CN104158418A - Photovoltaic grid-connected inverter device - Google Patents

Photovoltaic grid-connected inverter device Download PDF

Info

Publication number
CN104158418A
CN104158418A CN201410408718.4A CN201410408718A CN104158418A CN 104158418 A CN104158418 A CN 104158418A CN 201410408718 A CN201410408718 A CN 201410408718A CN 104158418 A CN104158418 A CN 104158418A
Authority
CN
China
Prior art keywords
grid
moment
input
output
voltage
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201410408718.4A
Other languages
Chinese (zh)
Other versions
CN104158418B (en
Inventor
刘卫亮
刘长良
张会超
马良玉
林永君
陈文颖
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
North China Electric Power University
Original Assignee
North China Electric Power University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by North China Electric Power University filed Critical North China Electric Power University
Priority to CN201410408718.4A priority Critical patent/CN104158418B/en
Publication of CN104158418A publication Critical patent/CN104158418A/en
Application granted granted Critical
Publication of CN104158418B publication Critical patent/CN104158418B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • YGENERAL 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
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02EREDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E10/00Energy generation through renewable energy sources
    • Y02E10/50Photovoltaic [PV] energy
    • Y02E10/56Power conversion systems, e.g. maximum power point trackers

Landscapes

  • Inverter Devices (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

A photovoltaic grid-connected inverter device comprises a plurality of miniature inverters in one-to-one correspondence with photovoltaic cell panels of a photovoltaic power station. Each miniature inverter comprises an MPU controller, an energy-storage capacitor, a flyback converter, a power frequency inverter bridge and an EMI filter, wherein the energy-storage capacitor, the flyback converter, the power frequency inverter bridge and the EMI filter are sequentially connected between the photovoltaic cell panel and a power grid; and the MPU controller collects the voltage of the photovoltaic cell panel and the voltage of the power grid through a first voltage sensor and a second voltage sensor respectively, collects the grid-connected current output by the EMI filter through a current sensor, and controls the flyback converter and the power frequency inverter bridge through two drive modules respectively. The photovoltaic grid-connected inverter device helps to solve the problem of poor reliability of a centralized inverter at the same time the power generating efficiency is improved. The device enables a neural network inverse model to be combined with a PI controller; not only linearization of the system can be realized, but also the robustness of the PI controller can be played; and thus the power quality is effectively improved.

