CN103437955A - Maximum power tracking device for mini permanent magnetic direct drive wind power generation system and control method - Google Patents

Abstract

The invention discloses a maximum power tracking device for a mini permanent magnetic direct drive wind power generation system and a control method in the technical field of wind power generation, wherein the maximum power tracking device comprises a fan, an MPPT (maximum power point tracking) controller, a rectifier, n air velocity transducers, a revolution speed transducer, a voltage transducer, a current transducer, a DC-DC (direct current to direct current) converter, a driver module, a first capacitor, a second capacitor and a load; the control method comprises the following steps of acquiring air velocity vectors by utilizing the air velocity transducers arranged at different positions, collecting a large number of air velocity vector-optimal revolution speed practical samples, establishing an air velocity-optimal revolution speed prediction model by utilizing a support vector machine, and carrying out the maximum power tracking by combining the prediction model with a small-step perturbation and observation method. The maximum power tracking device for the mini permanent magnetic direct drive wind power generation system and the control method, disclosed by the invention, have the advantages that the tracking speed is increased, and the power loss of a perturbation process is effectively reduced; after the characteristics of a fan changes, the prediction precision is ensured by repeatedly collecting samples and training a new prediction model.

Description

Minitype permanent magnetism directly-driving wind power generation system maximum power tracking device and controlling method

Technical field

The invention belongs to technical field of wind power generation, relate in particular to a kind of minitype permanent magnetism directly-driving wind power generation system maximum power tracking device and controlling method.

Background technique

Along with day being becoming tight of Energy situation, distributed power generation and power-saving technology that the small-size wind power-generating etc. of take is representative more and more come into one's own, and become current study hotspot.

Wind energy is the energy that a kind of randomness is very large, guarantee to capture to greatest extent wind energy, and speed change wind-force is sent out the system general control strategy that adopts MPPT maximum power point tracking (MPPT) at present.For the minitype permanent magnetism directly-driving wind power generation system, MPPT method commonly used has the methods such as optimized rotating speed is given, disturbance observation.

The given ratio juris of optimized rotating speed is: the power that under certain wind speed, blower fan absorbs has a maximum power point (MPP), and output power value is P _max, a corresponding optimized rotating speed is ω _max, the power-rotation speed characteristic provided according to blower fan producer, can determine the optimized rotating speed under certain wind speed easily, the rotating speed of target by it as blower fan is controlled and is got final product.This method has two shortcomings: the one, be difficult to realize the Measurement accuracy of wind speed.Because the area of draught fan impeller is larger, in whole impeller area, the wind speed that is not each position is all consistent, and the error that wind speed detects is larger; The 2nd, along with the impact of the external conditions such as blower fan wearing and tearing, the power-rotation speed characteristic of blower fan will change, thereby be difficult to guarantee to follow the tracks of accurately MPP.

Disturbance observation method (P& O) principle is: the rotating speed to blower fan constantly applies a fixing disturbing quantity, and determines the direction of disturbing quantity next time according to the change direction that blower fan is caught power, can make real work point constantly move towards MPP.P& The realization of O is relatively easy, but the operation point found can only be near MPP oscillatory operation, cause the loss of Partial Power.In addition, initial value and disturbance step-length have larger impact to precision and the speed of following the tracks of, and misjudgment phenomenon occurs sometimes.

Summary of the invention

For deficiencies such as accurately fixed poor, the easy generation erroneous judgements of the existing peak power output tracking method of mentioning in the above-mentioned background technology, the present invention proposes a kind of minitype permanent magnetism directly-driving wind power generation system maximum power tracking device and controlling method.

A kind of minitype permanent magnetism directly-driving wind power generation system maximum power tracking device, it is characterized in that, described device comprises blower fan, MPPT maximum power point tracking MPPT controller, rectifier, a n air velocity transducer, speed probe, voltage transducer, current sensor, DC-DC transducer, driver module, the first electric capacity, the second electric capacity and load;

Wherein, the three-phase input end of described rectifier is connected with the three-phase output end of blower fan, and the single-phase output plus terminal of rectifier is connected with the positive pole of the first electric capacity, the single-phase output negativing ending grounding of rectifier; The first electric capacity minus earth;

The voltage input end to be measured of described voltage transducer is connected with the first capacitance cathode, voltage transducer voltage output end ground connection to be measured; The measurement signal output terminal of voltage transducer is connected with MPPT maximum power point tracking MPPT controller;

