Academia.eduAcademia.edu

Outline

Title
Abstract
Introduction
Conclusion
References
All Topics
Mathematics
Probability

Unified Structure and Parameter Identification of Fuzzy Models

Profile image of Dimitar FilevDimitar Filev

2002, Systems, Man and Cybernetics, IEEE …

https://doi.org/10.1109/21.247902
visibility

…

description

8 pages

link

1 file

Abstract

The unified approach to fuzzy modeling developed in this correspondence addresses the problems of structure and parameter identification of fuzzy models. It demonstrates an alternative view to structure identification, transforming the problem of structure identification to estimation of the distribution of input space. A new concept of sample probability distributions (SPD) is introduced and a family of SPD is constructed. This allows us to simplify the problem of structure identification by replacing identification of membership functions of input variables with identification of the centers of cluster-like regions. The fuzzy model complex of fuzzy model is also discussed in connection with the modeler's confidence and two types of confidentpriori and a posteriori confidence-are also suggested. The identification problem is solved also under the additional requirement of simplification of the model structure. A learning algorithm realizing structure and parameter identification of QLFM with the simplest structure is proposed.

Related papers

Incorporating prior knowledge in fuzzy model identification
Robert Babuska

International Journal of Systems Science, 2000

This paper presents an algorithm for incorporating a priori knowledge into data-driven identification of dynamic fuzzy models of the Takagi-Sugeno type. Knowledge about the modelled process such as its stability, minimal or maximal static gain, or the settling time of its step response can be translated into inequality constraints on the consequent parameters. By using input-output data, optimal parameter values are then found by means of quadratic programming. The proposed approach has been applied to the identification of a laboratory liquid level process. The obtained fuzzy model has been used in model-based predictive control. Real-time control results show that when the proposed identification algorithm is applied, not only physically justified models are obtained, but also the performance of the model-based controller improves with regard to the case where no prior knowledge is involved.

View PDFchevron_right
Using a priori knowledge in fuzzy model identification
Ferenc Szeifert

International Journal of Systems Science, 2000

This paper presents an algorithm for incorporating a priori knowledge into data-driven identification of dynamic fuzzy models of the Takagi-Sugeno type. Knowledge about the modelled process such as its stability, minimal or maximal static gain, or the settling time of its step response can be translated into inequality constraints on the consequent parameters. By using input-output data, optimal parameter values are then found by means of quadratic programming. The proposed approach has been applied to the identification of a laboratory liquid level process. The obtained fuzzy model has been used in model-based predictive control. Real-time control results show that when the proposed identification algorithm is applied, not only physically justified models are obtained, but also the performance of the model-based controller improves with regard to the case where no prior knowledge is involved.

View PDFchevron_right
Discovery of Fuzzy Models from Observation Data
Antoni Wolski

Methods for automatic identification of fuzzy models for the purposes of realtime industrial process monitoring are studied and tested. Theoretical fuzzy and neurofuzzy approaches to identification of Mamdani and Takagi-Sugeno inference models are summarized. Support of fuzzy inference in the active database system RapidBase is discussed. Commercial products Matlab and fuzzyTech are tested in a case study of predicting abnormal states in a waste water treatment plant. The most challenging part of the modeling turns out to be the structural identification, that is the derivation of the rule format and the selected variables. Best results are produced, in Matlab, by using neurofuzzy learning (ANFIS) together with the sequential forward search and, in fuzzyTech, with the learning of degree of rule support. Applicability of the studied methods to automatic extraction of RapidBase fuzzy monitoring models from measurement data is discussed. FUME Project Discovery of Fuzzy Models...

