Download Computational Intelligence, Condition Monitoring and Optimization in Mechanical System- A Review

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the work of artificial intelligence, which forms the content of this project

Document related concepts

Control theory wikipedia, lookup

Islanding wikipedia, lookup

Variable-frequency drive wikipedia, lookup

Distribution management system wikipedia, lookup

Life-cycle greenhouse-gas emissions of energy sources wikipedia, lookup

Electric machine wikipedia, lookup

Induction motor wikipedia, lookup

Intermittent energy source wikipedia, lookup

Wind turbine wikipedia, lookup

Fault tolerance wikipedia, lookup

Control system wikipedia, lookup

Transcript
International Journal of Engineering Trends and Technology (IJETT) – Volume 17 Number 4 – Nov 2014
Computational Intelligence, Condition
Monitoring and Optimization in
Mechanical System- A Review
M. Prem Kumar#1, K. Ganesan*2
#
*
PG Student,Department of Mechanical Engineering, Nandha Engineering College, Erode-52. India
Assistant Professor, Department of Mechanical Engineering, Nandha Engineering College, Erode-52. India
Abstract
Energy is considered as the essential part for the national development in the form of mechanical
power or any other which has major contribution for improving the quality of life and enhancing the economic
growth. Thus, the use of wind turbine in the form of a renewable energy has become as one of the most viable
alternative resource of power generation due to some compensations of it such as cost-effective and ecofriendly. In condition monitoring system it is difficult to implementation due to many uncertain parameters. For
that uncertain parameters the computational intelligence technique is implemented like Neuro fuzzy, Fuzzy
logic and FMECA. For that technique optimization is performed. And literature review is conducted for
condition monitoring, computational intelligence and optimization.
Keywords: Condition Monitoring, FMEA, FMECA, Neuro fuzzy.
Introduction
The goal of fuzzy controllers is to mimic a
human operator’s actions or to make humanlike
decisions by using the knowledge about controlling
a target system (without knowing its model). This
is achieved with fuzzy rules that constitute a fuzzy
rule base. The fuzzy rule base is a central
component of the fuzzy controller and it represents
the “intelligence” in any fuzzy control algorithm.
This is the place where the designer’s knowledge
and experience must be correctly interpreted and
organized into an appropriate set of rules.(Fuzzy
rule) Let A and B be either fuzzy relations or fuzzy
propositions. Then the structure [FR: IF A THEN
B] is called a fuzzy rule.
Every fuzzy rule can be divided into an
antecedent part (IF . . .) and a consequent part
(THEN . . .), with antecedent parts describing
causes
and
consequent
parts
describing
consequences relevant for control action. Such a
form of fuzzy rules enables nonlinear mapping of
inputs and outputs and thus enables creation of
versatile static nonlinear control functions. The
nonlinear character of these functions allows the
fuzzy logic controller to cope successfully with
complex nonlinear control problems.
ISSN: 2231-5381
The size of the fuzzy rule base depends on
the number of fuzzy rules, while the number of
fuzzy rules depends on the number of input and
output variables and on the number of linguistic
values (fuzzy sets) associated with each of the
variables. In general, the formation of fuzzy rules
must follow some common sense in order to
preserve basic fuzzy rule base characteristics such
as consistency (contradiction), continuity, and
completeness [1].
A CMS is a tool to ensure and measure the
reliability of several running system. Evaluation of
CMS is carried out by watching how efficiently it
conveys the signal/alarm concerning an impending
fault/crack. Condition Monitoring System is a
method to realize the basic ideas of reliability
theory.
Neuro fuzzy logic
An integrated control model using an adaptive
neuro-fuzzy inference system for wind turbine
power management strategy has been introduced.
The vertical axis wind turbine is modeled for
analysis. An artificial neural network is employed
in this model to develop the fuzzy expert system to
achieve a more realistic evaluation of wind power
http://www.ijettjournal.org
Page 163
International Journal of Engineering Trends and Technology (IJETT) – Volume 17 Number 4 – Nov 2014
extraction. Experiments and Simulation have been
