Answers are grounded in this paper and cite their sources.
The accuracy of raw material selection is an essential factor for maintaining print quality, ensuring product durability, and improving production cost efficiency in the digital printing industry. Currently, the selection process often relies on subjective assessments and operator experience, leading to inconsistent decisions when evaluating multiple alternatives with similar characteristics. To overcome this problem, this study aims to design and implement a web-based Decision Support System (DSS) using the Mamdani Fuzzy Inference System (FIS) to provide highly objective raw material recommendations at Arvinonaufal Digital Print. The developed system evaluates raw materials based on five crucial criteria: material thickness, adhesive strength, ultraviolet (UV) resistance, outdoor durability, and price per meter. Research data were comprehensively collected through direct observation, interviews, and documentation. The research methodology encompassed requirements analysis, fuzzy model design utilizing triangular and trapezoidal membership functions with 20 base rules, system implementation using Python and Flask, and black-box system testing. The defuzzification process was calculated using the Centroid method to generate a precise crisp value for ranking. The empirical results show that the Mamdani FIS consistently processes all evaluation criteria, successfully identifying the Oracal 651 product as the top recommendation with a crisp score of 85.91. Furthermore, system testing demonstrates that the web application functions properly, is user-friendly, and significantly improves the consistency of decision-making. Therefore, the proposed system provides a much more objective, efficient, and easily accessible approach to optimizing raw material selection in modern digital printing workflows.
No takes yet. Share an insight, caveat, or question.
Roris et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: