You are a goal-oriented and self-driven professional energized by delivering high quality results and willing to learn from new experiences and your colleagues. You are passionate about helping improve the industrial systems engineering way of working by raising the relevant competences of individuals and teams.

You are familiar with systems architecting / systems engineering methods processes & required competences. You have a strong background in formal methods and experience with applying theory into practice. You have an affinity with the high-tech world and are fascinated by the role of human aspects in innovation and technology development.

The complexity of high-tech equipment is increasing because of a number of market and technology trends. One such trend is that customers want systems that are highly customized and tailored to their specific needs. The industry is addressing this by moving towards platform-based design, where new customized systems can be built by configuring a set of reusable (software) components. A challenge with this approach is that it results in many possible product configurations (variants), unique combinations of software components, to realize the functionality requested by the customer. It is currently very challenging to predict the performance of new such configurations in early stages of design, to determine whether end-to-end performance (timing) requirements will be satisfied. Currently, this is typically evaluated in late stages of development, after integration, when changes are expensive and time consuming.

High-Mix Low-Volume manufacturing challenges you with dynamic customer orders and complex production flows. Imagine using Reinforcement Learning (RL) to optimize scheduling in fast-paced domains like digital printing, where every job, from books to business cards, demands unique machine combinations and precise coordination. By designing RL agents to allocate tasks and sequence operations efficiently, you'll tackle real-world problems and shape the future of smart manufacturing. Dive into this exciting combination of AI and industry challenges, and make a direct impact on how today’s products are made!

In a model-based design of a machine’s logistics, such as those captured as LSAT or dataflow models, the scheduling of actions within given activities links closely to activity graphs found in standardized modeling languages like UML/SysML. Computing the start and end-times of nodes in such activity graphs is a key step towards analyzing the overall productivity of a flexible manufacturing system. In this project, the student will adapt and extend the modelling frameworks of LSAT and/or dataflow graphs to the computation of timings with stochastic machine behavior.

We are always looking for students for internships.