한국염색가공학회지 (Textile Coloration and Finishing)

  • 제19권6호
  • /
  • Pages.7-11
  • /
  • 2007
  • /
  • 1229-0033(pISSN)
  • /
  • 2234-036X(eISSN)
한국염색가공학회 (The Korean Society of Dyers and Finishers)
권호 표지

인공 신경망을 이용한 방적사 굵기 신호의 모델링

Modeling and Prediction of Yarn Density Profiles Using Neural Networks

  • 김주용 (숭실대학교 유기신소재.파이버 공학과)
  • Kim, Joo-Yong (Department of Organic Materials and Fiber Engineering, Soongsil University)
  • 발행 : 2007.12.27
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

A prediction model for yarn density profile was developed using the neural network methodology. The neural network model developed traces mass densities of a yarn within a section and predicts the mass profiles of the next yarn segment yet to be measured. The model does not require an assumption on the existence of a relationship between the past and future data sets. Four high-draft yarns made under different processing conditions were employed in order to test the performance of the model developed. It was shown that the model could predict the yarn density profiles without a significant error.

키워드

참고문헌

  1. A Quarterly Report to Cotton Incorporated, March, 1995
  2. H. Tong, 'Non-linear time series - A dynamic system approach', Oxford University Press, Oxford, 1990
  3. N. Bhat and T.J. McAvoy, 'Use of Neural Nets for Dynamic Modeling and Control of Chemical Process Systems', in Proc. American Control Conf., pp.1342-1347, 1989
  4. K. Hornik, Multilayer Feedforward Networks are Universal Approximators, Neural Networks, 2(5), 359-366(1989) https://doi.org/10.1016/0893-6080(89)90020-8
  5. R.N. Sharpe, Mo-yeun Chow, S. Brigg and L. Windingland, A Methodology using Fuzzy Logic to Optimize Feedforward Artificial Neural Network Configurations, IEEE Transactions on Systems, Man and Cybemetics, 24(5), 152-155 (1994) https://doi.org/10.1109/21.259696
  6. Werbos, Generalization of backpropagation with Application to a Recurrent Gas market Mode, Neural Networks, 1(4), 339-356(1988)