華岡紡織期刊 Journal of the Hwa Gang Textile
ISSN
1025-9678
發行 Publisher
中華民國紡織工程學會
Home / Archives / Vol. 23 No. 2 (2016) / Original Research Articles
Original Research Articles · 研究論文

Prediction of the Fiber stretching process Based on Support Vector Regression-Autoregressive exogenous

以向量回歸模型預測纖維拉伸製程性能
  • Fan Guo 郭凡 College of Information Sciences and Technology, Donghua University, Engineering Research Center of Digitized Textile & Apparel Technology, Ministry of Education
  • Yong-sheng Ding 丁永生 ✉ College of Information Sciences and Technology, Donghua University, Engineering Research Center of Digitized Textile & Apparel Technology, Ministry of Education
  • Kuan-grong Hao 郝礦榮 College of Information Sciences and Technology, Donghua University, Engineering Research Center of Digitized Textile & Apparel Technology, Ministry of Education

Abstract

The fiber stretching process plays a key role in the process of fiber production and its effects is measured by the stretching ratio. The stretching ratio is determined by the relative speed of the winding roller. The stretching ratio is impact on the performance of the final fiber filament and production directly. Focused on the importance of the stretching ratio, the SVR-ARX predictive model for the fiber stretching rate based on existing industry data is proposed. Simulations results demonstrate that the proposed SVR-ARX method can increase the predict results than the traditional SVR method.

Keywords

摘要

牽伸過程是纖維生產中的關鍵環節,其拉伸效果通過牽伸率來衡量。牽伸率主要由各牽伸環節內各個捲繞輥的相對轉速決定。牽伸率直接影響到最終製成的纖維原絲及成品的性能。針對牽伸率在纖維生產過程中的重要性,提出了基於SVR-ARX模型的纖維牽伸率預測方法,得出了纖維牽伸率的預測結果。實驗結果表明,SVM-ARX建立的回歸預測模型比SVR建立的回歸預測模型預測精度高。

關鍵字

Also in this issue

Full TOC →