CN112003327B - Neural network adaptive control-based grid-connected pre-synchronization control method and system - Google Patents
Neural network adaptive control-based grid-connected pre-synchronization control method and system Download PDFInfo
- Publication number
- CN112003327B CN112003327B CN202010902153.0A CN202010902153A CN112003327B CN 112003327 B CN112003327 B CN 112003327B CN 202010902153 A CN202010902153 A CN 202010902153A CN 112003327 B CN112003327 B CN 112003327B
- Authority
- CN
- China
- Prior art keywords
- grid
- voltage
- angular frequency
- axis component
- 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
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
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/40—Synchronising a generator for connection to a network or to another generator
-
- 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
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Inverter Devices (AREA)
Abstract
The invention discloses a grid-connected presynchronization control method based on neural network adaptive control, which comprises the step of outputting three-phase output voltage U of a power grid according to park transformationgabcIs converted into UgdAnd Ugq(ii) a According to the CMAC and PID composite adaptive control algorithm, U is adjustedgqAdjusted to zero to obtain the grid voltage angular frequency omegagAnd the voltage phase angle theta of the power grid in stable operationg(ii) a Will thetagAdded to three-phase output voltage UabcPark transformation of to obtain UdAnd Uq(ii) a According to the composite adaptive control algorithm, U is adjustedqAdjusted to zero to obtain phase-locked tracking compensation angular frequency omegasc(ii) a Will omegascAdding the voltage to a droop control link and superposing the voltage to the angular frequency omega of the power grid0Obtaining a reference angular frequency omega of the output voltage of the inverter; and adding omega into a voltage and current double closed-loop control link to enable the phase, frequency and amplitude of the output voltage of the micro-grid inverter to be consistent with the voltage of the power grid. The invention can lead the output voltage of the grid-connected inverter to quickly and accurately track the main grid voltage, and realize the safe switching of the micro-grid from an island mode to a grid-connected mode.
Description
Technical Field
The invention relates to the technical field of power system control, in particular to a grid-connected presynchronization control method and system based on neural network adaptive control, computer terminal equipment and a computer readable storage medium.
Background
Compared with an alternating-current micro-grid, the low-voltage direct-current micro-grid has the advantages of reducing power loss, facilitating distributed power supply and load access, improving electric energy quality and the like. The droop control has become a common control mode due to the characteristics of high current distribution precision, plug and play, simple realization, high reliability and the like.
The low-voltage direct-current micro-grid can work in an island operation mode and a grid-connected operation mode, and droop control is widely applied to micro-grid control. Under the grid-connected mode of the direct-current microgrid, the stability of the direct-current microgrid grid-connected inverter based on bus voltage differential feedforward when a virtual capacitor is added effectively inhibits the fluctuation of bus voltage during grid connection, and has larger inertia, but the influence of equivalent impedance between each DG and the bus in the model is not considered. In addition, a direct-current micro-grid-connected coordination control method based on a parallel inverter structure is adopted, a rapid voltage recovery strategy based on an inertial element is adopted, voltage loss is reduced, the quality of direct-current bus voltage is ensured, and circulating current on an alternating-current side is effectively inhibited. However, at present, research on the direct-current microgrid mainly focuses on the control of the voltage and power of the microgrid bus, and research on interaction of a large power grid is less.
When the power grid needs to more effectively utilize the energy of the micro-grid, each micro-grid needs to be connected with the main grid in parallel, and the micro-grid is in a grid-connected operation mode. When the microgrid and the main grid operate independently, the voltage amplitude, frequency and phase may not be the same. If the grid-connected operation is directly carried out at the moment, huge impact current can be generated, electric power system equipment is damaged, and even the whole power grid is paralyzed.
