Force/Velocity Control of a Pneumatic Gantry Robot for Contour Tracking With Neural Network Compensation

2008 ◽  
Author(s):  
Mohammed Abu-Mallouh ◽  
Brian Surgenor
Keyword(s):  
Neural Network ◽  
Coulomb Friction ◽  
Tangential Velocity ◽  
Limiting Factor ◽  
Contour Tracking ◽  
Velocity Control ◽  
Hybrid Controller ◽  
Controller Performance ◽  
Force Velocity ◽  
Gantry Robot

In this paper, the application of a pneumatic gantry robot to contour tracking is examined. A hybrid controller is structured to control the contact force and the tangential velocity, simultaneously. A previous study provided controller tuning and model validation results for a fixed gain PI-based force/velocity controller. Performance was limited by system lag and Coulomb friction. New results demonstrate that even with perfect friction compensation, the limiting factor is the system lag. A neural network (NN) compensator was subsequently developed to counter both effects. Results for straight and curved edged workpieces are presented to demonstrate the effectiveness of the NN compensator and the capabilities of a pneumatic gantry robot.

Hybrid Force/Velocity Control of a Pneumatic Gantry Robot for Contour Tracking: Tuning and Model Validation

2007 ◽  
Author(s):  
Mohammed Abu-Mallouh ◽  
Brian Surgenor
Keyword(s):  
Model Validation ◽  
Coulomb Friction ◽  
Tangential Velocity ◽  
Contour Tracking ◽  
Velocity Control ◽  
Negative Effects ◽  
Sufficient Detail ◽  
Force Velocity ◽  
Future Work ◽  
Gantry Robot

The paper examines hybrid force/velocity control of a pneumatic gantry robot for contour tracking. Both experimental and simulation results are presented. The control system is structured to control the contact force and the tangential velocity simultaneously. Controller tuning and model validation results are given for a fixed gain PI-based hybrid force/velocity controller. A simple yet effective model is presented in sufficient detail such that other researchers can perform their own simulations to investigate the utility of their own controller designs. The model is used to demonstrate the negative effects of Coulomb friction. Future work will focus on friction compensation techniques to improve performance.

Control of a Pneumatic Gantry Robot With Adaptive Neural Network Compensation

2010 ◽  
Author(s):  
Sasan Taghizadeh ◽  
Brian Surgenor ◽  
Mohammed Abu-Mallouh
Keyword(s):  
Neural Network ◽  
Contact Force ◽  
Coulomb Friction ◽  
Tangential Velocity ◽  
Contour Tracking ◽  
Adaptive Neural Network ◽  
Hybrid Controller ◽  
Simulation Results ◽  
Gantry Robot

In a previous paper, the application of a pneumatic gantry robot to contour tracking was examined. A hybrid controller was structured to control the contact force and the tangential velocity, simultaneously. Performance was found to be limited by system lag and Coulomb friction. A neural network (NN) compensator was subsequently developed to counter both effects. Simulation results for straight and curved edge workpieces demonstrated the effectiveness of the NN compensator. This paper validates the results experimentally, highlights the tuning issues associated with an adaptive NN compensator, and confirms the capabilities of a pneumatic gantry robot.

Hybrid Control of a Pneumatic Gantry Robot for Contour Tracking: Proportional Pressure Versus Proportional Flow Control

2009 ◽  
Author(s):  
Mohammed Abu-Mallouh ◽  
Brian Surgenor ◽  
Sasan Taghizadeh
Keyword(s):  
Flow Control ◽  
Coulomb Friction ◽  
Hybrid Control ◽  
Tangential Velocity ◽  
Pressure Control ◽  
Contour Tracking ◽  
Hybrid Controller ◽  
Simulation Results ◽  
Gantry Robot ◽  
Proportional Flow

The application of a pneumatic gantry robot to contour tracking is examined. A hybrid controller is structured to control the contact force and the tangential velocity, simultaneously. In a previous study, experimental contour tracking results for the robot were obtained with electronic proportional pressure control (PPC) valves. The results demonstrated the potential of pneumatic actuation for contour tracking applications. In another study it was found that improvement in performance was limited by system lag and Coulomb friction. A neural network (NN) compensator was developed to counter both effects. Simulation results demonstrated the effectiveness of the NN compensator. Although improvement in performance with NN compensation was significant, this was offset by the requirement for substantive design effort. This paper shows experimentally that equally significant improvement can be achieved by switching from PPC valves to proportional flow control (PFC) valves. The PFC approach requires less design effort.

Iterative-Learning Hybrid Force/Velocity Control for Contour Tracking

2010 ◽  
Vol 26 (2) ◽  
pp. 388-393 ◽  
Author(s):  
A. Visioli ◽  
G. Ziliani ◽  
G. Legnani
Keyword(s):  
Iterative Learning ◽  
Contour Tracking ◽  
Velocity Control ◽  
Force Velocity

scholarly journals Gain Scheduling for Hybrid Force/Velocity Control in Contour Tracking Task

10.5772/5717 ◽  
2006 ◽  
Vol 3 (4) ◽  
pp. 49 ◽  
Author(s):  
Giacomo Ziliani ◽  
Antonio Visioli ◽  
Giovanni Legnani
Keyword(s):  
Gain Scheduling ◽  
Tracking Task ◽  
Contour Tracking ◽  
Velocity Control ◽  
Force Velocity

Application of BP Neural Network PID Algorithm in Refrigerated Space Temperature Control

2014 ◽  
Vol 599-601 ◽  
pp. 827-830 ◽  
Author(s):  
Wei Tian ◽  
Yi Zhun Peng ◽  
Pan Wang ◽  
Xiao Yu Wang
Keyword(s):  
Neural Network ◽  
Temperature Control ◽  
Bp Neural Network ◽  
Pid Control ◽  
Bp Algorithm ◽  
Pid Algorithm ◽  
Controller Performance ◽  
Neural Network Algorithm ◽  
Adaptive Ability ◽  
Neural Network Pid

Taking the temperature control of a refrigerated space as example, this paper designs a controller which is based on traditional PID operation and BP neural network algorithm. It has better steady-state precision and adaptive ability. Firstly, the article introduces the concepts of the refrigerated space, PID and BP algorithm. Then, the temperature control of refrigerated space is simulated in MATLAB. The PID parameters will be adjusted by simulation in BP Neural Network. The PID control parameters could be created real-time online, which makes the controller performance best.

Sign in / Sign up

Export Citation Format

Share Document