View PDFchevron_right
TS fuzzy model identification by a novel objective function based fuzzy clustering algorithm
Tanmoy Dam

A Fuzzy C Regression Model (FCRM) distance metric has been used in Competitive Agglomeration (CA) algorithm to obtain optimal number rules or construct optimal fuzzy subspaces in whole input output space. To construct fuzzy partition matrix in data space, a new objective function has been proposed that can handle geometrical shape of input data distribution and linear functional relationship between input and output feature space variable. Premise and consequence parameters of Takagi-Sugeno (TS) fuzzy model are also obtained from the proposed objective function. Linear coefficients of consequence part have been determined using the Weighted Recursive Least Square (WRLS) framework. Effectiveness of the proposed algorithm has been validated using a nonlinear benchmark model.

View PDFchevron_right
Fuzzy modeling via optimal fuzzy clustering
Christos Kalloniatis

2004

Abstract: This paper introduces a new method for fuzzy modeling based on set of input-output data pairs. The method consists of a sequence of steps aiming towards developing a Sugeno-type fuzzy model of optimal structure. In the first place, the algorithm uses the fuzzy c-means to classify all the input training data vectors into a predefined number of clusters. The centers of these clusters are further processed by using optimal fuzzy clustering, which is based on the weighted fuzzy c-means algorithm.

View PDFchevron_right
Identification of Key Variables Using Fuzzy Average With Fuzzy Cluster Distribution
Kermit Davis

IEEE Transactions on Fuzzy Systems, 2000

Identification of the significance of input variables is very important for complex systems with high-dimensional input space. In this paper, a method using fuzzy average with fuzzy cluster distribution is proposed. To avoid the interference of different distributions of the sampling data, the distribution of fuzzy clusters in the sampling data is considered, instead of the original data set. To discover the input-output relationship, the methods of fuzzy rules and fuzzy C-means are first used to partition the original sampling data set into fuzzy clusters. A new data set with the same distribution of the fuzzy clusters is produced. The fuzzy average method is then applied to the new data set. By doing so, the interference of distribution of the original sampling data is removed. This method is straightforward and computationally easy. The performance is tested on both benchmark data and real-world data.

View PDFchevron_right
Identifying a fuzzy model by using the bipartite membership functions
Yo-Ping Huang

Fuzzy Sets and Systems, 2001

The gradient descent method and genetic algorithms have been widely used to reÿne fuzzy models constructed for the given data. This paper approaches from another viewpoint to adjusting the fuzzy model built for the preprocessed data. The membership functions deÿned for each premise variable are equally distributed and ÿxed in the transformed domain. To better identify the fuzzy model, either the transformation functions or consequent parts of fuzzy rules or both need to be optimized. Since adjusting a rule to satisfy one pattern may deteriorate the others performance and result in a lengthy tuning process, we then treat each triangular membership function as two disjoint ones such that each fuzzy rule is divided into mutually independent rules. This in turn beneÿts the reÿnement of consequent parts in the fuzzy rules since adjusting a rule will not a ect the others. Not only the simulation results from the proposed model will be demonstrated but also the results from the conventional approaches will be given for comparisons. We use the least squared method to calculate the desired consequent real numbers for the data located in the same region of transformed domain. The conformity of the after-tuned consequent parts in the fuzzy rules with the desired values further veriÿes the e ectiveness of the presented methodology.

View PDFchevron_right
Fuzzy Estimation Of Parameters In Statistical Models
mahmood taheri

2008

Using a set of confidence intervals, we develop a common approach, to construct a fuzzy set as an estimator for unknown parameters in statistical models. We investigate a method to derive the explicit and unique membership function of such fuzzy estimators. The proposed method has been used to derive the fuzzy estimators of the parameters of a Normal distribution and some functions of parameters of two Normal distributions, as well as the parameters of the Exponential and Poisson distributions.

View PDFchevron_right
Incorporating Prior Knowledge in Fuzzy -Regression Models – Application to System Identification
Janos Abonyi

Proceedings of the INTCOM’00 Tempus Symposium on Intelligent Systems in Control and Measurement, 2000

The identification of fuzzy c-regression models (FCRM) suffers from several problems characteristic of all calculus-based optimization methods, including good initialization, avoiding local minima and determining the number of clusters. This paper presents a grey-box approach that can solve the above-mentioned problems with the use of prior knowledge based constrained prototypes. The proposed approach has been applied to system identification, where the FCRM is used to initialize a Takagi-Sugeno fuzzy model of a nonlinear dynamic process. An example is shown to illustrate how knowledge about the type of nonlinearity can be incorporated into the FCRM used in the identification procedure.

