Discriminant analysis-based modeling of cotton fiber and yarn properties

Abstract

Purpose Like all other natural fibers, the physical properties of cotton also vary owing to changes in the related genetic and environmental factors, which ultimately affect both the mechanics involved in yarn spinning and the quality of the yarn produced. However, information is lacking about the degree of influence that those properties impart on the spinnability of cotton fiber and the strength of the final yarn. This paper aims to discuss this issue. Design/methodology/approach This paper proposes the application of discriminant analysis as a multivariate regression tool to develop the causal relationships between six cotton fiber properties, i.e. fiber strength (FS), fiber fineness (FF), upper half mean length (UHML), uniformity index (UI), reflectance degree and yellowness and spinning consistency index (SCI) and yarn strength (YS) along with the determination of the respective contributive roles of those fiber properties on the considered dependent variables. Findings Based on the developed discriminant function, it can be revealed that FS, UI, FF and reflectance degree are responsible for higher YS. On the other hand, with increasing values of UHML and fiber yellowness, YS would tend to decrease. Similarly, SCI would increase with higher values of FS, UHML, UI and reflectance degree, and its value would decrease with increasing FF and yellowness. Originality/value The discriminant functions can effectively envisage the contributive role of each of the considered cotton fiber properties on SCI and YS. The discriminant analysis can also be adopted as an efficient tool for investigating the effects of various physical properties of other natural fibers on the corresponding yarn characteristics.

Prediction Model of Rotor Yarn Quality Based on CNN-LSTM

“…From the point of view of reducing computation, computing time, and saving resources, this model chooses one-layer LSTM [20][21][22] Momentum, and Adam optimization algorithms. These four optimal algorithms have their own characteristics, SGD (Stochastic Gradient Descent) trains for large samples; Adagrad (Adaptive Gradient Algorithm) is an improvement of SGD to improve its robustness; Momentum is also an improvement on SGD, which can accelerate the convergence of SGD and has a strong inhibition on convergence oscillation; Adam (Adaptive Moment Estimation) only needs to give an initial learning rate, and can adapt the learning rate according to the situation in the training process [23,24]. As shown in Figure 15, four optimization algorithms are used for experiments; when Adam optimization algorithm is used, the MSE value of yarn strength reaches the lowest, that is, the prediction accuracy reaches the highest.…”

Yield and Fiber Quality Balance in Upland Cotton (Gossypium Hirsutum L.) Breeding

“…Results of the present study regarding fiber fineness showed that fiber fineness developed in a rather coarse direction and was above commercial limits. Fiber strength, uniformity index, fiber fineness and reflectance degree are responsible for higher yarn strength and SCI would increase with higher values of fiber strength, uniformity index, upper half mean length and reflectance degree, and its value would decrease with increasing fiber fineness and yellowness (Sarker et al 2022). From the present study it is hypothesized that fiber fineness could be bred at commercial limits by optimizing the associated traits.…”

Discriminant Analysis-based Parametric Study of an Electrical Discharge Machining Process

“…The VIF is the reciprocal of tolerance. In Table 5, values of tolerance and VIF are both 1 for all the independent variables, which indicate that these variables are orthogonal in nature with no multicollinearity [33].…”