Industry 4.0 III: Advanced Computational Technologies

This course provides an introduction to machine learning and artificial intelligence (AI) concepts, specifically tailored for industrial applications. Students will gain foundational knowledge in supervised and unsupervised learning techniques, including linear regression, classification, decision trees, and clustering methods like k-means and DBSCAN. Through practical examples, students will learn how these techniques are applied for fault detection, predictive maintenance, and process optimization in mechanical systems.

A key component of the course focuses on AI's role in industry, including the integration of machine learning models for realworld applications such as gear wear prediction and bearing failure analysis. Students will also explore the intersection of AI and computer vision in industrial systems, learning about convolution operations, image processing techniques like edge detection, and advanced object recognition methods like YOLO and Faster R-CNN, all of which are essential for quality control and automation in manufacturing. The course delves into the distinctions between AI, machine learning, and deep learning, equipping students with the knowledge to leverage these technologies effectively in industrial settings.

Additionally, students will explore reinforcement learning, particularly in the context of cobots (collaborative robots) that autonomously optimize assembly paths. By the end of the course, students will have a comprehensive understanding of how AI and machine learning can drive innovation and efficiency in modern manufacturing environments.