scholarly journals A REAL-TIME ADAPTIVE LEARNING CONTROL BASED ON EVOLUTIONARY ALGORITHM OF THE APPLICATION TO AN ELECTRO-HYDRAULIC SERVO SYSTEM

2002 ◽  
Vol 2002 (5-2) ◽  
pp. 573-578
Author(s):  
Sung Ouk Chang ◽  
Jin Kul Lee
Keyword(s):  
Evolutionary Algorithm ◽  
Real Time ◽  
Adaptive Learning ◽  
Servo System ◽  
Learning Control ◽  
Hydraulic Servo ◽  
Hydraulic Servo System ◽  
Adaptive Learning Control

Adaline neural network-based adaptive inverse control for an electro-hydraulic servo system

2011 ◽  
Vol 17 (13) ◽  
pp. 2007-2014 ◽  
Author(s):  
Jianjun Yao ◽  
Xiancheng Wang ◽  
Shenghai Hu ◽  
Wei Fu
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Servo System ◽  
Inverse Model ◽  
Lms Algorithm ◽  
Adaptive Inverse Control ◽  
Inverse Control ◽  
The Neural Network ◽  
Hydraulic Servo ◽  
Hydraulic Servo System

Based on adaptive inverse control theory, combined with neural network, neural network adaptive inverse controller is developed and applied to an electro-hydraulic servo system. The system inverse model identifier is constructed by neural network. The task is accomplished by generating a tracking error between the input command signal and the system response. The weights of the neural network are updated by the error signal in such a way that the error is minimized in the sense of mean square using (LMS) algorithm and the neural network is close to the system inverse model. The above steps make the gain of the serial connection system close to unity, realizing waveform replication function in real-time. To enhance its convergence and robustness, the normalized LMS algorithm is applied. Simulation in which nonlinear dead-zone is considered and experimental results demonstrate that the proposed control scheme is capable of tracking desired signals with high accuracy and it has good real-time performance.

Sign in / Sign up

Export Citation Format

Share Document