The main objective of this work is to propose two fuzzy controllers: one based on the Mamdani inference
method and another controller based on the Takagi- Sugeno inference method, both will be designed for
application in a position control system of a servomechanism. Some comparations between the methods
mentioned above will be made with regard to the performance of the system in order to identify the
advantages of the Takagi- Sugeno method in relation to the Mamdani method in the presence of
disturbances and nonlinearities of the system. Some results of simulation and practical application are
presented and results obtained showed that controllers based on Takagi- Sugeno method is more efficient
than controllers based on Mamdani method for this specific application.
INTERVAL TYPE-2 INTUITIONISTIC FUZZY LOGIC SYSTEM FOR TIME SERIES AND IDENTIF...ijfls
This paper proposes a sliding mode control-based learning of interval type-2 intuitionistic fuzzy logic system for time series and identification problems. Until now, derivative-based algorithms such as gradient descent back propagation, extended Kalman filter, decoupled extended Kalman filter and hybrid method of decoupled extended Kalman filter and gradient descent methods have been utilized for the optimization of the parameters of interval type-2 intuitionistic fuzzy logic systems. The proposed model is based on a Takagi-Sugeno-Kang inference system. The evaluations of the model are conducted using both real world and artificially generated datasets. Analysis of results reveals that the proposed interval type-2 intuitionistic fuzzy logic system trained with sliding mode control learning algorithm (derivative-free) do outperforms some existing models in terms of the test root mean squared error while competing favourable with other models in the literature. Moreover, the proposed model may stand as a good choice for real time applications where running time is paramount compared to the derivative-based models.
INTERVAL TYPE-2 INTUITIONISTIC FUZZY LOGIC SYSTEM FOR TIME SERIES AND IDENTIF...ijfls
This paper proposes a sliding mode control-based learning of interval type-2 intuitionistic fuzzy logic system for time series and identification problems. Until now, derivative-based algorithms such as gradient descent back propagation, extended Kalman filter, decoupled extended Kalman filter and hybrid method of decoupled extended Kalman filter and gradient descent methods have been utilized for the optimization of the parameters of interval type-2 intuitionistic fuzzy logic systems. The proposed model is based on a Takagi-Sugeno-Kang inference system. The evaluations of the model are conducted using both real world and artificially generated datasets. Analysis of results reveals that the proposed interval type-2 intuitionistic fuzzy logic system trained with sliding mode control learning algorithm (derivative-free) do outperforms some existing models in terms of the test root mean squared error while competing favourable with other models in the literature. Moreover, the proposed model may stand as a good choice for real time applications where running time is paramount compared to the derivative-based models.
Piecewise Controller Design for Affine Fuzzy SystemsISA Interchange
This paper studies the problem of state feedback controller design for a class of nonlinear systems, which are described by continuous-time affine fuzzy models. A convex piecewise affine controller design method is proposed based on a new dilated linear matrix inequality (LMI) characterization, where the system matrix is separated from Lyapunov matrix such that the controller parametrization is independent of the Lyapunovmatrix. In contrast to the existing work, the derived stabilizability condition leads to less conservative LMI characterizations and much wider scope of the applicability. Furthermore, the results are extended to H∞ state feedback synthesis. Finally, two numerical examples illustrate the superiority and effectiveness of the new results.
Bayesian-Network-Based Algorithm Selection with High Level Representation Fee...ITIIIndustries
A real-world intelligent system consists of three basic modules: environment recognition, prediction (or estimation), and behavior planning. To obtain high quality results in these modules, high speed processing and real time adaptability on a case by case basis are required. In the environment recognition module many different algorithms and algorithm networks exist with varying performance. Thus, a mechanism that selects the best possible algorithm is required. To solve this problem we are using an algorithm selection approach to the problem of natural image understanding. This selection mechanism is based on machine learning; a bottom-up algorithm selection from real-world image features and a top-down algorithm selection using information obtained from a high level symbolic world description and algorithm suitability. The algorithm selection method iterates for each input image until the high-level description cannot be improved anymore. In this paper we present a method of iterative composition of the high level description. This step by step approach allows us to select the best result for each region of the image by evaluating all the intermediary representations and finally keep only the best one.
Interval Type-2 Fuzzy Logic Systems (IT2 FLSs) have shown popularity, superiority, and more accuracy in performance in a number of applications in the last decade. This is due to its ability to cope with uncertainty and precisions adequately when compared with its type-1 counterpart. In this paper, an Interval Type-2 Fuzzy Logic System (IT2FLS) is employed for remote vital signs monitoring and predicting of shock level in cardiac patients. Also, the conventional, Type-1 Fuzzy Logic System (T1FLS) is applied to the prediction problems for comparison purpose. The cardiac patients’ health datasets were used to perform empirical comparison on the developed system. The result of study indicated that IT2FLS could coped with more information and handled more uncertainties in health data than T1FLS. The statistical evaluation using performance metrices indicated a minimal error with IT2FLS compared to its counterpart, T1FLS. It was generally observed that the shock level prediction experiment for cardiac patients showed the superiority of IT2FLS paradigm over T1FLS.