carried out to investigate the effect of control
strategy parameters of the wind turbine and its
power extraction.
The mathematical model has been
formulated by understanding the wind nature,
analyzing the mechanics of wind turbine blade
interaction and the interaction of air-flowaerodynamics. For simulating and optimizing the
design parameters the mathematical model is used
for the system performance and wind power
generation. Two kinds of air-flow model have been
employed in simulating the aerodynamics of the
wind turbine. One is the overall flow model, and
the other is a local flow model. The overall flow
model is based on a double multiple-stream tube
model, including flow expansion in the lateral
direction. The blade tip effects are significantly
important in this model in order to use Prandtl
lifting theory. The overall flow model is well suited
for design investigation due to its reliable output
results. The local flow model is based on one blade
section conformal recording placed into a circle.
The analytical model is employed with input data
in terms of lift force and pitching moment [2].
A fuzzy scheme for failure mode screening
In reliability centered maintenance
(RCM), it is necessary to evaluate all the functional
interrelationships among the system’s elements to
assess the overall effects of the different
component failure modes. In large system the
nature of the dependencies may be unknown. Thus,
fuzzy set operators, such as disjunction and
conjunction operators, may denote a natural and
simple way of representing the possibility of
interdependencies among machines. It should be
noted that these fuzzy operators need to be
carefully chosen or formulated so that the
equipment interdependencies under scrutiny can be
properly rejected in the analysis.
Fuzzy logic has also been considered for
manipulating the morphological terms that an
analyst employs in performing a failure modes,
effects and criticality analysis (FMECA). The
Linguistic variables can be adopted to describe the
frequency of occurrence, severity, and detect
capability of failure modes. Each one of such
linguistic terms can be represented by fuzzy
ISSN: 2231-5381
trapezoidal numbers. Through a defuzzification
method or procedure, a conclusive linguistic
variable (i.e., moderate, important, very important,
etc.) can be resolved to determine the risk of each
component failure mode.
A fuzzy reasoning algorithm was
developed and implemented via an expert system to
evaluate and assess the likelihood of equipment
failure mode and augmentation. The scheme is
based upon the fuzzification of the effects of
precipitating factors annoying the failure. It
consists of a fuzzy mathematical formulation which
linearly relates the presence of factors catalogued
as important, critical or related to the occurrence of
machine failure modes. The fuzzy algorithm was
created to enable the implication mechanism of a
constructed knowledge-based system to screen
industrial equipment failures according to their
likelihood of occurrence[3].
Failure Detection Depends on Fuzzy Inference
System
The devices used for protection and
operators have responsibilities for the failure
detection in a power system. The alarms are used
for the protection devices and they are displayed to
the operator by SCADA to respond to the
respective appropriate and timely actions to be
done. This paper is a part of a risk assessment study
on the alarm of power system control centers using
the Failure Modes and Effects Analysis (FMEA)
that seeks to assess the failure detection in power
system. The effective factors as fuzzy variables are
used to evaluate them by use of fuzzy inference
system. Advantages of the proposed fuzzy
detection score are involving human reliability
factors in addition to relay performance and
modifying detection rate. The risk assessment
depends on three variables: Failure occurrence (O),
Severity of consequences(S) and detection of
failures (D). This paper mainly focused on
detection variable and prepared a specific model
for the failure detection in a control center.
Detection probability (D) means probability to
detect the failure mode/causes. For detection of
probability in FMEA are based on two definitions.
First one is probability that the failure to be
detected earlier to a customer. Second one is
probability that the failure to be detected by a
customer earlier to a disaster. At the beginning, the
http://www.ijettjournal.org
Page 164
International Journal of Engineering Trends and Technology (IJETT) – Volume 17 Number 4 – Nov 2014