The current input terminal to be measured of described current sensor is connected with voltage transducer is anodal, and the current output terminal to be measured of current sensor is connected with the input end of DC-DC transducer; The measurement signal output terminal of current sensor is connected with MPPT maximum power point tracking MPPT controller;

The pulse-width signal input end of described DC-DC transducer is connected with driver module one end, the other end of driver module is connected with the MPPT controller; The output terminal of DC-DC transducer is connected with the second capacitance cathode; The second electric capacity minus earth;

The measurement signal output terminal of a described n air velocity transducer is connected with MPPT maximum power point tracking MPPT controller respectively;

Two input ends of described speed probe are connected with the wherein two ends in the blower fan three-phase output end, and the measurement signal output terminal of speed probe is connected with the MPPT controller;

Described load one end is connected with the second capacitance cathode, the other end ground connection of load.

Described n air velocity transducer collection is installed on the draught fan impeller front side, the diverse location in and equal-sized plane coaxial, parallel with the impeller circular area.

Described DC-DC converter using Boost circuit.

Described speed probe adopts voltage zero-cross to detect the formula frequency meter.

A kind of minitype permanent magnetism directly-driving wind power generation system maximum power tracking method, is characterized in that, described method specifically comprises step:

Step 1: adopt the air speed data of the diverse location of n air velocity transducer output to form wind velocity vector V=[V ₁, V ₂..., V _n] ^t;

Step 2: with wind velocity vector V=[V ₁, V ₂..., V _n] ^tas input, utilize the SVM prediction model to obtain the optimized rotating speed predicted value ω that maximum power point is corresponding _ref;

Step 3: the passing ratio integral control method is regulated the rotating speed of blower fan, makes blower fan reach the optimized rotating speed predicted value ω that maximum power point is corresponding _ref;

Step 4: the corresponding optimized rotating speed predicted value ω with maximum power point _reffor initial value, adopt the disturbance observation method to follow the tracks of the peak output of blower fan with the disturbance step delta ω set;

Step 5: the power difference before and after the disturbance that the disturbance observation method is tried to achieve is more than or equal to setting threshold T _rthe time, illustrating that sudden change has occurred wind speed, repeating step 1 is to step 4; Otherwise, continue to adopt the disturbance observation method to follow the tracks of the peak output of blower fan with the disturbance step-length of setting.

In step 2, utilize the SVM prediction model to obtain the optimized rotating speed predicted value ω that maximum power point is corresponding _refprocess be:

The effect of support vector machines forecasting model is according to the wind velocity vector V=[V recorded by a plurality of air velocity transducers ₁, V ₂..., V _n] ^tgive blowing machine maximum power point optimum speed ω _optpredicted value ω _ref;

Step 201: collect training sample;

Remember that the wind velocity vector under a certain wind speed environment is V (i)=[V ₁(i), V ₂(i) ..., V _n(i)] ^t, corresponding blower fan maximum power point rotating speed is ω _opt(i), can form pair of sample (V (i), ω _opt(i)); By collecting the sample pair under various different wind speed environment, form sample set { (V (i), ω _opt(i)) },

Under a certain wind speed environment, obtaining of training sample adopts method of trial to gather; Gatherer process is:

Step 2011: the pulse duty factor D of the pwm signal of initialization DC-DC transducer is with less initial value D ₀, it is constantly increased with fixed increment Δ D at every turn, for the k time, have

D(k)=D ₀+k·ΔD （1）

Wherein: D (k) is k subpulse dutycycle;

D ₀for the dutycycle initial value;

Δ D is fixed increment;

Step 2012: by voltage transducer and current sensor, gather the VD V of blower fan after rectifier _dcand average anode current I (k) _dc(k), calculate the output power P (k) of current blower fan:

P(k)=V _dc(k)·I _dc(k) （2）

Step 2013: with the output power P (k-1) of front primary air fan relatively, when P (k)<P (k-1) occurring, think that now the working state of blower fan has approached maximum power point; Order:

D(k)=D ₀+(k-0.5)·ΔD （3）

Record rotation speed of fan now is as the maximum power point rotational speed omega _opt, and wind velocity vector V (i)=[V (i) ₁, V ₂..., V _n] ^t, complete once and gather, obtain pair of sample V (i), ω _opt(i));

Step 202: Training Support Vector Machines SVM model; Detailed process is:

Step 2021: given sample set

wherein, X _i∈ R ⁿfor input vector, y _i∈ R is corresponding output value, and N is number of samples, and n is the input vector dimension;