Mining association rules is one of the most important data mining tasks. Its purpose is to
generate intelligible relations between attributes in a database. However, its use in practice is
difficult and still raises several challenges, in particular, the number of learned rules is often
very large. Several techniques for reducing the number of rules have been proposed as
measures of quality, syntactic filtering constraints, etc. However, these techniques do not limit
the shortcomings of these methods. In this paper, we propose a new approach to mine
association, assisted by a Boolean modeling of results in order to mitigate the shortcomings
mentioned above and propose a cellular automaton based on a boolean process for mining,
optimizing, managing and representing of the learned rules.
An introduction to variable and feature selectionMarco Meoni
Presentation of a great paper from Isabelle Guyon (Clopinet) and André Elisseeff (Max Planck Institute) back in 2003, which outlines the main techniques for feature selection and model validation in machine learning systems
Piecewise Controller Design for Affine Fuzzy SystemsISA Interchange
This paper studies the problem of state feedback controller design for a class of nonlinear systems, which are described by continuous-time affine fuzzy models. A convex piecewise affine controller design method is proposed based on a new dilated linear matrix inequality (LMI) characterization, where the system matrix is separated from Lyapunov matrix such that the controller parametrization is independent of the Lyapunovmatrix. In contrast to the existing work, the derived stabilizability condition leads to less conservative LMI characterizations and much wider scope of the applicability. Furthermore, the results are extended to H∞ state feedback synthesis. Finally, two numerical examples illustrate the superiority and effectiveness of the new results.
Bayesian-Network-Based Algorithm Selection with High Level Representation Fee...ITIIIndustries
A real-world intelligent system consists of three basic modules: environment recognition, prediction (or estimation), and behavior planning. To obtain high quality results in these modules, high speed processing and real time adaptability on a case by case basis are required. In the environment recognition module many different algorithms and algorithm networks exist with varying performance. Thus, a mechanism that selects the best possible algorithm is required. To solve this problem we are using an algorithm selection approach to the problem of natural image understanding. This selection mechanism is based on machine learning; a bottom-up algorithm selection from real-world image features and a top-down algorithm selection using information obtained from a high level symbolic world description and algorithm suitability. The algorithm selection method iterates for each input image until the high-level description cannot be improved anymore. In this paper we present a method of iterative composition of the high level description. This step by step approach allows us to select the best result for each region of the image by evaluating all the intermediary representations and finally keep only the best one.
Interval Type-2 Fuzzy Logic Systems (IT2 FLSs) have shown popularity, superiority, and more accuracy in performance in a number of applications in the last decade. This is due to its ability to cope with uncertainty and precisions adequately when compared with its type-1 counterpart. In this paper, an Interval Type-2 Fuzzy Logic System (IT2FLS) is employed for remote vital signs monitoring and predicting of shock level in cardiac patients. Also, the conventional, Type-1 Fuzzy Logic System (T1FLS) is applied to the prediction problems for comparison purpose. The cardiac patients’ health datasets were used to perform empirical comparison on the developed system. The result of study indicated that IT2FLS could coped with more information and handled more uncertainties in health data than T1FLS. The statistical evaluation using performance metrices indicated a minimal error with IT2FLS compared to its counterpart, T1FLS. It was generally observed that the shock level prediction experiment for cardiac patients showed the superiority of IT2FLS paradigm over T1FLS.
Mining association rules is one of the most important data mining tasks. Its purpose is to
generate intelligible relations between attributes in a database. However, its use in practice is
difficult and still raises several challenges, in particular, the number of learned rules is often
very large. Several techniques for reducing the number of rules have been proposed as
measures of quality, syntactic filtering constraints, etc. However, these techniques do not limit
the shortcomings of these methods. In this paper, we propose a new approach to mine
association, assisted by a Boolean modeling of results in order to mitigate the shortcomings
mentioned above and propose a cellular automaton based on a boolean process for mining,
optimizing, managing and representing of the learned rules.
An introduction to variable and feature selectionMarco Meoni
Presentation of a great paper from Isabelle Guyon (Clopinet) and André Elisseeff (Max Planck Institute) back in 2003, which outlines the main techniques for feature selection and model validation in machine learning systems
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
SPECIFICATION OF THE STATE’S LIFETIME IN THE DEVS FORMALISM BY FUZZY CONTROLLERijait
This paper aims to develop a new approach to assess the duration of state in the DEVS formalism by fuzzy
controller. The idea is to define a set of fuzzy rules obtained from observers or expert knowledge and to
specify a fuzzy model which computes this duration, this latter is fed into the simulator to specify the new
value in the model. In conventional model, each state is defined by a mean lifetime value whereas our
method, calculates for each state the new lifetime according to inputs values. A wildfire case study is
presented at the end of the paper. It is a challenging task due to its complex behavior, dynamical weather
condition, and various variables involved. A global specification of the fuzzy controller and the forest fire
model are presented in the DEVS formalism and comparison between conventional and fuzzy method is
illustrated.