input data should be fuzzified and their
membership degree to be identified. For this
purpose, the triangular membership function is
used. This paper represents a method based on
fuzzy inference system to assess finding variable.
At first the factors that influence failure
mode detection are identified. Then a model is
suggested based on a fuzzy inference system. The
detection rate is modified and relay performance is
calculated using the Bayes theory. The model
validation is reviewed from two points of views.
Finally, an illustrative example is presented. The
model strengths include: To evaluate the detection
variable, the ‘alarm status’ and ‘relay performance’
is considered. The ‘alarm status’ affects operator
failure rate. Therefore, we have combined operator
failure factors in control center with relay
performance. This is a new work in risk assessment
and failure detection assessment for a control
center. They have identified factors that influence
the failure detection and provided a model to
determine the score. To determine the relay
performance score, signal detection theory concept
and Bayes rule are applied. This method has
changed classic view of FMEA to detection score
and false alarm is hitted, Miss and Correct rejection
probabilities are calculated [4].
Fuzzy controller for DFIG
A maximum power point tracking method
is developed for the DFIG wind turbine system. To
control rotor side converter the fuzzy controller is
used to capture the maximum wind energy without
measuring the wind velocity. To validate the
proposed control strategy for 10KW DFIG wind
generator the MATLAB /SIMULINK is used. This
generator allows the production of electricity has
variable speed, it allows them to better exploit the
wind resources for different wind velocities.
Underneath optimal control conditions, the variable
speed wind system can extract a maximum wind
power for a wide range of wind. A DFIG consists
of a wound rotor induction generator with the stator
windings directly connected to a three-phase power
grid and with the rotor winding mounted to a
bidirectional back-to-back IGBT frequency
converter.Rotor side converter RSC and the grid
side converter GSC are in 20-30% apparent power
size. Controller of the utility side converter
regulates the voltage across the DC link for power
transmission to the gird; The RSC regulates the
ISSN: 2231-5381
electro-magnetic torque or active power and it
supplies some of the reactive power.
A fuzzy logic controller is proposed to
control the speed of the DFIG in order to track the
maximum power operating point for a wide range
of wind speed. The fuzzy logic controller is applied
to control the rotor side converter (RSC) by using a
stator flux oriented strategy. And an optimal speed
position is estimated from the wind speed. At a
given wind speed, the maximum energy obtained at
an optimal TSR (tip speed ratio). Therefore as wind
speed changes the turbine rotor speed needs to vary
accordingly in order to maintain the tip speed ratio.
The fuzzy controller (FLC) is mainly used in
nonlinear modeled and have more inputs, uncertain
factors and inaccurate properties. But in this case
the fuzzy controller includes four parts: reasoning
and defuzzification, fuzzification, fuzzy rule base.
They have presented wind energy conversion
system made with a doubly fed induction
generator. A DFIG with the stator is connected
directly to the grid while the rotor is connected to
the grid through AC-DC-AC PWM converters.
Based on a fuzzy logic controller (FLC) the rotor
side converter is controlled. For controlling the
RSC is to extract a maximum power from the wind
without capturing his speed. The capability of the
proposed controller is verified by using
MATLAB/SIMULINK [5].
DFIG using Fuzzy-PI Control
HAMANE et.al studied study analysis of a
wind energy conversion system (WECS) based on
a doubly fed induction generator (DFIG) connected
to the electric power grid. The objective of the
work is to apply and compare the dynamic
performances of two types of controllers (PI and
Fuzzy-PI) for the WECS. In terms of tracking and
robustness WECS with respect to the wind
fluctuation as well as the impact on the quality of
the energy produced. The vector control with stator
flux orientation of the DFIG is also utilized to
control the active and reactive powers between the
stator and the grid. Doubly-fed induction machine
is an electrical three-phase asynchronous machine
with wound rotor accessible for control. The power
