Proceedings of the International scientific and practical conference ―Science, Technology and Culture: Interaction, Evolution and Progress‖ (December 21-23, 2025) / Publisher website: www.naukainfo.com. – Copenhagen, Denmark, 2026. – 161 p.

40 eliminates uncertainties through structured control rules. This view is supported by the playbook on manufacturing metrics [6], which notes that comprehensive quality indicators like cost of poor quality, defect rates, and overall equipment effectiveness (OEE) drive proactive risk reduction. A broader perspective has been adopted by the Early Manufacturing Quality Engineering Guide [7], which argues that maturity levels (TRLs/MRLs) and assessments like MRAs serve as comprehensive indicators for defense systems, ensuring producibility and risk mitigation from early stages. Conversely, the guide reported no significant difference in outcomes without early integration, highlighting the importance of plans like MMPs. In contrast to design-focused models, T. Xiaoqing et al. [5] focuses on assembly-specific controls, whilst Early Manufacturing Quality Engineering Guide [7] is more concerned with overarching engineering activities. Some authors have mainly been interested in questions concerning real-time and methodological aspects. For instance, the methodological processing of quality control presents an approach to analyzing technological processes through structured data acquisition, though it fails to take scalability into account fully [8]. Others have highlighted the relevance of AI for high-level decisions [9], but studies on comprehensive indicators are still lacking. The problem with this approach is that it does not address distributed environments adequately. A key limitation of previous research is that it does not fully integrate predictive and prescriptive analytics. Together, these studies indicate that comprehensive quality indicators, aggregating metrics like yield, variability, and costs, are crucial for ensuring operations. Overall, these studies highlight the need for models that combine information interoperability [1], AI prediction [3,4], and structured assessments [5,7]. Collectively, these studies outline a critical role for adaptive frameworks, yet contradictions arise in handling data quality and adaptability. The evidence presented in this section suggests that while strengths like improved accuracy exist, weaknesses such as interpretability issues persist. The study would have been more useful if it had included more cross-industry applications.