Description

A kind of photovoltaic network inverter
Technical field
The present invention relates to a kind of grid-connected Miniature inverter system that adopts neural network contrary modeling control, belong to technical field of power generation.
Background technology
Along with energy crisis and problem of environmental pollution day by day serious, solar energy power generating is as clean green energy resource, its grid-connected control technology becomes that countries in the world are paid close attention to and the focus of research.
Utilization ratio and the quality of power supply requirement of modern society to the energy is more and more higher.Existing grid-connected photovoltaic inverter mostly is centralized inverter, by carrying out electric energy output by a high-power inverter after a large amount of photovoltaic cell connection in series-parallel.Owing to can not ensureing that each photovoltaic cell works in maximum power point, there is inefficient shortcoming in this mode.More seriously, the reliability of this mode is poor, if centralized inverter breaks down, will cause connected all photovoltaic cells to stop electric energy output.Therefore, the microminiaturization of photovoltaic DC-to-AC converter is by the development trend becoming from now on.In addition,, there is the shortcoming that grid-connected current harmonic content is higher in the simple PI controller of the many employings of existing grid-connected photovoltaic inverter.Can suppress to a certain extent harmonic wave by increasing output filtering unit, but but make the output impedance of system present even high-order LC characteristic of second order, easily cause system unstable.Visible, in order to improve the quality of power supply, must seek better control method.
Summary of the invention
The object of the invention is to the drawback for prior art, a kind of photovoltaic network inverter is provided, effectively to improve reliability and the quality of power supply of photovoltaic generation.
Problem of the present invention realizes with following technical proposals:
A kind of photovoltaic network inverter, formation comprises each photovoltaic battery panel multiple Miniature inverters one to one with photovoltaic plant, each Miniature inverter comprises MPU controller and is connected in successively the storage capacitor between photovoltaic battery panel and electrical network, anti exciting converter, power frequency inverter bridge and electromagnetic interface filter, described MPU controller gathers respectively photovoltaic battery panel voltage and line voltage by the first voltage sensor and second voltage transducer, gather the grid-connected current of electromagnetic interface filter output by current sensor, and control respectively anti exciting converter and power frequency inverter bridge by two driver modules, described MPU controller operates in the following manner:
1. gather photovoltaic battery panel voltage by the first voltage sensor v pv , gather line voltage by second voltage transducer v grid , gather grid-connected current by current sensor i ac ; Using Miniature inverter as object, set up and train corresponding neural network contrary modeling, specific as follows:
A. choose the inversion model of three layers of BP neural network system, wherein, input layer nodes is 10, hidden layer neuron nodes is 18, output layer neuron node number is 1, hidden layer neuron transfer function uses hyperbolic tangent function, and output layer neuron transfer function uses S type function;
B. on photovoltaic miniature inverter, gather service data;
Utilize single loop PI controller to carry out grid-connected current control, make photovoltaic miniature inverter respectively under the operating mode in rated power, 80% rated power, 60% rated power, 40% rated power, 20% rated power, continuous acquisition under every kind of operating mode ngroup grid-connected current i ac , line voltage v grid , anti exciting converter pwm signal duty ratio d, photovoltaic battery panel voltage v pv , form altogether 5 ngroup service data;
C. utilize the service data structure sample gathering;
For the k moment, the sample of constructing for v grid (k), v grid (k-1), v grid (k-2), i ac (k), i ac (k-1), i ac (k+1), d(k-1), d(k-2), d(k-3), v pv (k), d(k) }, wherein, v grid (k) be the line voltage in k moment, v grid (k-1) be the line voltage in k-1 moment, v grid (k-2) be the line voltage in k-2 moment, i ac (k) be the grid-connected current in k moment, i ac (k-1) be the grid-connected current in k-1 moment, i ac (k+1) be the grid-connected current in k+1 moment, d(k-1) be the anti exciting converter pwm signal duty ratio in k-1 moment, d(k-2) be the anti exciting converter pwm signal duty ratio in k-2 moment, d(k-3) be the anti exciting converter pwm signal duty ratio in k-3 moment, v pv (k) be the voltage of the photovoltaic battery panel in k moment, d(k) be the anti exciting converter pwm signal duty ratio in k moment, 5 ngroup service data forms 5 altogether nindividual sample;
D. randomly draw 5 nin individual sample data 4 nindividual as training sample, all the other nthree layers of individual as test samples, training is set up BP neural net; In training process, for the sample in k moment, first input of getting BP neural net is the line voltage in k moment v grid (k), second line voltage that input is the k-1 moment v grid (k-1), the 3rd input is the line voltage in k-2 moment v grid (k-2), the 4th input is the grid-connected current in k moment i ac (k), the 5th input is the grid-connected current in k-1 moment i ac (k-1), the 6th input is the grid-connected current in k+1 moment i ac (k+1), the 7th the anti exciting converter pwm signal duty ratio that input is the k-1 moment d(k-1), the 8th the anti exciting converter pwm signal duty ratio that input is the k-2 moment d(k-2), the 9th the anti exciting converter pwm signal duty ratio that input is the k-3 moment d(k-3), the tenth input is the voltage of the photovoltaic battery panel in k moment v pv (k), BP neural net is output as the anti exciting converter pwm signal duty ratio in k moment d(k);
