Accurate prediction of cotton ring-spun yarn quality from high-volume instrument and mill processing data

Abstract

The derivation and performance of yarn quality prediction models in a program called Cottonspec is reported. Cottonspec incorporates a large database of fiber and yarn data from commercial spinning mills, a series of regression-based models predicting yarn quality from measured cotton fiber quality parameters and yarn specifications and a user interface. The inclusion of independent variables into prediction equations was dependent on the criteria that their inclusion was statistically significant and that variables had a theoretically direct influence on yarn structure. Yarn data was corrected to allow for twist, yarn count and yarn irregularity before correlation with fiber properties. Differences in yarn testing results between mills could be corrected by a Mill Correction Factor. Adherence to these criteria and the ability to draw on the very large database meant prediction ability of the models was excellent, as demonstrated in a series of cross-validations.

Tensile, physical, and microstructure properties of glycine treated cotton fibers

“…The base value for cotton fiber strength (specific stress) is usually 28 cN/tex with small increases in strength and fiber elongation (strain) resulting in higher quality yarn in terms of yarn tenacity and work-to-break properties. 1–3 Improved yarn tensile properties translate as increased burst strength, abrasion resistance, and wear-life of the fabric. In order to improve these properties various chemical processes, such as cross-linking with resins 4–9 and modification of cotton cellulose through swelling in strong alkali 10–16 have been applied.…”

A method for yarn quality fluctuation prediction based on multi-correlation parameter feature subspace mechanism in spinning process

“…20 –22 there have been remarkable research works on the prediction modeling with various algorithms. Yang and Gordon 23 proposed a spinning quality prediction method based on multiple regression model. The prediction model is constructed by a large amount of spinning historical data to achieve accurate prediction of yarn quality.…”

Discovering the relationships between yarn and fabric properties using association rule mining

“…With significant innovations and improvements in the textile domain, it became necessary to analyze textile data, including material properties, machine settings, and process parameters. Thus, several studies on the prediction of yarn [8] and fabric [9] properties have been conducted by using traditional methods such as regression model [10], kernel estimation [11], and correlation analysis [12]. Although all of these traditional methods provide predictions about yarn and fabric properties and influences, they unfortunately remain incapable of analyzing complex relationships among data attributes, estimating unknown attribute values, or investigating hidden patterns among instances.…”