Shamshirband Energy

8202019 Shamshirband Energy

httpslidepdfcomreaderfullshamshirband-energy 17

Adaptive neuro-fuzzy maximal power extraction of wind turbinewith continuously variable transmission

Dalibor Petkovic a Zarko Cojbasic a Vlastimir Nikolic a Shahaboddin Shamshirband bMiss Laiha Mat Kiah b Nor Badrul Anuar b Ainuddin Wahid Abdul Wahab b

a University of Nis Faculty of Mechanical Engineering Department for Mechatronics and Control Aleksandra Medvedeva 14 18000 Nis Serbiab Departmentof ComputerSystem and Technology Facultyof ComputerScience andInformationTechnologyUniversityof Malaya50603 KualaLumpurMalaysia

a r t i c l e i n f o

Article history

Received 19 June 2013

Received in revised form

28 October 2013

Accepted 30 October 2013

Available online 26 November 2013

Keywords

Wind turbine

Power coef 1047297cient

Continuously variable transmission

Intelligent control

ANFIS controller

a b s t r a c t

In recent years the use of renewable energy including wind energy has risen dramatically Because of the

increasing development of wind power production improvement of the control of wind turbines using

classical or intelligent methods is necessary To optimize the power produced in a wind turbine the

speed of the turbine should vary with the wind speed Variable-speed operation of wind turbines pre-

sents certain advantages over constant-speed operation In this paper in order to maintain the maximal

output power of wind turbine a novel intelligent controller based on the adaptive neuro-fuzzy inference

system (ANFIS) is designed To improve the wind energy available in an erratic wind speed regime a

wind generator equipped with continuously variable transmission (CVT) was proposed In this model the

ANFIS regulator adjusts the system speed ie CVT ratio for operating at the highest ef 1047297ciency point The

performance of proposed controller is con1047297rmed by simulation results Some outstanding properties of

this new controller are online implementation capability structural simplicity and its robustness against

any changes in wind speed and system parameter variations Based on the simulation results the

effectiveness of the proposed controllers was veri1047297ed

2013 Elsevier Ltd All rights reserved

1 Introduction

Renewable energies such as wind and solar energy conversion

systems have driven attention during the past decade due to the

environmental concerns Wind is a natural resource that features

many advantages since it is clean and considered reliable in some

areas

A wind turbine system is a system that converts the wind tur-

binersquos mechanical energy obtained from wind into electrical energy

through a generator and can be categorized by the types of gen-

erators used power control methods constant- or variable-speed

operation and methods of interconnecting with the grid [1]Variable-speed operation of a wind turbine is generally more ad-

vantageous over constant-speed operation since a variable-speed

operation is able to track the maximum power of the wind tur-

bine with wind speed changes Modern high-power wind turbines

are equipped with adjustable speed generators [2] It was shown

that the control strategies have a major effect on the wind turbine

and whatever the kind of the wind turbine the control strategy

remains a key factor [3e6]

As wind energy becomes more dominant there is growing in-

terest in controlling wind turbines or wind plants in an intelligent

manner to minimize the cost of wind energy This can be done by

controllingthe turbines to extract more energy from thewind In the

wind energy conversion systems the control problem consists of

delivering the maximum power available from the wind to ensure

the system reliability and security in order to deal with the variable

nature of the generated energy [7e9] Wind power conversion de-

pends essentially on the power coef 1047297cient ldquoC prdquo of the machine

which transforms the ef 1047297ciency of converting wind power to elec-trical power In order to implement maximum wind power extrac-

tion the wind turbine generator must be operated at variable-speed

mode The power coef 1047297cientis characterizedas a function of both tip

speed ratio and the blade pitch angle The tip speed ratio is the ratio

of linear speed at the tip of blades to the speed of the wind Optimal

performance of thewind turbine can be obtained if the transmission

ratio could change with the wind speed [1011] In this paper a

continuously variable transmission (CVT) has been installed be-

tween a wind turbine and a generator to make the turbine operate

along the maximum ef 1047297ciency The aim of the investigation was to

change the transmission ratio between the wind turbine and the

Corresponding author Tel thorn60 146266763

E-mail addresses dalibortcgmailcom (D Petkovic) shahab1396gmailcom

(S Shamshirband)

Contents lists available at ScienceDirect

Energy

j o u r n a l h o m e p a g e w w w e l s e v i e r c o m l o c a t e e n e r g y

0360-5442$ e see front matter 2013 Elsevier Ltd All rights reserved

httpdxdoiorg101016jenergy201310094

Energy 64 (2014) 868e874



generator at different wind speeds so that the turbine may be kept

running at maximum ef 1047297ciency levels at all wind speeds It is known

about automatic CVT regulation to adjust and stabilize their trans-

mission ratio according to transmitted torques without relying on

other regulating or control mechanisms [1213] Considering all

these it is interesting to explore the feasibility of installing an

automatic CVT in a wind turbine since such a solution may optimize

the ef 1047297ciency of these systems by means of simple technologies

To improve the control of thewind turbines fuzzy logic (FL) [14e19] or arti1047297cial neural network (ANN) control has attracted much

attention in recent years [20e27] As a non-linear function [28e31]