2. utilize the BP neural network contrary modeling training to control Miniature inverter, concrete steps are:
A. utilize the BP neural network contrary modeling training to carry out the calculating of anti exciting converter pwm signal duty ratio, for the current k moment, get the line voltage that first input is the k moment v grid (k), second line voltage that input is the k-1 moment v grid (k-1), the 3rd input is the line voltage in k-2 moment v grid (k-2), the 4th input is the grid-connected current in k moment i ac (k), the 5th input is the grid-connected current in k-1 moment i ac (k-1), the 6th input is the grid-connected current set point in k+1 moment i * ac (k+1), the 7th the anti exciting converter pwm signal duty ratio that input is the k-1 moment d(k-1), the 8th the anti exciting converter pwm signal duty ratio that input is the k-2 moment d(k-2), the 9th the anti exciting converter pwm signal duty ratio that input is the k-3 moment d(k-3), the tenth input is the voltage of the photovoltaic battery panel in k moment v pv (k), show that BP neural net is output as d(k);
B. by next moment grid-connected current set point i * ac (k+1) with current k moment grid-connected current i ac (k) deviation is sent into PI controller, obtains closed-loop control amount d c(k),
Wherein: e (k)= i * ac (k+1)- i ac (k), k p represent proportionality coefficient, k i represent integral coefficient;
C. by the output of neural network contrary modeling dand the output of PI controller (k) d c(k) stack after as final anti exciting converter pwm signal duty ratio d(k), that is:
D(k)= d(k)+ d C(k)。
Above-mentioned photovoltaic network inverter, the training of BP neural net is adopted to the error back propagation algorithm that becomes learning rate, be specially: first weight coefficient and threshold value in each layer of neuron are initialized as to (1, + 1) random quantity between, again using 10 neuron output values of input layer as the each neuronic input of hidden layer, 18 neuron output values of hidden layer are as the single neuronic input of output layer, and the single neuronic output valve of output layer is network and finally exports, for kindividual training sample, calculates the tthe actual output of network after inferior training with desired output error:
And 4 nthe error of sum square of individual training sample is:
Complete one time of every calculating, relatively e t with anticipation error e o if, e t < e o , train end condition to meet, training finishes; Otherwise, will e t carry out backpropagation along access path, and adjust one by one weight coefficient and the threshold value of each layer, until e t < e o till; Then, utilize nindividual test samples is tested model, calculates sample mean square error mSE, if having mSE < t r ( t r for a certain fixed threshold), think that trained BP neural network model meets required precision, now records each neuronic weight coefficient and threshold value; Otherwise, again BP neural network model is trained, until it meets required precision.
Above-mentioned photovoltaic network inverter, described anti exciting converter comprises transformer, the first power tube, diode and the second electric capacity, the primary coil of described transformer connects photovoltaic battery panel voltage through the first power tube, its secondary coil is powered to power frequency inverter bridge through diode, the second electric capacity is connected to the direct-flow input end of power frequency inverter bridge, and the grid of the first power tube connects the output of the first driver module.
Above-mentioned photovoltaic network inverter, described electromagnetic interface filter comprises three inductance and six electric capacity, the head end of two coils of the first inductance connects respectively two ac output ends of power frequency inverter bridge, the two ends that their tail end gets access to grid through the second inductance and the 3rd inductance respectively, the 3rd electric capacity is attempted by the ac output end of power frequency inverter bridge, one end ground connection of the 4th electric capacity and the 5th electric capacity, the other end connects respectively two ac output ends of power frequency inverter bridge, the two ends of the 6th electric capacity connect respectively the tail end of two coils of the first inductance, one end ground connection of the 7th electric capacity and the 8th electric capacity, the two ends that the other end gets access to grid respectively.
Above-mentioned photovoltaic network inverter, described power frequency inverter bridge is the fully controlled bridge being connected into by four power tubes, the grid of four power tubes connects the output of the second driver module.
The present invention utilizes multiple Miniature inverters to replace the centralized inverter in conventional photovoltaic power station, makes each photovoltaic battery panel work in maximum power point, in improving generating efficiency, has also solved the problem of centralized inverter poor reliability.This device combines neural network contrary modeling and PI controller, both can realize system linearity, can bring into play again the robustness of PI controller, thereby has effectively improved the quality of power supply.
