Optimization of cotton two-ply yarn parameters to enhance tensile strength using the grey wolf optimization algorithm

Area of Science:

• Textile Engineering
• Materials Science
• Computational Intelligence

Background:

• Optimizing structural parameters of two-ply yarn is crucial for enhancing mechanical properties in textile applications.
• Traditional methods may lack the precision required for complex parameter interactions.
• Data-driven approaches are increasingly vital for material performance optimization.

Purpose of the Study:

• To develop and validate an intelligent hybrid framework combining Artificial Neural Networks (ANN) with the Grey Wolf Optimizer (GWO) for optimizing cotton two-ply yarn parameters.
• To maximize the tenacity of two-ply yarns through systematic parameter adjustment.
• To compare the predictive performance of ANN against Multiple Linear Regression (MLR).

Main Methods:

• Development of a hybrid Artificial Neural Network (ANN) and Grey Wolf Optimizer (GWO) framework.
• Comparative modeling using ANN and Multiple Linear Regression (MLR) to assess predictive accuracy.
• Systematic optimization of two-ply yarn parameters including twist per meter (TPM) and twist direction.
• Sensitivity analysis to determine the influence of individual parameters on yarn tenacity.

Main Results:

• The ANN model demonstrated superior predictive accuracy and generalization ability compared to the MLR model.
• The optimized configuration identified was 1000 TPM twist for single yarns, 790 TPM for two-ply yarn twist, and a Z twist direction.
• Under optimal conditions, yarn tenacity increased from 28.72 cN/tex to 35.81 cN/tex.
• Two-ply yarn twist direction was identified as the most influential parameter, affecting 32.61% of tenacity variation.

Conclusions:

• The proposed ANN-GWO framework is a robust and effective data-driven approach for optimizing two-ply yarn structural parameters.
• This method enables precise regulation and significant enhancement of yarn mechanical performance, specifically tenacity.
• The findings provide an industry-relevant tool for improving textile material quality and performance.