ANNs can be used for identifying the extremely non-linear systemparameters with high accuracy Neural networks can learn from

data However understanding the knowledge learned by neural

networks has been dif 1047297cult In contrast fuzzy rule based models are

easy to understand because they use linguistic terms and the

structure of IF-THEN rules Unlike neural networks however fuzzy

logic by itself cannot learn [32] Since neural networks can learn it is

natural to merge these two techniques This merged technique of

the learning power of the ANNs with the knowledge representation

of FL has created a new hybrid technique called neuro-fuzzy net-

works or adaptive neuro-fuzzy inference system (ANFIS) [33] ANFIS

as a hybrid intelligent system that enhances the ability to auto-

matically learn and adapt was used by researchers for modeling

[34e37] predictions [38e40] and control [41e45] in various engi-

neering systems The basic idea behind these neuro-adaptivelearning techniques is to provide a method for the fuzzy modeling

procedure to learn information about data [46e53]

In this paper the application of ANFIS is proposed to control the

CVT ratio to extract the maximal wind energy through the wind

turbine As inputs in the controller current wind speed and current

wind turbine rotor speed are used The output should be optimal

generator speed

2 Wind turbine power extraction and continuously variable

transmission

The major components of a typical wind energy conversion

system include a wind turbine a generator interconnection appa-

ratus and control system Therefore the design of a wind energyconversion system is complex The most important part of a wind

energy conversion system is the wind turbine transforming the

wind kinetic energy into mechanical or electric energy The system

basically comprises a blade a mechanical part and an electric engine

coupled to each other The kinetic energy of wind is the function of

wind speed the speci1047297c mass of air the area of air space where the

wind is captured and the height at which the rotor is placed The

power available in a uniform wind 1047297eld can be expressed as

P w frac14 1

2r Ay3

where P w is the power [W] of the wind with air density r [kgm3]

and wind speed n [ms] is passing through the swept area A [m

2

] of

a rotor disk that is perpendicular to the wind 1047298ow Thewind turbine

can only capture a fraction of the power available from the wind

The ratio of captured power to available power is referred to as the

power coef 1047297cient

C pethb V eUr RTHORN

which is a function of the collective blade pitch angle b effective

wind speed V e rotor speedUr and rotor radius R The value of C p can

be expressed according to Ref [54] as

A characterization of the power coef 1047297cient C p for the wind

turbine used in this study is optimized to achieve maximum valueThe optimization procedures is expressed as

maxC p frac14 C pethb V eUr RTHORN45

b 0

50 m=s V e 8 m=s30 rpm Ur 60 rpmR frac14 25 m

(1)

In this paper a new approach to a CVT power transmission sys-

tem is presented It is added just before the generator avoiding the

need to change the main gearbox and the aerodynamic tip brake

control pipes Fig1 shows a widely used power transmission system

of a wind turbine with the proposed CVT system installed The po-

wer 1047298ows from the rotor hub through the input shaft to the main

gearbox It is the same unit that is used in a 1047297xed speed wind tur-bine This gearbox could consist of a planetary stage and two simple

spur gear stages The disc brake is conventionally installed after the

main gearbox In a 1047297xed speed design the power would 1047298ow from

the main gearbox directly to the generator This is the point where

the proposed CVT system is installed It is suggested to use for CVT

system two spring-loaded pulleys one at the driving shaft and one

at the driven shaft With such a simple and inexpensive solution the

CVT was automatically regulated and adjusted its transmission ratio

tothe torque appliedon the driving pulley A layout of thedrive train

components of the wind turbine is illustrated in Fig 2

The general speed ratio iCVT is given by

iCVT

frac14 uA

uB

where uA is the angular velocity of the power input shaft and is

connected to the output shaft of the main gearbox The uB is the

angular velocity of the output shaft connected to the generator

Finally there is adjustment shaft with angular velocity uC which is

connected to the hydraulic system Variation of the speed of the

adjustment shaft leads to variation of the total transmission ratio of

the gearbox The angular velocities of the three shafts uA uB uC

ful1047297ll the following relationship

uC frac14 x$uA thorn y$uB

where x and y areconstants de1047297ned by the numbers of teeth of each

gear and the overall gearbox system In the special case where

C pethb V eUr RTHORN frac14 05176

0B 116

1

RUr

V e 008b

0035

b3thorn 1

04b 5

1CAe

211

RUrV e

008b0035

b3 thorn1thorn 00068

RUr

V e

D Petkovic et al Energy 64 (2014) 868e874 869



uC frac14 0 the angular velocities of the input and output shaft are uA0

and uB0 and the speed ratio is

iCVT frac14 uA0

uB0frac14

y

x

A new variable f is introduced to describe the difference of the

current angular velocity of the input shaft uA from uA0

f frac14 u A u A0

u A0(2)

f frac14 0 means that uA frac14uA0 In terms of f the speed ratio of the

gearbox is given by

iCVT frac14 y

x$eth1 thorn fTHORN frac14 iCVT0$eth1 thorn fTHORN

The speed ratio iR between the adjustment shaft uC and the

input shaft uA can also be expressed in terms of f

iR frac14 uA

uCfrac14

1

x$

1 thorn f

f

In quasi steady state conditions the power and moment equi-

libriums of the black box is

P A thorn P B thorn P C frac14 0 (3)