An Optimum Time Quantum Using Linguistic Synthesis for Round Robin Cpu Schedu...ijsc
In Round Robin CPU scheduling algorithm the main concern is with the size of time quantum and the increased waiting and turnaround time. Decision for these is usually based on parameters which are assumed to be precise. However, in many cases the values of these parameters are vague and imprecise. The performance of fuzzy logic depends upon the ability to deal with Linguistic variables. With this intent, this paper attempts to generate an Optimal Time Quantum dynamically based on the parameters which are treated as Linguistic variables. This paper also includes Mamdani Fuzzy Inference System using Trapezoidal membership function, results in LRRTQ Fuzzy Inference System. In this paper, we present an algorithm to improve the performance of round robin scheduling algorithm. Numerical analysis based on LRRTQ results on proposed algorithm show the improvement in the performance of the system by reducing unnecessary context switches and also by providing reasonable turnaround time.
AN OPTIMUM TIME QUANTUM USING LINGUISTIC SYNTHESIS FOR ROUND ROBIN CPU SCHEDU...ijsc
In Round Robin CPU scheduling algorithm the main concern is with the size of time quantum and the increased waiting and turnaround time. Decision for these is usually based on parameters which are assumed to be precise. However, in many cases the values of these parameters are vague and imprecise.
The performance of fuzzy logic depends upon the ability to deal with Linguistic variables. With this intent, this paper attempts to generate an Optimal Time Quantum dynamically based on the parameters which are treated as Linguistic variables. This paper also includes Mamdani Fuzzy Inference System using Trapezoidal membership function, results in LRRTQ Fuzzy Inference System. In this paper, we present an algorithm to improve the performance of round robin scheduling algorithm. Numerical analysis based on LRRTQ results on proposed algorithm show the improvement in the performance of the system by reducing unnecessary context switches and also by providing reasonable turnaround time.
Intelligent Controller Design for a Chemical ProcessCSCJournals
Abstract - Chemical process control is a challenging problem due to the strong on-line non-linearity and extreme sensitivity to disturbances of the process. Ziegler – Nichols tuned PI and PID controllers are found to provide poor performances for higher-order and non–linear systems. This paper presents an application of one-step-ahead fuzzy as well as ANFIS (adaptive-network-based fuzzy inference system) tuning scheme for an Continuous Stirred Tank Reactor CSTR process. The controller is designed based on a Mamdani type and Sugeno type fuzzy system constructed to model the dynamics of the process. The fuzzy system model can take advantage of both a priori linguistic human knowledge through parameter initialization, and process measurements through on- line parameter adjustment. The ANFIS, which is a fuzzy inference system, is implemented in the framework of adaptive networks. The proposed ANFIS can construct an input-output mapping based on both human knowledge (in the form of fuzzy if-then rules) and stipulated input-output data pairs. In this method, a novel approach based on tuning of fuzzy logic control as well as ANFIS for a CSTR process, capable of providing an optimal performance over the entire operating range of process are given. Here Fuzzy logic control as well as ANFIS for obtaining the optimal design of the CSTR process is explained. In this approach, the development of rule based and the formation of the membership function are evolved simultaneously. The performance of the algorithm in obtaining the optimal tuning values has been analyzed in CSTR process through computer simulation.
Interval Type-2 Intuitionistic Fuzzy Logic System for Time Series and Identif...ijfls
This paper proposes a sliding mode control-based learning of interval type-2 intuitionistic fuzzy logic system for time series and identification problems. Until now, derivative-based algorithms such as gradient descent back propagation, extended Kalman filter, decoupled extended Kalman filter and hybrid method of decoupled extended Kalman filter and gradient descent methods have been utilized for the optimization of the parameters of interval type-2 intuitionistic fuzzy logic systems. The proposed model is based on a Takagi-Sugeno-Kang inference system. The evaluations of the model are conducted using both real world and artificially generated datasets. Analysis of results reveals that the proposed interval type-2 intuitionistic fuzzy logic system trained with sliding mode control learning algorithm (derivative-free) do outperforms some existing models in terms of the test root mean squared error while competing favourable with other models in the literature. Moreover, the proposed model may stand as a good choice for real time applications where running time is paramount compared to the derivative-based models.
On line Tuning Premise and Consequence FIS: Design Fuzzy Adaptive Fuzzy Slidi...Waqas Tariq
One of the most active research areas in the field of robotics is robot manipulators control, because these systems are multi-input multi-output (MIMO), nonlinear, and uncertainty. At present, robot manipulators is used in unknown and unstructured situation and caused to provide complicated systems, consequently strong mathematical tools are used in new control methodologies to design nonlinear robust controller with satisfactory performance (e.g., minimum error, good trajectory, disturbance rejection). Robotic systems controlling is vital due to the wide range of application. Obviously stability and robustness are the most minimum requirements in control systems; even though the proof of stability and robustness is more important especially in the case of nonlinear systems. One of the best nonlinear robust controllers which can be used in uncertainty nonlinear systems is sliding mode controller (SMC). Chattering phenomenon is the most important challenge in this controller. Most of nonlinear controllers need real time mobility operation; one of the most important devices which can be used to solve this challenge is Field Programmable Gate Array (FPGA). FPGA can be used to design a controller in a single chip Integrated Circuit (IC). In this research the SMC is designed using VHDL language for implementation on FPGA device (XA3S1600E-Spartan-3E), with minimum chattering and high processing speed (63.29 MHz).
