Mean-value-based functional reasoning techniques in the development of fuzzy neural network control systems

Author(s):  
Keigo Watanabe ◽  
Spyros G. Tzafestas
2021 ◽  
Vol 22 ◽  
pp. 2
Author(s):  
Qin He ◽  
Peng Zhang ◽  
Shunxin Cao ◽  
Ruijun Zhang ◽  
Qing Zhang

Aiming at the inconsistency between the vibration of the car and the car frame in the actual operation of a high-speed elevator and the horizontal vibration caused by the roughness excitation of the guide rail, this study designs a gas–liquid active guide shoe and establishes a horizontal vibration model of the 8-DOF high-speed elevator car system separated from the car and the car frame. Then, the correctness of the model is verified by experiments. Based on this, a fuzzy neural network intelligent vibration reduction controller based on the Mamdani model is designed and simulated by MATLAB. The results show that the root mean square value, mean value, and maximum value of vibration acceleration are reduced by more than 55% after using the fuzzy neural network control method, and the suppression effect is better than that of BP neural network control. Therefore, the intelligent vibration absorption controller designed by this research institute can effectively suppress the horizontal vibration of high-speed elevators.


2020 ◽  
Vol 28 (10) ◽  
pp. 2543-2554 ◽  
Author(s):  
Parham Mohsenzadeh Kebria ◽  
Abbas Khosravi ◽  
Saeid Nahavandi ◽  
Dongrui Wu ◽  
Fernando Bello

Sign in / Sign up

Export Citation Format

Share Document