Course information

Objectives

Embark on a journey into Machine Learning in Digital Manufacturing, where data-driven strategies
converge with advanced manufacturing technologies. This course provides MSc students with insight into
the expanding role of ML in process monitoring and optimization across diverse domains, including Additive
Manufacturing (AM), 3D printing, laser-assisted manufacturing processes, and surface engineering.
Learners will develop a theoretical foundation on in-situ process monitoring, sensorization, sensors, and
data acquisition pipelines, emphasizing their application in defect detection, anomaly identification, and
process quality assurance within ML-powered settings. The curriculum navigates through the fundamentals
of neural networks (NNs), backpropagation, and deep learning, demonstrating why these core concepts are
critical for enabling real-time process evaluation and consistent product outputs—ultimately connecting
the dots across manufacturing processes. Through case studies and discussions, students will bridge theory
and practice, examining how ML-driven systems enhance reliability, sustainability, and data-driven
decision-making. They will also explore how ML tools revolutionize design practices, optimize raw material
use, refine process parameters, and boost data-driven control for more robust manufacturing workflows.

Upon completion of this course, students will have:
- Explored in-situ process monitoring and sensorization techniques for real-time defect detection.
- Investigated neural network and sensor data fundamentals to elevate manufacturing workflows.
- Examined how ML-driven strategies boost sustainability and data-informed decision-making in industrial
contexts