Abstract
This paper presents a comparative analysis of three experimental designs-Taguchi, Box-Behnken Design (BBD), and Central Composite Design (CCD)-for optimizing process parameters in a system with four factors at three levels. The study aims to identify the most effective experimental design by evaluating the relationship between variables and their contributions using Analysis of Variance (ANOVA). Quantitative results show that the Taguchi method, requiring fewer experimental runs, provides a more cost-effective solution, while BBD and CCD deliver more accurate optimization results with higher precision. Specifically, the Taguchi method achieves an optimization accuracy of 92%, BBD reaches 96%, and CCD yields 98% accuracy. The optimum set of parameters for each method is presented, and the adequacy of each model, as well as potential lack of fit, is assessed using R programming. The findings highlight the trade-offs between efficiency, accuracy, and experimental cost, offering practical guidance for selecting an appropriate experimental design based on specific optimization needs.