is connected with a centralized voltage and load sharing controller.
Experimental example 1
Table 1 gives the parameter settings of the parallel inverter and the load for simulation.
TABLE 1
In addition, expected state references (X * (t)) is calculated as follows:
v * (t)＝V m sin(ωt)
in the formula ,Vm For a selected amplitude of the output voltage ω is the fundamental frequency of the system.
To verify the effectiveness of the present invention, case #1, a step change from no load to linear load, balances the parameter settings of each inverter.
By means of SimPowerSystem in MATLAB Simulink TM Simulations were performed. The total simulation time is 1 second, but only 0.4 to 0.6 secondsThe results in seconds are exaggerated and for a better illustration of case #1, the simulation results for case #1 are shown in fig. 3. The test is carried out under the condition of parameter balance, namely the inductance, the resistance and the capacitance between the parallel modules are equal. In the simulation process, the system is initially connected without load, and the neural network learns from system interference. The linear step load is then increased at 0.495s and the neural network learns from system disturbances. It should be noted that the linear load is deliberately connected to the system when the current peaks, so that a larger disturbance can be observed. Thus, as can be seen from fig. 3 (a), the four currents i1, i2, i3, i4 flowing through the inverter are identical and overlap. As shown in fig. 3 (b), the circulating currents (i 1-i2, i2-i3, i3-i 4) become zero. As shown in fig. 3 (c), the voltage output (v o ) Can always track the reference voltage v well and quickly * (v ref ) Even at the moment of increasing the load. The load current (iLoad) is then plotted in fig. 3 (d).
Experimental example 2
Table 2 gives the parameter settings of the parallel inverter and the load for simulation.
TABLE 2
In addition, expected state references (X * (t)) is calculated as follows:
v * (t)＝V m sin(ωt)
in the formula ,Vm For a selected amplitude of the output voltage ω is the fundamental frequency of the system.
The simulation results for case # 2 are shown in fig. 4. The effectiveness of the control algorithm in inhibiting the circulating current is verified through the setting of unbalance parameters of each inverter. Therefore, the inductance of one inverter is intentionally reduced to half of the original value. I.e. L1 decreases from 2mH to 1mH, while L2, L3, L4 remain 2mH, the output current of the inverter under linear load conditions is shown in fig. 4 (a). As can be seen from fig. 4 (b), during transients, the circulating current increases due to the decreasing inductance of one of the inverter modules. In addition, the output voltage can still track the reference voltage, as shown in fig. 4 (c), and the overall performance is good.
The foregoing describes in detail preferred embodiments of the present invention. It should be understood that numerous modifications and variations can be made in accordance with the concepts of the invention by one of ordinary skill in the art without undue burden. Therefore, all technical solutions which can be obtained by logic analysis, reasoning or limited experiments based on the prior art by the person skilled in the art according to the inventive concept shall be within the scope of protection defined by the claims.
Claims (8)
1. A parallel UPS system state feedback control method based on a neural network is characterized in that: the method comprises the following steps:
establishing a state space model of the parallel UPS system;
performing state feedback tracking control design of completely known system dynamics;
carrying out parallel UPS system parameter identification based on a neural network;
the establishing of the state space model of the parallel UPS system comprises the following steps:
the control input U (t) of the system is a set of voltage references for each inverter, expressed as equation (1):
wherein ,vj An input voltage of the jth inverter is represented, and n represents the total number of inverters;
the state variable X (t) of the system is the output voltage v of the parallel inverter o And the output current i of the inverter j Expressed as formula (2):
wherein ,ij The output current of the jth inverter is obtained, and n is the total number of inverters;
state space model of system
For a continuous time linear system, expressed as formula (3):
wherein ：
wherein ,Lj Output inductance of output filter of jth inverter, C j The capacitance of the output filter for the jth inverter, r j An output resistor of the output filter for the j-th inverter; d (t) represents a compensation coefficient.
2. The neural network-based parallel UPS system status feedback control method of claim 1, wherein: the parallel UPS system comprises n inverters which are arranged in parallel, wherein the output ends of the n inverters are respectively connected with one LC filter, each LC filter is connected with an alternating current bus, and each inverter is connected with a centralized voltage and load sharing controller.
