Enter the fascinating world of the German Aerospace Center (Deutsches Zentrum für Luft- und Raumfahrt; DLR) and help shape the future through research and innovation! We offer an exciting and inspiring working environment driven by the expertise and curiosity of our 11,000 employees from 100 nations and our unique infrastructure. Together, we develop sustainable technologies and thus contribute to finding solutions to global challenges. Would you like to join us in addressing this major future challenge? Then this is your place!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 operationWhat to expect: 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. What we expect from you:
- 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.DLR stands for diversity, appreciation and equality for all people. We promote independent work and the individual development of our employees both personally and professionally. To this end, we offer numerous training and development opportunities. Equal opportunities are of particular importance to us, which is why we want to increase the proportion of women in science and management in particular. Applicants with severe disabilities will be given preference if they are qualified. Further information: Starting date: 01.12.2024
Duration of contract: 9 months
Type of employment: part-time Remuneration: up to the German TVöD 05 Vacancy-ID: 98437
Contact:
Jan Lewen
Insitut für Solarforschung
Tel.: 02203 601 1326
