MEASURED PERFORMANCE EVALUATION OF PID AND NEURAL NET CONTROL OF A HYDRAULICALLY DRIVEN INERTIA LOAD WITH NONLINEAR FRICTION

Authors

  • Weiman Qian National Research council, 3250 East Mall, Vancouver, BC Canada
  • Greg Schoenau Department of Mechanical Engineering, University of Saskatchewan, 57 Campus Drive, Saskatoon, Saskachewan, Canada, S7N 5A9
  • Richard Burton Department of Mechanical Engineering, University of Saskatchewan, 57 Campus Drive, Saskatoon, Saskachewan, Canada, S7N 5A9

Keywords:

hydraulic, PID, neural network, control, nonlinear

Abstract

Hydraulic systems are inherently nonlinear. When used to control an inertial load, which also exhibits nonlinear be-haviour due to slip-stick friction at the contact surface, the result is a system which is highly non-linear and poses a dif-ficult control problem. The study described in this paper examines the experimental performance of velocity control of a mass on a sliding contact surface using a servovalve and linear actuator. Conventional PID control is compared to artificial neural net (ANN) based controllers. A modified multi-input PID controller was used to train the ANN control-ler. The ANN based controller outperformed the PID controller when subjected to a wide variety of input signals. A second ANN co-controller was added to the loop to provide an additional corrective signal in the form of a pulse to give the system an extra surge of input to overcome the stiction friction in the zero velocity cross-over region. Excellent re-sults were achieved with improved accuracy compared to the single ANN controller when subjected to a series of ran-dom input signals, indicating the robustness of the ANN controllers.

Downloads

Download data is not yet available.

Author Biographies

Weiman Qian, National Research council, 3250 East Mall, Vancouver, BC Canada

Weiman Qian Born in Shenyang, China. He obtained his B.Sc. and M.Sc. degrees in mechanical manufacturing from Northeastern University in 1987 and 1990, respectively. He immi-grated to Canada and obtained an M.Sc. degree in the fluid power area from the University of Saskatchewan in 1998. At present he is employed with the National Research Council of Canada at Vancouver in the control and diagnostics area.

Greg Schoenau, Department of Mechanical Engineering, University of Saskatchewan, 57 Campus Drive, Saskatoon, Saskachewan, Canada, S7N 5A9

Greg Schoenau Professor of Mechanical Engineering at the University of Saskatchewan. He was Head of that Department from 1993 to 1999. He obtained B.Sc. and M.Sc. degrees from the University of Saskatchewan in mechanical engineering in 1967 and 1969, respectively. In 1974 he obtained his Ph.D. from the University of New Hampshire in fluid power control systems. He continues to be active in research in this area and in the thermal systems area as well. He has also held posi-tions in numerous outside engineering and technical organizations.

Richard Burton, Department of Mechanical Engineering, University of Saskatchewan, 57 Campus Drive, Saskatoon, Saskachewan, Canada, S7N 5A9

Richard Burton Born Sept. 6, 1947. Richard Burton is a Professor of Mechanical Engineering at the University of Saskatche-wan, Saskatoon, Canada and is now Assis-tant Dean of Undergraduate Studies at this same institution. He received his B.E degree in Engineering Physics and M.Sc. and Ph.D. in Hydraulic Controls from the Univ. of Saskatchewan. He has been and continues to be active in research in the Fluid Power area. He is a member of the ASME (FPST), SAE and NCFP Advisory Boards. He is also convenor for FPN (Canada).

References

Bilabdi, S. 1997. Identification of Frictional Effects and Structural Dynamics for Improved Control of Hy-draulic Manipulators. Dept. of Electrical Engineer-ing, Univ. of British Columbia, Ph.D. Thesis.

Dupont, P. E. 1993. Avoiding Stick-slip through PD Control. IEEE Transactions on Automatic Control, 39(5), pp. 1094-1097.

Dupont, P. E. and Dunlap, E. P. 1993. Friction Model-ling and PD Compensation at Very Low Velocities. ASME Journal of Dynamic Systems Measurement and Control, Vol. 117, pp. 8-14.

Murrill, P. 1998. Fundamentals of Process Control Theory. Creative Services Inc. New York, NY, pp. 103-116.

Qian, W., Burton, R. T., Schoenau, G. J. and Ukrainetz, P. R. 1998. A Comparison of a PID Controller to a Neural Net Controller in a Hydraulic System with Nonlinear Friction. Proceedings of the 1998 ASME International Mechanical Engineering Congress, Anaheim, CA, Nov, pp. 91-98.

Qian, W., Burton, R. T. and Schoenau, G. J. 1999. Model Based Evaluation of Neural Net Control of an Inertial System with Nonlinear Friction. TBA.

Tafazoli, S., Lawrence, P., Salcudean, S. E., Chan, D., Bachmann, S. and de Silva, C. W. 1996. Pa-rameter Estimation and Actuator Friction Analysis for a Mini Excavator. Proc. of the IEEE Interna-tional Conference on Robotics and Automation, Minneapolis, Minnesota, Vol. 1, pp. 329-334.

Downloads

Published

2001-03-01

How to Cite

Qian, W., Schoenau, G., & Burton, R. (2001). MEASURED PERFORMANCE EVALUATION OF PID AND NEURAL NET CONTROL OF A HYDRAULICALLY DRIVEN INERTIA LOAD WITH NONLINEAR FRICTION. International Journal of Fluid Power, 2(1), 31–36. Retrieved from https://journals.riverpublishers.com/index.php/IJFP/article/view/645

Issue

2001: Vol 02 Iss 1

Section

Original Article