Step 2022: setting support vector machines linear regression function used is:

y _i=f(X _i)=Wφ(X _i)+b （4）

Wherein: y _ifor the output of linear regression function;

φ (X _i) be the Nonlinear Mapping from the input space to the high-dimensional feature space;

X _ifor input vector;

W is weight vector;

B is biasing;

Weight vector W and biasing b calculate by minimizing formula (5):

$\frac{1}{2}{\left|\right|W\left|\right|}^2+C\frac{1}{N}\underset{i=1}{\overset{N}{\mathrm{\&Sigma;}}}{\mathrm{\&xi;}}_i$

$s.t.\left\{\begin{array}{c}{y}_i-\mathrm{W\&phi;}\left(X_i\right)-b\&le;\mathrm{\&epsiv;}+{\mathrm{\&xi;}}_i\\ {\mathrm{\&xi;}}_i\&GreaterEqual;0\end{array}\right.---\left(5\right)$

Wherein: W is weight vector, the 1st

determine the generalization ability of regression function; C is penalty factor (C>0), for controlling the punishment degree of the sample to exceeding; N is number of samples; The slack variable of ξ i for introducing; ε is error;

Step 2023: set up Lagrange's equation according to minimizing formula (5), solve the linear regression function and be:

$\left(X_i\right)=\underset{j=1}{\overset{N}{\mathrm{\&Sigma;}}}{\mathrm{\&alpha;}}_{j}K(X_i,X_j)+b---\left(6\right)$

Wherein: K (X _i, X _j) be kernel function,

kernel function is Gaussian function

δ ²width parameter for gaussian kernel function; α _jfor Lagrangian coefficient; X _jfor sample vector, and non-vanishing α _jcorresponding vectorial X _jbe called support vector; After supported vector, can try to achieve regression function y=f (X _i);

Step 2024: adopt statistic average relative error Δ _mREthe performance of valuation prediction models; Its representation is:

${\mathrm{\&Delta;}}_{\mathrm{MRE}}=\frac{1}{N}\underset{i=1}{\overset{N}{\mathrm{\&Sigma;}}}\left|\frac{Y-\hat{Y}}{Y}\right|\&times;100\%---\left(7\right)$

In formula:

Δ _mREfor the statistic average relative error;

The true value that Y is sample;

estimated value for Y;

Step 2025: evenly extract 3/5ths in total sample as training sample, all the other get respectively different C and δ 2/5ths as test samples ², utilize training sample to be learnt, and calculate the Δ on test samples _mRE, select minimum Δ _mREcorresponding model is as final forecasting model;

Step 203: by wind velocity vector V=[V ₁, V ₂..., V _n] ^tobtaining blower fan maximum power point rotor speed forecast value by final forecasting model is ω _ref.

Beneficial effect of the present invention is: when (1) changes when external environment, by means of forecasting model, can directly working speed be adjusted to optimized rotating speed predicted value ω _refnear, avoided disturbance observation method P& The process that O progressively sounds out, thus tracking velocity improved; (2) with optimized rotating speed predicted value ω _refwhile for initial value, carrying out disturbance observation process, due to optimized rotating speed predicted value ω _refextremely approached the actual optimum rotating speed, thus less disturbance step-length can be set, thus effectively reduce the power loss of perturbation process; (3), after the characteristic of blower fan changes, can, by again collecting sample, train new forecasting model to guarantee precision of prediction.

The accompanying drawing explanation

Fig. 1 is hardware structure diagram of the present invention;

Fig. 2 is disturbance observation method P& The O algorithm flow chart;

The flow chart that Fig. 3 is a kind of minitype permanent magnetism directly-driving wind power generation system maximum power tracking method provided by the invention;

Wherein, 1-air velocity transducer; The 2-permanent magnet direct-driving aerogenerator; The 3-speed probe; The 4-rectifier; The 5-voltage transducer; 6-the first electric capacity; 7-the second electric capacity; The 8-current sensor.

Embodiment

Below in conjunction with accompanying drawing, preferred embodiment is elaborated.Should be emphasized that following explanation is only exemplary, rather than in order to limit the scope of the invention and to apply.