Brief description of the drawings
Below in conjunction with accompanying drawing, the invention will be further described.
Fig. 1 is the structured flowchart of grid-connected Miniature inverter device;
Fig. 2 is neural network contrary modeling schematic diagram;
Fig. 3 is single neuronic structural representation;
Fig. 4 is the test result of BP neural network contrary modeling;
Fig. 5 is the program structure diagram of nerve network reverse controller;
Fig. 6 is the grid-connected current curve of grid-connected Miniature inverter output;
Fig. 7 is the grid-connected current error curve of grid-connected Miniature inverter output.
In figure, each list of reference numerals is: UT1, the first voltage sensor, UT2, second voltage transducer, CT, current sensor, D1, diode, Q1~Q5, the first power tube~five power tube, C1~C8, the first electric capacity~eight electric capacity, L1~L3, the first inductance~three inductance, TX1, transformer.
In literary composition, each symbol inventory is: v pv for photovoltaic battery panel voltage, v grid for line voltage, i ac for grid-connected current, v grid (k) be the line voltage in k moment, dfor anti exciting converter pwm signal duty ratio, v grid (k-1) be the line voltage in k-1 moment, v grid (k-2) be the line voltage in k-2 moment, i ac (k) be the grid-connected current in k moment, i ac (k-1) be the grid-connected current in k-1 moment, i ac (k+1) be the grid-connected current in k+1 moment, d(k-1) be the anti exciting converter pwm signal duty ratio in k-1 moment, d(k-2) be the anti exciting converter pwm signal duty ratio in k-2 moment, d(k-3) be the anti exciting converter pwm signal duty ratio in k-3 moment, v pv (k) be the voltage of the photovoltaic battery panel in k moment, d(k) be the anti exciting converter pwm signal duty ratio in k moment, i * ac (k+1) be the grid-connected current set point in k+1 moment, for tthe actual output of network after inferior training, for tdesired output after inferior training, e o for anticipation error, e t for tafter inferior training 4 nthe error of sum square of individual training sample.
Embodiment
The present invention is made up of multiple Miniature inverters, each Miniature inverter comprises: storage capacitor (being the first capacitor C 1 in Fig. 1), anti exciting converter is (by transformer TX1, the first power tube Q1, diode D1 and the second capacitor C 2 form), power frequency inverter bridge (being formed by the second power tube Q2~five power tube Q5), electromagnetic interface filter is (by the 3rd capacitor C 3~eight capacitor C 8, the first inductance L 1~three inductance L 3 forms), the first driver module (being the driver module 1 in Fig. 1), the second driver module (being the driver module 2 in Fig. 1), MPU controller, the first voltage sensor UT1, second voltage transducer UT2, current sensor CT, the positive pole of storage capacitor is connected with photovoltaic battery panel is anodal, the minus earth of storage capacitor, the minus earth of the first voltage sensor, the positive pole of the first voltage sensor are connected with photovoltaic battery panel positive pole, the measuring-signal output of the first voltage sensor is connected with MPU controller, the input anode of anti exciting converter is connected with photovoltaic battery panel is anodal, the input negativing ending grounding of anti exciting converter, the output plus terminal of anti exciting converter is connected with power frequency inverter bridge one input, and the output negative terminal of anti exciting converter is connected with another input of power frequency inverter bridge, one output of power frequency inverter bridge is connected with electromagnetic interface filter one input, and another input of another output and electromagnetic interface filter of power frequency inverter bridge is connected, one output of electromagnetic interface filter is connected with the positive pole of current sensor, and another output of electromagnetic interface filter is connected to electrical network, the positive pole of current sensor is connected with an output of electromagnetic interface filter, and the negative pole of current sensor is connected to electrical network, and the measuring-signal output of current sensor is connected with MPU controller, the positive pole of second voltage transducer is connected to the negative pole of current sensor, and the negative pole of second voltage transducer is connected to electrical network, and the measuring-signal output of second voltage transducer is connected with MPU controller, the input of the first driver module is connected with MPU controller, and the output of the first driver module is connected with the first power tube grid in anti exciting converter, the input of the second driver module is connected with MPU controller, one output of the second driver module is connected with the second power tube in power frequency inverter bridge, the grid of the 5th power tube, and another output of the second driver module is connected with the 3rd power tube in power frequency inverter bridge, the grid of the 4th power tube, MPU controller is connected with the measuring-signal output of the first voltage sensor, second voltage transducer, current sensor, and MPU controller is also connected with the input of the first driver module, the second driver module,