FUNCTION PROJECTIVE SYNCHRONIZATION OF NEW CHAOTIC REVERSAL SYSTEMSijcseit
In the present work, Lyapunov stability theory, nonlinear adaptive control law and the parameter update
law were utilized to derive the state of two new chaotic reversal systems after being synchronized by the
function projective method. Using this technique allows for a scaling function instead of a constant thereby
giving a better method in applications in secure communication. Numerical simulations are presented to
demonstrate the effective nature of the proposed scheme of synchronization for the new chaotic reversal
system.
FUNCTION PROJECTIVE SYNCHRONIZATION OF NEW CHAOTIC REVERSAL SYSTEMSijcseit
In the present work, Lyapunov stability theory, nonlinear adaptive control law and the parameter update
law were utilized to derive the state of two new chaotic reversal systems after being synchronized by the
function projective method. Using this technique allows for a scaling function instead of a constant thereby
giving a better method in applications in secure communication. Numerical simulations are presented to
demonstrate the effective nature of the proposed scheme of synchronization for the new chaotic reversal
system.
A Learning Linguistic Teaching Control for a Multi-Area Electric Power SystemCSCJournals
This paper presents a new methodology for designing a neuro-fuzzy control for complex physical systems. By developing a Neural -Fuzzy system learning with linguistic teaching signals. The advantage of this technique is that, produce a simple and well-performing system because it selects the fuzzy sets and the numerical numbers and process both numerical and linguistic information. This approach is able to process and learn numerical information as well as linguistic information. The proposed control scheme is applied to a multi-area power system with hydraulic and thermal turbines.
Similar to FUZZY CONTROL OF A SERVOMECHANISM: PRACTICAL APPROACH USING MAMDANI AND TAKAGI- SUGENO CONTROLLERS (20)
CW RADAR, FMCW RADAR, FMCW ALTIMETER, AND THEIR PARAMETERSveerababupersonal22
It consists of cw radar and fmcw radar ,range measurement,if amplifier and fmcw altimeterThe CW radar operates using continuous wave transmission, while the FMCW radar employs frequency-modulated continuous wave technology. Range measurement is a crucial aspect of radar systems, providing information about the distance to a target. The IF amplifier plays a key role in signal processing, amplifying intermediate frequency signals for further analysis. The FMCW altimeter utilizes frequency-modulated continuous wave technology to accurately measure altitude above a reference point.
Hierarchical Digital Twin of a Naval Power SystemKerry Sado
A hierarchical digital twin of a Naval DC power system has been developed and experimentally verified. Similar to other state-of-the-art digital twins, this technology creates a digital replica of the physical system executed in real-time or faster, which can modify hardware controls. However, its advantage stems from distributing computational efforts by utilizing a hierarchical structure composed of lower-level digital twin blocks and a higher-level system digital twin. Each digital twin block is associated with a physical subsystem of the hardware and communicates with a singular system digital twin, which creates a system-level response. By extracting information from each level of the hierarchy, power system controls of the hardware were reconfigured autonomously. This hierarchical digital twin development offers several advantages over other digital twins, particularly in the field of naval power systems. The hierarchical structure allows for greater computational efficiency and scalability while the ability to autonomously reconfigure hardware controls offers increased flexibility and responsiveness. The hierarchical decomposition and models utilized were well aligned with the physical twin, as indicated by the maximum deviations between the developed digital twin hierarchy and the hardware.
Immunizing Image Classifiers Against Localized Adversary Attacksgerogepatton
This paper addresses the vulnerability of deep learning models, particularly convolutional neural networks
(CNN)s, to adversarial attacks and presents a proactive training technique designed to counter them. We
introduce a novel volumization algorithm, which transforms 2D images into 3D volumetric representations.
When combined with 3D convolution and deep curriculum learning optimization (CLO), itsignificantly improves
the immunity of models against localized universal attacks by up to 40%. We evaluate our proposed approach
using contemporary CNN architectures and the modified Canadian Institute for Advanced Research (CIFAR-10
and CIFAR-100) and ImageNet Large Scale Visual Recognition Challenge (ILSVRC12) datasets, showcasing
accuracy improvements over previous techniques. The results indicate that the combination of the volumetric
input and curriculum learning holds significant promise for mitigating adversarial attacks without necessitating
adversary training.
Cosmetic shop management system project report.pdfKamal Acharya
Buying new cosmetic products is difficult. It can even be scary for those who have sensitive skin and are prone to skin trouble. The information needed to alleviate this problem is on the back of each product, but it's thought to interpret those ingredient lists unless you have a background in chemistry.
Instead of buying and hoping for the best, we can use data science to help us predict which products may be good fits for us. It includes various function programs to do the above mentioned tasks.
Data file handling has been effectively used in the program.
