Evolving Granular Fuzzy Model-Based Control of Nonlinear Dynamic Systems

2015 ◽  
Vol 23 (4) ◽  
pp. 923-938 ◽  
Author(s):  
Daniel Leite ◽  
Reinaldo M. Palhares ◽  
Victor C. S. Campos ◽  
Fernando Gomide
Keyword(s):  
Dynamic Systems ◽  
Nonlinear Dynamic ◽  
Fuzzy Model ◽  
Nonlinear Dynamic Systems ◽  
Model Based Control ◽  
Model Based

Application of a Fuzzy Model to the Task of Filtering in Nonlinear Dynamic Systems

2020 ◽  
pp. 85-100
Author(s):  
N.P. Demenkov ◽  
D.M. Tran
Keyword(s):  
Kalman Filter ◽  
Dynamic Systems ◽  
Nonlinear Dynamic ◽  
Process Model ◽  
Unscented Kalman Filter ◽  
Fuzzy Model ◽  
Nonlinear Dynamic Systems ◽  
S Model ◽  
Takagi Sugeno ◽  
Softening Coefficient

In this paper, we consider various approaches to the problem of filtering in nonlinear dynamic systems and their algorithms. The Strong Tracking Unscented Kalman Filter, based on the combination of Unscented Kalman Filter and Strong Tracking Kalman Filter, provides stability to the uncertainty of the process model directly using a suboptimal scaling factor (SSF). The softening coefficient is part of the SSF and it improves the smoothness of the system state assessment. The coefficient is determined empirically and is included in the entire filtering process, which leads to a loss of accuracy in the time segments in which the process model is defined. The paper explores the use of Takagi --- Sugeno fuzzy model (T-S model) to adjust in real time the softening coefficient when the object's dynamics changes. As a result of a comparative analysis of the accuracy of the studied filters for the nonlinear model, it was found that the new filter using a fuzzy logical adaptive system possesses good smoothness of assessment and the greatest accuracy

FUZZY SUPERVISED NONLINEAR PID CONTROL OF A CLASS OF UNKNOWN NONLINEAR SYSTEMS

2010 ◽  
Vol 19 (08) ◽  
pp. 1847-1862 ◽  
Author(s):  
L. TOUNSI REKIK ◽  
MOHAMED CHTOUROU
Keyword(s):  
Dynamic Systems ◽  
Fuzzy System ◽  
Nonlinear Dynamic ◽  
Design Method ◽  
Fuzzy Model ◽  
Nonlinear Process ◽  
Nonlinear Dynamic Systems ◽  
Identification Algorithm ◽  
Potential Applications ◽  
Fuzzy Supervisor

Fuzzy control has been successfully applied in many cases to which conventional control algorithms are difficult to be applied. Recently, it was proven that fuzzy systems are capable of approximating any real continuous function to arbitrary accuracy. This result motivates us to use the fuzzy identifiers for nonlinear dynamic systems and then design the fuzzy supervised nonlinear PID controller based on the fuzzy system. There are two main objectives in this paper: (1) We use the Takagi and Sugeno's fuzzy models as an identifier for nonlinear dynamic systems, and derive the identification algorithm, (2) the fuzzy supervisor design method for tracking control is proposed based on this fuzzy system. In order to improve the dynamic response of the closed loop fuzzy model, the optimization of the performance of the fuzzy supervisor will be considered. To prove the potential applications of the proposed strategy, simulation was carried out for the speed control of a DC motor with serial excitation and a first order nonlinear process.

Sign in / Sign up

Export Citation Format

Share Document