<![CDATA[This study develops and evaluates an explainable zero order Fuzzy Sugeno expert system for assessing the feasibility of Melamine Moulding Compound (MMC) dyes in the melamine industry. The objective is to support consistent dye assessment by converting expert knowledge of boiling point, processing time, and injection pressure into a structured decision model. Each input variable is represented by low, medium, and high fuzzy sets, while four domain experts contributed to the definition and review of the membership ranges, rule base, and feasibility outcomes. The model contains 27 rules with singleton consequents of 10, 20, and 30 for not feasible, conditionally feasible, and feasible decisions, respectively, with midpoint decision boundaries of 15 and 25. The model was evaluated using 23 historical process profiles and classified 10 samples as not feasible (43.48%), 8 as conditionally feasible (34.78%), and 5 as feasible (21.74%). MMC103, with a boiling point of 165 °C, processing time of 65 seconds, and pressure of 55 bar, activated eight rules and produced a Sugeno score of 26.67, resulting in a feasible classification. A ±5% sensitivity analysis with 10,000 random perturbations produced MMC103 scores from 25.86 to 27.29 and retained its feasible classification in all runs, while overall class stability across the 23 profiles reached 98.86%. Sugeno classifications agreed with Mamdani inference for 20 of 23 profiles and with a crisp rule baseline for 18 profiles. By combining expert knowledge formalization, sensitivity evaluation, comparative analysis, and web implementation, this study provides an explainable and traceable decision support approach for MMC dye feasibility assessment in melamine production.]]>
Copyrights © 2026
