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.

39 and execution while minimizing risks. The problem lies in the lack of integrated systems that dynamically assess and optimize quality across all process stages, leading to inefficiencies and higher costs. In recent years, research on quality assurance in manufacturing has become very popular, particularly with the advent of Industry 4.0 technologies. Several publications have appeared in recent years documenting the shift from traditional methods to AI and data-driven approaches. To solve this problem, many researchers have proposed various methods of integrating information models and predictive analytics. One of the first examples of addressing process integration is presented in [1], where an object-oriented manufacturing process information model is developed to enable interoperability among design, planning, and execution. The results offered by Feng and Song suggest that hierarchical structures, including artifacts, activities, and estimated costs/times, can support quality evaluation, though the model does not explicitly define comprehensive indicators. This approach is complemented by [2], who propose a computer-aided process planning methodology that evaluates workpiece surfaces and eliminates infeasible options, ensuring efficient operations in distributed sites. Similarly, their system optimizes based on local conditions like machine capabilities, which points to the need for adaptive quality metrics. In the literature, several theories have been proposed to explain the role of AI in quality control. Argue that Industry 4.0 enables predictive frameworks using machine learning, shifting from reactive inspection to zero-defect manufacturing [3]. They have demonstrated that technologies like IoT and big data improve defect prediction, but limitations such as data quality issues persist. In the same vein, studied AI techniques for additive manufacturing, showing that convolutional neural networks and reinforcement learning enhance defect detection and process optimization [4]. However, our researchers have concluded that these methods need better integration with comprehensive indicators to handle heterogeneous data. T. Xiaoqing et al. [5] have also found that a quality assurance model in mechanical assembly, combining process, activity control, and data models,