en روش های تحلیل و تصمیم گیری Decision Analysis and Methods پژوهشي Research <p style="text-align: justify;"><span style="font-size:11pt"><span new="" roman="" style="font-family:" times=""><span style="color:#000000"><span style="font-style:normal"><span style="font-weight:400"><span style="white-space:normal"><span style="text-decoration:none"><i>This paper proposes an&nbsp;explainable artificial intelligence (XAI)&ndash;based framework for automating dye recipe formulation&nbsp;in industrial textile manufacturing, with a focus on&nbsp;yarn rope dyeing for denim production. A&nbsp;deep learning multi-output regression model&nbsp;is developed to predict the resulting yarn shade components </i><span lang="EN-US" style="font-size:10pt">(L_cable, a_cable, b_cable)&nbsp;</span><i>&nbsp;from heterogeneous industrial inputs, including customer-defined fabric shade targets, cotton fiber characteristics, and washing recipe parameters. To ensure transparency and industrial interpretability,&nbsp;Shapley Additive Explanations (SHAP)&nbsp;are integrated to provide global and output-specific explanations of the model&rsquo;s predictions. The analysis reveals the dominant influence of cotton fiber properties, such as tenacity, micronaire, and fiber uniformity, alongside key controllable process parameters, including neutralization time, cellulose treatment duration, and detergent temperature. The proposed framework enables a clear distinction between raw-material-driven variability and process-adjustable levers, transforming the predictive model into an interpretable decision-support tool. The approach is validated using&nbsp;real industrial data from a Tunisian denim manufacturer&nbsp;and is readily transferable to similar textile dyeing and finishing processes.</i></span></span></span></span></span></span></span></p> Explainable Artificial Intelligence (XAI),Shapley Additive Explanations (SHAP),Deep Learning,Dye Recipe Formulation,Textile Industry. 34 42 http://ijiepr.iust.ac.ir/browse.php?a_code=A-10-2990-1&slc_lang=en&sid=1 Mohamed Njah mohamed.njah@enis.tn 1800319475328460014988 1800319475328460014988 No Full professor, Laboratory of Advanced Technologies for Medicine and Signals, National Engineering School of Sfax, University of Sfax & Digital Research Center of Sfax, Technopole of Sfax, Tunisia. M. Hamdi Ridha hamdi.ridha@univgb.tn 1800319475328460014989 1800319475328460014989 No Advanced Technologies in Medicine and Signals (ATMS),National Engineering de Sfax (ENIS), University of Sfax, Tunisia, Mounir Zaag zaag.mounir@sitex.com.tn 1800319475328460014990 1800319475328460014990 Yes Engineer, Industrial textiles company (SITEX), Ksar Hellal, Tunisia