View PDFchevron_right
A random sets-based method for identifying fuzzy models
Luciano Sánchez

Fuzzy Sets and Systems, 1998

The nature of interference sources in signal processing is a key problem in many applied disciplines. These interferences are often modelled by random processes, although it has been shown that many models can be favourably modified when some of the uncertainty sources are treated as fuzzy experiments. Following this spirit, the objective of this paper is to build a mathematical model which explains a set of imprecise measurements taken on a physical system. Furthermore, it is assumed that the effect of unmodelled inputs to the system can be regarded as a random process, but the imprecision in the measures is better described by means of a possibility distribution. (~) 1998 Elsevier Science B.V. All rights reserved.

View PDFchevron_right

References (14)

  1. E. Bauman, A. Dorofeyuk, and D. Filev, ''Fuzzy identification of nonlinear dynamical systems," in Proc. Znt. Con$ on Fwzy Logic and Neural Nets., July 1990, pp. 895-898.
  2. J. Bezdek, Pattern Recognition with Fuuy Objective Function Algo- rithms. New York: Plenum, 1981.
  3. D. Filev, "Fuzzy modelling of complex systems," Znt. J. Approximate Res., vol. 5, pp. 281-290, 1991.
  4. -, "Towards the concept of quasilinear fuzzy systems," in Proc. In?.
  5. Con$ on Fuzzy Logic and Neural Nets, Iizuka, Ed., 1990.
  6. D. Filev and P. Angelov, ''Fuzzy optimal control," Fuuy Sets Syst., vol. 47, pp. 151-156, 1992.
  7. K. Fukunaga, Introduction to Statistical Pattern Recognition. New York: Academic Press, 1990.
  8. I. Hayashi, H. Normura, and N. Wakami, "Learning control of inverted pendulum system by neural network driven fuzzy reasoning," in Proc. 2nd Joint Technology Workshop on Neural Networks and Fwzy Logic, NASA, Houston, TX, Apr. 1990. [SI -, "Artificial neural network driven fuzzy control and its application to the learning of inverted pendulum system," in 3rd ZFSA Congr., Seattle, WA, 1989, pp. 61M13.
  9. A. G. Ivakhnenko, V. N. Vysotskiy, and N. A. Ivakhnenko, "Principal versions of the minimum bias criterion for a model and an investigation of their noise immunity," Sov. Automat. Contr., vol. 11, pp. 2745, 1978.
  10. M. Sugeno and G. T. Kang, "Fuzzy modeling and control of multilayer incinerator," Fuuy Sets Syst., vol. 18, pp. 329-346, 1986. 1111 -, "Structure identification of fuzzy model," Fuuy Sets Syst., vol.
  11. T. Takagi and M. Sugeno, "Derivation of fuzzy control rules from human operator's actions," in Proc. ZFAC Symp. on Fuuy Information, Knowledge Representation and Decision Analysis (Marseilles, France, July 1983), pp. 56-60. [ 131 -, "Fuzzy identification of systems and its applications to modeling and control," IEEE Trans. Syst., Man, Cybern., vol. SMC-15, pp. 116-132, 1985.
  12. H. J. Zimmermann, "Fuzzy mathematical programming," Comput. Oper. Res., vol. 10, pp. 291-298, 1983.
  13. D. Filev and R. R. Yager, "A generalized defuzzification method via BAD distribution," Int. J. Intell. Syst., vol. 6, pp. 687-697, 1991.
  14. R. R. Yager, "A model of participatory learning," ZEEE Trans. Syst., Man, Cybern., vol. 20, pp. 1229-1234, 1990. 28, pp. 15-33, 1988.

