Predicting cotton fiber properties from fiber length parameters measured by dual-beard fibrograph

Abstract

Cotton ber properties, although in uenced tremendously by plant growing conditions, are largely dictated by cotton variety, and therefore certain associations inherently exist among the properties. Previous studies have examined cotton properties that have direct impacts on others, e.g., ber maturity on strength, but latent associations between ber properties, such as ber length vs. maturity, have not been explored. This paper focuses on investigating the relationships between ber length and other important properties (e.g., strength and maturity), and creating the regression models to predict these properties in case the testing conditions are unattainable. We rstly selected 117 cotton samples and divided them into a training set (100 samples) and a testing set (17 samples). We then measured the ber length parameters with Dual-beard Fibrograph (DBF) that can generate accurate ber length distributions, and the seven other ber properties, strength, elongation, micronaire, nep, neness, immature-ber-content and maturity-ratio, with High Volume Instrument (HVI) and Advanced Fiber Information System (AFIS). Finally, we performed multivariate regression, Bland-Altman plot, clustering and other statistical analyses to assess the correlations, multicollinearity, agreements and clusters of the ber properties. It was found that ber length parameters had moderate associations (0.3<|r|<0.7) with the seven properties, and the prediction errors on the training set varied from 2.25% (for maturity-ratio) to 14.36% (for nep). The Bland-Altman analysis proved that for any of the seven properties, more than 94.9% of the predicted and actual points were within the 95% limits of agreement and without systematic biases. The regression models based on cotton clusters signi cantly lowered the prediction errors because the cluster centroids better represented the collective features of the ber properties. The analyses on the testing set showed the prediction models can generate comparable results for both the training and testing sets, and demonstrated good generalization over new samples.

Investigating the Ideal Combination of Virgin Cotton Fibre Length with Recycled Fibre for Better Yarn Quality

“…Additionally, the sustainable aspects of utilizing recycled fibres enhance yarn quality, bringing unique characteristics to the blend that influence yarn properties alongside virgin cotton fibre length [14]. The distribution of variations in fibre length plays a crucial role in predicting yarn properties; an increase in yarn linear density leads to increased hairiness, and the inclusion of https://doi.org/10.31881/TLR.2024.009 recycled fibres introduces specific considerations in this context [3]. fibre length significantly influences hairiness, with longer fibres associated with reduced hairiness.…”