Fuzzy Model Identification for Control
Fuzzy Model Identification
Fuzzy model identification is an effective tool for the approximation of uncertain nonlinear systems on the basis of measured data. The identification of a fuzzy model using input-output data can be divided into two tasks: structure identification, which determines the type and number of the rules and membership functions, and parameter identification. For both structural and parametric adjustment, prior knowledge plays an important role. Hence, in this book the rules of the fuzzy system are designed based on the available a priori knowledge and the parameters of the membership, and the consequent functions are adapted in a learning process based on the available input-output data. Hence, this chapter is devoted mainly to the parameteridentification of the proposed fuzzy models, but certain structure identification tools are also discussed.
Fuzzy Model Based Control
This chapter discusses how the proposed fuzzy models can be used in model-based control. The developed Takagi --- Sugeno, Hybrid Fuzzy Convolution and Fuzzy Hammerstein dynamic fuzzy models will be applied in several inversion and linearization-based control schemes. Taking the identification of the Takagi --- Sugeno fuzzy models into account, guidelines will be given as which control configuration is most advantageous.
Process Models Used for Case Studies
In this section the models used in the application examples are presented.
List of Examples (PDF)
This book presents new approaches to the construction of fuzzy models for model-based control. New model structures and identification algorithms are described for the effective use of heterogenous information in the form of numerical data, qualitative knowledge and first-principle models. By exploiting the mathematical properties of the proposed model structures, such as invertibility and local linearity, new control algorithms have been developed which are closely related to inverse model-based control, model predictive control, block-oriented model-based control, and multiple model adaptive control. In this chapter the background and the concept of this framework is described.
Identification for Control
János Abonyi, University of Veszprém, Hungary
January 2003 / 288 pp. / 132 ill. / Hardcover
This book presents new approaches to the construction of fuzzy models for model-based control. New model structures and identification algorithms are described for the effective use of heterogeneous information in the form of numerical data, qualitative knowledge, and first principle models. The main methods and techniques are illustrated through several simulated examples and real-world applications from chemical and process engineering practice.
detailed review of algorithms and approaches developed for modeling and identification for control
numerous illustrations to facilitate the understanding of ideas and methods presented
extensive references give a good overview of the current state of identification and control of dynamic systems and fuzzy modeling, and suggest further reading for additional research
supporting MATLAB and Simulink files, available at the website www.fmt.vein.hu/softcomp, create a computational platform for exploration and illustration of many concepts and algorithms presented in the book (ZIP file of the MATLAB files of Example E2_1-E_49) (E5_1-E5_5 are under developement).
The book is aimed primarily at researchers, practitioners, and professionals in process control and identification, but it is also accessible to graduate students in electrical, chemical, and process engineering. Technical prerequisites include an undergraduate-level knowledge of control theory and linear algebra. Additional familiarity with fuzzy systems is helpful but not required.
Fuzzy Model Structures and their Analysis
This chapter gives introduces fuzzy modeling and describes the structures of fuzzy models utilized throughout this book. The successful control-relevant application of fuzzy models requiresgenerating elements of model-based controllers, like model inversion and linearization. The second part of this chapter presents these useful tools.
Fuzzy Models of Dynamical Systems
Model-based engineering tools require the availability of suitable dynamical models. Consequently, the development of a suitable nonlinear model is of paramount importance. Given the highexpectations of fuzzy models in the area of identification and control, it becomes necessary to analyze and extract control-relevant information from fuzzy models of dynamical processes. Hence, in this chapter after an introduction to the data-driven modeling of dynamical systems, the following characteristics of TS fuzzy models will be analyzed:
- Fuzzy models of dynamical systems
- State-space realization of the model
- Prediction of the equilibrium points
- Stability of the equilibrium points
- Extraction of a linear dynamical model around an operating point
Based on this analysis, new fuzzy model structures
- Hybrid Fuzzy Convolution Model
- Fuzzy Hammerstein Model
will be proposed which can more effectively represent special nonlinear dynamic processes than conventional fuzzy systems.