Disclosure of Invention
The invention aims to provide a neural network adaptive control-based grid-connected pre-synchronization control method and system, computer terminal equipment and a computer readable storage medium thereof in a grid-connected operation mode, so as to solve the problems that when a micro-grid and a main grid operate independently and the voltage amplitude, frequency and phase of the micro-grid and the main grid are different, the grid-connected operation is directly carried out, huge impact current can be generated, electric power system equipment is damaged, and even the whole power grid is paralyzed.
In order to achieve the above object, an embodiment of the present invention provides a grid-connected pre-synchronization control method based on adaptive neural network control, including:
outputting three-phase voltage U of power grid according to park transformationgabcInto d-axisComponent UgdAnd q-axis component Ugq；
According to a CMAC and PID composite adaptive control algorithm, the q-axis component U is processedgqAdjusted to zero to obtain the grid voltage angular frequency omegagAnd the voltage phase angle theta of the power grid in stable operationg；
The voltage phase angle theta of the power grid in stable operationgAdded to three-phase output voltage UabcIn the park transformation of (1), a d-axis component U is obtaineddAnd q-axis component Uq；
According to the CMAC and PID composite adaptive control algorithm, the q-axis component U is processedqAdjusted to zero to obtain phase-locked tracking compensation angular frequency omegasc；
Tracking the phase lock to compensate for angular frequency omegascAdding the droop control link and the grid voltage angular frequency omega0Obtaining a reference angular frequency omega of the output voltage of the inverter;
and adding the reference angular frequency omega to a voltage and current double closed-loop control link so as to enable the phase, frequency and amplitude of the output voltage of the micro-grid inverter to be consistent with the voltage of the power grid.
In one embodiment, the CMAC and conventional PID composite adaptive control algorithm specifically includes:
u(k)＝un(k)+up(k) (2)
wherein, ω isiIs a weight, aiIs a binary selection vector, c is a normalization parameter of the CMAC network, un(k) For the output, u, obtained at the end of each control cycle of the CMACp(k) U (k) is the total output of the composite adaptive controller, which is the output of the traditional PID algorithm;
wherein, the CMAC has the following adjustment indexes:
w(k)＝w(k-1)+Δw(k)+α(w(k)-w(k-1)) (5)
where η (0< η <1) is a learning rate of the network, and α (0< α <1) is an inertia coefficient.
In one embodiment, the learning speed η of the network is modified by a weight correction index up(k) And (3) dynamically adjusting, wherein the calculation formula is as follows:
η(up(k))＝2-exp(-up(k)/β) (6)
where β is a smoothing coefficient, and β is 10.
In one embodiment, the voltage phase angle θ when the power grid is in stable operationgAdded to three-phase output voltage UabcIn the park transformation of (1), a d-axis component U is obtaineddAnd q-axis component UqThe method specifically comprises the following steps:
converting the three-phase output voltage U of the converter by park conversion of the following formulaabcConversion to d-axis component UdAnd q-axis component Uq：
In one embodiment, the reference angular frequency ω of the inverter output voltage is calculated as follows:
ω＝ω0+ωsc (9)。
in one embodiment, the rated angular frequency ω of the grid voltageff＝100πrad/s。
The embodiment of the invention also provides a grid-connected presynchronization control system based on the neural network adaptive control, which comprises the following steps:
a first conversion unit for outputting three-phase output voltage U of the power grid according to park conversiongabcConversion to d-axis component UgdAnd q-axis component Ugq；
A first adjusting unit for combining the q-axis component U according to CMAC and PIDgqAdjusted to zero to obtain the grid voltage angular frequency omegagAnd the voltage phase angle theta of the power grid in stable operationg；
A second conversion unit for converting the voltage phase angle theta of the power grid in stable operationgAdded to three-phase output voltage UabcIn the park transformation of (1), a d-axis component U is obtaineddAnd q-axis component Uq；
A second adjusting unit for combining the q-axis component U according to the CMAC and PID composite adaptive control algorithmqAdjusted to zero to obtain phase-locked tracking compensation angular frequency omegasc；
A computing unit for tracking the phase lock and compensating the angular frequency omegascAdding the droop control link and the grid voltage angular frequency omega0Obtaining a reference angular frequency omega of the output voltage of the inverter;
and the control unit is used for adding the reference angular frequency omega to the voltage and current double closed-loop control link so as to enable the phase, the frequency and the amplitude of the output voltage of the micro-grid inverter to be consistent with the grid voltage.
