With the advent of advanced technologies, organisations across various sectors worldwide have transformed their operations to improve the quality of their products and services. Among these technologies, Artificial Intelligence (AI) is increasingly applied to decision-intensive processes to support human decision-making. In the manufacturing sector, AI holds significant potential for addressing various issues that arise at different stages of Quality Management Systems (QMS). However, despite expressing positive attitudes toward its adoption, a survey conducted to assess the level of AI adoption in QMS within Thai organisations revealed that many have not yet implemented the technology, primarily due to a lack of resources and expertise. Furthermore, the black-box nature of complex AI models poses challenges for workers with limited or no experience in using AI, making it difficult for them to interpret how decisions are made and, consequently, reducing their confidence in the technology. In this context, Explainable AI (XAI) offers a valuable solution. This study proposes a QMS framework that integrates XAI to enhance the interpretability of AI-driven prediction models. The XAI model consists of three components, each performing distinct tasks, ultimately generating forecasted quality-related data along with explanations that clarify the rationale behind the decisions made.
Sangdean et al. (Wed,) studied this question.