Further illustrate the present invention below in conjunction with the drawings and specific embodiments.
In the present embodiment, choose the 235W photovoltaic battery panel that Ying Li company produces, its parameter at standard test condition is: short circuit current i sc=8.54A, open circuit voltage v oc=37V, maximum power point electric current i max=7.97A, maximum power point voltage v max=29.5V.
The Miniature inverter structured flowchart designing for this photovoltaic battery panel as shown in Figure 1.This device mainly comprises: storage capacitor (the first electric capacity) C1, anti exciting converter, power frequency inverter bridge, electromagnetic interface filter, the first driver module, the second driver module, MPU controller, the first voltage sensor UT1, second voltage transducer UT2, current sensor CT; Wherein MPU controller is selected the high performance float-point digital signal processor TMS320F28335 of TI company, the functional modules such as I/O module, ADC module, PWM module, CAN module, UART and SPI module that this digital signal processor is integrated; Storage capacitor C1 selects 2200uF electrochemical capacitor; In anti exciting converter, transformer TX1 adopts NA5814-AL, and the first power tube Q1 selects TK50X15J1, and diode D1 adopts C2D05120E, and the second capacitor C 2 is selected 0.47uF polarity free capacitor; The second power tube Q2, the 3rd power tube Q3, the 4th power tube Q4, the 5th power tube Q5 select IPB60R190C6, and the first driver module and the second driver module are MCP14E4; In electromagnetic interface filter, the 3rd capacitor C 3, the 6th capacitor C 6 are selected 0.015uf polarity free capacitor, the 4th capacitor C 4, the 5th capacitor C 5, the 7th capacitor C 7, the 8th capacitor C 8 are selected 4700pF polarity free capacitor, the first inductance L 1 is selected FE2X03-4-3NL, and the second inductance L 2, the 3rd inductance L 3 are selected 2100LL-151-H-RC; Voltage sensor adopts MCP6022; Current sensor CT adopts Hall current sensor ACS712ELCTR-058-1;
Fig. 2 is three layers of set up BP neural network contrary modeling.Input layer nodes is 10, and hidden layer neuron nodes is 18, and output layer neuron node number is 1.
Fig. 3 is single neuronic structural representation, for neuronic input signal, for neuronic weight coefficient, for neuronic threshold value, neuronic being output as:
Hidden layer neuron transfer function uses hyperbolic tangent function,
Wherein:
for transfer function input;
for transfer function output.
Output layer neuron transfer function uses S type function,
(3)
Wherein:
for transfer function input;
for transfer function output.
In embodiment, gathering service data process is specially: utilize single loop PI controller to carry out grid-connected current control, make photovoltaic miniature inverter respectively under the operating mode in rated power, 80% rated power, 60% rated power, 40% rated power, 20% rated power, under every kind of operating mode with the sample frequency continuous acquisition of 114KHz n=10000 groups of grid-connected current i ac , line voltage v grid , anti exciting converter pwm signal duty ratio d, photovoltaic battery panel voltage v pv , obtain altogether 50000 groups of service datas, thereby form 50000 samples.Randomly draw wherein 40000 as training sample, all the other 10000 as test samples.
In embodiment, arrange e o =1.5, threshold value t r =0.01, iteration is trained after 9876 times, e t =1.47, meet end condition e t < e o , training finishes.Now, recycling test samples is tested model, and partial test result as shown in Figure 4, calculates sample mean square error mSE=0.006, has mSE< t r , therefore think and meet inversion model required precision, now record each neuronic weight coefficient and threshold value.
In embodiment, the parameter tuning of PI controller is k p =0.01, k i =800; Grid-connected current set point i * ac change given by digital signal processor according to discrete sine rule.
Write software program and implant in dsp chip according to above-mentioned steps, can realize the control of the nerve network reverse controller of photovoltaic miniature inverter.Software program comprises system main program and Neural network inverse control interrupt service subroutine, and block diagram is as Fig. 5.
Fig. 6 is the grid-connected current curve of photovoltaic miniature inverter output after use control method of the present invention, and Fig. 7 is grid-connected current aberration curve.Visible, grid-connected current can be good at following the tracks of its set point, has less deviation.
In order further to analyze the effect of control method of the present invention, under 20%, 40%, 60%, 80%, 100% rated power output operating mode, itself and conventional PI control method (are got respectively k p =0.01, k i =800) contrast, table 1 is the grid-connected current harmonic content comparing result of two kinds of methods, known the inventive method has good robustness for the variation of operating mode, grid-connected current harmonic content under different operating modes is significantly less than conventional PI control method, meets the grid-connected harmonic content standard (THD<5%) of national grid.
Table 1
The above; it is only preferably embodiment of the present invention; but protection scope of the present invention should be not limited to this; core technology, the variation that can make or replacement that any those skilled in the art of being familiar with disclose according to the present invention, within all should being encompassed in protection scope of the present invention.

