ABSTRACT Considerable research has been conducted on the control of pneumatic systems. However, nonlinearities continue to limit their performance. To compensate, advanced nonlinear and adaptive control strategies can be used. But the more successful advanced strategies typically need a mathematical model of the system to be controlled. The advantage of neural networks is that they do not require a model. This paper reports on a study whose objective is to explore the potential of a novel adaptive on-line neural network compensator (ANNC) for the position control of a pneumatic gantry robot. It was found that by combining ANNC with a traditional PID controller, tracking performance could be improved on the order of 45% to 70%. This level of performance was achieved after careful tuning of both the ANNC and PID components. The paper sets out to document the ANNC algorithm, the adopted tuning procedure, and presents experimental results that illustrate the adaptive nature of NN and confirms the performance achievable with ANNC. A major contribution is demonstration that tuning of ANNC requires no more effort than the tuning of PID.
Cite this paper
nullB. Dehghan, S. Taghizadeh, B. Surgenor and M. Abu-Mallouh, "A Novel Adaptive Neural Network Compensator as Applied to Position Control of a Pneumatic System," Intelligent Control and Automation, Vol. 2 No. 4, 2011, pp. 388-395. doi: 10.4236/ica.2011.24044.
 G. M. Bone and S. Ning, “Experimental Comparison of Position Tracking Control Algorithms for Pneumatic Cylinder Actuators,” IEEE/ASME Transactions on Mechatronics, Vol. 12, No. 5, 2007, pp. 557-561. doi:10.1109/TMECH.2007.905718
 Y. Wang, H. Su, K. Harrington and G. Fischer, “Sliding Mode Control of Piezoelectric Valve Regulated Pneumatic Actuator for MRI-Compatible Robotic Intervention,” Proceeding of ASME Dynamic Systems and Control Conference, Cambridge, 12-15 September 2010, pp. 1-6.
 S. C. Gi, K. L. Han and H. C. Gi, “A Study on Tracking Position Control of Pneumatic Actuators using Neural Network,” Proceeding of 24th Annual Conference on IEEE Industrial Electronics Society, Aachen, 31 Augudt-4 September 1998, pp. 1749-1753.
 D. C. Gross and K.S. Rattan, “Pneumatic Cylinder Trajectory Tracking Control using a Feedforward Multilayer Neural Network,” Proceedings of the IEEE 1997 National Aerospace and Electronics Conference, Dayton, 14-17 July 1997, pp. 777-784.
 Y. Li and T. Asakura, “A Study on Neural Network Control of Explosion-Proof 2-link Pneumatic Manipulator,” 2003 IEEE/ASME International Conference on Advanced Intelligent Mechatronics, Kobe, 20-24 July 2003, pp. 1286-1291. doi:10.1109/AIM.2003.1225528
 X. Wang and G. Peng, “Modeling and Control for Pneumatic Manipulator Based on Dynamic Neural Network,” Proceeding of IEEE International Conference on Systems, Man and Cybernetics, Washington, DC, 5-8 October 2003, pp. 2231-2236.
 G. Kothapalli and M. Y. Hassan, “Design of a Neural Network Based Intelligent PI Controller for a Pneumatic System,” IAENG International Journal of Computer Science, Vol. 35, No. 2, 2008, pp. 217-225.
 S. Taghizadeh, B. Surgenor and M. Abu Mallouh, “Control of a Pneumatic Gantry Robot with Adaptive Neural Network Compensation,” Proceeding of 34th Mechanisms and Robotics Conference, Montreal, 15-18 August 2010.
 F. L. Lewis, “Neural Network Control of Robot Manipulators,” IEEE Expert, Vol. 11, No. 3, 1996, pp. 64-75.
 G. Campa, M. Fravolini and M. Napolitano, “A Library of Adaptive Neural Networks for Control Purposes,” 2002 IEEE International Symposium on Computer Aided Control System Design, Glasgow, 18-20 September 2002, pp. 115-120. doi:10.1109/CACSD.2002.1036939
 F. W. Lewis, S. Jagannathan and A. Yesildirak, “Neural Network Control of Robot Manipulators and Non-Linear Systems,” Taylor & Francis, London, 1999.
 R. C. Rice, “PID Tuning Guide,” Rockwell Automation, Milwaukee, 2010.