In one embodiment, the CMAC and conventional PID composite adaptive control algorithm specifically includes:
u(k)＝un(k)+up(k) (2)
wherein, ω isiIs a weight, aiIs a binary selection vector, c is a normalization parameter of the CMAC network, un(k) For the output, u, obtained at the end of each control cycle of the CMACp(k) For the output of the conventional PID algorithm, u (k) is composite adaptiveThe total output of the system;
wherein, the CMAC has the following adjustment indexes:
w(k)＝w(k-1)+Δw(k)+α(w(k)-w(k-1)) (5)
where η (0< η <1) is a learning rate of the network, and α (0< α <1) is an inertia coefficient.
The embodiment of the invention also provides computer terminal equipment which comprises one or more processors and a memory. A memory coupled to the processor for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the method for controlling grid-connection presynchronization based on neural network adaptive control according to any one of the embodiments.
The embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for controlling grid-connected pre-synchronization based on neural network adaptive control according to any of the above embodiments.
Compared with the prior art, the grid-connected presynchronization control method based on the neural network adaptive control has the following beneficial effects that:
the improved grid-connected pre-synchronization control algorithm based on the neural network self-adaptive control is provided, so that the output voltage of a grid-connected inverter can quickly and accurately track the main grid voltage, and the safe switching of a micro-grid from an island mode to a grid-connected mode is realized.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flowchart of a grid-connected pre-synchronization control method based on adaptive neural network control according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a pre-synchronization control algorithm based on adaptive neural network control according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a CMAC and PID complex control architecture according to an embodiment of the invention;
fig. 4 is a schematic diagram of a pre-synchronization process based on adaptive neural network control according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a grid-connected pre-synchronization control system based on adaptive control of a neural network according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a computer terminal device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be understood that the step numbers used herein are for convenience of description only and are not intended as limitations on the order in which the steps are performed.
It is to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
The terms "comprises" and "comprising" indicate the presence of the described features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
The term "and/or" refers to any and all possible combinations of one or more of the associated listed items and includes such combinations.
Referring to fig. 1, an embodiment of the present invention provides a grid-connected pre-synchronization control method based on adaptive control of a neural network, including:
s10, outputting the three-phase output voltage U of the power grid according to park transformationgabcConversion to d-axis component UgdAnd q-axis component Ugq；
S20, according to the CMAC and PID composite adaptive control algorithm, the q-axis component U is processedgqAdjusted to zero to obtain the grid voltage angular frequency omegagAnd the voltage phase angle theta of the power grid in stable operationg；
S30, stabilizing the voltage phase angle theta of the power grid in operationgAdded to three-phase output voltage UabcIn the park transformation of (1), a d-axis component U is obtaineddAnd q-axis component Uq；
S40, according to the CMAC and PID composite adaptive control algorithm, the q-axis component U is processedqAdjusted to zero to obtain phase-locked tracking compensation angular frequency omegasc；
S50, tracking the phase lock and compensating the angular frequency omegascAdding the droop control link and the grid voltage angular frequency omega0Obtaining a reference angular frequency omega of the output voltage of the inverter;
and S60, adding the reference angular frequency omega to a voltage and current double closed-loop control link to enable the phase, frequency and amplitude of the output voltage of the micro-grid inverter to be consistent with the grid voltage.