Claims (5)

1. a photovoltaic network inverter, it is characterized in that, it comprises each photovoltaic battery panel multiple Miniature inverters one to one with photovoltaic plant, each Miniature inverter comprises MPU controller and is connected in successively the storage capacitor between photovoltaic battery panel and electrical network, anti exciting converter, power frequency inverter bridge and electromagnetic interface filter, described MPU controller gathers respectively photovoltaic battery panel voltage and line voltage by the first voltage sensor (UT1) and second voltage transducer (UT2), gather the grid-connected current of electromagnetic interface filter output by current sensor (CT), and control respectively anti exciting converter and power frequency inverter bridge by two driver modules, described MPU controller operates in the following manner:
1. gather photovoltaic battery panel voltage by the first voltage sensor (UT1) v pv , gather line voltage by second voltage transducer (UT2) v grid , gather grid-connected current by current sensor (CT) i ac ; Using Miniature inverter as object, set up and train corresponding neural network contrary modeling, specific as follows:
A. choose the inversion model of three layers of BP neural network system, wherein, input layer nodes is 10, hidden layer neuron nodes is 18, output layer neuron node number is 1, hidden layer neuron transfer function uses hyperbolic tangent function, and output layer neuron transfer function uses S type function;
B. on photovoltaic miniature inverter, gather service data;
Utilize single loop PI controller to carry out grid-connected current control, make photovoltaic miniature inverter respectively under the operating mode in rated power, 80% rated power, 60% rated power, 40% rated power, 20% rated power, continuous acquisition under every kind of operating mode ngroup grid-connected current i ac , line voltage v grid , anti exciting converter pwm signal duty ratio d, photovoltaic battery panel voltage v pv , form altogether 5 ngroup service data;
C. utilize the service data structure sample gathering;
For the k moment, the sample of constructing for v grid (k), v grid (k-1), v grid (k-2), i ac (k), i ac (k-1), i ac (k+1), d(k-1), d(k-2), d(k-3), v pv (k), d(k) }, wherein, v grid (k) be the line voltage in k moment, v grid (k-1) be the line voltage in k-1 moment, v grid (k-2) be the line voltage in k-2 moment, i ac (k) be the grid-connected current in k moment, i ac (k-1) be the grid-connected current in k-1 moment, i ac (k+1) be the grid-connected current in k+1 moment, d(k-1) be the anti exciting converter pwm signal duty ratio in k-1 moment, d(k-2) be the anti exciting converter pwm signal duty ratio in k-2 moment, d(k-3) be the anti exciting converter pwm signal duty ratio in k-3 moment, v pv (k) be the voltage of the photovoltaic battery panel in k moment, d(k) be the anti exciting converter pwm signal duty ratio in k moment, 5 ngroup service data forms 5 altogether nindividual sample;
D. randomly draw 5 nin individual sample data 4 nindividual as training sample, all the other nthree layers of individual as test samples, training is set up BP neural net; In training process, for the sample in k moment, first input of getting BP neural net is the line voltage in k moment v grid (k), second line voltage that input is the k-1 moment v grid (k-1), the 3rd input is the line voltage in k-2 moment v grid (k-2), the 4th input is the grid-connected current in k moment i ac (k), the 5th input is the grid-connected current in k-1 moment i ac (k-1), the 6th input is the grid-connected current in k+1 moment i ac (k+1), the 7th the anti exciting converter pwm signal duty ratio that input is the k-1 moment d(k-1), the 8th the anti exciting converter pwm signal duty ratio that input is the k-2 moment d(k-2), the 9th the anti exciting converter pwm signal duty ratio that input is the k-3 moment d(k-3), the tenth input is the voltage of the photovoltaic battery panel in k moment v pv (k), BP neural net is output as the anti exciting converter pwm signal duty ratio in k moment d(k);
2. utilize the BP neural network contrary modeling training to control Miniature inverter, concrete steps are:
A. utilize the BP neural network contrary modeling training to carry out the calculating of anti exciting converter pwm signal duty ratio, for the current k moment, get the line voltage that first input is the k moment v grid (k), second line voltage that input is the k-1 moment v grid (k-1), the 3rd input is the line voltage in k-2 moment v grid (k-2), the 4th input is the grid-connected current in k moment i ac (k), the 5th input is the grid-connected current in k-1 moment i ac (k-1), the 6th input is the grid-connected current set point in k+1 moment i * ac (k+1), the 7th the anti exciting converter pwm signal duty ratio that input is the k-1 moment d(k-1), the 8th the anti exciting converter pwm signal duty ratio that input is the k-2 moment d(k-2), the 9th the anti exciting converter pwm signal duty ratio that input is the k-3 moment d(k-3), the tenth input is the voltage of the photovoltaic battery panel in k moment v pv (k), show that BP neural net is output as d(k);
B. by next moment grid-connected current set point i * ac (k+1) with current k moment grid-connected current i ac (k) deviation is sent into PI controller, obtains closed-loop control amount d c(k),
Wherein: e(k)= i * ac (k+1)- i ac (k), k p represent proportionality coefficient, k i represent integral coefficient;
C. by the output of neural network contrary modeling dand the output of PI controller (k) d c(k) stack after as final anti exciting converter pwm signal duty ratio d(k), that is:
D(k)= d(k)+ d C(k)。
2. a kind of photovoltaic network inverter according to claim 1, it is characterized in that, the training of BP neural net is adopted to the error back propagation algorithm that becomes learning rate, be specially: first weight coefficient and threshold value in each layer of neuron are initialized as to (1, + 1) random quantity between, again using 10 neuron output values of input layer as the each neuronic input of hidden layer, 18 neuron output values of hidden layer are as the single neuronic input of output layer, the single neuronic output valve of output layer is network and finally exports, for kindividual training sample, calculates the tthe actual output of network after inferior training with desired output error:
And 4 nthe error of sum square of individual training sample is:
Complete one time of every calculating, relatively e t with anticipation error e o if, e t < e o , train end condition to meet, training finishes; Otherwise, will e t carry out backpropagation along access path, and adjust one by one weight coefficient and the threshold value of each layer, until e t < e o till; Then, utilize nindividual test samples is tested model, calculates sample mean square error mSE, if having mSE < t r ( t r for a certain fixed threshold), think that trained BP neural network model meets required precision, now records each neuronic weight coefficient and threshold value; Otherwise, again BP neural network model is trained, until it meets required precision.
3. a kind of photovoltaic network inverter according to claim 1 and 2, it is characterized in that, described anti exciting converter comprises transformer (TX1), the first power tube (Q1), diode (D1) and the second electric capacity (C2), the primary coil of described transformer (TX1) connects photovoltaic battery panel voltage through the first power tube (Q1), its secondary coil is given the power supply of power frequency inverter bridge through diode (D1), the second electric capacity (C2) is connected to the direct-flow input end of power frequency inverter bridge, the grid of the first power tube (Q1) connects the output of the first driver module.
4. a kind of photovoltaic network inverter according to claim 3, it is characterized in that, described electromagnetic interface filter comprises three inductance and six electric capacity, the head end of two coils of the first inductance (L1) connects respectively two ac output ends of power frequency inverter bridge, the two ends that their tail end gets access to grid through the second inductance (L2) and the 3rd inductance (L3) respectively, the 3rd electric capacity (C3) is attempted by the ac output end of power frequency inverter bridge, one end ground connection of the 4th electric capacity (C4) and the 5th electric capacity (C5), the other end connects respectively two ac output ends of power frequency inverter bridge, the two ends of the 6th electric capacity (C6) connect respectively the tail end of two coils of the first inductance (L1), one end ground connection of the 7th electric capacity (C7) and the 8th electric capacity (C8), the two ends that the other end gets access to grid respectively.
5. a kind of photovoltaic network inverter according to claim 4, is characterized in that, described power frequency inverter bridge is the fully controlled bridge being connected into by four power tubes, and the grid of four power tubes connects the output of the second driver module.
CN201410408718.4A 2014-08-19 2014-08-19 A kind of photovoltaic network inverter Expired - Fee Related CN104158418B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410408718.4A CN104158418B (en) 2014-08-19 2014-08-19 A kind of photovoltaic network inverter