3. The neural network-based parallel UPS system status feedback control method of claim 1, wherein: based on state space system model, ideal state track X of system * (t) TableShown as formula (4):
wherein ,
representing the output voltage reference, i * Representing the output current reference. />
4. The neural network-based parallel UPS system status feedback control method of claim 3, wherein: the state feedback tracking control design for completely known system dynamics comprises the following steps:
the tracking error is defined as E (t) =x (t) -X * (t) the tracking error dynamics formula obtainable from equation (3), expressed as equation (5):
according to equation (5), the stable tracking control equation is expressed as equation (6):
U(t)＝U e (t)+U D (t)+U des (t) (6)
wherein ,
for ensuring convergence of tracking error->
To estimate a state vector; u (U) D (t)＝-M 1 D(t)；U des (t)＝-M 2 X * (t)；K,M 1 and M2 For controlling the gain matrix;
substituting formula (6) into formula (5) to obtain formula (9)
wherein 
Is a state estimation error; and selecting proper K through pole allocation, so that all characteristic values of (A-BK) are negative, and the tracking error is converged to zero.
5. The neural network-based parallel UPS system status feedback control method of claim 4, wherein: k, M 1 and M2 For controlling the gain matrix, the requirements of the matrix are formula (7), formula (8):
BU D (t)＝-BM 1 D(t)＝-D(t) (7)
6. the neural network-based parallel UPS system status feedback control method of claim 5, wherein: guarantee of
The speed of convergence to zero is much faster than the speed of convergence of E (t) to zero.
7. The neural network-based parallel UPS system status feedback control method of claim 1, wherein: the neural network-based parallel UPS system parameter identification method comprises the following steps:
formula (3) discrete system dynamics with sampling interval Ts is rewritten as formula (10):
X[k+1]＝A d X[k]+B d U[k]+D[k] (10)
wherein ,
discrete system dynamics (10) are represented on an omega tight set as formula (11) with a neural network
X[k+1]＝W A X[k]+ε A [k]+W B U[k]+ε B [k]+D[k]
＝W s σ s [k]+ε s [k]+D[k] (11)
wherein ,
is an input vector; />
The target weight matrix; epsilon s [k]＝ε A [k]+ε B [k]Reconstructing an error for the neural network; d [ k ]]Is a measurable load current;
using the neural network identifier, the state of the system at k estimates a model pattern, expressed as equation (12):
the error equation is identified as:
wherein ,
estimating an error for the neural network weight; definition of e [ k+1 ]]＝αe[k]And 0 is<α<1 is a decreasing gradient of the error e, resulting in formula (14):
more weight of neural networkNew law
Represented by formula (15):
wherein ,
to activate function sigma s [k]Is a pseudo-inverse of (a).
8. The neural network-based parallel UPS system status feedback control method of claim 7, wherein: the upper bound of the weight of the target neural network is W s ||≤W sM Wherein is W sM A positive constant; the upper bound of the neural network activation function and the reconstruction error is ||sigma s [k]||≤σ sM And |ε s [k]||≤ε sM ，σ sM and εsM Is a positive constant.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110194518.3A CN112968516B (en) | 2021-02-20 | 2021-02-20 | Parallel UPS system state feedback control method based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110194518.3A CN112968516B (en) | 2021-02-20 | 2021-02-20 | Parallel UPS system state feedback control method based on neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112968516A CN112968516A (en) | 2021-06-15 |
| CN112968516B true CN112968516B (en) | 2023-06-09 |
Family
ID=76285340
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110194518.3A Active CN112968516B (en) | 2021-02-20 | 2021-02-20 | Parallel UPS system state feedback control method based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112968516B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114336751B (en) * | 2022-01-04 | 2023-12-05 | 中国船舶重工集团公司第七0四研究所 | LCL type single-phase grid-connected inverter state feedback control method |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108199600A (en) * | 2018-01-18 | 2018-06-22 | 扬州大学 | A kind of adaptive dynamic surface control device of full-bridge inverter |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102611140B (en) * | 2012-03-23 | 2014-04-30 | 合肥工业大学 | Grid-connected inverter island detection method based on wavelet transform and neural network |
