1. Introduction: Industry 4.0 and 5.0, Data-driven manufacturing, Knowledge discovery process, Data mining vs. Machine learning 2. Supervised learning: applications in manufacturing (e.g., predictive maintenance, product quality), regression algorithms, classification algorithms, deep learning, coding examples in Python 3. Unsupervised learning: applications in manufacturing (e.g., product/customer clustering, outlier detection), clustering algorithms, coding examples in Python 4. Reinforcement learning: manufacturing applications (e.g., robot walking, nesting), reinforcement learning algorithms, coding examples in Python

No specific prerequisites

Data has become a highly valuable resource, even being cheap to be captured and stored. The diffusion of the Internet of Things (IoT) has allowed manufacturers to better manage productivity and efficiency on the shop floor. To further improve operations, manufacturers have turned to artificial intelligence and machine learning to leverage the massive amounts of data that is created during production. The aim of the course is introducing machine learning and how it can be useful in manufacturing applications. Each of the main ML techniques (i.e. supervised, unsupervised and reinforcement learning) is briefly described from the theoretical point of view, before presenting several applications in the manufacturing domain. Finally, some use cases will be implemented using Python language.

In presenza

Presentazione report scritto - Presentazione orale - Test a risposta multipla

P.D.1-1 - Gennaio