Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 Fibres & Textiles in Eastern Europe

2 2011

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Improving the Quality of Combed Yarn Spun by OE Rotor Spinning Using the Grey-Taguchi Method

Su T. L., Chen H. M., Ma C. M., Lu C. F.

Fibres & Textiles in Eastern Europe

2011

Vol. 19, no. 2 (85)

23-27

Open-end (OE) rotor spinning is a high-productive-efciency as well as a space and energy saving method of producing combed yarns with better evenness, regularity and abrasion resistance, as well as a brighter shade and sharpness. However, the setting of process parameters decides yarn quality, which can be done only afer accumulating experience involving tremendous cost, time and manpower. Firstly, the L9(34) orthogonal array is used to plan the process parameters that have an impact on OE rotor spinning. In this study, the experimental quality characteristrics focused on are the strength and unevenness of combed yarns. Aferwards grey relational analysis is used to establish individual quality characteristics, the demerit of the Taguchi Method, and an optimal set of process parameters of multiple quality characteristics obtained from a response graph of the grey relational analysis. Moreover, a signal-to-noise ratio computation and analysis of variance (ANOVA) are conducted to evaluate the results of the experiments. Using ANOVA, the signifcant factors impacting the quality characteristics of combed yarns are obtained; that is, control over the preceding factors indicates valid control over the quality characteristics of combed yarns. Finally, the reliability and reproducibility are verifed at a 95% confdence interval of the confrmation experiments.

Automated Vision System for Recognising Lycra Spandex Defects

Su T. L., Lu C. F.

Fibres & Textiles in Eastern Europe

2011

Vol. 19, no. 1 (84)

43-46

Fabric defect detection and classifcation plays a very important role in the automatic detection process for fabrics. This paper refers to the seven commonly seen defects of lycra spandex: laddering, end-out, hole, oil spot, dye stain, snag, and crease mark. First of all, the gray level co-occurrence matrix was used to collect the features of the fabric image texture, and then the back-propagation neural network was used to establish faw classifcations of the fabric. In addition, by using the Taguchi method combined with BPNN, the BPNN drawback was improved upon, which requires overly time consuming trial-and-error to fnd the learning parameters, and could therefore converge even faster with an even smaller convergence error and better recognition rate. The experimental results proved that the fnal root-mean-square error convergence of the Taguchi-based BPNN was 0.000104, and that the recognition rate can reach 97.14%.