Partitioned Neural Network Control and Hierarchical Fuzzy Logic Control for Space Flexible Manipulator With Unknown Parameters

2010 ◽  
Author(s):  
Dengfeng Huang ◽  
Li Chen
Keyword(s):  
Neural Network ◽  
Fuzzy Logic ◽  
Trajectory Tracking ◽  
Rigid Motion ◽  
Flexible Manipulator ◽  
Coordinated Motion ◽  
Fast Subsystem ◽  
Unknown Parameters ◽  
Neural Network Controller ◽  
Slow Subsystem

The trajectory tracking and vibration suppression control of free-floating space flexible manipulator with an attitude controlled base are discussed. With the law of conservation of momentum, the Lagrangian principle is utilized to model the dynamic function of the space flexible manipulator incorporating the assumed modes method. Using singular perturbation theory, a slow subsystem describing the rigid motion and a fast subsystem corresponding to the flexible motion are obtained. Then, a two-time scale controller for coordinated motion between the base’s attitude and the manipulator’s joints of space flexible manipulator system is designed. The slow-subsystem partitioned neural network controller dominates the trajectory tracking of coordinated motion in the presence of unknown parameters. The fast-subsystem controller damps out the vibration of the flexible link by hierarchical fuzzy logic controller. Numerical simulation results illustrate that the proposed controller is reliable and effective.

A Neural Network Method for Miniature Unmanned Helicopter Heading Control

2012 ◽  
Vol 468-471 ◽  
pp. 93-96
Author(s):  
Meng Bai ◽  
Min Hua Li
Keyword(s):  
Neural Network ◽  
Control Method ◽  
Network Control ◽  
Neural Network Control ◽  
Unmanned Helicopter ◽  
Unknown Parameters ◽  
Neural Network Controller ◽  
The Neural Network ◽  
Heading Control ◽  
Helicopter Aerodynamics

A neural network control method for heading control of miniature unmanned helicopter is proposed. For the complexity of miniature helicopter aerodynamics, it is difficult to identify the unknown parameters of yaw dynamics model. To design heading controller of miniature helicopter without modelling yaw dynamics, BP neural network is designed as heading controller, which is trained by collected flight data. By training, the neural network controller can learn the artificial operation strategy and realize the heading control of miniature unmanned helicopter. Simulation results demonstrate the validity of the proposed neural network control method.

Inverse Dynamics Based Trajectory Tracking for a One-Link Flexible Arm

1991 ◽  
Author(s):  
Santiago López-Linares ◽  
Roberto F. Jacobus ◽  
Eliodoro Carrera ◽  
Miguel A. Serna
Keyword(s):  
Trajectory Tracking ◽  
Dynamic Problem ◽  
Inverse Dynamics ◽  
Open Loop ◽  
Flexible Manipulator ◽  
Linear Quadratic ◽  
Unknown Parameters ◽  
Inverse Dynamic ◽  
Flexible Arm ◽  
Inverse Dynamic Problem

Abstract This paper presents a new method for controlling a one-link flexible manipulator, based on the solution to the Inverse Dynamic Problem and on a Linear Quadratic Gaussian regulator (LQG). The inverse dynamic solution provides the torque that must be applied by the actuator at the hub to obtain a given trajectory at the tip. This torque can then be used in an open-loop control but, in practice, errors in tip position will appear along the way due to friction, unknown parameters in the model, disturbances, etc. To cope with these problems a trajectory following control is suggested. The technique consists in designing an LQG capable of driving the arm to intermediate states computed in the Inverse Dynamic Problem. Computer simulations with a Finite Element Model of the flexible arm are presented showing a very accurate trajectory tracking.

Adaptive Neural Network Compensating Control for Coordinated Motion of Space-Based Robot System With Uncertain Parameters and External Disturbances

2009 ◽  
Author(s):  
Chen Zhiyong ◽  
Chen Li
Keyword(s):  
Neural Network ◽  
System Stability ◽  
Uncertain Parameters ◽  
Coordinated Motion ◽  
Adaptive Neural Network ◽  
Robot System ◽  
External Disturbances ◽  
Neural Network Controller ◽  
The Neural Network ◽  
On Line

The control problem of space-based robot system with uncertain parameters and external disturbances is considered. With Lagrangian formulation and augmentation approach, the dynamic equations of space-based robot system in workspace are derived. Based on the results, an adaptive neural network compensating control scheme for coordinated motion between the base’s attitude and end-effector of space-based robot system is developed. It is based on the inertia-related method, and incorporates a neural network controller to compensate the uncertainties. The closed-loop system stability with the neural network adapted on-line is discussed in detail through the Lyapunov stability approach. Comparing with many adaptive and robust control schemes, the controller proposed does not require one to determine the regression matrix for space robot system and then avoids tedious computations. Numerical simulations are provided to show the effectiveness of the approach.

A Combination of Fuzzy Logic and Neural Network Algorithms for Active Vibration Control

1996 ◽  
Vol 210 (3) ◽  
pp. 153-167 ◽  
Author(s):  
S-J Huang ◽  
R-J Lian
Keyword(s):  
Neural Network ◽  
Fuzzy Logic ◽  
Vibration Control ◽  
Vibration Amplitude ◽  
Mimo System ◽  
Active Vibration Control ◽  
Lumped Mass ◽  
Network Algorithms ◽  
Neural Network Controller ◽  
Active Vibration

The construction of a dynamic absorber incorporating active vibration control is described. The absorber is a 2 degree of freedom spring-lumped mass system sliding on a guide pillar, with two internal vibration disturbance sources. Both the main mass and the secondary absorber mass were acted on by direct current (d.c.) servo motors, respectively, to suppress the vibration amplitude. In this paper, a new control approach is proposed by combining fuzzy logic and neural network algorithms to control the multi-input/multi-output (MIMO) system. Firstly, the fuzzy logic controller was designed for controlling the main influence part of the MIMO system. Secondly, the coupling neural network controller was employed to take care of the coupling effect and refine the control performance of the MIMO system. The experimental results show that the control system effectively suppresses the vibration amplitude and with good position tracking accuracy.

Sign in / Sign up

Export Citation Format

Share Document