A FUZZY NEURAL NETWORK APPROACH TO MODEL HYDRAULIC COMPONENT FROM INPUT/OUTPUT DATA

Authors

  • Wei Xiang School of Mechanical & Production Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore 639798
  • Sai Cheong Fok School of Mechanical & Production Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore 639798
  • Fook Fak Yap School of Mechanical & Production Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore 639798

Keywords:

fuzzy neural network (FNN), fluid power system, virtual prototyping

Abstract

The knowledge of dynamics of hydraulic components are vital for the virtual prototyping of fluid power systems. This paper proposes a fuzzy neural network approach to model the behavior of a hydraulic component from its input-output data. The main advantage of this approach is that the network structure can be determined based on the analysis of the input variables to output response, without trial and error, network pruning or network growing techniques. The process involves resolving the significant inputs through an analysis of their effects with respect to the output. The number of fuzzy rules is determined based on partitioning of the input-output space. The number of significant inputs and the number of fuzzy rules together define the fuzzy neural network structure. A hydraulic pressure relief valve is used to demonstrate the proposed approach. The results indicate that the structure of the fuzzy neural network deter-mined based on the proposed approach can effectively model the dynamics of the relief valve. This work constitutes initial effort towards determining the structure of neural networks based on the analysis of input-output data.

Downloads

Download data is not yet available.

Author Biographies

Wei Xiang, School of Mechanical & Production Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore 639798

Wei Xiang Received the M.Sc degree in Mechanical Engineering from Dalian University of Technology, China, in 1996. She worked as a research assistant in Dept. of Mechanical Engineering of Hongkong Polytechnic Uni-versity from 1997-1998. She is currently the Ph.D. candidate in School of Mechanical & Production Engineering at Nanyang Techno-logical University, Singapore.

Sai Cheong Fok, School of Mechanical & Production Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore 639798

Sai-Cheong Fok Received the B.A.Sc. degree in engineering from University of Ottawa, Canada in 1985 and the Ph.D. degree in mechanical engi-neering from Monash University, Australia in 1990. He has worked as an engineer in the aircraft industry. He is currently an Associ-ate Professor in the Sch. of Mechanical & Production Engineering at Nanyang Techno-logical University, Singapore. His current research interests are in virtual prototyping, machine learning, and intelligent modeling and control.

Fook Fak Yap, School of Mechanical & Production Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore 639798

Fook-Fak Yap Received the B.A.Sc. degree and Ph.D. degree in engineering from University of Cambridge, UK. in 1990 and 1994. He is currently an Associate Professor in the Sch. of Mechanical & Production Engineering at Nanyang Technological University, Singa-pore. His current research interests are in Dynamics, Statistical Energy Analysis, Vibro-acoustic Analysis, Virtual Dynamic Prototyping .

References

Burton, R. T., Ukrainetz, P. R., Nikiforuk, P. N. and Schoenau, G. J. 1999. Neural networks and hy-draulic control-from simple to complex applica-tions. Proc. Instn, Mech. Engrs. Part I. Vol. 213, pp. 349-358.

Drews, P. and Weyrich, M. 1997. A system for Digi-tal Mock-up’s and Virtual Prototype Design in In-dustry: The Virtual Workbench. Proc. IEEE Inter-national Symposium on Industrial Electronics. Vol. 3, pp. 1292-1296.

Dransfield, P. 1981. Hydraulic control Systems—Design and Analysis of Their Dynamics. Springer-Verlag.

Fok, S. C., Xiang, W. and Yap, F. F. 2000. Feature-based Component Models for Virtual Prototyping of Hydraulic Systems. International Journal of Ad-vanced Manufacturing Technology.

Horikawa, S., Furuhashi, T. and Uchikawa, Y. 1992. On fuzzy modelling using fuzzy neural networks with the back-propagation algorithm. IEEE Trans-actions on Neural Networks. Vol.3, No.5, pp. 801-806.

Juang, C. F. and Lin, C. T. 1998. An on-line self-constructing neural fuzzy inference network and its applications. IEEE Transactions on Fuzzy systems. Vol.6, No.1, pp. 12-32.

Leonard, J. A. and Kramer, M. A. 1990. Improve-ment of the back-propagation algorithm for training neural networks. Computers Chem. Eng. Vol. 14, pp. 337-341.

Lin, Y., Cunnihingham III, G. A. and Coggeshall, S. V. 1997. Using fuzzy partitions to create fuzzy sys-tems from input-output data and set the initial weights in a fuzzy neural network. IEEE Transac-tions on Fuzzy systems. Vol. 5, No. 4, pp. 614-621.

Poggio, T. and Girosi, F. 1990. Networks for approx-imation and learning. Proc. IEEE. Vol. 78, No. 9, pp. 1481-1497.

Ruspini, E. H. 1982. Recent development in fuzzy clustering. Fuzzy Set and Possibility Theory. New York: North Holland, pp. 113-147.

Sun, C. T. and Jang, J. S. 1993. A neuro-fuzzy classi-fier and its applications. Proc. IEEE Int. Conf. Fuzzy System. San Francisco, CA, Mar. Vol I, pp. 94-98

Tanaka, K. 1997. Introduction to fuzzy logic for prac-tical application. New York: Springer.

Watton, J. and Xue, Y. 1995. Identification of fluid power component behavior using dynamic flow rate measurement. Proc. Instn Mech. Egnrs. Part C, Journal of Mechanical Engineering Science. Vol. 209, No. 3, pp. 179-191.

Xiang, W., Fok, S. C. and Yap, F. F. 2000. Computa-tional Tools for Fluid Power System Design: To-wards distributed artificial intelligence and virtual reality. International Journal of Computer Applica-tions in Technology. Vol. 13, No. 6, pp. 295-301.

Xue, Y. and Watton, J. 1995. A self-organizing neural network approach to data-based modelling of fluid power systems dynamics using the GMDH algo-rithm. Proc. Instn. Mech. Engrs. Part I. Vol. 209, pp. 229-240.

Xue, Y. and Watton, J. 1998. Dynamics modeling of fluid power systems applying a global error descent algorithm to a self-organising Radial Basis Function network. Mechatronics. Vol. 8, No. 7, pp. 728-745.

Downloads

Published

2001-03-01

How to Cite

Xiang, W., Fok, S. C., & Yap, F. F. (2001). A FUZZY NEURAL NETWORK APPROACH TO MODEL HYDRAULIC COMPONENT FROM INPUT/OUTPUT DATA. International Journal of Fluid Power, 2(1), 37–47. Retrieved from https://journals.riverpublishers.com/index.php/IJFP/article/view/646

Issue

2001: Vol 02 Iss 1

Section

Original Article