T A thorn T B thorn T C frac14 0 (4)

By replacing P frac14 u$T in Eq (3) and combining with Eqs (4) and

(2) and adjustment power ratio can be obtained in terms of f

P CP A

frac14 f

1 thorn f

The above equation directly relates the power P C required to

change the speed uA by a factor of (1 thorn f) to the input power P A

3 ANFIS controller design

A controller is a device which controls each and every operation

in a decision-making system From the control system point of

view it brings stability to the system when there is a disturbance

thus safeguarding the equipment from further damage It may be a

hardware-based controller or a software-based controller or a

combination of both In this section the development of the control

strategy for control of the wind turbine rotor radius and rotor speed

is presented using the concepts of ANFIS control scheme the block

diagrams of both the control schemes are shown in Fig 3 The fuzzy

logic controller provides an algorithm which converts the lin-

guistic control based on expert knowledge into an automatic

control strategy Linguistic variables de1047297ned as variables whose

values are sentences in a natural language (such as large or small)

may be represented by the fuzzy sets A fuzzy set is an extension of

a lsquocrisprsquo set where an element can only belong to a set (full mem-bership) or not belong at all (no membership) Fuzzy sets allow

partial membership which means that an element may partially

belong to more than one set Therefore the fuzzy logic algorithm is

much closer in spirit to human thinking than traditional logical

systems The main problem with the fuzzy logic controller gener-

ation is related to the choice of the regulator parameters For this

reason we apply the ANFIS methodology to adapt the parameters

of the fuzzy controller according to real data about the problem

Fig 1 Power transmission system of a CVT regulated wind energy converter

Fig 2 Wind turbine drive train components

Fig 3 Block diagram of the ANFIS control scheme for the wind turbine rotor radius

control

D Petkovic et al Energy 64 (2014) 868e874870



The ANFIS structure is tuned automatically by least-square

estimation and the back propagation algorithm ANFIS controllers

in general have six modules which are as follows

1 Preprocessing during preprocessing different values of effective

wind speed and rotor speed are chosen

2 Fuzzi 1047297cation process by which a particular input is rated in

terms of its belongingness to a certain membership function

(MF) Here the crisp variables were converted into fuzzy vari-

ables or the linguistic variables

3 Fuzzy inference engine values of linguistic variables are acquired

using fuzzi1047297cation which makes it easier to implement During

the second fuzzi1047297cation stage the set point is converted into

linguistic variables

4 Rule base a rule base was acquired for the functioning of fuzzy

controller The developed fuzzy rules were obtained during the

construction of ANFIS controller

5 Defuzzi 1047297cation done on the output data that is achieved after

the data has been passed through the module

6 Post-processing the output of the input fuzzy system here was

the prescribed numerical optimal CVT ratio and obtained power

output of the wind turbine

Fig 4 shows an ANFIS structure for two inputs effective wind

speed and rotor speed and for one output the optimal wind turbine

CVT ratio According to these inputs and the training inputoutput

data pairs the ANFIS network could make decision for to achieve

maximal wind energy conversion from the wind turbine Training

inputoutput data pairs were collected from the presented opti-

mization procedures (1) and from CVT ratio related expressions

In this work the 1047297rst-order Sugeno model with two inputs and

fuzzy IF-THEN rules of Takagi and Sugenorsquos type is used

if x is A and y is C then f 1 frac14 p1 x thorn q1 y thorn r 1

The 1047297rstlayer consistsof inputvariables (MFs)input 1 andinput

2 This layer just supplies the input values to the next layer In the1047297rst layer every node is an adaptive node In this study triangle MFs

with maximum equal to 1 and minimum equal to 0 are chosen

(Fig 5) such as

meth xTHORN frac14 triangleeth x ai bi c iTHORN frac14

8gtgtgtgtgtgtgtgtgtltgtgtgtgtgtgtgtgtgt

0 x ai

xai

biai ai x bi

c i xc ibi

bi x c i

0 c i x

where ai b i c i is the set of parameters set that in this layer are

referred to as premise parameters In this layer x and y are the

inputs to nodes and they are effective wind speed and rotor speed

Table 1 summarizes relation between effective wind speed and

rotor speed used in this study as the ANFIS inputs

The second layer (membership layer) checks for the weights of

each MFs It receives the input values from the1047297rst layer and acts as

MFs to represent the fuzzy sets of the respective input variables

Every node in the second layer is non-adaptive and this layer

multiplies the incoming signals and sends the product out like

wi frac14 m( x)m( y) Each node output represents the 1047297ring strength of a

rule

The third layer is called the rule layer Each node (each neuron)