In order to realize safe grid-connected operation of the microgrid, parameters of output voltage of a direct current microgrid inverter need to be controlled, and main grid voltage needs to be accurately tracked. Therefore, in the embodiment of the invention, in a grid-connected operation mode, on the basis of a structure of droop control and based on neural network self-adaptive control, an improved grid-connected pre-synchronous control algorithm is provided to further optimize the droop control, so that the output voltage of the microgrid inverter can quickly and accurately track the voltage of a power grid. The simulation case verifies the effectiveness of the algorithm.
The invention provides a CMAC and traditional PID composite adaptive control algorithm on the basis of a Cerebellar Model Architecture Controller (CMAC). Referring to fig. 2, the specific control algorithm is:
three-phase output voltage U of power grid through park transformationgabcIs converted into UgdAnd Ugq. Q-axis component UgqComparing with zero, and adjusting by adopting CMAC and PID composite adaptive control algorithm to obtain UgqGradually tending to zero. When U is turnedgq＝0，ωgIs the angular frequency of the grid voltage. By this closed loop regulation process, θgIs the voltage phase angle when the power grid operates stably. In one embodiment, the rated angular frequency ω of the grid voltage ff100 pi rad/s. Will thetagAdded to three-phase output voltage UabcIn the park transformation. Q-axis component UqComparing with zero, and adjusting by composite self-adaptive control algorithm to obtain UqGradually tending to zero. U shapeqWhen equal to 0, the output angular frequency omegascThe angular frequency is compensated for phase lock tracking. To regulate omegascAdding the obtained product into a droop control link, and superposing the angular frequency omega obtained by the original droop calculation0The reference angular frequency ω of the inverter output voltage can be obtained.
In one embodiment, the reference angular frequency ω of the inverter output voltage is calculated as follows:
ω＝ω0+ωsc (9)。
and adding the reference angular frequency omega to a voltage and current double closed-loop control link. Finally, the phase, frequency and amplitude of the output voltage of the micro-grid inverter are consistent with the voltage of the power grid, and the condition of grid-connected operation is achieved.
Compared with the prior art, the grid-connected presynchronization control method based on the neural network adaptive control has the following beneficial effects that:
the improved grid-connected pre-synchronization control algorithm based on the neural network self-adaptive control is provided, so that the output voltage of a grid-connected inverter can quickly and accurately track the main grid voltage, and the safe switching of a micro-grid from an island mode to a grid-connected mode is realized.
Referring to fig. 3, in one embodiment, the CMAC and conventional PID composite adaptive control algorithm specifically includes:
u(k)＝un(k)+up(k) (2)
wherein, ω isiAs a weight, aiIs a binary selection vector, c is a normalization parameter of the CMAC network, un(k) For the output, u, obtained at the end of each control cycle of the CMACp(k) U (k) is the total output of the composite adaptive controller, which is the output of the traditional PID algorithm;
wherein, the CMAC has the following adjustment indexes:
w(k)＝w(k-1)+Δw(k)+α(w(k)-w(k-1)) (5)
where η (0< η <1) is a learning rate of the network, and α (0< α <1) is an inertia coefficient.
The CMAC adopts feedforward control to realize an inverse dynamic model of a controlled object, and the traditional PID adopts feedback control to restrain disturbance. At the end of each control cycle of the CMAC, an output u is obtainedn(k) In that respect Compared with the total output u (k) of the composite adaptive controller, the weight is corrected, and the learning process is started, so that the CMAC can control the input and the output of the total controlThe difference of (a) is minimized. The total system output is generated by the CMAC. At first, let ω be 0, un＝0，u＝upThe system adopts the traditional PID algorithm for control; in the learning process of the CMAC, up(k) Gradually approaches to 0, un(k) Gradually approaching the total output of the system
In order to ensure that the convergence speed of the CMAC neural network is high and the convergence process is stable in the learning process, the weight correction of the formula (4) is improved. In one embodiment, the learning speed η of the network is modified by a weight correction index up(k) And (3) dynamically adjusting, wherein the calculation formula is as follows:
η(up(k))＝2-exp(-up(k)/β) (6)
where β is a smoothing coefficient, and β is 10.
