Student (f/m/x) machine learning, informatics, engineering, physics or similar

Steigen Sie ein in die faszinierende Welt des Deutschen Zentrums für Luft- und Raumfahrt (DLR), um mit Forschung und Innovation die Zukunft mitzugestalten! Mit dem Know-how und der Neugier unserer 11.000 Mitarbeitenden aus 100 Nationen sowie unserer einzigartigen Infrastruktur, bieten wir ein spannendes und inspirierendes Arbeitsumfeld. Gemeinsam entwickeln wir nachhaltige Technologien und tragen so zur Lösung globaler Herausforderungen bei. Möchten Sie diese große Zukunftsaufgabe mit uns zusammen angehen? Dann ist Ihr Platz bei uns!

For our Insitute of Solar Research in Köln we are looking for a Student (f/m/x) machine learning, informatics, engineering, physics or similar, Artificial Intelligence for optimized Solar Power Plant operation

Das erwartet Sie:

At the German Aerospace Center's (DLR) Institute of Solar Research, our goal is to make environmentally friendly energy supply both technically and economically viable through cutting-edge Artificial Intelligence (AI) techniques. In the Solar Power Plant Technology department, we focus on developing and testing machine learning methods for intelligent and autonomous solar tower power plants. In a solar power plant, heliostats—mirrors with two-axis tracking capabilities—focus sunlight onto a central receiver. Each heliostat has distinct surface imperfections that, if left undetected, can undermine the safety and efficiency of the plant's operation. Over the past year, we have developed a cutting-edge machine learning technique called inverse Deep Learning Raytracing (iDLR) [1], which enables us to accurately predict the condition of heliostat surfaces using data collected during the plant’s regular operations. This project seeks to implement this innovative method with new data and heliostat types from a solar power facility in Spain. We are looking for a highly motivated individual who wants to do both in our reasearch group, a mandatory internship and the subsequent master thesis.

[1] http://www.arxiv.org/abs/2408.10802

You taks during the internship and the master thesis will be:

• Setup our heliostat digital twin for the new heliostat type
• Setup the digital raytracing environment of the power plant and validate it against the real data
• Train the deep learning model with the simulated data from the raytracing environment and transfer them to real data
• Find solution to scientific question that will arise during the project
• Compare the heliostat surface predictions and compare them to existing measurements

You look for mandatory internship and master thesis in one of the following degrees: machine leraning, computer science, mechanical engineering, mathematics, physics, automation technology, electrical engineering, or a related field.

Das erwarten wir von Ihnen:

• You possess very good knowledge of Python and PyTorch, enabling you to work independently on state-of-the-art deep learning models
• You have a basic understand of raytracing and you are interested in executing optical simulations
• You demonstrate above-average academic performance and have prior knowledge in deep learning, ideally image generation
• You are characterized by a structured, independent, and goal-oriented way of working
• You have very good English skills necessary for studying technical litera- ture
• You will be part of an interdisciplinary and international team of scientists from the fields of engineering, physics, informatics and mathematics
• Our departments have experts in both modeling machine learning pipelines and experimental validation, who will be happy to support you.

Unser Angebot:

Das DLR steht für Vielfalt, Wertschätzung und Gleichstellung aller Menschen. Wir fördern eigenverantwortliches Arbeiten und die individuelle Weiterentwicklung unserer Mitarbeitenden im persönlichen und beruflichen Umfeld. Dafür stehen Ihnen unsere zahlreichen Fort- und Weiterbildungsmöglichkeiten zur Verfügung. Chancengerechtigkeit ist uns ein besonderes Anliegen, wir möchten daher insbesondere den Anteil von Frauen in der Wissenschaft und Führung erhöhen. Bewerbungen schwerbehinderter Menschen bevorzugen wir bei fachlicher Eignung.

Weitere Angaben:

• Eintrittsdatum: 01.12.2024
• Dauer: 9 monthes
• Vergütung: Je nach Qualifikation und Aufgabenübertragung bis Entgeltgruppe 05 TVöD.
• Kennziffer: 98437