A new multi-model internal model control scheme based on neural network

2008 ◽  
Author(s):  
Zhicheng Zhao ◽  
Zhiyuan Liu ◽  
Xinyu Wen ◽  
Jianggang Zhang
Keyword(s):  
Neural Network ◽  
Internal Model ◽  
Internal Model Control ◽  
Control Scheme ◽  
Model Control

Design of a neural internal model control system for a robot

Robotica ◽  
2000 ◽  
Vol 18 (5) ◽  
pp. 505-512 ◽  
Author(s):  
D. T. Pham ◽  
Şahin Yildirim
Keyword(s):  
Internal Model ◽  
Neural Model ◽  
Internal Model Control ◽  
Bp Algorithm ◽  
Recurrent Networks ◽  
Neural Controller ◽  
Inverse Control ◽  
Control Scheme ◽  
Model Control ◽  
Two Degree Of Freedom

This paper describes the design of an Internal Model Control (IMC) system for a planar two-degree-of-freedom robot. IMC was investigated as an alternative to the basic inverse control scheme which is difficult to implement. The proposed IMC system consisted of a forward internal neural model of the robot, a neural controller and a conventional feedback controller, all of which were realised easily. Both the neural model and the neural controller were based on recurrent networks which were trained using the backpropagation (BP) algorithm. The paper presents the results obtained with two types of recurrent networks as well as a conventional PID system.

scholarly journals New Smith Internal Model Control of Two-Motor Drive System Based on Neural Network Generalized Inverse

2016 ◽  
Vol 2016 ◽  
pp. 1-12 ◽  
Author(s):  
Guohai Liu ◽  
Jun Yuan ◽  
Wenxiang Zhao ◽  
Yaojie Mi
Keyword(s):  
Neural Network ◽  
Control Strategy ◽  
Internal Model ◽  
Generalized Inverse ◽  
Control Structure ◽  
Control Method ◽  
Internal Model Control ◽  
Drive System ◽  
Motor Drive ◽  
Model Control

Multimotor drive system is widely applied in industrial control system. Considering the characteristics of multi-input multioutput, nonlinear, strong-coupling, and time-varying delay in two-motor drive systems, this paper proposes a new Smith internal model (SIM) control method, which is based on neural network generalized inverse (NNGI). This control strategy adopts the NNGI system to settle the decoupling issue and utilizes the SIM control structure to solve the delay problem. The NNGI method can decouple the original system into several composite pseudolinear subsystems and also complete the pole-zero allocation of subsystems. Furthermore, based on the precise model of pseudolinear system, the proposed SIM control structure is used to compensate the network delay and enhance the interference resisting the ability of the whole system. Both simulation and experimental results are given, verifying that the proposed control strategy can effectively solve the decoupling problem and exhibits the strong robustness to load impact disturbance at various operations.

Sign in / Sign up

Export Citation Format

Share Document