According to (7), when up(k) The larger the learning rate, the faster the convergence rate of the network. As the number of learning increases, up(k) Gradually decreased with learning speed of up(k) Is reduced gradually to ensure the convergence process to be stable and avoid larger oscillation.
In order to meet grid-connected conditions, under the droop control, the amplitude and the frequency of the output voltage of the inverter are consistent with reference values. Only the phase factor can be considered at this time. ThetagAnd angular frequency ωgThe phase angle and the angular frequency of the main network output voltage are obtained through a phase-locked structure. And then, the phase difference between the microgrid inverter and the main grid voltage gradually approaches zero by adjusting the angular frequency of the output voltage of the microgrid inverter. At this moment, Δ θ is 0, the voltages of the microgrid and the main grid are completely synchronized. The schematic diagram is shown in fig. 4.
In one embodiment, the voltage phase angle θ when the power grid operates stablygAdded to three-phase output voltage UabcIn the park transformation of (3), the d-axis component U is obtaineddAnd q-axis component UqThe method specifically comprises the following steps:
by means of the park transformation of the following formula,will the three-phase output voltage U of the converterabcConversion to d-axis component UdAnd q-axis component Uq：
Similarly, in one embodiment, the three-phase output voltage U of the power grid is converted by park transformation of the following formulagabcConversion to d-axis component UgdAnd q-axis component Ugq：
Referring to fig. 5, an embodiment of the present invention provides a grid-connected pre-synchronization control system based on adaptive control of a neural network, including:
a first conversion unit for outputting three-phase output voltage U of the power grid according to park conversiongabcConversion to d-axis component UgdAnd q-axis component Ugq；
A first adjusting unit for combining the q-axis component U according to CMAC and PID composite adaptive control algorithmgqAdjusted to zero to obtain the grid voltage angular frequency omegagAnd the voltage phase angle theta of the power grid in stable operationg；
A second conversion unit for converting the voltage phase angle theta of the power grid in stable operationgAdded to three-phase output voltage UabcIn the park transformation of (1), a d-axis component U is obtaineddAnd q-axis component Uq；
A second adjusting unit for combining the q-axis component U according to the CMAC and PID composite adaptive control algorithmqAdjusted to zero to obtain phase-locked tracking compensation angular frequency omegasc；
A computing unit for tracking the phase lock and compensating the angular frequency omegascAdding the droop control link and the grid voltage angular frequency omega0Obtaining a reference angular frequency omega of the output voltage of the inverter;
and the control unit is used for adding the reference angular frequency omega to the voltage and current double closed-loop control link so as to enable the phase, the frequency and the amplitude of the output voltage of the micro-grid inverter to be consistent with the grid voltage.
In one embodiment, the CMAC and conventional PID composite adaptive control algorithm specifically includes:
u(k)＝un(k)+up(k) (2)
wherein, ω isiIs a weight, aiIs a binary selection vector, c is a normalization parameter of the CMAC network, un(k) For the output, u, obtained at the end of each control cycle of the CMACp(k) U (k) is the total output of the composite adaptive controller, which is the output of the traditional PID algorithm;
wherein, the CMAC has the following adjustment indexes:
w(k)＝w(k-1)+Δw(k)+α(w(k)-w(k-1)) (5)
where η (0< η <1) is a learning rate of the network, and α (0< α <1) is an inertia coefficient.
For specific limitations of the grid-connected pre-synchronization control system based on the neural network adaptive control, reference may be made to the above limitations of the grid-connected pre-synchronization control method based on the neural network adaptive control, and details are not repeated here. All or part of each module in the grid-connected pre-synchronous control system based on the neural network adaptive control can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
Referring to fig. 6, an embodiment of the invention provides a computer terminal device, which includes one or more processors and a memory. The memory is coupled to the processor and is configured to store one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method for controlling the grid-connected pre-synchronization based on the neural network adaptive control as in any of the above embodiments.