handled by the rotor side (slip power) is
proportional to the slip; the energy required for
rotor-side power converter which it handles only a
small fraction of the overall system power. PI
http://www.ijettjournal.org
Page 165
International Journal of Engineering Trends and Technology (IJETT) – Volume 17 Number 4 – Nov 2014
parameters are adjusted by fuzzy controller and it
generates new parameters so that it fits all
operating conditions, based on the error and its
derivative. To analyze the system and compare
efficiently the two proposed controllers, a set of
simulation tests have been performed for 0.1sec,
using Matlab–Simulink.
In this paper, a decoupling control method
of active and reactive powers for DFIG is
developed. The appropriate model and vector
control strategy have been established. There are
two types of controllers are used as classical PI and
Fuzzy-PI are synthesized to perform powers
reference tracking and efficient disturbance
dismissal. The results obtained that with the FuzzyPI controller is that the settling time is reduced
considerably, peak overshoot of values are limited
and oscillations are damped out faster compared to
the conventional PI Controller. The transient
response provided by the Fuzzy-PI Controller has
been superior to the classical PI controller [6].
Fault Identification in Pitch-controlled System
LIU Hao et.al developed a new method to
diagnose faults in pitch-controlled system of wind
turbine.The fuzzy theory is used to solve
uncertainty inference problem through the
establishment of the fault tree.The fault diagnosis
research in wind turbines from abroad mainly focus
on induction motor and gearbox.These methods
have been successfully applied for automated fault
diagnosis and have achieved well commercial
result in practical applications. The number of
faults occur in pitch-controlled system of wind
turbine just followed the electrical system, and it
also account for a large proportions of the longest
machine halt time in parts and single failure longest
downtime.It is difficult to be designated between
fault mechanism and fault causes by mathematical
models in the pitch-controlled system due to
complexity and uncertainty or this, the rules of
fuzzy fault diagnosis are presented (i) aimed at
features of equipment fault in pitch-controlled
system of wind turbine, combining the actual
performance of wind turbine generating units and
the ‘spot workers' and the ‘experts' experiences.(ii)
based on the fuzzy reasoning, are formed. The
purpose is to identify the fault cause based on
failure indications, and give some quantitative
positions to the maintenance staffs.
ISSN: 2231-5381
The essence of beginning fault mechanism
intelligent inference is to diagnosis the failure of
pitch system by drawing support from the expert’s
experiences and take a certain search strategy
combines with fuzzy inference. The inference is
divided into precise inference and fuzzy
inference.In precise inference the fault location is
determined through signs of phenomena observed,
and then slightpossibility. According to some
typical diagnosis till the final failure is
identified.Rule-based FT is used to carry on precise
inference in the intelligent fuzzy system. In Fuzzy
inference the relationship between symptoms and
fault reasons is designated by fuzzy fault diagnosis
method which uses membership functions and
fuzzy relation matrix in fuzzy set theory and it
obtains membership functions of symptoms
through membership functions of fault reasons.A
fault diagnosis in pitch-controlled system of wind
turbine using fuzzy interference with fault tree is
developed. The membership and fuzzy rules, with
collected operating data and fault information of
wind turbine in wind farm, by trying neural
network method, can be determined so that the
dependence of experience and perception can be
reduced [7].
Comparison of Sugeno-Type and MamdaniType Fuzzy Inference Systems
ArshdeepKauret.aldeveloped a Fuzzy
inference system for air conditioning system using
Mamdani-type
and
Sugeno-type
fuzzy
models.Classical control theory is based on the
mathematical models. It describes the physical
plant under consideration. Fuzzycontrol is used to
build a model of human expert who is capable of
controlling the plant without thinking in terms of
mathematical model.Fuzzy logic control was
superior to traditional control. To set correct rules
and determining the essence and range of fuzzy
variables is time consuming work.Mamdani
method is widely accepted for capturing expert