The automated cosmetic shop management system should deal with the automation of general workflow and administration process of the shop. The main processes of the system focus on customer's request where the system is able to search the most appropriate products and deliver it to the customers. It should help the employees to quickly identify the list of cosmetic product that have reached the minimum quantity and also keep a track of expired date for each cosmetic product. It should help the employees to find the rack number in which the product is placed.It is also Faster and more efficient way.
Student information management system project report ii.pdfKamal Acharya
Our project explains about the student management. This project mainly explains the various actions related to student details. This project shows some ease in adding, editing and deleting the student details. It also provides a less time consuming process for viewing, adding, editing and deleting the marks of the students.
HEAP SORT ILLUSTRATED WITH HEAPIFY, BUILD HEAP FOR DYNAMIC ARRAYS.
Heap sort is a comparison-based sorting technique based on Binary Heap data structure. It is similar to the selection sort where we first find the minimum element and place the minimum element at the beginning. Repeat the same process for the remaining elements.
Using recycled concrete aggregates (RCA) for pavements is crucial to achieving sustainability. Implementing RCA for new pavement can minimize carbon footprint, conserve natural resources, reduce harmful emissions, and lower life cycle costs. Compared to natural aggregate (NA), RCA pavement has fewer comprehensive studies and sustainability assessments.
FUZZY CONTROL OF A SERVOMECHANISM: PRACTICAL APPROACH USING MAMDANI AND TAKAGI- SUGENO CONTROLLERS
1. International Journal of Fuzzy Logic Systems (IJFLS) Vol.11, No.2/3/4, October 2021
DOI : 10.5121/ijfls.2021.11402 19
FUZZY CONTROL OF A SERVOMECHANISM:
PRACTICAL APPROACH USING MAMDANI AND
TAKAGI-SUGENO CONTROLLERS
Renato Aguiar and Izabella Sirqueira
Department of Electrical Engineering, Centro Universitario FEI, S.B.C, Brazil
ABSTRACT
The main objective of this work is to propose two fuzzy controllers: one based on the Mamdani inference
method and another controller based on the Takagi- Sugeno inference method, both will be designed for
application in a position control system of a servomechanism. Some comparations between the methods
mentioned above will be made with regard to the performance of the system in order to identify the
advantages of the Takagi- Sugeno method in relation to the Mamdani method in the presence of
disturbances and nonlinearities of the system. Some results of simulation and practical application are
presented and results obtained showed that controllers based on Takagi- Sugeno method is more efficient
than controllers based on Mamdani method for this specific application.
KEYWORDS
Fuzzy Logic, Fuzzy Controller, Mamdani Inference Method, Takagi- Sugeno Inference Method.
1. INTRODUCTION
The desire of human beings since first industrial revolution is to gain more control and autonomy
of processes in order to obtain more efficiency and productivity. This produces the development
of efficient machines, which solve complex problems and perform actions using the same
procedure of the reasoning of the human brain through the incorporation of skills to deal with
inaccurate and uncertain situations.
In general, industrial processes to contain many nonlinearities and may be affected by external
disturbances. These disturbances can damage the performance of the system as a whole and this
makes a major challenge with regarding to control of certain variables of a system, so that its
dynamics is satisfactory even in presence of disturbances,nonlinearities and uncertainties in
the plant model.
However, fuzzy logic is able handle with nonlinearities of a process and can imitate the human
procedure in its decisions.
The first publication on fuzzy logic emerged in the context fuzzy sets theory introduced by Lotfi
Zadeh in 1965 [1], who created logic combining the concepts of classical logic and Lukasiewicz's
sets defining the membership degrees that allow an element partially to belong to more than one
cluster simultaneously [2]. In short, fuzzy logic can be defined as a mathematical treatment of
certain linguistic terms, such as approximately, very high, very low, around, among others.
Some studies have been done applying these two inference methods: Mamdani and Takagi-
2. International Journal of Fuzzy Logic Systems (IJFLS) Vol.11, No.2/3/4, October 2021
20
Sugeno. As example, in [6] is presented a comparative study of the application of these two
methods to predictive the traffic flow. In [7] the authors present a comparative study between
Mamdani and Takagi- Sugeno inference methods to control speed of an induction motor drive
system. In [8] a comparison between Mamdani and Takagi- Sugeno inference systems is realized
for dynamic spectrum allocation. Authors,in [9], applied fuzzy controller for to control position of
each finger of a robotic hand and in [10] authors used fuzzy controllers to control vibrations of 3
cars crane system, among others.
In this way, in this work will be used fuzzy set theory to position control of a servomechanism
even in presence of disturbances and nonlinearities of the system. More precisely, two
inference methods will be used for fuzzy position control: the Mamdani method and the Takagi-
Sugeno method. Simulations of these two fuzzycontrollers applied to the mathematical model of
the servomechanism will be realized and an application of these two fuzzy controllers will be
realized in the real plant, whererobustness tests will be done.
This paper is organized as follows: in section 2 a review of fuzzy concepts and Mamdaniand
Takagi- Sugeno inference methods are presented; in the section 3 the methodology adopted and
the results of the simulation and practical application are presented; in section 4 the conclusions
are recorded.
