Back-Propagation (BP) neural network and its modified algorithm are introduced. Two series of BP neural network models have been established to predict yarn properties and to deduce wool fiber qualities. The results f...Back-Propagation (BP) neural network and its modified algorithm are introduced. Two series of BP neural network models have been established to predict yarn properties and to deduce wool fiber qualities. The results from these two series of models have been compared with the measured values respectively, proving that the accuracy in both the prediction model and the deduction model is high. The experimental results and the corresponding analysis show that the BP neural network is an efficient technique for the quality prediction and has wide prospect in the application of worsted yarn production system.展开更多
Three-dimensional Rotational Microscopy was used to take the photos of the fabrics. Three categories of yarn appearance diameters in the worsted fabrics were discussed. The fabrics were grouped into two to explore the...Three-dimensional Rotational Microscopy was used to take the photos of the fabrics. Three categories of yarn appearance diameters in the worsted fabrics were discussed. The fabrics were grouped into two to explore the relationships between yam appearance diameters at the interlacing points, opening points, and the calculated yam diameters. The correlations between the appearance diameters and fabric parameters were given, and the results showed that the calculated yam diameter and warp cover factor had a very big influence on yam appearance diameter. The equations expressing the relationship between yam appearance diameters and fabric parameters are established using step-regression method. The validation of the equations for one type of fabrics shows a good accuracy with the average error below 9% except the weft fdaments exceeding 22%.展开更多
Yam hairiness is a complex concept, which generally cannot be completely defined by a single figure. Hairiness can be considered as the fiber ends and loops standing out from the main compact yarn body. Uster hairines...Yam hairiness is a complex concept, which generally cannot be completely defined by a single figure. Hairiness can be considered as the fiber ends and loops standing out from the main compact yarn body. Uster hairiness system characterizes the hairiness by H value, i.e. the mean value of the total length of all hairs within one centimeter of yarn. The raw data HI are in fact realization of spatial process （hairiness spatial process -- HSP） and can be used for more complex evaluation of hairiness characteristics in the space and frequency domain. The main aim of this contribution is description of some tools for spatial characterization of yarn hairiness. The simple methods for complex characterization of lISP statistical behavior （stationarity, independence, linearity etc. ） are presented. The techniques based on the embedding dimension and correlation integral or long-range dependences evaluation are discussed. The selected methods are core of HYARN program in MATLAB. Application of this program for deeper characterization of artificial data and cotton type yam are shown.展开更多
文摘Back-Propagation (BP) neural network and its modified algorithm are introduced. Two series of BP neural network models have been established to predict yarn properties and to deduce wool fiber qualities. The results from these two series of models have been compared with the measured values respectively, proving that the accuracy in both the prediction model and the deduction model is high. The experimental results and the corresponding analysis show that the BP neural network is an efficient technique for the quality prediction and has wide prospect in the application of worsted yarn production system.
文摘Three-dimensional Rotational Microscopy was used to take the photos of the fabrics. Three categories of yarn appearance diameters in the worsted fabrics were discussed. The fabrics were grouped into two to explore the relationships between yam appearance diameters at the interlacing points, opening points, and the calculated yam diameters. The correlations between the appearance diameters and fabric parameters were given, and the results showed that the calculated yam diameter and warp cover factor had a very big influence on yam appearance diameter. The equations expressing the relationship between yam appearance diameters and fabric parameters are established using step-regression method. The validation of the equations for one type of fabrics shows a good accuracy with the average error below 9% except the weft fdaments exceeding 22%.
基金Supported by the research project"Textile center"of Czech Ministry of Education1M4674788501
文摘Yam hairiness is a complex concept, which generally cannot be completely defined by a single figure. Hairiness can be considered as the fiber ends and loops standing out from the main compact yarn body. Uster hairiness system characterizes the hairiness by H value, i.e. the mean value of the total length of all hairs within one centimeter of yarn. The raw data HI are in fact realization of spatial process （hairiness spatial process -- HSP） and can be used for more complex evaluation of hairiness characteristics in the space and frequency domain. The main aim of this contribution is description of some tools for spatial characterization of yarn hairiness. The simple methods for complex characterization of lISP statistical behavior （stationarity, independence, linearity etc. ） are presented. The techniques based on the embedding dimension and correlation integral or long-range dependences evaluation are discussed. The selected methods are core of HYARN program in MATLAB. Application of this program for deeper characterization of artificial data and cotton type yam are shown.