The processor is used for controlling the overall operation of the computer terminal equipment so as to complete all or part of the steps of the grid-connected pre-synchronization control method based on the neural network adaptive control. The memory is used to store various types of data to support the operation at the computer terminal device, which data may include, for example, instructions for any application or method operating on the computer terminal device, as well as application-related data. The Memory may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk.
In an exemplary embodiment, the computer terminal Device may be implemented by one or more Application Specific 1 integrated circuits (AS 1C), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components, and is configured to perform the above-mentioned neural network adaptive control-based grid-connected pre-synchronization control method, and achieve technical effects consistent with the above-mentioned methods.
In another exemplary embodiment, a computer readable storage medium including program instructions, which when executed by a processor, implement the steps of the method for controlling pre-synchronization for grid connection based on adaptive control of a neural network in any one of the above embodiments is also provided. For example, the computer readable storage medium may be the above-mentioned memory including program instructions, which can be executed by a processor of a computer terminal device to implement the above-mentioned method for controlling pre-synchronization for grid connection based on adaptive control of a neural network, and achieve the technical effects consistent with the above-mentioned method.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (8)
1. A grid-connected presynchronization control method based on neural network adaptive control is characterized by comprising the following steps:
outputting three-phase voltage U of power grid according to park transformationgabcConversion to d-axis component UgdAnd q-axis component Ugq；
According to a CMAC and PID composite adaptive control algorithm, the q-axis component U is processedgqAdjusted to zero to obtain the grid voltage angular frequency omegagabcAnd the voltage phase angle theta of the power grid during stable operationg(ii) a The CMAC and PID composite adaptive control algorithm specifically comprises the following steps:
u(k)＝un(k)+up(k) (2)
wherein, ω isiAs a weight, aiIs selected in two elementsSelecting vector, c is normalization parameter of CMAC network, un(k) For the output, u, obtained at the end of each control cycle of the CMACp(k) U (k) is the total output of the composite adaptive controller, which is the output of the traditional PID algorithm;
wherein, the CMAC has the following adjustment indexes:
w(k)＝w(k-1)+Δw(k)+α(w(k)-w(k-1)) (5)
wherein η (0< η <1) is a learning rate of the network, and α (0< α <1) is an inertia coefficient;
the voltage phase angle theta of the power grid in stable operationgThree-phase output voltage U added to power gridgabcIn the park transformation of (1), a d-axis component U is obtaineddAnd q-axis component Uq；
According to the CMAC and PID composite adaptive control algorithm, the q-axis component U is processedqAdjusted to zero to obtain phase-locked tracking compensation angular frequency omegasc；
Tracking the phase lock to compensate for angular frequency omegascAdding the droop control link and the grid voltage angular frequency omegagabcObtaining a reference angular frequency omega of the output voltage of the inverter;
and adding the reference angular frequency omega to a voltage and current double closed-loop control link so as to enable the phase, frequency and amplitude of the output voltage of the micro-grid inverter to be consistent with the voltage of the power grid.
2. The method as claimed in claim 1, wherein the learning speed η of the network is a weight correction index up(k) And (3) dynamically adjusting, wherein the calculation formula is as follows:
η(up(k))＝2-exp(-up(k)/β) (6)
where β is a smoothing coefficient, and β is 10.