2. THEORY REVIEW
Fuzzy logic deals with vague or nebulous information, such as: very hot, warm, very high, among
others. This theory has skill of handle with imprecise and vagueness situations found in the real
world. So, fuzzy logic allows a certain element belong to more than one class simultaneously, but
with different membership degrees that are numbers contained in the range [0;1], where the
number 0 represents absence of similarity, the number 1 represents total similarities and numbers
between 0 and 1 represent partial similarities.
As an example, consider the Figure 1 that represents a set of numbers in the range [0;10]. What
is the set of numbers approximately equal to 5?
Analyzing the Figure 1 it’s possible to claim that the number 5 belongs to the set with maximum
similarity, because it is the number itself. However, there is no certainty ifthe number 4.5
belongs to the set of numbers approximately equal to 5. In this case, the answer is not unique and
objective, because belonging or not may depend on the type ofproblem in question. However, in
this case, it can be affirmed that 4.5 belongs to the set of numbers approximately equal to 5 with a
degree of similarity approximately equal to 0.9.
3. International Journal of Fuzzy Logic Systems (IJFLS) Vol.11, No.2/3/4, October 2021
21
Figure 1. Cluster of the numbers approximately equal to 5
As can be seen, Figure 1 show a gaussian function that consists of numbers close to 5. Thus,
fuzzy logic theory represents a real element in a membership degree with regardto given class.
There are numerous functions to represent a class, such as: triangular, gaussian, trapezoidal,
among others. These functions are called membership functions and each class is called by a
linguistic variable that represents a certain fuzzyness.
Through these functions it is possible to perform some operations with fuzzy sets, such as
intersection, union and complement in order to obtain an interrelationship betweenthe system
variables. In addition, membership functions are fundamental elements ofthe fuzzy system [3].
Briefly, Figure 2 represents a fuzzy system
Figure 2. FuzzySystem
a. Input Variables: real values (crisp numbers) such as height equal to 10 meters, temperature
equal to 75 degrees Celsius.
b. Fuzzifier: the crisp values are transformed into degrees of similarity.
c. Fuzzy Rule Base: the fuzzy rules, also called "IF-THEN" rules represent the knowledge of
the system and information about the parameters of the membership functions (fuzzy sets).
The relationship between input and output is produced through of therules.
d. Fuzzy Inference: Performs fuzzy set mapping and interprets input values based on a ruleset
and assigning a value to the output vector, that is, determining how rules are activated and
combined.
e. Defuzzifer: this step converting a fuzzy value into a real number (crisp value). The mostused
method is based on the calculation of the area centroid of a fuzzy set, where the output value
is the center of gravity of the distribution function of possibility of the control action.
f. Output variables: Output in real values.
Clearly, can be noted that the fuzzy controller is a fuzzy system. However, there are two classes
of fuzzy controllers very utilized in the practice: the fuzzy controller based on Mamdani's
4. International Journal of Fuzzy Logic Systems (IJFLS) Vol.11, No.2/3/4, October 2021
22
inference method [11] and another controller based on Takagi-Sugeno’s inference method [12].
The Mamdani method has its rules described according toequation 1 [4].
(1)
In this case, the consequential is a fuzzy number, defined by a membership function which must
go through the defuzzification process. One of defuzzification methods is the center- of- gravity
of the means of areas from each rule represented. Equation 2 represents this process [4].
(2)
On the other hand, Takagi- Sugeno's inference method work with rules that follow the format
described in equation 3 [5]:
(3)
As can be seen in equation 9 the consequence is a function of the linguistic variables of the input,
and the values from the y function is weighted by the membership degree from the
antecedent, as showed in equation 4 [5].
(4)
As can be seen, in Takagi- Sugeno’s inference method, the defuzzification step does notexist once
equation 10 produces a crisp value. In this work, two fuzzy systems (or fuzzycontrollers) will be
developed to control the position of a servo mechanism, one based on Mamdani’s inference
method and another controller based on Takagi- Sugeno's inference method. Some robustness
tests will be realized in the practical application in the real plant.
3. RESULTS
In this work, the fuzzy controller considered has the configuration shown in Figure 3, where error
and derivative of error are the inputs and output is the control effort.
5. International Journal of Fuzzy Logic Systems (IJFLS) Vol.11, No.2/3/4, October 2021
23
Figure 3. Fuzzy System
The table 1 shows the input and output data, as well as the linguistic values and its
respective notation.
Table 1. Variablesandlinguistic values
Linguistic Variable: Error (E)
Linguistic Value Notation
very negative VN
negative N
null NN
positive P
very positive VP
Linguistic Variable: Derivative of Error (DE)
Linguistic Value Notation
Small S
Large L
Linguistic Variable: Control Effort (CE)
Linguistic Value Notation
Very Negative VN
Negative Medium NM
Medium M
Positive Medium PM
Very Positive VP
The Figure 4 shows the block diagram utilized in simulation, where the block called dead
zone is representing the friction existing in the motor.