Related papers

A novel clustering method for fuzzy model identification
meena tushir

TENCON 2009 - 2009 IEEE Region 10 Conference, 2009

Takagi-Sugeno models are an important class of fuzzy rule based oriented models, generally used for prediction and control. Fuzzy clustering is one of effective methods for identification. In this method, we propose to use a fuzzy clustering method (Kernel based fuzzy c-means method) for automatically constructing a multi-input fuzzy model to identify the structure of a fuzzy model. To clarify the advantages of the proposed method, it also shows some examples of modeling, among them a model of a human operator's control action and a qualitative model to explain the trends in the time series data of the price of a stock.

View PDFchevron_right
Identification of fuzzy models
José RAGOT

1994

ABSTRACT The objective of this work is to describe a numerical technique to identify parameters of a fuzzy model. When this model and the membership functions of the input variables are continuously differentiable, we show that the estimation of parameters can be performed with a two-levels hierarchical algorithm, comprising the estimation of the model parameters and the estimation of the membership functions parameters. The proposed algorithm is then applied to an example describing a non-linear system.

View PDFchevron_right
Fuzzy Model Identification Using Support Vector Clustering Method
aysegul ucar

Lecture Notes in Computer Science, 2003

can provide cluster boundaries of arbitrary shape based on a Gaussian kernel abstaining from explicit calculations in the high-dimensional feature space. This allows us to apply the method to the training set for building a fuzzy model. In this paper, we suggested a novel method for fuzzy model identification. The premise parameters of rules of the model are identified by the support vector clustering method while the consequent ones are tuned by the least squares method. Our model does not employ any additional method for parameter optimization after the initial model parameters are generated. It gives also promising performances in terms of a large number of rules. We compared the effectiveness and efficiency of our model to the fuzzy neural networks generated by various input spacepartition techniques and some other networks.

View PDFchevron_right
New approaches on structure identification of fuzzy models: Case study in an electro-mechanical system
Nicolas Lori

1996

The main problem in design fuzzy models is to identify their structure. This means recognise the variables that better characterise the system dynamics, the number of membership functions partitioning each variable, as well as their distribution and fuzziness degree. This work presents two pre-processing methods for structure identification of fuzzy models. The first approach uses the statistical method of Principal Component Analysis (PCA). The second one uses a clustering technique called autonomous mountain-clustering method. The statistical method of Principal Component Analysis helps to select the variables that dominate the system dynamics. Besides, this method contributes to design fuzzy models with better performance. The second approach identifies the fuzzy model order. That is, the method identifies the number of membership functions attributed to each variable, as well as their position and width. So, the autonomous mountain-clustering eliminates the usual "trial-and-error" mechanism. The pre-processing methods can be used to initialize the neuro-fuzzy techniques and therefore accelerate their learning process. We test these methods using a simple learning process applied to extract the fuzzy model of an experimental electro-hydraulic system. The results show that a good modeling capability is achieved without employ any complicated optimisation procedure to structure identification.

View PDFchevron_right
Supervised Hierarchical Clustering in Fuzzy Model Identification
Luka Teslić, Oliver Nelles

IEEE Transactions on Fuzzy Systems, 2000

This paper deals with the problem of fuzzy nonlinear model identification in the framework of a local model network (LMN). A new iterative identification approach is proposed, where supervised and unsupervised learning are combined to optimize the structure of the LMN. For the purpose of fitting the cluster-centers to the process nonlinearity, the Gustafsson-Kessel (GK) fuzzy clustering, i.e., unsupervised learning, is applied. In combination with the LMN learning procedure, a new incremental method to define the number and the initial locations of the cluster centers for the GK clustering algorithm is proposed. Each data cluster corresponds to a local region of the process and is modeled with a local linear model. Since the validity functions are calculated from the fuzzy covariance matrices of the clusters, they are highly adaptable and thus the process can be described with a very sparse amount of local models, i.e., with a parsimonious LMN model. The proposed method for constructing the LMN is finally tested on a drug absorption spectral process and compared to two other methods, namely, Lolimot and Hilomot. The comparison between the experimental results when using each method shows the usefulness of the proposed identification algorithm.

