Lecture 1b AHP - Copy.pptwjsjw ww s d dd

The reliance on quality management systems based on data has revolutionized the operations of small and medium-sized enterprises (SMEs), allowing them to cope with challenges posed by the need to maintain product and operational quality. Manufacturers, especially SMEs, face constraints such as scarce resources, fast-changing technologies, and quick responses to customer needs in today’s competitive world. To address these challenges, industries and researchers have adopted modern approaches, including the use of data-driven techniques like machine learning (ML), neural networks, causal inference, and Industry 4.0 principles, which enable proactive quality management rather than reactive problem-solving[1]. Causal inference, as proposed by Pearl in “The Book of Why,” goes beyond mere correlation to establish cause-and-effect relationships within production systems. This approach is particularly beneficial for SMEs, allowing them to scale operations by making data-driven decisions and addressing specific quality problems. By employing causal models, SMEs can move from merely predicting defects to improving overall production quality[2]. Machine learning techniques, including regression, clustering, and neural networks, enable SMEs to analyze production data for pattern recognition and decision-making. These tools enhance defect detection, prevent resource waste, and automate quality management processes. For example, ML-based systems help address quality issues in a timely and efficient manner, making SMEs more effective in managing their operations [3]. Industry 4.0 technologies, such as the Internet of Things (IoT) and cyber-physical systems, further revolutionize data-driven quality management. IoT sensors facilitate instant data collection, providing real-time insights into production environments. Analytical models based on this data enable SMEs to streamline processes, reduce delays, and make independent decisions. Moreover, real-time dashboards and visualization tools enhance transparency, enabling continuous improvement [4, 5]. Digital Twin technology, a key component of Industry 4.0, allows SMEs to create virtual replicas of physical systems. These models simulate and optimize production processes without disrupting operations, improving precision and reducing downtime. The integration of these advanced tools ensures that SMEs remain competitive and sustainable in an increasingly demanding market environment[6]. While these data-driven approaches provide numerous benefits, they come with challenges such as high costs for infrastructure and skilled personnel, as well as concerns about data security. Addressing these barriers is essential for the widespread adoption of modern quality management practices[7].