6. International Journal of Fuzzy Logic Systems (IJFLS) Vol.11, No.2/3/4, October 2021
24
Figure 4. Fuzzy Control System for the simulation
Figure 4 represents a position control system, and the work consists of two steps: in order to
assessing and validating the proposed controllers, simulation is done using the Matlab software.
After, the fuzzy controllers are applied in the real plant where some robustness tests will be done
in the presence uncertainties and disturbances. The table 2 summarizes the rules set proposed
when Mamdani inference method is applied.
Table 2. Mamdani rules
NVL NL N PL PVL
S X X PM X X
L X X NM X X
X VN NM M PM VP
In table 2, X means not significant, that is, it does not significantly interfere in the dynamics of
the system. The membership functions utilized were obtained after many tests and are shown in
figures 5, 6 and 7.
Figure 5. Membership functions: Error
7. International Journal of Fuzzy Logic Systems (IJFLS) Vol.11, No.2/3/4, October 2021
25
Figure 6. Membership functions: Derivative of error
Figure 7. Membership functions: Output
The rules defined in Takagi- Sugeno inference method is shown in table 3.
Table 3. Takagi-Sugeno rules
if And Then control
effort is
Error is null - 0
Error is negative - -5
Error is positive - 5
Error is positive
medium
-
Error is negative
medium
-
Error is null Derivativeof
error
Error is null Derivativeof
error
8. International Journal of Fuzzy Logic Systems (IJFLS) Vol.11, No.2/3/4, October 2021
26
where 𝑥1 = error and 𝑥2 = derivative of error
These rules were obtained through of knowledge of plant after many tests and changing rules and
membership functions until to obtain a satisfactory response.
3.1. Simulation Results
The simulations were done through of Matlab software and considering mathematical model of
the plant as shown in Figure 4. The system response to the step as a set point and applying
Mamdani's inference method is shown in Figure 8.
Figure 8. Response to the step of value equal to 2- Mamdani
Figure 9 shows the output of the system when is applied Takagi- Sugeno's inference method.
Figure 9. Response to the step of value equal to 2- Takagi- Sugeno
As can be seen in figures 8 and 9, the Takagi- Sugeno inference method presents better results
than Mamdani inference with regard to the steady state error and settling time. Table 4 show the
approximated values of performance of the system.
9. International Journal of Fuzzy Logic Systems (IJFLS) Vol.11, No.2/3/4, October 2021
27
Table 4. Comparison of Performance- Simulation
Output Performance
Mamdani Takagi- Sugeno
Error 0.3 0.07
Settling Time 2 seconds 1.5 second
Overshoot 0% 0%
This application in simulation shows that the fuzzy controller proposed can be promising in
application in a real plant. It is known that mathematical model is an approximation of the real
plant and do not consider non- linearities, backlash effect and some parameters of the system
when compared to the real plant. So, becomes necessary to apply the fuzzy controllers obtained in
the real plant which contain non- linearities, backlash effect due to the gears and some noises.
3.2. Experimental Results
The fuzzy controllers shown in the preview section will be implemented in a real systemthrough
data acquisition process using the data acquisition toolbox contained in Matlab software. Here
was utilized a real servomechanism, a data acquisition board National Instruments 6221- 37 pin
installed in the computer and an interface National Instruments for communication between
Simulink and real plant. The Figure 9 illustrates a basic idea of the configuration utilized.
Figure 9. Layout for tests in real plant
Figure 10 shows the model utilized in the Simulink/ Matlab using data acquisition. The set point
is a square wave form of 0.2Hz and peak value equal to 2.
10. International Journal of Fuzzy Logic Systems (IJFLS) Vol.11, No.2/3/4, October 2021
28
Figure 10. Fuzzy Control System
The membership functions of the inputs and outputs are showed in figures 11, 12 and 13,
respectively. In this practical application was necessary to change membership functions.
Figure 11. New membership functions: Error
Figure 12. New membership functions: Derivative of error
11. International Journal of Fuzzy Logic Systems (IJFLS) Vol.11, No.2/3/4, October 2021
29
Figure 13. New membership functions: Output
The rules adopted are shown in table 5.
Table 5. Mamdani rules
if And Then control effort is
Error is null - null
Error is
negative
- negative
Error is positive - positive
Error is positive
medium
- positive medium
Error is
negativemedium
- negative medium
Error is null Derivative of
error
positive medium
Error is null Derivative of
error
negative medium
The figures 14 and 15 show the results obtained without disturbance and with disturbance,
respectively.
12. International Journal of Fuzzy Logic Systems (IJFLS) Vol.11, No.2/3/4, October 2021
30
Figure 14. Response of the real system using the Mamdani inference method without disturbance
Figure 15. Response of the real system using the Mamdani inference
method with the addition ofdisturbance
The same procedure was realized applying the Takagi- Sugeno’s inference method. Inthis case,
the rules that produced the best results are shown in table 6.