The hardware structure diagram that Fig. 1 is the embodiment of the present invention, wherein, minitype permanent magnetism direct wind-driven generator 2 major parameters are: rotor diameter is 1.2m, rated power is 300W, and voltage rating is 24V, rated speed 800r/min, start wind speed 1m/s, rated wind speed 10m/s, survival wind speed 25m/s, the major parameter of maximum power tracking device is: the MPPT controller adopts the dsPIC33FJ06GS101 single-chip microcomputer, DC-DC converter using Boost circuit, driver module is selected MCP14E3, voltage transducer selecting and purchasing LV28-P, current sensor 8 is selected LA25-NP, air velocity transducer 1 adopts JL-FS2, totally 5: be installed on respectively 0.5 meter of draught fan impeller front side, coaxial with the impeller circular area, circle centre position in parallel and equal-sized circular flat and apart from the center of circle 1/4 radius, 1/2 radius, 3/4 radius, 1 times of radius, speed probe 3 adopts voltage zero-cross to detect the formula frequency meter, the first capacitor C 1=10uF, the second capacitor C 2=100uF.

Carry out the collection of training sample according to step 201.In embodiment, utilize blower, frequency variator and straight length to form the small test wind-tunnel, control blower by the frequency setting value of regulating frequency variator and exert oneself, and then create different wind speed environment.Control frequency converter frequency from 10Hz, the 0.2Hz of take rises to 60Hz as interval, and 250 kinds of wind speed environment can be provided, i.e. { V (i)=[V ₁(i), V ₂(i), V ₃(i), V ₄(i), V ₅(i)] ^t, i=1 ..., 250}, thus can construct 250 pairs of samples.

Carry out the training of SVM model according to step 202.Evenly 150 couple in the total sample of extraction is as training sample, and all the other 100 pairs as test samples.For preventing the study phenomenon or owing to learn phenomenon, get respectively different C=10 ^-1, 10 ⁰, 10 ¹, 10 ², 10 ³, δ ²=10 ^-2, 10 ^-1, 10 ⁰, 10 ¹, 10 ², utilize training sample to be learnt, and calculate the Δ on test samples _mRE, select minimum Δ _mREcorresponding model, as final forecasting model, wherein comprises 56 support vectors altogether, these support vectors is write to the storage of single-chip microcomputer for calling.

Fig. 2 is disturbance observation method P& The flow chart of O, its principle is the rotating speed (ω+Δ ω) of periodically disturbance blower fan, more relatively the power of its disturbance front and back changes, if output power increases, means that perturbation direction is correct, continues (+Δ ω) disturbance in the same direction; If output power reduces, towards contrary (Δ ω) direction disturbance.Because completing once sampling, the AD module of dsPIC33FJ06GS101 only needs 0.5us, when the VD of measurement blower fan, average anode current, the signal jitter caused in order to eliminate the copped wave of DC-DC transducer medium-high frequency, make the AD module change and average as measured value for 10 times continuously.

The flow chart that Fig. 3 is a kind of minitype permanent magnetism directly-driving wind power generation system maximum power tracking method provided by the invention.During beginning, at first gather the output of 5 air velocity transducers that are installed on diverse location, form wind velocity vector V=[V ₁, V ₂, V ₃, V ₄, V ₅] ^t, it is sent into to the SVM prediction model, obtain the optimized rotating speed predicted value ω that maximum power point is corresponding _ref; Proportional integral PI controller is according to blower fan actual speed ω and ω _refthe PWM dutycycle of deviation adjustment DC-DC transducer, make real work voltage track to fast ω _ref.Then with ω _reffor initial value, utilize less disturbance step delta ω to start P& The O process.At P& In the O process, the difference power Δ P before and after disturbance each time and a certain threshold value Tr are compared, when | Δ P|<T _rthe time, continue P& The O process, otherwise think that now sudden change has occurred the wind speed environment, again by the support vector machines model prediction, go out ω _ref, and repeat said process.For the blower fan of 300W, the present embodiment is got T _r=10W.

Above-mentioned maximal power tracing MPPT method is write to control chip dsPIC33FJ06GS101 by C programmer, and output PWM square wave drives the DC-DC transducer, can realize the maximal power tracing function.

The correctness of extracting method in order to verify, on hardware platform of the present invention by itself and conventional disturbance observation method P& O compares.Be specially: under same wind speed environment (frequency converter frequency that wind-tunnel is set is 40Hz), controlling the blower fan initial speed is ω ₀=600r/min, compare respectively the tracking velocity of two kinds of methods and the average power of steady-state process.

Conventional disturbance observation method P& The tracing process of O method (adjustment cycle T=5s, step delta ω=20r/min) is: after the continuous 15 postive direction disturbances of clapping, start at maximum power point MPP(ω _opt=900r/min) left and right vibration, enter steady-state process, and needed time is about 75 seconds altogether.