3. The grid-connected presynchronization control method based on neural network adaptive control as claimed in claim 1, wherein the voltage phase angle θ when the power grid is operated stablygThree-phase output voltage U added to power gridgabcIn the park transformation of (1), a d-axis component U is obtaineddAnd q-axis component UqThe method specifically comprises the following steps:
the three-phase output voltage U of the power grid of the converter is converted through park conversion of the following formulagabcConversion to d-axis component UdAnd q-axis component Uq：
4. The grid-connected presynchronization control method based on the neural network adaptive control as claimed in claim 1, wherein a reference angular frequency ω of the inverter output voltage is calculated as follows:
ω＝ω0+ωsc (9)。
5. the neural network adaptive control-based grid-connected presynchronization control method according to claim 1, wherein the rated value ω of the grid voltage angular frequency is set toff＝100πrad/s。
6. A grid-connected presynchronization control system based on neural network adaptive control is characterized by comprising the following components:
a first conversion unit for converting the power grid into three according to park conversionPhase output voltage UgabcConversion to d-axis component UgdAnd q-axis component Ugq；
A first adjusting unit for combining the q-axis component U according to CMAC and PID composite adaptive control algorithmgqAdjusted to zero to obtain the grid voltage angular frequency omegagabcAnd the voltage phase angle theta of the power grid during stable operationg(ii) a The CMAC and PID composite adaptive control algorithm specifically comprises the following steps:
u(k)＝un(k)+up(k) (2)
wherein, ω isiIs a weight, aiIs a binary selection vector, c is a normalization parameter of the CMAC network, un(k) For the output, u, obtained at the end of each control cycle of the CMACp(k) U (k) is the output of the conventional PID algorithm, and u (k) is the total output of the composite adaptive controller;
wherein, the CMAC has the following adjustment indexes:
w(k)＝w(k-1)+Δw(k)+α(w(k)-w(k-1)) (5)
wherein η (0< η <1) is a learning rate of the network, and α (0< α <1) is an inertia coefficient;
a second conversion unit for converting the voltage phase angle theta of the power grid in stable operationgThree-phase output voltage U added to power gridgabcIn the park transformation of (3), the d-axis component U is obtaineddAnd q-axis component Uq；
A second adjusting unit for adaptively compounding the CMAC and the PIDA system algorithm for calculating the q-axis component UqAdjusted to zero to obtain phase-locked tracking compensation angular frequency omegasc；
A computing unit for tracking the phase lock and compensating the angular frequency omegascAdding the droop control link and the grid voltage angular frequency omegagabcObtaining a reference angular frequency omega of the output voltage of the inverter;
and the control unit is used for adding the reference angular frequency omega to a voltage and current double closed-loop control link so as to enable the phase, the frequency and the amplitude of the output voltage of the microgrid inverter to be consistent with the voltage of a power grid.
7. A computer terminal device, comprising:
one or more processors;
a memory coupled to the processor for storing one or more programs;
when executed by the one or more processors, the one or more programs cause the one or more processors to implement the method for grid-tie pre-synchronization control based on neural network adaptive control of any one of claims 1-5.
8. A computer-readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the method for grid-connected pre-synchronization control based on neural network adaptive control according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010902153.0A CN112003327B (en) | 2020-08-31 | 2020-08-31 | Neural network adaptive control-based grid-connected pre-synchronization control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010902153.0A CN112003327B (en) | 2020-08-31 | 2020-08-31 | Neural network adaptive control-based grid-connected pre-synchronization control method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112003327A CN112003327A (en) | 2020-11-27 |
| CN112003327B true CN112003327B (en) | 2022-07-12 |
Family
ID=73465990
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010902153.0A Active CN112003327B (en) | 2020-08-31 | 2020-08-31 | Neural network adaptive control-based grid-connected pre-synchronization control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112003327B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113036810B (en) * | 2021-04-28 | 2023-02-28 | 青海伟航北创新能源科技有限公司 | Phase-locked control method and device for zero voltage ride through of photovoltaic grid-connected inverter |