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410408718.4A CN104158418B (en) 2014-08-19 2014-08-19 A kind of photovoltaic network inverter

Publications (2)

Publication Number Publication Date
CN104158418A true CN104158418A (en) 2014-11-19
CN104158418B CN104158418B (en) 2016-06-15

Family

ID=51883854

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410408718.4A Expired - Fee Related CN104158418B (en) 2014-08-19 2014-08-19 A kind of photovoltaic network inverter

Country Status (1)

Country Link
CN (1) CN104158418B (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104965558A (en) * 2015-05-27 2015-10-07 华北电力大学(保定) Photovoltaic power generation system maximum power tracking method and apparatus considering the factor of haze
CN106100398A (en) * 2016-06-06 2016-11-09 国网青海省电力公司 A kind of micro-capacitance sensor energy storage inverter control method based on gravitation neutral net
CN107910573A (en) * 2017-11-08 2018-04-13 南京晓庄学院 A kind of reversible fuel cell heap energy saver and control method
CN108075482A (en) * 2016-11-11 2018-05-25 中科诺维(北京)科技有限公司 Permanent magnet direct-drive wind turbine gird-connected inverter device and control method
CN109889069A (en) * 2019-03-05 2019-06-14 淮阴工学院 A kind of individual event inverter composite control method and system
CN110208721A (en) * 2019-07-09 2019-09-06 西南交通大学 A kind of method for diagnosing faults and device cascading three-level inverter
CN111742462A (en) * 2018-02-28 2020-10-02 罗伯特·博世有限公司 System and method for audio and vibration based power distribution equipment condition monitoring

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2004001942A1 (en) * 2002-06-23 2003-12-31 Powerlynx A/S Power converter
US20100156186A1 (en) * 2008-12-23 2010-06-24 Samsung Electro-Mechanics Co., Ltd. Photovoltaic and fuel cell hybrid generation system using dual converters and single inverter and method of controlling the same
CN102142693A (en) * 2011-03-10 2011-08-03 西安交通大学 Solar photovoltaic grid-connected inversion control system based on field programmable gate array (FPGA)
CN103106544A (en) * 2013-02-01 2013-05-15 东南大学 Photovoltaic power generation prediction system based on T-S-type fuzzy neural network
CN103441526A (en) * 2013-08-14 2013-12-11 华北电力大学(保定) Grid-connected off-grid small photovoltaic power generation system and control method