knowledge it allows us to describe the expertise in
more intuitive, more human-like manner. Sugeno
method is computationally efficient and works well
with based on adaptive techniques and
optimization, it makes very effective in control
problems, predominantly for dynamic non- linear
systems.In Mamdani method it consists of two
inputs from temperature and humidity sensors
providing the temperature and humidity of the
http://www.ijettjournal.org
Page 166
International Journal of Engineering Trends and Technology (IJETT) – Volume 17 Number 4 – Nov 2014
room. To controls the compressor speed the system
has one output. The temperature and humidity are
taken to be in ranges of 0ºC to 45ºC and 0% to
100% respectively. For each inputs four triangular
membership functions has been used. ForSugenotype model, the initial steps are same as Mamdanitype model. The output compressor speed can only
be either linear or constant in this FIS. The range of
output in Sugeno-type FIS can only be 0-1.The
results obtained for an air conditioning system
Mamdani-type FIS and Sugeno-type FIS works
similarly.Sugeno-type FIS air conditioning system
works up to its full capacity whereas in Mamdanitype FIS it does not work upto full
capacity.Sugeno-type FIS has an advantage that it
can integrated with neural networks and genetic
algorithm or other optimization techniques so that
the controller can adapt to individual user,
environment and weather [8].
Critically AssessmentFor
Using Fuzzy Logic
FMECA
Analysis
Failure Mode and Effects Analysis
(FMEA) is a structured, qualitative analysis of a
system to identify potential system failure modes,
their effects and the causes on the system
operation. FMECA extends this analysis by
including an evaluation of the failure criticality.
Due to fuzzy mathematicsit provides a tool for
directly manipulating with the linguistic terms. And
it also used in calculation RPN number. A
criticality assessment based on fuzzy logic allows
analysts to evaluate the risk associated with the
item failure modes in a natural and easy way.The
FMEA is a systematic approach for determining
and evaluating each system, subsystem, part and
component historical failure modes. This phase of
the analysis is called the failure mode portion
FMEA. If once the failure modes have been
defined for the system, the potential effects, or
impact on each part of system are evaluated
conferring to the mission system safety.FMECA is
often called as a safety analysis; its main benefit is
that the systems designers learn more about the
system while provide the analysis. FMECA should
be done iteratively as the design develops.A
FMECA is potentially one of the most beneficial
analyses done in a well reliability program.
FMECA is also one of the most tedious, time
consuming, errors prone and difficult in
development of a product. In future a computerized
ISSN: 2231-5381
assistance needs to be developed to help in
performing the analysis.. Fuzzy logic appears to be
a powerful tool for performing a criticality analysis
on a system design. And prioritizing failure
identified in a FMEA for corrective actions. Fuzzy
logic successfully combined both the quantitative
factors that affect the riskiness of a design. In
general, it provides an effective tool for
representing
and
manipulating
linguistic
knowledge of the type used in a FMECA [9].
Exposure of stator winding fault in induction
motor using fuzzy logic
Pedro Vicente JoverRodrı´guez and
Antero Arkkio presented a reliable method for the
detection of stator winding faults (which make up
38% of induction motor failures) based on
monitoring the line/terminal current amplitudes.
The online monitoring of induction motors is
flattering increasingly important. Difficulty in this
task is the lack of an accurate analytical model to
describe a faulty motor. To diagnose induction
motor faults a fuzzy logic approach may support.
Fuzzy logic is used to make decisions about the
stator motor condition in this method. The fuzzy
system is based on knowledge expressed in rules
and membership functions, which designate the
behaviour of the stator winding. The finite element
method (FEM) is utilized to generate virtual data
that support the construction of the membership
functions and give the probability to online test of
the proposed system. Layout has been implemented
in MATLAB-SIMULINK; with both data from a
FEM motor simulation program and real
measurements. In proposed method it is simple and
it has the ability to work with variable speed drives.
