Machine Learning in Manufacturing

Carlos A. Escobar is a recognized expert in industrial artificial intelligence with 15+ years of experience leading machine learning innovations across aerospace, automotive, and logistics. As a Sr. Machine Learning Principal Engineer at Howmet Aerospace, Carlos is pioneering the use of Generative AI, autoencoders, and diffusion models to drive zero-defect manufacturing. His work bridges research and real-world deployment, drawing on prior experience developing AI systems at Amazon for last-mile logistics and leading AI-driven process optimization at General Motors.Carlos also served as a Research Assistant at Harvard University, contributing to projects at the intersection of AI, education, and innovation. He is the author of the book Machine Learning in Manufacturing: Quality 4.0 and the Zero Defects Vision (Elsevier, 2024), and his second book, Alpha Sigma: Artificial Intelligence Manufacturing, is under development. He has delivered keynotes at Reuters Momentum AI, the American Society for Quality (ASQ), and the Society of Quality Assurance (SQA), and currently serves as an adjunct professor in Trine University's MS in Business Analytics program.Dr. Morales-Menendez obtained a Ph.D. in AI while at the Computational Intelligence Lab at the University of British Columbia, Canada (2003). As a consultant specializing in analysis and design of control systems, he has carried out projects with more than 20 international companies. Through international research projects, he has advised doctoral students at the institute of industrial automation (Spain) and the Institut Polytechnique de Grenoble (Gipsa-Lab, France). The Mexican Research System accredits his scientific production as Level 2 (2014) with more than 250 research papers. Dr. Morales-Menendez is listed in the Elsevier and Stanford University Top 2 % Scientists list in the Industrial Engineering & Automation (2023 & 2024). He is a member of the Mexican Academy of Sciences (2015) and the Mexican Academy of Engineering (2016).

• 1. Introduction2. The technologies3. The data4. Binary classification5. Machine learning6. Feature engineering7. Classifier development8. Learning quality control9. Case studies; structured and unstructured data10. Conclusion and call to action