13. International Journal of Fuzzy Logic Systems (IJFLS) Vol.11, No.2/3/4, October 2021
31
Table 6. Takagi-Sugeno rules
if And Then control effort is
Error is null - 0
Error is
negative
- -3
Error is positive - 3
Error is positive -
medium
Error is
negativemedium
-
Error is null Derivative of error
Error is null Derivative of error
The figures 16 and 17 shown the response of the system without disturbance and with
disturbance, respectively.
Figure 16. Response of the real system using the Takagi-Sugeno inference method without disturbance
14. International Journal of Fuzzy Logic Systems (IJFLS) Vol.11, No.2/3/4, October 2021
32
Figure 17. Response of the real system using the Takagi-Sugeno inference method with theaddition of
disturbance
As can be seen in the experimental results presented, Takagi- Sugeno inference method presents a
better result than Mamdani inference method in the application proposed in this work. As can be
seen in figures 16 and 17, when is utilized the fuzzy controller based in the Takagi- Sugeno
inference method, the response of the system is faster than fuzzy controller based in the Mamdani
inference method. Table 7 show the approximated values of performance of the system
Table 7. Comparison of Performance- Simulation
Output Performance
Mamdani Takagi- Sugeno
Error 0.56 0.22
Settling Time 1.5 seconds 0.5 second
Overshoot 3% 0%
Furthermore, the results indicate that for the application proposed here, the controller based on
Takagi- Sugeno inference method seems has more robustness and precision when compared to
the Mamdani inference method.
4. CONCLUSIONS
In this work, was proposed a position control using a fuzzy controller. The applicationis based
in two controllers: a fuzzy controller using Mamdani inference method and another controller
using Takagi- Sugeno inference method. Firstly, was done a simulation using the
15. International Journal of Fuzzy Logic Systems (IJFLS) Vol.11, No.2/3/4, October 2021
33
mathematical model of a servomechanism in order to assessing and validating the proposed
controllers. After, the two controllers were applied in real plant, where nonlinearities, noises and
backlash effect are present in the system.
Analyzing the responses presented by the simulations, Takagi-Sugeno inference methodpresents
low settling time and very low steady state error. When comparing the results obtained with the
experiments in real plants, was found that the method of inference Takagi-Sugeno presents
greater robustness, less steady state error and less settling time even in the presence of
disturbance and nonlinearities of the system. For both methods, changes in the membership
functions were necessary in practical application due to some non-linearities, noises and backlash
effect.
So, in the application proposed in this work, Takagi- Sugeno inference method toposition
control in the presence of uncertainties, disturbance and nonlinearities, produces a better result
when compared with Mamdani inference method Here, the control based on Takagi- Sugeno
inference method shown more robustness and better relative stability. As future study, can be
very promising the application of control basedon fuzzy type- 2.
REFERENCES
[1] Zadeh L. A. Fuzzy sets, Information and Control, p. 338–353, 1965.
[2] Zimmermann H. J. Fuzzy Set Theoryand its Aplication. Kluwer Academic, Boston, 1996.
[3] Altrok, C.V. Fuzzy Logic & Neurofuzzy Applications Explained, Prentice Hall,New Jersey, 1995.
[4] Mamdani E. H; Assilian S. An Experiment in Linguistic Synthesis with a Fuzzy Logic Controller. Int.
J. Man- Machine Studies, v.7, p. 1-13, 1975.
[5] Takagi T., Sugeno M. Fuzzy Identification of Systems and Its Applications to Modeling and Control.
IEEE Transactions on Systems, Man, and Cybernetics, v.15, 1985.
[6] Wang Y., Chen, Y. A Comparison of Mamdani and Sugeno Fuzzy InferenceSystems for Traffic Flow
Prediction. Journal of Computers, v.9, n. 1, 2014.
[7] Ariff, R.M.; Hanafi, D.; Utomo, W.M.; Sim, S.Y.; Bohari, A.A. Comparison of Sugeno-Type and
Mamdani-Type Speed Controller for Induction Motor Drive System. In Proceedings of the 3rd
International Conference on Computer Engineering and Mathematical Sciences (ICCEMS 2014),
Langkawi, Malaysia,4–5 December 2014; pp. 387–391.
[8] Subhedar M, Birajdar G. Comparison of Mamdani and Sugeno inference systems for dynamic
spectrum allocation in cognitive radio networks. Wireless Pers Commun.; v. 71, p.805–819, 2013.
[9] Rakovic M. et al. Fuzzy Position- velocity Control of Underactuated Finger ofFTN Robot Hand.
Journal of Intelligent and Fuzzy Systems, v. 34, 2018.
[10] Yildirim S. Angular Position Control of 3- Cars Crane System Using ProposedFuzzy- PID Controller.
Recent Innovations in Mechatronics, v.7, 2020.
[11] Mamdani E. H. Application of Fuzzy Logic to Approximate Reasoning Using Linguistic Synthesis.
IEEE Transactions on Computers, v. C26, p. 1182- 1191,1977.
[12] Takagi T., Sugeno M. Fuzzy Identification of Systems and its Applications to Modeling and Control.
IEEE Transactions on Systems, Man, and Cybernetics, v.SMC-15, p. 116- 132, 1985.