| CN113325714B (en) * | 2021-06-09 | 2023-02-24 | 西北工业大学 | Intelligent water-saving spraying system and method based on matrix completion and neural network PID |
| CN114243793A (en) * | 2021-11-12 | 2022-03-25 | 国网重庆市电力公司电力科学研究院 | Novel phase-locked loop suitable for VSC inserts under weak receiving end alternating current network |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102723741A (en) * | 2012-04-26 | 2012-10-10 | 南京航空航天大学 | Grid connection presynchronization control method of microgrid inverter based on droop control |
| CN103345159B (en) * | 2013-07-03 | 2015-08-05 | 江苏大学 | Based on the hybrid electric vehicle BSG system control method of neural Network Adaptive Inversion |
| CN109193794A (en) * | 2018-09-22 | 2019-01-11 | 东北电力大学 | A kind of Grid-connected Control Strategy of low-voltage direct micro-capacitance sensor |
| CN109347147B (en) * | 2018-11-23 | 2022-02-01 | 华北水利水电大学 | quasi-PR grid-connected inverter optimization control method for self-adaptive harmonic elimination |
| CN111313474B (en) * | 2020-04-01 | 2020-12-29 | 西华大学 | Improved micro-grid-connected presynchronization control method |
-
2020
- 2020-08-31 CN CN202010902153.0A patent/CN112003327B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112003327A (en) | 2020-11-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112003327B (en) | Neural network adaptive control-based grid-connected pre-synchronization control method and system | |
| WO2024021206A1 (en) | Method and system for energy storage system control based on grid-forming converter, storage medium, and device | |
| CN110212799B (en) | Passive backstepping control method for restraining circulating current of modular multilevel converter | |
| JP6397613B2 (en) | Control circuit for controlling inverter circuit, inverter device provided with the control circuit, power system provided with the inverter device, and control method | |
| CN112186804B (en) | Method and system for bus voltage unbalance and harmonic compensation of island microgrid | |
| Wong et al. | A consensus-based adaptive virtual output impedance control scheme for reactive power sharing in radial microgrids | |
| Sedhom et al. | A multistage H‐infinity–based controller for adjusting voltage and frequency and improving power quality in islanded microgrids | |
| CN113824160A (en) | Adaptive virtual inductor-based micro-grid parallel inverter power regulation method | |
| CN115589036A (en) | Method for adjusting parallel active power equalization of multiple inverters based on self-adaptive virtual impedance | |
| Liu et al. | Dynamic circulating current suppression method for multiple hybrid power parallel grid-connected inverters with model reference adaptive system | |
| CN110266044B (en) | Microgrid grid-connected control system and method based on energy storage converter | |
| JP5865090B2 (en) | Control circuit for power conversion circuit, grid-connected inverter system using this control circuit, and single-phase PWM converter system | |
| CN117879035A (en) | Distributed photovoltaic grid-connected power quality control method and system based on sagging control | |
| Liu et al. | Unified voltage control for grid-forming inverters | |
| Yu et al. | Frequency-dependent network analysis and stability enhanced design for voltage-source converters under weak grid conditions | |
| CN110277793B (en) | Two-stage photovoltaic inverter active power balance control method | |
| Chen et al. | Enhanced Q-axis Voltage Integral Damping Control for Fast PLL-Synchronized Inverters in Weak Grids | |
| CN106992548B (en) | Control method for improving stability of grid-connected converter | |
| CN116436091A (en) | Transient stability lifting control method of grid-structured converter and grid-structured converter system | |
| Lang et al. | Instantaneous power control within an advanced power generation center for more-electric aircraft applications | |
| Song et al. | Stationary frame control strategy for voltage source inverter under unbalanced and distorted grid voltage | |
| CN113690944A (en) | Predictive discrete complex variable resonance control method for inverter | |
| Park et al. | Nonlinear Optimization-Based Power-Voltage Control of Grid-Connected Converter in Weak Grid | |
| Rahman et al. | Dynamic Interactions and Stabilization of Weak Grid-Tied Parallel VSCs and Parallel CSCs Systems Considering PVG Dynamic Resistance | |
| Hoseini et al. | Improving the performance of grid-connected voltage-sourced inverters under unbalanced network conditions using a fuzzy sliding mode-based approach |
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 |