This course introduces Machine Learning (ML) and its applications in manufacturing. We use real-world case studies to explain how ML works and can be applied in different manufacturing-related problems.
In addition to the technical focus of applying ML in manufacturing, the course provides knowledge on prerequisites for generating business value from data-driven decision-making. We illustrate the importance of data pre-processing and structured work procedures in ML projects to secure data quality and successful analyses. The crucial link between data-driven decision-making, competence, and internal/external integration will be highlighted.
The exercises are prepared in a way to minimize programming and allow you more time to focus on interpreting the quality of the results.
This two-day course is intended for engineers working in manufacturing, maintenance or R&D.
Basic knowledge in mathematics, statistics and programming.
Introduction to AI and Machine Learning
Opportunities and limitations of using Machine Learning
Success factors for generating business value from data-driven decision-making
Dimensions, indicators, and work procedures for securing data quality
Structured work-procedures for applying AI in Manufacturing Engineering
Introduction to specific machine-learning algorithms used in the practical exercises
Descriptive, diagnostic, predictive and prescriptive analytics of throughput bottleneck (critical and constraining resources) management in manufacturing using Manufacturing Execution System (MES) data.
Predictive maintenance from multiple streams of sensor data, including dimensionality reduction.
We will use a computer classroom and MATLAB for the practical exercises.
This is just a declaration of interest, not a firm application.