Abstract
<jats:p>Modern manufacturing is transforming rapidly from manual, experience-driven practices to autonomous, data-driven decision-making powered by IIoT, advanced sensing, and digital production systems. This shift generates massive, heterogeneous data streams across the entire product lifecycle—from design and planning to machining, inspection, and field service. The challenge lies in converting these fragmented, high-volume data into reliable, real-time decisions that improve productivity, quality, and sustainability while ensuring safety and compliance. When done effectively, data-driven manufacturing reduces defects, minimizes waste, and fosters better human-machine collaboration.</jats:p> <jats:p>This book bridges the gap between raw manufacturing data and trustworthy actions on the shop floor. It offers a rigorous yet practical roadmap, covering fundamentals like data pipelines, feature engineering, and core AI/ML models, as well as advanced topics such as edge analytics, digital twins, and predictive maintenance. Readers will explore methods that integrate domain knowledge, physics-based reasoning, and machine learning to enable robust, explainable, and real-time decision-making. With case studies in CNC machining, additive manufacturing, and intelligent inspection, the book serves graduate students, researchers, engineers, and technical managers seeking to harness AI and data science for smart, resilient manufacturing systems.</jats:p>