Integrating between Taguchi methodology and boosted decision trees machine learning: a case study in enhancing quality electrical conductor manufacturing

This study introduces an integrated approach that combines Taguchi methodology and machine learning techniques to enhance production quality in electrical cable manufacturing.The Taguchi method was employed to identify critical factors such as compaction percentage, wire diameter, raw materials, assembly procedures, and operating voltage, converging on an optimal solution.Various decision-making algorithms, including decision trees, random forests, boosted decision trees, linear regression, and k-star, were utilized alongside evaluation metrics like sensitivity, F1-score, and accuracy.The integration of Taguchi and machine learning facilitated the identification of key process parameters and their optimal settings, significantly improving the quality and efficiency of cable manufacturing.The optimal solution achieved included a 666 kg/km weight, 2.64 cm diameter, and a 30% compaction rate, reducing the poor quality cost from 5% to 1.7%.This synergistic approach allowed for the optimization of critical process factors, resulting in significant improvements in product quality and reductions in defects and costs.