in this layer performs the pre-condition matching of the fuzzy

rules ie they compute the activation level of each rule the number

of layers being equal to the number of fuzzy rules Each node of

these layers calculates the weights which are normalized The third

layer is also non-adaptive and every node calculates the ratio of the

rulersquos 1047297ring strength to the sum of all rulesrsquo 1047297ring strengths like

wi frac14 wi=w1 thorn w2 i frac14 1 2 The outputs of this layer are called

normalized 1047297ring strengths

The fourth layer is called the defuzzi1047297cation layer and it pro-

vides the output values resulting from the inference of rules Every

node in the fourth layer is an adaptive node with node function

O4i frac14 wi xf frac14 wi eth pi x thorn qi y thorn r iTHORN where piqi r is the parameter setand in this layer is referred to as consequent parameters

The 1047297fth layer is called the output layer which sums up all the

inputs coming from the fourth layer and transforms the fuzzy

classi1047297cation results into a crisp (binary) The single node in the

Fig 4 ANFIS structure

Fig 5 A trapezoidal membership function

Table 1

ANFIS input parameters

Wind speed [ms] Rotor speed [rpm]

8 36

10 36

12 40

14 47

16 54

18 60

20 60

22 60

24 58

26 53

28 506

30 494

32 485

34 485

36 485

38 485

40 485

42 485

44 485

46 485

48 485

50 485




1047297fth layer is notadaptive and this node computes the overall output

as the summation of all incoming signals

O4i frac14

Xi

wi xf frac14

Piwi f Piwi

This type of adaptive network is functionally equivalent to a

type-3 fuzzy inference system The hybrid learning algorithms

were applied to identify the parameters in the ANFIS architecturesIn the forward pass of the hybrid learning algorithm functional

signals go forward until Layer 4 and the consequent parameters are

identi1047297ed by the least-squares estimate In the backward pass the

error rates propagate backwards and the premise parameters are

updated by the gradient descent

4 Results

In this paper ANFIS training and checking data are extracted

using above mentioned optimization procedure (1) and by CVT

ratio related expressions Power coef 1047297cient is used as numerical

indicator for the wind turbine energy estimation

The 1047297nal decision surfaces after ANFIS training is shown in

Figs 6e

8The wind turbine power coef 1047297cient as function of the effective

wind speed and rotor speed is implemented in MATLAB Simulink

block diagrams as shown in Fig 9 It shows block diagram for

estimation of the optimal wind turbine CVT ratio to achieve

maximal power coef 1047297cient while the rotor speed is variable This

approach is very useful for fast estimation of the maximal wind

turbine power coef 1047297cient according to the main wind turbine pa-

rameters and wind speed variation as well

5 Conclusion

In summary wind energy is a rapid growing industry and

this growth has led to a large demand for better modeling and

control of wind turbines The uncertainties and dif 1047297culties inmeasuring the wind in1047298ow to wind turbines makes the control

dif 1047297cult and more advanced modeling via system identi1047297cation

techniques and a number of advanced control approaches should

be explored to reduce the cost of wind energy The wind

resource available worldwide is large and much of the world rsquos

future electrical energy needs can be provided by wind energy

alone if the technological obstacles are overcome The applica-

tion of advanced controls for wind energy systems is still in its

infancy and there are many fundamental and applied issues that

can be addressed by the systems and control community to

signi1047297cantly improve the ef 1047297ciency operation and lifetimes of

wind turbinesVariable-speed operation of wind turbine is necessary to in-

crease power generation ef 1047297ciency The presented research work

deals with variable-speed wind control design in order to achieve

the objectives of maximizing the extracted energy from the wind

This paper has suggested coupling a wind turbine rotor to a

generator by means of a continuously variable transmission to

maximize turbine ef 1047297ciency The CVT is added just before the

generator avoiding the need to change the main gearbox and the

aerodynamic tip brake control pipes It allows for varying the speed

of the rotor according to the current wind speed while retaining the

speed of the generator constant leading to a better exploitation of

the available wind energy potential The implementation of the

system does not require a new main gearbox Instead it can be

mounted just before the generator

Fig 6 ANFIS predicted relationships between (a) effective wind speed (input 1) rotor

speed (input 2) and CVT ratio (output) e

ANFIS 1

Fig 7 ANFIS predicted relationships for the optimal CVT ratio between (a) effective

wind speed (input 1) rotor speed (input 2) and generator speed (output) e ANFIS 2

