KTEK0070 Machine Learning in Digital Manufacturing

University of Turku, Department of Mechanical and Materials Engineering, 2025

Overview

This course provides an in-depth study of Machine Learning (ML) in Digital Manufacturing, demonstrating how 📊 data-driven insights and 🤖 intelligent decision-making enhance process monitoring and quality assurance. It begins with exploring process quality and in-situ monitoring, highlighting how real-time data acquisition enables defect detection and precision optimization. Participants will examine sensorization technologies 📡, including optical and acoustic sensors, and data acquisition methods that transform raw sensor outputs into actionable insights, ensuring accurate process control.

📌 Key Topics Include:

Introduction to ML in Digital Manufacturing: Concepts and industry applications.
Process quality and in-situ monitoring: Real-time data acquisition for defect detection.
Sensorization technologies: Optical and acoustic sensors for manufacturing control.
Data processing and statistical methods: Cleaning, transforming, and analyzing datasets.
ML Fundamentals: Data-driven modeling, neural networks, and backpropagation.
Applications in defect detection and automation: Improving production efficiency.
Integration of intelligent systems: IIoT, self-adaptive manufacturing, and AI-driven decision-making.
Real-world case studies: Applications in AM, 3D printing, laser-assisted processes, and surface engineering.
Future trends and interactive discussions: AI in manufacturing, sustainable automation, and industrial advancements.

🎓 Who Should Attend?

This course is designed for:

Graduate students, researchers, and industry professionals seeking expertise in ML applications for manufacturing.
Individuals interested in understanding how sensor data and ML-driven strategies** can optimize workflows.
Professionals looking to apply AI-driven process control for improved manufacturing quality and efficiency.

🏆 Learning Outcomes

By the end of the course, learners will be able to:

🔍 Gain hands-on experience with **real-time defect detection** through sensorization techniques.
🤖 Understand how ML models process sensor data for manufacturing workflows.
📈 Design ML-driven strategies for improved manufacturing performance.

📚 References

The contents are taken from the following list of publications:

🔍 Optimizing In-situ Monitoring for Laser Powder Bed Fusion Process: Deciphering Acoustic Emission and Sensor Sensitivity with Explainable Machine Learning.

Vigneashwara Pandiyan