Browse > Article

The Precision Position Control of the Pneumatic Rodless Cylinder Using Recurrent Neural Networks  

노철하 (금오공과대학교 기전공학과 대학원)
김영식 (금오공과대학교 기계공학)
김상희 (금오공과대학교 전자공학부)
Publication Information
Abstract
This paper develops a control method that is composed of the proportional control algorithm and the learning algorithm based on the recurrent neural networks (RNN) for the position control of a pneumatic rodless cylinder. The proportional control algorithm is suggested for the modeled pneumatic system, which is obtained easily simplifying the system, and the RNN is suggested for the compensation of the modeling errors and uncertainties of the pneumatic system. In the proportional control, two zones are suggested in the phase plane. One is the transient zone for the smooth tracking and the other is the small movement zone for the accurate position control with eliminating the stick-slip phenomenon. The RNN is connected in parallel with the proportional control for the compensation of modeling errors and frictions, compressibilities, and parameter uncertainties in the pneumatic control system. This paper experimentally verifies the feasibility of the proposed control algorithm for such pneumatic systems.
Keywords
recurrent neural networks; stick-slip; pneumatic rodless cylinder; proportional control algorithm;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Choi, S. H., Hong, Y. S. and Lee, C. O., 'A Study on the Position Control and Simulation of Pneumatic Servo System,' Journal of the Korean Society of Precision Engineering, Vol. 13, No. 6, 1996
2 Lin, X., 'Modeling and Test of an Electropneumatic Servovalve Controlled Long Rodless Actuator,' ASME, J. of Dynamic Systems, Measurement and Control, Vol. 118, pp. 457-467, 1996   DOI   ScienceOn
3 Kim, Y. S. and Roh, C. H., 'Development of the Small-displacement-movement of a Pneumatic Piston and the Hybrid Control Algorithm for Precision Position Control,' Journal of the Korean Society of Precision Engineering, Vol. 18, No. 7, pp. 40-45,2001   과학기술학회마을
4 Williams, R. J. and Jing Peng, 'An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network Trajectories,' Neural Computation, Vol. 2, pp. 490-501, 1990   DOI
5 Shearer, J. L., 'Study of Pneumatic Processes in The Continuous Control of Motion with Compressed Air, I, II,' Trans. of the ASME, pp. 233-249, Feb. 1956
6 Burrow, C. R., 'Effect of Position on The Stability of Pneumatic Servomechanism,' J. Mech. Eng. Sci., Vol. 11, No. 6, pp. 615-616,1969   DOI
7 Eun, T., Cho, Y. J. and Cho, H. S., 'Stability and Positioning Accuracy of a Pneumatic On-off Servomechanisms,' Proceedings of American Control Conference, June 1982
8 Williams, R. J. and Zipser, D., 'A Learning Algorithm for Continually Running Fully Recurrent Neural Networks,' Neural Computation Vol. 1, pp. 270-280, 1989   DOI
9 Narendra, K. S. and Parthasarathy, K, 'Identification and Control of Dynamical Systems Using Neural Networks,' IEEE Trans. Neural Networks, Vol. 1, No. 1, pp. 4-27, Mar. 1990   DOI
10 Kuan, C. M., Hornik, K. and White H., 'A Convergence Result for Learning in Recurrent Neural Networks,' Neural Computation, Vol. 1, pp. 420-440, 1993
11 Matsukuma, T. and Fujiwara, A., 'Non-Linear PID Controller Using Neural Networks,' IEEE Trans. Neural Networks, Vol. 2, No. 1, pp. 811 -814, Jun 1997   DOI
12 Marendra, K. S., 'Neural Networks for Control: Theory and Practice,' IEEE, Vol. 84, No, 10, pp. 1385-1406, Oct. 1996   DOI   ScienceOn