Embedded Adaptive Fuzzy Controller Based on Reinforcement Learning for DC Motor with Flexible Shaft

2015 ◽  
Vol 40 (8) ◽  
pp. 2389-2406 ◽  
Author(s):  
A. Aziz Khater ◽  
Mohammad El-Bardini ◽  
Nabila M. El-Rabaie
Keyword(s):  
Reinforcement Learning ◽  
Fuzzy Controller ◽  
Dc Motor ◽  
Adaptive Fuzzy Controller ◽  
Adaptive Fuzzy ◽  
Flexible Shaft

scholarly journals Embedded two level direct adaptive fuzzy controller for DC motor speed control

2018 ◽  
Vol 9 (1) ◽  
pp. 65-75 ◽  
Author(s):  
Ahmad M. Zaki ◽  
Mohammad El-Bardini ◽  
F.A.S. Soliman ◽  
Mohammed Mabrouk Sharaf
Keyword(s):  
Fuzzy Controller ◽  
Speed Control ◽  
Dc Motor ◽  
Motor Speed ◽  
Adaptive Fuzzy Controller ◽  
Adaptive Fuzzy

scholarly journals Speed Control of Seperately Excited DC motor for Electric Vehicles (EVs) By Inverse Model Based Fuzzy Learning Controller

2021 ◽  
Author(s):  
mehmet bulut
Keyword(s):  
Fuzzy Controller ◽  
Expert Knowledge ◽  
Dc Motor ◽  
Inverse Model ◽  
Fuzzy Rules ◽  
System Stability ◽  
Model Learning ◽  
Adaptation Mechanism ◽  
Adaptive Fuzzy Controller ◽  
Adaptive Fuzzy

The adaptation mechanism, which adjusts the controller coefficients according to the parameter changes in the system, ensures that the controller is adaptable. Fuzzy logic can be used to calculate the gain coefficients of the controller in the system by using the adaptive fuzzy method instead of a traditional algorithm for the adaptation mechanism. Normally, the rules of a fuzzy controller system are derived from the system's internal structure and system behavior using expert knowledge that has experienced the system. However, it is not possible to derive fuzzy rules based on expert human knowledge for all systems in this way. It is necessary to use different methods to derive fuzzy rules in highly variable behavior and nonlinear systems. In this study, an adaptive fuzzy controller design for dc motor was made using a learning-based reference model learning algorithm using fuzzy inverse model; It has been shown that it is applicable for dc motors with the results obtained. Simulation of the designed system was carried out using the Matlab program, and the behavior of the system was investigated by using constant and variable loads. The results showed that it is satisfactory to drive a dc motor with adaptive fuzzy controller in terms of system stability.

scholarly journals Fuzzy controller, designed by reinforcement learning, for vehicle traction system application

2021 ◽  
Vol 8 (2) ◽  
pp. 168-183
Author(s):  
L. I. Demkiv ◽  
◽  
A. O. Lozynskyy ◽  
V. V. Vantsevich ◽  
D. J. Gorsich ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Fuzzy Controller ◽  
Reference Signal ◽  
Fine Tuning ◽  
External Disturbances ◽  
Adaptive Fuzzy Controller ◽  
Adaptive Fuzzy ◽  
Fuzzy Logic Theory ◽  
Traction System ◽  
Reference Input

In this article, a fuzzy controller tuned by reinforcement learning is proposed. The developed algorithm utilizes a fuzzy logic theory and a reinforcement learning for fine-tuning parameters of the membership function for the fuzzy controller. Apart from the fuzzy controller developed, a fuzzy corrector of reference input (set-point) signal to the controller is applied. The fuzzy corrector changes the input (reference) signal of the system and takes into account an original reference input and type of external disturbances. Thus, the designed fuzzy control that is tuned by reinforcement learning is capable to ensure the stable, optimal, and safe performance of the system and takes into account external disturbances. To verify the performance of the proposed controller, the adaptive fuzzy controller tuned by reinforcement learning is applied to the mathematical model of a wheel locomotion module of an electric vehicle to advance a traction control system. Therefore, the effectiveness of the proposed adaptive fuzzy controller is proven through the simulation results.

scholarly journals Speed Control of Seperately Excited DC motor for Electric Vehicles (EVs) By Inverse Model Based Fuzzy Learning Controller

2021 ◽  
Author(s):  
mehmet bulut
Keyword(s):  
Fuzzy Controller ◽  
Expert Knowledge ◽  
Dc Motor ◽  
Inverse Model ◽  
Fuzzy Rules ◽  
System Stability ◽  
Model Learning ◽  
Adaptation Mechanism ◽  
Adaptive Fuzzy Controller ◽  
Adaptive Fuzzy

The adaptation mechanism, which adjusts the controller coefficients according to the parameter changes in the system, ensures that the controller is adaptable. Fuzzy logic can be used to calculate the gain coefficients of the controller in the system by using the adaptive fuzzy method instead of a traditional algorithm for the adaptation mechanism. Normally, the rules of a fuzzy controller system are derived from the system's internal structure and system behavior using expert knowledge that has experienced the system. However, it is not possible to derive fuzzy rules based on expert human knowledge for all systems in this way. It is necessary to use different methods to derive fuzzy rules in highly variable behavior and nonlinear systems. In this study, an adaptive fuzzy controller design for dc motor was made using a learning-based reference model learning algorithm using fuzzy inverse model; It has been shown that it is applicable for dc motors with the results obtained. Simulation of the designed system was carried out using the Matlab program, and the behavior of the system was investigated by using constant and variable loads. The results showed that it is satisfactory to drive a dc motor with adaptive fuzzy controller in terms of system stability.

Sign in / Sign up

Export Citation Format

Share Document