Fig 8 ANFIS predicted relationships between (a) optimal CVT ratio (input 1) gener-

ator speed (input 2) and wind turbine power output (output) e ANFIS 3




An intelligent controller has been suggested The ANFIS

controller was developedin orderto implement a maximum power

tracking scheme for a wind turbine This method is based on the

regulation of CVT ratio We found that under the same operating

conditions the proposed method is able to gain more power if the

wind turbine is operated at variable-speed mode by the proposed

scheme As the parameter for measuring performance of the wind

turbine power coef 1047297cient C p was used Two Simulink models weredeveloped in MATLAB with the ANFIS networks The main advan-

tage of designing the ANFIS coordination scheme is to achieve

maximal wind turbine power coef 1047297cient as the main turbine

parameter according to optimal CVT ratio Simulations were run in

MATLAB and the results were observed on the corresponding

output blocks The main advantages of the ANFIS scheme are

computationally ef 1047297cient well-adaptable with optimization and

adaptive techniques The developed strategy is not only simple but

also reliable and may be easy to implement in real time applica-

tions using some interfacing cards like the dSPACE data acquisition

cards NI cards etc for control of various parameters This can also

be combined with expert systems and rough sets for other appli-

cations ANFIS can also be used with systems handling more

complex parameters Another advantage of ANFIS is its speed of operation which is much faster than in other control strategies the

tedious task of training membership functions is done in ANFIS

Using the CVT is more ef 1047297cient in areas with turbulent wind

distribution

The research is at an early stage hence cost and performance of

the system are unknown Being the analytical behavior of the sys-

tem was limited to the steady state only the application of the

proposed system has to be further investigated ie dynamical

simulations of the proposed system should be interesting in order

to investigate the response to a gust

Acknowledgment

The corresponding author would like to acknowledge the1047297nancial support of the Bright Spark Program at University of

Malaya This paper is supported by Project Grant TP35005

ldquoResearch and development of new generation wind turbines of

high-energy ef 1047297ciencyrdquo (2011e2014) 1047297nanced by Ministry of Edu-

cation Science and Technological Development Republic of Serbia

The last author work is partly funded by the Malaysian Ministry of

Higher Education under the University of Malaya High Impact

Research Grant UMC6251HIRMOHEFCSIT17

References

[1] Marques J Hey H A survey on variable-speed wind turbine system Proc BrazConf Electron Power 20031732e8

[2] Boukhezzar B Siguerdidjane H Review of state of the art in smart rotor

control research for wind turbines Prog Aerosp Sci 2010461e

27

[3] Boukhezzar B Siguerdidjane H Nonlinear control with wind estimation of aDFIG variable speed wind turbine for power capture optimization EnergyConvers Manage 200950885e92

[4] Laks JH Pao LY Wright AD Control of wind turbines past present and futureIn American control conference 2009 ACC rsquo09 2009 pp 2096e103

[5] Song YD Dhinakaran B Bao XY Variable speed control of wind turbines usingnonlinear and adaptive algorithms J Wind Eng Ind Aerodyn 200085293e308

[6] Aho J Buckspan A Laks J Jeong Y Dunne F Pao L Tutorial of wind turbine

control for supporting grid frequency through active power control InAmerican control conference Montreal Canada June 27e29 2012 2012

[7] Sedaghati R A novel control strategy study for DFIG-based wind turbine In-dian J Sci Technol December 20125(12) ISSN 0974-6846

[8] Mihet-Popa L Blaabjerg F Wind turbine generator modeling and simulationwhere rotational speed is the controlled variable IEEE Trans Ind Appl JanuaryFebruary 200440(1)

[9] Muljadi E Butter1047297eld CP Pitch-controlled variable-speed wind turbine gen-eration In Presented at the 1999 IEEE Industry Applications Society AnnualMeeting Phoenix Arizona October 3e7 1999 1999

[10] Hall JF Chen D Performance of a 100 kW wind turbine with a variable ratiogearbox Renew Energy 201244261e6

[11] Ribeiro F Teixeira JC Continuously variable transmission in medium-sizedwind generatorsIn ABCM symposium series in mechatronics vol 5 2012pp 1329e38 Section VIII e Sensors and Actuators

[12] Mihailidis A Karaoglanidis G Nerantzis I A CVT system for wind energyconverters In The second international conference ldquopower transmissions2006 2006 pp 411e6

[13] Gorla C Cesana P Ef 1047297ciency models of wind turbines gearboxes with hy-

drostatic CVT Balkan J Mech Transm 20111(2)17e

24[14] Zadeh LA Fuzzy sets Inf Control 19658338e53[15] Zadeh LA Fuzzy sets and systems system theory Brooklyn NY Polytechnic

Press 1965 pp 29e39[16] Mamdani EH Application of fuzzy algorithms for control of simple dynamic

plant Proc Inst Electr Eng 19741211585e8[17] Shamshirband S Kalantari S Daliri ZS Shing Ng L Expert security system in

wireless sensor networks based on fuzzy discussion multi-agent systems SciRes Essays 201024(5)3840e9

