Fuzzy Self-Organizing and Neural Network Control of Sliver Linear Density in a Drawing Frame

Abstract

This paper presents an experimental study of fuzzy self-organizing and neural network control in developing an autoleveling system with a drawing frame. Without the need of modeling, both control strategies can cope with nonlinear or very complex processes, even when subject to random disturbances such as drafting processes. In fuzzy self-organizing control, control rules to improve sliver irregularities are constructed in the basic fuzzy control level. The self-organizing scheme is able to improve the rules automatically. A three-layer neural network model, which approximates the process, is used to compute the Jacobian matrix, which is needed in training the weights and thresholds on-line with the neural network controller. In a laboratory scale of the drawing frame with two drafting zones and two-sliver doubling, the draft ratio is adjustable by regulating the speed of the middle roller. Levelness performance is evaluated by the CV% of sliver products. The experimental results show that both controllers are effective in reducing the CV%, and the neural network controller yields more level slivers than the fuzzy self-organizing controller.

Get full access to this article

View all access options for this article.

References

1. Bowles, A. H., and Davies, I., The Influence of Drawing and Doubling Processes on the Evenness of Spun Yams, Part V: Automatic Control of Regularity, Textile Inst. Ind. (2), 72–76 (1979).

2. Burke, L. , and Ignizio, J. P. , A Practical Overview of Neural Networks, J. Intell. Manufact. 8, 157–165 (1997).

3. Catling, H. , and Davies, I. , Conservation of Mean Level in Autolevelling, J. Textile Inst. 57, T395–415 (1966).

4. Davies, I. , Some Theoretical Limitations of Sliver Autolevelling Systems, J. Textile Inst. 57, 10–38 (1968).

5. Djiev, S. N. , Modeling a Double-Zone Drafter as an Object of Control, Textile Res. J. 64, 449–456 (1994).

6. Klir, G. J. , and Yuan, B. , “Fuzzy Sets and Fuzzy Logic,” Prentice-Hall, NJ, 1995.

7. Lee, C. C. , Fuzzy Logic in Control Systems: Fuzzy Logic Controller, Part I, IEEE Trans. Syst. Man. Cybern. 20, 404–418 (1990).

8. Lee, C. C. , Fuzzy Logic in Control Systems: Fuzzy Logic Controller, Part II, IEEE Trans. Syst. Man. Cybern. 20, 419–435 (1990).

9. Lin, C. T. , and Lee, C. S. G. , “Neural Fuzzy Systems,” Prentice-Hall, NJ, 1996.

10.

10. Psaltis, D., Sideris, A., and Yamamura, A. A., A Multilayered Neural Network Controller, IEEE Control Sys. Mag. (4), 17–21 (1988).

11.

11. Shao, S. , Fuzzy Self-Organizing Controller and Its Application for Dynamic Processes, Fuzzy Sets Syst. 26, 151–164 (1988).

12.

12. Yager, R. R. , and Zadeh, L. A. , “Fuzzy Sets, Neural Networks, and Soft Computing,” Van Nostrand Reinhold, NY, 1994.

13.

13. Yang, C. R., A Real-Time Linguistically Approached Self-Organizing Fuzzy Logical Controller, Masters thesis, National Taiwan University, 1992.