Sage Journals: Discover world-class research

Abstract

Grey superior analysis (GS) has been primarily studied in order to select the efficient input variables of an artificial neural network during the worsted yarn manufacturing. The analysis of the processed data indicates that the parameter selection by means of the grey relevancy matrix can obtain the corresponding sequence according to their correlation degree and derive out a group of main factors as the input variables with high grey-correlation for the ANN model. Through the actual calculation and prediction accuracy analysis, the parameters selected by using the grey superior analysis are more correct and effective but less in number than those produced by the subjective and empirical method popularly used in the field of the textile industry. The prediction and the optimization of the processing techniques can be executed with the ANN model optimized by GS. Moreover, three coefficients for the evaluation of the validity of the input variables selected to ANN have been put forward, which are covering experience coefficient, α, experience redundant coefficient, β, and new information coefficient, γ. Comparing the subjective and experiential method (SE) with GS, α = 0.30~0.60, β = 1.00~ 2.75, and γ = 0.17~0.35, that means the traditional used SE method is only partial correct with a relatively high redundancy.

Keywords

grey superior analysis neural network parameter selection optimization

Get full access to this article

View all access options for this article.

References

Groot, G. J. J. B. de , The Use of Effective Fineness to Determine the Effect of Wool-fibre-diameter Distribution on Yarn Properties , J. Textile Inst., 86(1), 33—44 (1995).

Huang, X.C. , and Oxenham, W. , Predicting End Breakage Rates in Worsted Spinning, Part II: A New Model for End Break Prediction , Textile Res. J., 64(12), 717—722 (1994).

Lamb, R.P. , and Yang, S. , Choosing the Right Top for Spinning , in Proceedings of Top-Tech Int. Wool Secretar. CSIRO Australia, pp. 258—276 ( 1996).

Martindale, J.D. , A New Method of Measuring the Irregularity of Yarns with Some Observations on the Origin of Irregularities in Worsted Slivers and Yarns , J. Textile Inst., 36, 35—47 (1945).

Beltran, R. , Wang, L. , and Wang, X. , Predicting Worsted Spinning Performance with An Artificial Neural Network Model , Textile Res. J., 74(9), 757—763 (2004).

Dong, K. , and Yu, W. , A Worsted Yarn Virtual Production System Based on BP Neural Networks . J. Donghua University (Eng. Ed.), 21(4), 34—37 (2004).

Wang, K. , Yang S. , Humphries, W. , and Huang, X.B. , Applications of Neural Network in Worsted Spinning Prediction , in “Proceeding for ACIAR Project Achievements Review Seminar,” W. Humphrie, B. Zhu, and X. Huang, (Eds.), Printing House of Xi'an University of Engineering Science and Technology, Xi'an , pp. 109—120, 2003.

Carpenter, G.A. , and Grossberg, S. , Neural Dynamics of Category Recognition and Learning: Attention, Memory Consolidation and Amnesia, in “Brain Structure, Learning and Memory ,” Westview Press, Boulder, CO , USA, pp. 233—290, 1986.

Hopfield, J.J. , Neural Networks and Physical

Systems with Emergent Collective Computational Abilities, Proc. Natl

Acad. Sci. U S A, 79, 2554—2558 (1982).

10.

Rumelhart, D.E. , Hinton, G.E. , and Williams , R.J. , Learning Internal Representations by Error Propagation in “Parallel Distributed Processing: Exploration in the Microstructure of Cognition. Vol 1: Foundation,” MIT Press, Cambridge, MA , USA, 1986/

11.

Cheng, L. , and Adams, D.L. , Yarn Strength Prediction using Neural Networks. Part I: Fiber Properties and Yarn Strength Relationship , Textile Res. J., 65(9), 495—500 (1995).

12.

Ertugrul, S. , and Ucar, N. , Predicting Bursting Strength of Cotton Plain Knitted Fabrics using Intelligent Techniques , Textile Res. J.,70(10), 845—851 ( 2000).

13.

Fan, J. , and Hunter, L. , A Worsted Fabric Expert System. Part II: An Artificial Neural Network Model for Predicting the Properties of Worsted Fabric , Textile Res. J., 68(10), 763— 771 (1998).

14.

Fan, J. , Newton, Au, E. R. , and Chan, S.C.F. , Predicting Garment Drape with a Fuzzy-neural Network , Textile Res. J., 71(7), 605—608 ( 2001).

