The growing adoption of artificial intelligence (AI) in production systems has revolutionized quality assurance processes. Fault detection capability is a critical enabler of production performance and process variability reduction. This study explores the relationship between AI integration, represented by AI-supported decision-making, real-time processing, fault anticipation, and data integration, and production quality assurance. It also assesses the mediating role of fault detection capability in industrial production environments. A quantitative approach was used to gather data from staff in production, quality assurance, process monitoring, maintenance, and operational control units of industrial companies. Participants included production managers, quality assurance managers, process engineers, maintenance supervisors, data analysts, and operational specialists with experience in production process management and digital technologies. The results show that enhancing AI integration across the four dimensions positively impacts production quality assurance by increasing process visibility, facilitating real-time decisions, anticipating faults, and integrating production data across functional activities. The research also reveals that fault detection capability acts as a key mediator, allowing production units to detect anomalies early, prevent quality issues, and boost the stability of production outcomes. It concludes that AI integration positively impacts production quality assurance both directly and indirectly through fault detection capability, helping industrial organizations achieve higher quality standards, process reliability, and production control.
Nijem et al. (Thu,) studied this question.