The tracing process of the method for the invention is at first wind velocity vector to be measured, then through support vector machines model maximum power point rotor speed forecast value ω _refafter=915r/min, by the PI controller, directly working speed ω is adjusted to 915r/min, then starts to carry out the long disturbance of small step and observe P& O(adjustment cycle T=5s, step delta ω=5r/min), due to ω _refitself approach very much maximum power point MPP(ω _opt=900r/min), after the continuous 3 negative direction disturbances of clapping, entered steady-state process, needed time is about 15 seconds altogether.Hence one can see that, and the tracking velocity of institute of the present invention extracting method will be apparently higher than conventional disturbance observation method P& The O method.

After entering steady-state process, calculate respectively the average power of 60 seconds steady-state processs, draw conventional disturbance observation method P& The O method is 210 watts, and the method for the invention is 236 watts, and this explanation adopts the method for the invention can effectively reduce power loss.

The above; be only the present invention's embodiment preferably, but protection scope of the present invention is not limited to this, anyly is familiar with in technical scope that those skilled in the art disclose in the present invention; the variation that can expect easily or replacement, within all should being encompassed in protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of claim.

Claims (6)

1. a minitype permanent magnetism directly-driving wind power generation system maximum power tracking device, it is characterized in that, described device comprises blower fan, MPPT maximum power point tracking MPPT controller, rectifier, a n air velocity transducer, speed probe, voltage transducer, current sensor, DC-DC transducer, driver module, the first electric capacity, the second electric capacity and load;

Wherein, the three-phase input end of described rectifier is connected with the three-phase output end of blower fan, and the single-phase output plus terminal of rectifier is connected with the positive pole of the first electric capacity, the single-phase output negativing ending grounding of rectifier; The first electric capacity minus earth;

The voltage input end to be measured of described voltage transducer is connected with the first capacitance cathode, voltage transducer voltage output end ground connection to be measured; The measurement signal output terminal of voltage transducer is connected with MPPT maximum power point tracking MPPT controller;

The current input terminal to be measured of described current sensor is connected with voltage transducer is anodal, and the current output terminal to be measured of current sensor is connected with the input end of DC-DC transducer; The measurement signal output terminal of current sensor is connected with MPPT maximum power point tracking MPPT controller;

The pulse-width signal input end of described DC-DC transducer is connected with driver module one end, the other end of driver module is connected with the MPPT controller; The output terminal of DC-DC transducer is connected with the second capacitance cathode; The second electric capacity minus earth;

The measurement signal output terminal of a described n air velocity transducer is connected with MPPT maximum power point tracking MPPT controller respectively;

Two input ends of described speed probe are connected with the wherein two ends in the blower fan three-phase output end, and the measurement signal output terminal of speed probe is connected with the MPPT controller;

Described load one end is connected with the second capacitance cathode, the other end ground connection of load.

2. device according to claim 1, is characterized in that, described n air velocity transducer collection is installed on the draught fan impeller front side, the diverse location in and equal-sized plane coaxial, parallel with the impeller circular area.

3. device according to claim 1, is characterized in that, described DC-DC converter using Boost circuit.

4. device according to claim 1, is characterized in that, described speed probe adopts voltage zero-cross to detect the formula frequency meter.

5. a minitype permanent magnetism directly-driving wind power generation system maximum power tracking method, is characterized in that, described method specifically comprises step:

Step 1: adopt the air speed data of the diverse location of n air velocity transducer output to form wind velocity vector V=[V ₁, V ₂..., V _n] ^t;

Step 2: with wind velocity vector V=[V ₁, V ₂..., V _n] ^tas input, utilize the SVM prediction model to obtain the optimized rotating speed predicted value ω that maximum power point is corresponding _ref;

Step 3: the passing ratio integral control method is regulated the rotating speed of blower fan, makes blower fan reach the optimized rotating speed predicted value ω that maximum power point is corresponding _ref;

Step 4: the corresponding optimized rotating speed predicted value ω with maximum power point _reffor initial value, adopt the disturbance observation method to follow the tracks of the peak output of blower fan with the disturbance step delta ω set;

Step 5: the power difference before and after the disturbance that the disturbance observation method is tried to achieve is more than or equal to setting threshold T _rthe time, illustrating that sudden change has occurred wind speed, repeating step 1 is to step 4; Otherwise, continue to adopt the disturbance observation method to follow the tracks of the peak output of blower fan with the disturbance step-length of setting.