15.

Huang, C.C. , and Chang, K.T. , Fuzzy Self-organizing and Neural Network Control of Sliver Linear Density in a Drawing Frame , Textile Res. J., 71(11), 987—992 ( 2001).

16.

Mori, T. , and Komiyama, J. , Evaluation of Wrinkle Fabrics with Image Analysis and Neural Networks , Textile Res. J., 72(5), 417—422 (2002).

17.

Pynckels, F. , Kiekens, P. , Sette, S. , Van Langenhove , L. , and Impe, K. , Use of Neural Nets for Determining the Spinnability of Fibers , J. Textile Inst. , 86(3), 425—437 ( 1995).

18.

Pynckels, F. , Kiekens, P. , Sette, S. , Langenhove, L.V. , and Impe, K. , Use of Neural Nets to Simulate the Spinning Process. J. Textile Inst., 88(4), 440—448 (1997).

19.

Sette, S. , Boullart, L. , Langenhove, L.V. , and Kiekens, P. , Optimizing the Fiber-to-Yarn Process with a Combined Neural Network/Genetic Algorithm Approach , Textile Res. J., 67(2), 84—92 (1997).

20.

Veit, D. , Bauer-Kurz, I. , and Wulfhorst, B. , Prediction of Yarn Characteristics in the False-Twist Texturing Process with Neural Networks, Chem . Fibers Intl, 47(1), 82—86 (1997).

21.

Zhu, R. , and Ethridge, M.D. , Predicting Hairiness for Ring and Rotor Spun Yarns and Analyzing the Impact of Fiber Properties , Textile Res. J., 67(9), 694—698 (1997).

22.

Ramesh, M.C. , Rajamanickam, R. , and Jayaraman, S. , The Prediction of Yarn Tensile Properties by Using Artificial Neural Networks, J. Textile Inst., 86(3), 459—469 (1995).

23.

Gao, D. , On Structures of Supervised Linear Basis Function Feedforward Three-layered Neural Networks, Chinese J . Computers, 21(1), 80—86 (1998).

24.

Deng, J. , Control Problems of Grey System , Syst. Contr. Lett., 1(5), 288—294 (1982).

25.

Chen, C. , and Tien, T. , A New Transfer Function Model: the Gray Dynamic Model GDM(2,2,1) , Int. J. System, 27(12), 1371—1379 (1996).

26.

Hsiao, S.W. , and Liu, M.C. , A Morphing Method for Shape Generation and Image Prediction in Product Design, Design Studies, 23(5), 533—556 (2002).

27.

Hsu, C.I. , and Wen, Y.H. , Improved Grey Prediction Model for Trans-pacific Air Passenger Market, Transport . Planning Technol, 22(2), 87—107 (1998).

28.

Hsu, L. , Applying the Grey Prediction Model to the Global Integrated Circuit Industry, Technol . Forecasting Social Change, 70, 177—186 (2003).

29.

Le, K. , Grey Forecasting Control: a New Control Scheme, Adv . Model Simul., 14(2), 27—36 (1988 ).

30.

Song, S. , The Application of Grey System Theory to Earthquake Prediction in Jiangsu Area, J. Grey System, 4(4), 359— 367 (1992), in Chinese.

31.

Wu, W.Y. , and Chen, S.P. , A Prediction Method using the Grey Model GMC (1, n) Combined with the Grey Relational Analysis: a Case Study on Internet Access Population Forecast , Appl. Math.s Comput., 169, 198—217 (2005).

32.

Liu, S.F. , Dang, Y.G. , and Fang, Z.G. , “ Grey System Theory and Its Application” (in Chinese), Tsinghua University Press, Beijing , 1999

33.

Luo, M. , and Kuhnell, B.T. , Fault Detection using Grey Relational Grade Analysis, J. Grey System, 5(4), 319—328 ( 1993).

34.

Meng, Q. , The Application of Grey Relational Analysis to Patent Information, J. Grey System, 6(1), 69—73 (1993).

35.

Deng, J.L. , “ Grey Control System” (in Chinese), Huazhong University of Science and Technology Press, Wuhan , 1993.

Selection and Evaluation of Input Parameters of Neural Networks Using Grey Superior Analysis

Abstract

Keywords

Get full access to this article

References