[18] Shamshirband S A distributed approach for coordination between traf 1047297clights based on game theory Int Arab J Inf Technol March 20129(2)148e53

[19] Feizollah A Shamshirband S Anuar NB Salleh R Mat Kiah ML Anomalydetection using cooperative fuzzy logic controller intelligent robotics sys-tems inspiring the NEXT Commun Comput Inf Sci 2013(376)220e31

[20] Barlas TK van Kuik GAM Application of neural network controller formaximum power extraction of a grid-connected wind turbine system ElectrEng 20058845e53

[21] Kassem AM Neural control design for isolated wind generation system based

on SVC and nonlinear autoregressive moving average approach WSEAS TransSyst February 201211(2)39e49[22] Li H Shi KL McLaren P Neural network based sensorless maximum wind

energy capture with compensated power coef 1047297cient IEEE Trans Ind Appl200541(6)1548e56

[23] Rajaji L Kumar C Neural network controller based induction generator forwind turbine applications Indian J Sci Technol Feb 20092(2) ISSN 0974-6846

[24] Ricalde LJ Cruz BJ Saacutenchez EN High order recurrent neural control for windturbine with a permanent magnet synchronous generator Comput Sist201014(2) ISSN 1405-5546133e43

[25] Sedighizadeh M Rezazadeh A Adaptive PID control of wind energy conver-sion systems using rasp1 mother wavelet basis function networks Proc WorldAcad Sci Eng Technol February 200827 ISSN 1307-6884

[26] Qiao W Liang J Venayagamoorthy GK Harley R Computational intelligencefor control of wind turbine generators In 2011 IEEE power and energy so-ciety general meeting 2011 httpdxdoiorg101109PES20116039778

[27] Shamshirband Shahaboddin Anuar NB Kiah MLM Patel A An appraisal anddesign of a multi-agent system based cooperative wireless intrusion detection

Fig 9 Simulink block diagram for estimation of the optimal wind turbine CVT ratio




computational intelligence technique Eng Appl Artif Intell October201326(9)2105e27

[28] Shiraz Muhammad Gani Abdullah Hafeez Khokhar Rashid Buyya RajkumarA review on distributed application processing frameworks in smart mobiledevices for mobile cloud computing IEEE Commun Surv Tutorials November201215(3)1294e313 httpdxdoiorg101109surv201211141200045

[29] Ahmed Ejaz Shiraz Muhammad Gani Abdullah Spectrum-aware distributedchannel assignment in cognitive radio wireless mesh networks Malaysian JComput Sci September 201326(3)232e50

[30] Anuar NB Sallehudin H Gani A Zakari O Identifying false alarm for network

intrusion detection system using hybrid data mining and decision treeMalaysian J Comput Sci 200821(2)101e15

[31] Mansoori M Zakaria O Gani A Improving exposure of intrusion deceptionsystem through implementation of hybrid honeypot Int Arab J Inf Technol20129(5)436e44

[32] Enayatifar Rasul Sadaei Hossein Javedani Abdullah Abdul HananGani Abdullah Imperialist competitive algorithm combined with re1047297nedhigh-order weighted fuzzy time series for short term load forecasting EnergyConvers Manage Dec 2013761104e16

[33] Jang J-SR ANFIS adaptive-network-based fuzzy inference systems IEEE TransSyst Man Cybern 199323665e85

[34] Petkovic D Pavlovic ND Applications and adaptive neuro-fuzzy estimation of conductive silicone rubber properties Strojarstvo 201354(3)

[35] Petkovic D Pavlovic ND Cojbasic Z Pavlovic NT Adaptive neuro fuzzy esti-mation of underactuated robotic gripper contact forces Expert Syst Appl201340(1) ISSN 0957-4174281e6

[36] Petkovic D Issa M Pavlovic ND Pavlovic NT Zentner L Adaptive neuro-fuzzyestimation of conductive silicone rubber mechanical properties Expert SystAppl 201239(10) ISSN 0957-41749477e82

[37] Petkovic D Cojbasic Z Adaptive neuro-fuzzy estimation of automatic nervoussystem parameters effect on heart rate variability Neural Comput Appl201221(8)2065e70

[38] Petkovic D Cojbasic Z Lukic S Adaptive neuro fuzzy selection of heart ratevariability parametersaffected by autonomic nervous system Expert Syst ApplSeptember 201340(11)4490e5

[39] Khajeh A Modarress H Rezaee B Application of adaptive neuro-fuzzy infer-ence system for solubility prediction of carbon dioxide in polymers ExpertSyst Appl 2009365728e32

[40] Sivakumar R Balu K ANFIS based distillation column control IJCA J 201067e73 (Special issue on Evolutionary Computation for Optimization Techniques)

[41] Petkovic D Issa M Pavlovic ND Zentner L Intelligent rotational directioncontrol of passive robotic joint with embedded sensors Expert Syst Appl201340(4) ISSN 0957-41741265e73