6. method according to claim 5, is characterized in that, in described step 2, utilizes the SVM prediction model to obtain the optimized rotating speed predicted value ω that maximum power point is corresponding _refprocess be:

Step 201: collect training sample;

Remember that the wind velocity vector under a certain wind speed environment is V (i)=[V ₁(i), V ₂(i) ..., V _n(i)] ^t, corresponding blower fan maximum power point rotating speed is ω _opt(i), can form pair of sample (V (i), ω _opt(i)); By collecting the sample pair under various different wind speed environment, form sample set { (V (i), ω _opt(i)) }; Gatherer process is:

Step 2011: the pulse duty factor D of the pwm signal of initialization DC-DC transducer is with less initial value D ₀, it is constantly increased with fixed increment Δ D at every turn, for the k time, have:

D(k)=D ₀+k·ΔD

Wherein: D (k) is k subpulse dutycycle;

D ₀for the dutycycle initial value;

Δ D is fixed increment;

Step 2012: by voltage transducer and current sensor, gather the VD V of blower fan after rectifier _dcand average anode current I (k) _dc(k), calculate the output power P (k) of current blower fan:

P(k)=V _dc(k)·I _dc(k)

Step 2013: with the output power P (k-1) of front primary air fan relatively, when P (k)<P (k-1) occurring, think that now the working state of blower fan has approached maximum power point; Order:

D(k)=D ₀+(k-0.5)·ΔD

Record rotation speed of fan now is as the maximum power point rotational speed omega _opt, and wind velocity vector V (i)=[V (i) ₁, V ₂..., V _n] ^t, complete once and gather, obtain pair of sample V (i), ω _opt(i));

Step 202: Training Support Vector Machines SVM model; Detailed process is:

Step 2021: given sample set

wherein, X _i∈ R ⁿfor input vector, y _i∈ R is corresponding output value, and N is number of samples, and n is the input vector dimension;

Step 2022: setting support vector machines linear regression function used is:

y _i=f(X _i)=Wφ(X _i)+b

Wherein: y _ifor the output of linear regression function;

φ (X _i) be the Nonlinear Mapping from the input space to the high-dimensional feature space;

X _ifor input vector;

W is weight vector;

B is biasing;

Weight vector W and biasing b by minimizing the formula formula are:

$\frac{1}{2}{\left|\right|W\left|\right|}^2+C\frac{1}{N}\underset{i=1}{\overset{N}{\mathrm{\&Sigma;}}}{\mathrm{\&xi;}}_i$

$S.t.\left\{\begin{array}{c}{y}_i-\mathrm{W\&phi;}\left(X_i\right)-b\&le;\mathrm{\&epsiv;}+{\mathrm{\&xi;}}_i\\ {\mathrm{\&xi;}}_i\&GreaterEqual;0\end{array}\right.$

Wherein: W is weight vector, the 1st determine the generalization ability of regression function; C is penalty factor (C>0), for controlling the punishment degree of the sample to exceeding; N is number of samples; ξ _ifor the slack variable of introducing; ε is error;

Step 2023: according to minimizing the Formula Lagrange's equation, solve the linear regression function and be:

$f\left(X_i\right)=\underset{j=1}{\overset{N}{\mathrm{\&Sigma;}}}{\mathrm{\&alpha;}}_{j}K(X_i,X_j)+b$

Wherein: K (X _i, X _j) be kernel function, kernel function is Gaussian function: $K(X_i,X_j)=\exp (-\frac{{\left|\right|X_i-X_j\left|\right|}^2}{{\mathrm{\&delta;}}^2}),$ δ ²width parameter for gaussian kernel function; α _jfor Lagrangian coefficient; X _jfor sample vector, and non-vanishing α _jcorresponding vectorial X _jbe called support vector;

Step 2024: adopt statistic average relative error Δ _mREthe performance of valuation prediction models; Its representation is:

${\mathrm{\&Delta;}}_{\mathrm{MRE}}=\frac{1}{N}\underset{i=1}{\overset{N}{\mathrm{\&Sigma;}}}\left|\frac{Y-\hat{Y}}{Y}\right|\&times;100\%$

In formula:

Δ _mREfor the statistic average relative error;

The true value that Y is sample;

estimated value for Y;

Step 2025: evenly extract 3/5ths in total sample as training sample, all the other get respectively different C and δ 2/5ths as test samples ², utilize training sample to be learnt, and calculate the Δ on test samples _mRE, select minimum Δ _mREcorresponding model is as final forecasting model;

Step 203: by wind velocity vector V=[V ₁, V ₂..., V _n] ^tobtaining blower fan maximum power point rotor speed forecast value by final forecasting model is ω _ref.

Images