| US9362781B2 (en) * | 2012-09-14 | 2016-06-07 | Chloride Srl | Uninterruptible power supply system with fast transfer for undervoltage source line failures |
| CN105116346A (en) * | 2015-09-15 | 2015-12-02 | 盐城工业职业技术学院 | Series-connected battery system and method for estimating state of charge thereof |
| US10574086B2 (en) * | 2016-04-08 | 2020-02-25 | Rhombus Energy Solutions, Inc. | Nonlinear control algorithm and system for a single-phase AC-AC converter with bidirectional isolated DC-DC converter |
| US10284008B2 (en) * | 2016-09-13 | 2019-05-07 | Abb Schweiz Ag | Isolated parallel ups system with fault location detection |
| CN112087178A (en) * | 2020-09-14 | 2020-12-15 | 四川长虹电器股份有限公司 | Parameter identification method of permanent magnet synchronous motor |
-
2021
- 2021-02-20 CN CN202110194518.3A patent/CN112968516B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108199600A (en) * | 2018-01-18 | 2018-06-22 | 扬州大学 | A kind of adaptive dynamic surface control device of full-bridge inverter |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112968516A (en) | 2021-06-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Baghaee et al. | Nonlinear load sharing and voltage compensation of microgrids based on harmonic power-flow calculations using radial basis function neural networks | |
| Badoni et al. | Adaptive neurofuzzy inference system least-mean-square-based control algorithm for DSTATCOM | |
| Zainuri et al. | DC‐link capacitor voltage control for single‐phase shunt active power filter with step size error cancellation in self‐charging algorithm | |
| Abdelsalam et al. | An integrated control strategy with fault detection and tolerant control capability based on capacitor voltage estimation for modular multilevel converters | |
| Gupta et al. | Fuzzy logic controlled shunt active power filter for reactive power compensation and harmonic elimination | |
| CN108767869B (en) | Static reactive power compensator voltage adjusting method based on artificial neural network | |
| Mangaraj et al. | Adaptive LMBP training‐based icosϕ control technique for DSTATCOM | |
| CN108923430A (en) | Active Power Filter-APF neural network overall situation fast terminal sliding-mode control and calculating equipment | |
| Saidi et al. | Fuzzy logic controller for three‐level shunt active filter compensating harmonics and reactive power | |
| Sedghi et al. | Voltage and frequency control of an islanded microgrid through robust control method and fuzzy droop technique | |
| Singh et al. | A review on Shunt active power filter control strategies | |
| Soliman et al. | Experimental validation for artificial data-driven tracking control for enhanced three-phase grid-connected boost rectifier in DC microgrids | |
| CN112968516B (en) | Parallel UPS system state feedback control method based on neural network | |
| Tan et al. | Intelligent controlled dynamic voltage restorer for improving transient voltage quality | |
| Malla et al. | Supplementary control for virtual synchronous machine based on adaptive dynamic programming | |
| Thirumoorthi et al. | Adaptive method for power quality improvement through minimization of harmonics using artificial intelligence | |
| Coteli et al. | Phase angle control of three level inverter based D-STATCOM using neuro-fuzzy controller | |
| Pedapenki et al. | Soft control techniques for shunt active power filter | |
| Wang et al. | Self-Feedback Neural Network Sliding Mode Control with Extended State Observer for Active Power Filter | |
| Vukadinovic et al. | Stator resistance identification based on neural and fuzzy logic principles in an induction motor drive | |
| Fei et al. | Adaptive Fuzzy-Neural-Network Control of Active Power Filter Using Fuzzy Backstepping Approach | |
| Abdeslam et al. | A neural approach for the control of an active power filter | |
| Srivastava et al. | A Whale Optimization Algorithm Based Shunt Active Power Filter for Power Quality Improvement | |
| Kamarposhti | Power quality compensation in distribution system based on instantaneous power theory and recursive fuzzy proportional-integral controller | |
| Pedapenki et al. | Application of neural networks in power quality |
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 |