Data-driven methods for managing manufacturing processes

During the course, the students will analyze, design and improve a manufacturing process, based on data from practice (e.g., benchmark data, practical operation data from physical robots).
During lectures, the students will study techniques that can be applied to guide the design and improvement of a manufacturing process and apply these techniques to the dataset, such as

1. scientific methods, such as BPM and CRISP-DM, to set up a data-driven manufacturing process;
2. process mining or data mining to get insight into how manufacturing processes are performing and how they can be improved;
3. machine learning methods to reduce machine downtime and production costs and increase productivity, and so on.
   Students will perform relevant group assignments with data, and will be given the means to acquire the required knowledge through lectures, working sessions and office hours that are held by the lecturers.

After this course, students are able to:

1. explain which information systems are involved in manufacturing processes, which processes they support, and which relevant data can be extracted from them;
2. set-up a data-driven analysis project in the manufacturing context according to scientific methodologies such as BPM and CRISP-DM;
3. apply descriptive analytics techniques, including process mining and general data mining, to derive information about the way in which manufacturing processes are executed and their performance;
4. apply machine learning and AI techniques to predict events or states of the process, in order to recommend decisions and actions to improve operations/process in manufacturing.

You must meet one of the following collections of requirements

• Collection 1
• Completed Final examination Bsc program
• Collection 2
• Completed Pre-Master

• Selected scientific papers (accessible via TU/e library) to be made available in the course syllabus