Fuzzy system is able to identify the motor stator
condition with high accuracy. Three-phase
induction motors are the ‘‘workhorses’’ of industry
and it is most widely used in electrical machine. As
of its simple structure and high reliability,
induction motor is used for many purposes such as:
blowers, pumps, fans, compressors, transportation,
etc. In an industrialized nation, they can consume
between 40 and 50% of total generated capacity of
that country. Early detection of abnormalities in the
motor will help to avoid expensive failures. To
reduce unexpected failures and downtime the
modern industry has widely used reliability-based
and condition-based maintenance strategies. This
paper expressed the feasibility of spotting stator
http://www.ijettjournal.org
Page 167
International Journal of Engineering Trends and Technology (IJETT) – Volume 17 Number 4 – Nov 2014
failures in an induction motor by monitoring the
motor current amplitudes using fuzzy logic. It is
used in application of variable speed drives. Fuzzy
logic system could be implemented in the software
of the inverter to monitor the stator condition
online. This paper presented the fusion between
soft computing (fuzzy logic) and hard computing
techniques (FEM) in order to design a reliable
system. A possible drawback of the method is
associated with the fact that a current imbalance
originating from the supply source may be
identified as a fault condition of the motor. But this
shortcoming can be overcome by monitoring the
voltage and introducing new rules in the inference
system [10].
Risk estimation in failure mode and effects
analysis
Ying-Ming Wang et.al.examined the fuzzy
risk priority numbers (FRPNs) are proposed for
prioritization of failure modes. FRPNs are defined
as fuzzy weighted geometric means of the fuzzy
ratings for occurrence (O), Severity (S) and
Detection (D), and can be computed using alphalevel sets and linear programming models. Intended
for ranking purpose, the FRPNs are defuzzified
using centroid defuzzification method, in which a
new centroid defuzzification formula based on
alpha-level sets is derived. Trapezoidal
and
triangular fuzzy numbers are defined for FMEA in
linguistic terms. This paper examined a new fuzzy
FMEA which allows the risk factors and their
relative weights to be evaluated in a linguistic
manner rather than in a defined way and a fuzzy
RPN rather than a crusty RPN or fuzzy if–then
rules to be defined for prioritization of failure
modes. The proposed fuzzy FMEA provided a
useful, effective, practical and flexible way for risk
evaluation in FMEA [11].
Condition monitoring system (CMS)
Adriaan Van Horenbeeket.al.examined
that incondition monitoring system it is difficult to
implementation during decision due to many
uncertain parameters. In certainly the case for the
wind turbine industry where factors like long
logistical times and weather conditions have a
major influence on the economic advantage. One of
the parameters that are neglected in most of the
existing literature is the performance of the
ISSN: 2231-5381
condition monitoring system itself. This paper
reveals a new concept for modeling this
performance based on the P–F curve of different
failure modes. A stochastic simulation model is
constructed in order to quantify the economic
added value of implementing a defectively
performing condition monitoring system into a
gearbox. A condition monitoring system (CMS)
plays a critical role in beating the maximum
potential of wind energy through wind turbine by
minimizing the idle time. The cost of CMS design
and installation is significant in comparison to
other maintenance approaches but in the longer run
CMS provides benefits exceeding the costs [12-15].
In fig.1 indicates the failure patterns that can be
identified by condition monitoring and highlights
the importance of the P–F curve and P–F interval.
This curve envisions the drop in time of a particular
component. While a component is operated, it will
start to deteriorate until it entirely loses its ability to
carry out its task. The point in time where the
component undergoes critical failure is referred to
as functional failure ‘F’. At that point the
component can perform its regular task. The point
in time where an indication of deterioration of the
component can be detected is mentioned to as a
potential failure ‘P’.
Fig.1. P-F curve
The expected life cycle cost of two maintenance
strategies is determined and compared by a
stochastic simulation model, that the performance