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2004001942A1 (en) * 2002-06-23 2003-12-31 Powerlynx A/S Power converter
US20100156186A1 (en) * 2008-12-23 2010-06-24 Samsung Electro-Mechanics Co., Ltd. Photovoltaic and fuel cell hybrid generation system using dual converters and single inverter and method of controlling the same
CN102142693A (en) * 2011-03-10 2011-08-03 西安交通大学 Solar photovoltaic grid-connected inversion control system based on field programmable gate array (FPGA)
CN103106544A (en) * 2013-02-01 2013-05-15 东南大学 Photovoltaic power generation prediction system based on T-S-type fuzzy neural network
CN103441526A (en) * 2013-08-14 2013-12-11 华北电力大学(保定) Grid-connected off-grid small photovoltaic power generation system and control method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
李光明等: "并网光伏发电系统发电量预测方法的探讨", 《云南师范大学学报》 *

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104965558A (en) * 2015-05-27 2015-10-07 华北电力大学(保定) Photovoltaic power generation system maximum power tracking method and apparatus considering the factor of haze
CN106100398A (en) * 2016-06-06 2016-11-09 国网青海省电力公司 A kind of micro-capacitance sensor energy storage inverter control method based on gravitation neutral net
CN108075482A (en) * 2016-11-11 2018-05-25 中科诺维(北京)科技有限公司 Permanent magnet direct-drive wind turbine gird-connected inverter device and control method
CN107910573A (en) * 2017-11-08 2018-04-13 南京晓庄学院 A kind of reversible fuel cell heap energy saver and control method
CN107910573B (en) * 2017-11-08 2020-10-09 南京晓庄学院 Energy-saving device of reversible fuel cell stack and control method
CN111742462A (en) * 2018-02-28 2020-10-02 罗伯特·博世有限公司 System and method for audio and vibration based power distribution equipment condition monitoring
CN109889069A (en) * 2019-03-05 2019-06-14 淮阴工学院 A kind of individual event inverter composite control method and system
CN110208721A (en) * 2019-07-09 2019-09-06 西南交通大学 A kind of method for diagnosing faults and device cascading three-level inverter
CN110208721B (en) * 2019-07-09 2024-06-11 西南交通大学 Fault diagnosis method and device for cascaded three-level inverter

Also Published As

Publication number Publication date
CN104158418B (en) 2016-06-15

Similar Documents

Publication Publication Date Title
CN104158418A (en) Photovoltaic grid-connected inverter device
Wang et al. Dynamic modeling and small signal stability analysis of distributed photovoltaic grid-connected system with large scale of panel level DC optimizers
CN112103946B (en) Particle swarm algorithm-based microgrid energy storage optimization configuration method
CN206060577U (en) A kind of multichannel MPPT Miniature inverter
CN102142693A (en) Solar photovoltaic grid-connected inversion control system based on field programmable gate array (FPGA)
CN103593711B (en) A kind of distributed power source Optimal Configuration Method
Chen et al. An any-cell (s)-to-cell (s) equalization method with a single magnetic component for Lithium-ion battery pack
CN111222097B (en) Reliability evaluation and sensitivity analysis method for photovoltaic direct-current boosting and collecting system
CN104333034B (en) Grid-connected Miniature inverter based on SVMs Adverse control
CN110739719A (en) Two-step decision method for optimized access of flexible multi-state switch
Zainan et al. Research on voltage level and simulation model of medium-low voltage of DC distribution network
CN105896613B (en) A kind of micro-capacitance sensor distribution finite-time control method for considering communication time lag
CN104967353B (en) A kind of off-network type wind power generation inverter
CN115564142A (en) Site selection and volume fixing optimization method and system of hybrid energy storage system
CN110061627A (en) A kind of two-way DC/DC converter of high-gain suitable for energy-storage system
Sahin et al. FPA Tuned Fuzzy Logic Controlled Synchronous Buck Converter for a Wave/SC Energy System.
CN108336731A (en) A kind of computational methods of power distribution network distributed generation resource allowed capacity
Wang et al. Studies of multi-type composite energy storage for the photovoltaic generation system in a micro-grid
CN107104429A (en) A kind of power system load dispatching method of meter and distributed energy storage system
CN108233373B (en) Probability harmonic analysis method considering weather scene for distributed photovoltaic access power distribution network
Sandhu et al. Harmonic minimization in modified multilevel inverter for hybrid renewable energy sources
CN105760636A (en) Real-time simulation system and method for power generating system
He et al. Topology Evolution of AC-DC Distribution Network
Kumar et al. Photovoltaic—Standalone system with SMES-battery energy storage system cascaded MLI for rural area applications
Zeng et al. Optimal configuration of new energy grid connected energy storage capacity from the perspective of dual carbon

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20160615

Termination date: 20180819

CF01 Termination of patent right due to non-payment of annual fee