Master thesis - From process parameter recipes to process intent in LPBF
- Heltid
Master thesis - From process parameter recipes to process intent in LPBF
About the Role
Job ID 304989 Location Sweden Oestergoetlands laen Finspaang Company Siemens Energy AB Organization Gas Services Business Unit Distributed Full / Part time Full-time Experience Level Student / Intern / Apprentice
Master Thesis – The future of laser powder bed fusion: From Fixed Recipes to Adaptive Manufacturing
A Snapshot of Your Day
Imagine developing a new LPBF component without first having to search for or develop the "right" parameter recipe. In this Master Thesis, you will explore how we can move from today's recipe-based manufacturing towards a self-adaptive process where the desired outcome, such as density, geometry, surface quality and productivity, determines how the component should be manufactured.
You will work with real manufacturing and monitoring data and investigate how material properties, geometry, thermal history and in-situ process information can be used to predict manufacturing outcomes and ultimately recommend suitable manufacturing strategies. The work connects additive manufacturing with areas such as Optical Tomography, digital twins, adaptive process control and data-driven manufacturing.
The ambition is bigger than optimizing another parameter set. The thesis asks whether we can eventually remove the need for traditional parameter recipes altogether, enabling a more scalable and adaptive approach to LPBF manufacturing.
How You’ll Make an Impact
- Analyze historical LPBF manufacturing data to understand the complexity and engineering effort associated with today's parameter-recipe approach.
- Develop a feature-based description of the manufacturing process using factors such as geometry, material, thermal history, build position and neighboring-part interaction.
- Explore how Optical Tomography, monitoring data, process settings and geometry information can be used to predict outcomes such as density, porosity, dimensional accuracy, distortion and surface quality
- Develop and evaluate an intent-based recommendation concept that translates quality and productivity requirements into appropriate manufacturing actions and process settings.
- Challenge the developed approach using a new geometry or material and investigate its potential for a first-time-right manufacturing strategy without developing a new parameter recipe.
What You Bring
- You are studying towards a Master's degree in Mechanical Engineering, Additive Manufacturing, Materials Engineering, Production Engineering, Applied Physics, Data Science, Machine Learning or a related field.
- You are curious about the intersection between physical manufacturing processes, engineering and data-driven methods, and want to solve problems with real industrial relevance.
- You have an analytical mindset and are comfortable working with complex datasets; experience with Python, MATLAB or similar data-analysis tools is beneficial.
- Knowledge of LPBF/additive manufacturing, process monitoring, machine learning, digital twins or manufacturing simulation is an advantage, but we value curiosity and the ability to learn just as highly.
- You enjoy taking an open research question, structuring it into testable hypotheses and translating the results into practical engineering solutions.
- You are comfortable working collaboratively with specialists from different technical disciplines while also driving your own thesis work independently.