[42] Petkovic D Issa M Pavlovic ND Zentner L Cojbasic Z Adaptive neuro fuzzycontroller for adaptive compliant robotic gripper Expert Syst Appl201239(18) ISSN 0957-417413295e304

[43] Areed FG Haikal AY Mohammed RH Adaptive neuro-fuzzy control of aninduction motor Ain Shams Eng J 2010171e8

[44] Altin N Sefa I Mohammed RH dSPACE based adaptive neuro-fuzzy controllerof grid interactive inverter Energy Convers Manage 201256130e9

[45] Tian L Collins C Adaptive neuro-fuzzy control of a 1047298exible manipulatorMechatronics 2005151305e20

[46] Aldair AA Wang WJ Design an intelligent controller for full vehicle nonlinearactive suspension systems Int J Smart Sens Intell Syst 20114(2)224e43

[47] Dastranj MR Ebroahimi E Changizi N Sameni E Control DC motorspeed withadaptive neuro-fuzzy control (ANFIS) Austr J Basic Appl Sci 20115(10)1499e504

[48] Wahida Banu RSD Shakila Banu A Manoj D Identi1047297cation and control of nonlinear systems using soft computing techniques Int J Model Optim20111(1)24e8

[49] Grigorie TL Botez RM Adaptive neuro-fuzzy inference system-based con-trollers for smart material actuator modelling J Aerosp Eng 2009655e68

[50] Akcayol MA Application of adaptive neuro-fuzzy controller for SRM Adv EngSoftw 200435129e37

[51] Moustakidis SP Rovithakis GA Theocharis JB An adaptive neuro-fuzzytracking control for multi-input nonlinear dynamic systems Automatica2008441418e25

[52] Peymanfar A Khoei A Hadidi K Design of a general proposed neuro-fuzzycontroller by using modi1047297ed adaptive-network-based fuzzy inference sys-tem Int J Electron Commun 201064433e42

[53] Omar BAA Haikal AYM Areed FFG Design adaptive neuro-fuzzyspeed controller for an electro-mechanical system Ain Shams Eng J 2011299e107

[54] Heier S Wind energy conversion systems In Grid integration of windenergy conversion systems Chichester UK John Wiley amp Sons Ltd 1998pp 34e6




generator at different wind speeds so that the turbine may be kept

running at maximum ef 1047297ciency levels at all wind speeds It is known

about automatic CVT regulation to adjust and stabilize their trans-

mission ratio according to transmitted torques without relying on

other regulating or control mechanisms [1213] Considering all

these it is interesting to explore the feasibility of installing an

automatic CVT in a wind turbine since such a solution may optimize

the ef 1047297ciency of these systems by means of simple technologies

To improve the control of thewind turbines fuzzy logic (FL) [14e19] or arti1047297cial neural network (ANN) control has attracted much

attention in recent years [20e27] As a non-linear function [28e31]

ANNs can be used for identifying the extremely non-linear systemparameters with high accuracy Neural networks can learn from

data However understanding the knowledge learned by neural

networks has been dif 1047297cult In contrast fuzzy rule based models are

easy to understand because they use linguistic terms and the

structure of IF-THEN rules Unlike neural networks however fuzzy

logic by itself cannot learn [32] Since neural networks can learn it is

natural to merge these two techniques This merged technique of

the learning power of the ANNs with the knowledge representation

of FL has created a new hybrid technique called neuro-fuzzy net-

works or adaptive neuro-fuzzy inference system (ANFIS) [33] ANFIS

as a hybrid intelligent system that enhances the ability to auto-

matically learn and adapt was used by researchers for modeling

[34e37] predictions [38e40] and control [41e45] in various engi-

neering systems The basic idea behind these neuro-adaptivelearning techniques is to provide a method for the fuzzy modeling

procedure to learn information about data [46e53]

In this paper the application of ANFIS is proposed to control the

CVT ratio to extract the maximal wind energy through the wind

turbine As inputs in the controller current wind speed and current

wind turbine rotor speed are used The output should be optimal

generator speed

2 Wind turbine power extraction and continuously variable

transmission

The major components of a typical wind energy conversion

system include a wind turbine a generator interconnection appa-

ratus and control system Therefore the design of a wind energyconversion system is complex The most important part of a wind

energy conversion system is the wind turbine transforming the

wind kinetic energy into mechanical or electric energy The system

basically comprises a blade a mechanical part and an electric engine

coupled to each other The kinetic energy of wind is the function of

wind speed the speci1047297c mass of air the area of air space where the

wind is captured and the height at which the rotor is placed The

power available in a uniform wind 1047297eld can be expressed as

P w frac14 1

2r Ay3

where P w is the power [W] of the wind with air density r [kgm3]

and wind speed n [ms] is passing through the swept area A [m

2

] of

a rotor disk that is perpendicular to the wind 1047298ow Thewind turbine

can only capture a fraction of the power available from the wind

The ratio of captured power to available power is referred to as the

power coef 1047297cient

C pethb V eUr RTHORN

which is a function of the collective blade pitch angle b effective

wind speed V e rotor speedUr and rotor radius R The value of C p can

be expressed according to Ref [54] as

A characterization of the power coef 1047297cient C p for the wind

turbine used in this study is optimized to achieve maximum valueThe optimization procedures is expressed as

maxC p frac14 C pethb V eUr RTHORN45

b 0

50 m=s V e 8 m=s30 rpm Ur 60 rpmR frac14 25 m

(1)

