Development of a Self-Organized Neuro-Fuzzy Model for System Identification

[+] Author and Article Information
S. M. Yang1

Institute of Aeronautics and Astronautics, National Cheng Kung University, Taiwan, ROCsmyang@mail.ncku.edu.tw

C. J. Chen, Y. Y. Chang, Y. Z. Tung

Institute of Aeronautics and Astronautics, National Cheng Kung University, Taiwan, ROC


Corresponding author.

J. Vib. Acoust 129(4), 507-513 (Dec 14, 2006) (7 pages) doi:10.1115/1.2731417 History: Received December 16, 2005; Revised December 14, 2006

It has been known that it is difficult to establish a fuzzy logic model with effective fuzzy rules and the associated membership functions. Neural network with its learning capability has been incorporated to make the fuzzy model more adaptive and effective. A self-organized neuro-fuzzy model by integrating the Mamdani fuzzy model and the backpropagation neural network is developed in this paper for system identification. The five-layer network adaptively adjusts the membership functions and dynamically optimizes the fuzzy rules. A benchmark test is applied to validate the model accuracy in nonlinear system identification. Experimental verifications on the dynamics of a composite smart structure and on an acoustics system also demonstrate that the neuro-fuzzy model is superior to the neural network and to an adaptive filter in system identification. The model can be established systematically and is shown to be effective in engineering applications.

Copyright © 2007 by American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.



Grahic Jump Location
Figure 1

The schematic of (a) a feedforward network model and (b) a fuzzy system

Grahic Jump Location
Figure 2

The structure of a five-layer neuro-fuzzy model with the connection weights between layers 3 and 4

Grahic Jump Location
Figure 5

The neuro-fuzzy network with the 90th and the 170th rules

Grahic Jump Location
Figure 6

Verification of the neuro-fuzzy system by a sinusoid input

Grahic Jump Location
Figure 7

(a) Schematic diagram of the neuro-fuzzy model in system identification, (b) system identification by the neuro-fuzzy model, and (c) system identification by the [6-7-2] neural network

Grahic Jump Location
Figure 8

(a) Experimental setup of system identification of the acoustics dynamics (marked by the shaded region), (b) system identification by the neuro-fuzzy model, and (c) the ARX model in 220 moving average parameters

Grahic Jump Location
Figure 3

The input u(k), y(k−1), and y(k−2) and output y(k) after completing (a) phase-one of initializing the membership functions and (b) the phase-three of optimizing the membership functions

Grahic Jump Location
Figure 4

Variations of the sum-squared error of (a) phase-two and (b) phase-three learning process



Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In