of a CMS should be taken into account in order to
draw the right conclusions on the real economic
value [12].
Conclusion
From the present review the following
conclusion are drawn (i) an adaptive neuro-fuzzy
inference system for wind turbine power
management strategy has been introduced. And an
artificial neural network is employed in this model
to develop the fuzzy expert system to achieve a
more realistic evaluation of wind power extraction.
http://www.ijettjournal.org
Page 168
International Journal of Engineering Trends and Technology (IJETT) – Volume 17 Number 4 – Nov 2014
(ii) A fuzzy reasoning algorithm was developed
and implemented via an expert system to evaluate
and assess the likelihood of equipment failure
mode and augmentation. The control of the rotor
side converter based on a fuzzy logic controller
(FLC) is presented. the Fuzzy-PI controller is that
the settling time is reduced considerably, peak
overshoot of values are limited and oscillations are
damped out faster compared to the conventional PI
Controller. A FMECA is potentially one of the
most beneficial analyses done in a well reliability
program. Fuzzy logic is used to make decisions
about the stator motor condition. (iii) A new fuzzy
FMEA which allows the risk factors and their
relative weights to be evaluated in a linguistic
manner rather than in a defined way and a fuzzy
RPN rather than a crusty RPN or fuzzy if–then
rules to be defined for prioritization of failure
modes.(iv)Condition monitoring system for wind
turbine is presented.
11.
12.
13.
14.
15.
fuzzy logic”. Applied Soft Computing 8, pp. 1112–1120,
2008.
Ying-Ming Wang a, Kwai-Sang Chin, Gary KaKwai Poon,
Jian-Bo Yang, “Risk evaluation in failure mode and effects
analysis using fuzzy weighted geometric mean”. Expert
Systems with Applications 36, pp. 1195–1207, 2009.
Adriaan Van Horenbeek n, Joris Van Ostaeyen, Joost R.
Duflou, LilianePintelon, “Quantifying the added value of
an imperfectly performing condition monitoring system—
Application to a wind turbine gearbox”. Reliability
Engineering and System Safety, pp. 45-57, 2013.
Z. Hameed, S.H. Ahn, Y.M. Cho, “Practical aspects of a
condition monitoring system for a wind turbine with
emphasis on its design, system architecture, testing and
installation”. Renewable Energy 35, pp. 879–894, 2010.
Abdulwahed A. Salem, Ahmed Abu-Siada, and Syed
Islam, “Condition Monitoring Techniques of the Wind
Turbines Gearbox and Rotor”. International Journal of
Electrical Energy, Vol. 2, No. 1, March 2014.
Wenxian Yang, “Condition Monitoring the Drive Train of
a Direct Drive Permanent Magnet Wind Turbine Using
Generator Electrical Signals”. Journal of Solar Energy
Engineering, Vol. 136, May 2014.
References
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
ZdenkoKovaˇci´c and StjepanBogdan, “Fuzzy Controller
Design Theory and Applications”. Taylor & Francis
Group, LLC, 2006.
Enrico Zi, GiulioGola, “A neuro-fuzzy technique for fault
diagnosis and its application to rotating machinery”.
Reliability Engineering and System Safety 94, pp. 78–
88,2009.
Daniel J. Fonsecaa, Gerald M. Knappb, “A fuzzy scheme
for failure mode screening”. Fuzzy Sets and Systems 121,
pp. 453–457, 2001.
SohrabKhanmohammadi, Kamran Rezaei, JavadJassbi and
ShabnamTadayon, “A Model of the Failure Detection
Based on Fuzzy Inference System for the Control Center
of a Power System”. Applied Mathematical Sciences, Vol.
6, No. 36, pp. 1747 – 1758, 2012.
M.Bezza, B.EL.Moussaoui and A.Fakkar, “Sensorless
MPPT fuzzy controller for DFIG wind turbine”. Energy
Procedia 18, pp. 339 – 348, 2012.
B.Hamane, M.Benhanem, A.M Bouzid, A. Belabbes, M.
Bouhamida “Control for Variable Speed Wind Turbine
Driving a Doubly Fed Induction Generator using Fuzzy-PI
Control”. Energy Procedia 18, pp. 476 – 485, 2012.
Liu Hao, Dong Xing-Hui, Yang Zhi-Ling, Zheng Kai,
“The Application of Intelligent Fuzzy inference to the
Fault Diagnosis in Pitch-controlled System”. Energy
Procedia 16, pp. 1839 – 1844, 2012.
ArshdeepKaur, AmritKaur, “Comparison of MamdaniType and Sugeno-Type Fuzzy Inference Systems for Air
Conditioning System”. International Journal of Soft
Computing and Engineering, Vol. 2, No. 2, pp. 323-325,
2012.
Kováčová
Monika,
Jančo
Roland,
“Critically
AssesmentForFmeca Analysis Using Fuzzy Logic”.
Journal of Applied Mathematics, Vol. 1, No. 1, pp. 261270, 2008.
Pedro Vicente JoverRodrı´guez , Antero Arkkio,
“Detection of stator winding fault in induction motor using
ISSN: 2231-5381
http://www.ijettjournal.org
Page 169