In this paper a new approach to a CVT power transmission sys-

tem is presented It is added just before the generator avoiding the

need to change the main gearbox and the aerodynamic tip brake

control pipes Fig1 shows a widely used power transmission system

of a wind turbine with the proposed CVT system installed The po-

wer 1047298ows from the rotor hub through the input shaft to the main

gearbox It is the same unit that is used in a 1047297xed speed wind tur-bine This gearbox could consist of a planetary stage and two simple

spur gear stages The disc brake is conventionally installed after the

main gearbox In a 1047297xed speed design the power would 1047298ow from

the main gearbox directly to the generator This is the point where

the proposed CVT system is installed It is suggested to use for CVT

system two spring-loaded pulleys one at the driving shaft and one

at the driven shaft With such a simple and inexpensive solution the

CVT was automatically regulated and adjusted its transmission ratio

tothe torque appliedon the driving pulley A layout of thedrive train

components of the wind turbine is illustrated in Fig 2

The general speed ratio iCVT is given by

iCVT

frac14 uA

uB

where uA is the angular velocity of the power input shaft and is

connected to the output shaft of the main gearbox The uB is the

angular velocity of the output shaft connected to the generator

Finally there is adjustment shaft with angular velocity uC which is

connected to the hydraulic system Variation of the speed of the

adjustment shaft leads to variation of the total transmission ratio of

the gearbox The angular velocities of the three shafts uA uB uC

ful1047297ll the following relationship

uC frac14 x$uA thorn y$uB

where x and y areconstants de1047297ned by the numbers of teeth of each

gear and the overall gearbox system In the special case where

C pethb V eUr RTHORN frac14 05176

0B 116

1

RUr

V e 008b

0035

b3thorn 1

04b 5

1CAe

211

RUrV e

008b0035

b3 thorn1thorn 00068

RUr

V e






iCVT frac14 uA0

uB0frac14

y

x



f frac14 u A u A0

u A0(2)


gearbox is given by

iCVT frac14 y




iR frac14 uA

uCfrac14

1

x$

1 thorn f

f







P CP A

frac14 f

1 thorn f





























control






































(Fig 5) such as



0 x ai

xai

biai ai x bi

c i xc ibi

bi x c i

0 c i x












rule



















Table 1



8 36

10 36

12 40

14 47

16 54

18 60

20 60

22 60

24 58

26 53

28 506

30 494

32 485

34 485

36 485

38 485

40 485

42 485

44 485

46 485

48 485

50 485






O4i frac14

Xi

wi xf frac14

Piwi f Piwi








4 Results






Figs 6e









5 Conclusion






























ANFIS 1































distribution







Acknowledgment









References




27



































































iCVT frac14 uA0

uB0frac14

y

x



f frac14 u A u A0

u A0(2)


gearbox is given by

iCVT frac14 y




iR frac14 uA

uCfrac14

1

x$

1 thorn f

f







P CP A

frac14 f

1 thorn f





























control






































(Fig 5) such as



0 x ai

xai

biai ai x bi

c i xc ibi

bi x c i

0 c i x












rule



















Table 1



8 36

10 36

12 40

14 47

16 54

18 60

20 60

22 60

24 58

26 53

28 506

30 494

32 485

34 485

36 485

38 485

40 485

42 485

44 485

46 485

48 485

50 485






O4i frac14

Xi

wi xf frac14

Piwi f Piwi








4 Results






Figs 6e









5 Conclusion






























ANFIS 1































distribution







Acknowledgment









References




27



































































































(Fig 5) such as



0 x ai

xai

biai ai x bi

c i xc ibi

bi x c i

0 c i x












rule



















Table 1



8 36

10 36

12 40

14 47

16 54

18 60

20 60

22 60

24 58

26 53

28 506

30 494

32 485

34 485

36 485

38 485

40 485

42 485

44 485

46 485

48 485

50 485






O4i frac14

Xi

wi xf frac14

Piwi f Piwi








4 Results






Figs 6e









5 Conclusion






























ANFIS 1































distribution







Acknowledgment









References




27



































































O4i frac14

Xi

wi xf frac14

Piwi f Piwi








4 Results






Figs 6e









5 Conclusion






























ANFIS 1































distribution







Acknowledgment









References




27
























































































distribution







Acknowledgment









References




27































































































Documents

Shamshirband Energy