View PDFchevron_right

Related topics

  • Probability Distribution & Appli...
  • Parameter Identification

    • Cited by

    Wavelet-neuro-fuzzy control of hybrid building-active tuned mass damper system under seismic excitations
    Yeesock Kim, Young-Jin Cha

    Journal of Vibration and Control, 2013

    This paper investigates the multi-objective optimization of active control systems for vibration control of three-dimensional (3D) high-rise buildings under a variety of earthquake excitations. To this end, a novel multi-objective genetic algorithm is developed through the integration of the best features of a non-dominated sorting II (NS2) genetic algorithm (GA) and an implicit redundant representation (IRR) GA. The proposed NS2-IRR GA finds not only minimum distributions of both actuators and sensors within structures, but also minimum dynamic responses of 3D structures. Linear quadratic Gaussian controllers, hydraulic actuators and accelerometers are used for implementation of active control systems within the 3D buildings. To demonstrate the effectiveness of the proposed NS2-IRR GA, two 3D building models are investigated using finite element methods, including low-and high-rise buildings. It is shown that the proposed NS2-IRR GA is effective in finding not only optimal locations and numbers of both actuators and sensors in 3D buildings, but also minimum responses of the 3D buildings. The simulation also shows that the control performances of the proposed approach significantly enhance those of the engineering judgment oriented benchmark layout, which is validated by comparisons of each performance using the same number of actuators.

    View PDFchevron_right
    Building fuzzy-qualitative models for simulation and control
    Jorge Barreto

    Simulation Practice and Theory, 1996

    A procedure for building fuzzy-qualitative models of dynamical systems is described and the influence on the modelling accuracy of several factors related to quantity spaces and membership functions involved in fuzzification and/or defuzzification interfaces is investigated via a simulation analysis. It is shown that using multi-valued universes of discourse and introducing fuzziness allow accurate fuzzy-qualitative simulations. Simulation results for linear and nonlinear first-order systems and for second-order systems with real or complex poles are presented and discussed. ]. Such models are also useful for teaching and instruction purposes, in particular as explanatory tools for process operators or for scientists with a low mathematical background; see e.g. [10,38,39,42]. There are several approaches to building qualitative models, depending on the purpose of the model and some behavioural properties such as precision, accuracy and uncertainty [5,28] ; one of these approaches is based on the use of a fuzzy-qualitative transposition of numerical discrete-time models [ 19,30,40], which can be an answer to some problems presented in the original purely qualitative approach . An attractive feature of this fuzzy-qualitative approach is that it can be used in model-based control systems [18] as well as for relatively accurate simulation of dynamical systems [ 19,36]. Obviously, the accuracy of such a qualitative simulation, in other words the closeness of the model behaviour to that of the modelled system, depends on several factors, in particular on the number of distinctions supported by the description of the behaviour [37] and on the functions and operators used in fuzzification and defuzzification processes [1,19], as it will be shown in the next sections.

    View PDFchevron_right
    Fuzzy Modeling and Controlling of a Fan-Coil
    Christian Ghiaus

    International Journal of Solar Energy, 2001

    Fuzzy models and controllers are represented by if-then rules and thus can provide a user-friendly and understandable representation of combined quantitative and qualitative description. The qualitative rules result in a quantitative non-linear controller well suited to nonlinear systems controlling thermal comfort with vague defined objectives as fan-coils used in solar energy systems. The fuzzy models are achieved through identification by varying the inputs so that the fan-coil reaches the states encountered in normal operation. These models may be used for control or for simulation. On its domain of validity, the fuzzy controller behaves better then a classical controller. In fact, the main advantage of fuzzy controller is the easiness of introducing operating modes and poor defined objectives specific for solar energy systems such as freeze and overtemperature protection, or draining.

    View PDFchevron_right
    580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved