Ähnliche Jobangebote
![Logo von Northrop Grumman LITEF GmbH](https://d3f6gjnauy613m.cloudfront.net/system/production/companies/006/695/d359d7ef0302d3c32efe1f0acf0bd78a674d991b/tiny_litef-logo-pnUdZCEpgWkszAn.jpg?1724038213)
![Logo von Northrop Grumman LITEF GmbH](https://d3f6gjnauy613m.cloudfront.net/system/production/companies/006/695/d359d7ef0302d3c32efe1f0acf0bd78a674d991b/tiny_litef-logo-pnUdZCEpgWkszAn.jpg?1724038213)
![Logo von Northrop Grumman LITEF GmbH](https://d3f6gjnauy613m.cloudfront.net/system/production/companies/006/695/d359d7ef0302d3c32efe1f0acf0bd78a674d991b/tiny_litef-logo-pnUdZCEpgWkszAn.jpg?1724038213)
![Logo von Northrop Grumman LITEF GmbH](https://d3f6gjnauy613m.cloudfront.net/system/production/companies/006/695/d359d7ef0302d3c32efe1f0acf0bd78a674d991b/tiny_litef-logo-pnUdZCEpgWkszAn.jpg?1724038213)
Master thesis: Advanced AI for time series prediction in automotive safety
Jetzt bewerbenStellenbeschreibung
The Fraunhofer-Gesellschaft (www.fraunhofer.de) currently operates 76 institutes and research facilities in Germany and is the world's leading organization for application-oriented research. Around 30,800 employees work on the annual research volume of 3.0 billion euros.
The Fraunhofer Institute for High-Speed Dynamics, Ernst-Mach-Institut EMI, in Freiburg with its 300 employees offers committed people challenging and varied tasks with responsibility and a lot of creative freedom. We apply the latest scientific and research findings to specific projects in an interdisciplinary manner on behalf of our customers from various sectors of industry and government. The applications are in the fields of defense, security, aerospace, automotive and aviation.
For our institute site in Freiburg, we are offering a master thesis in the Digital Engineering group on the subject of: Advanced AI for time series prediction in automotive safety engineering.
What you will do
Background:
The Digital Engineering group develops methods to support virtual design processes of crash-loaded structures, a crucial aspect of automotive safety engineering. Through virtual crash simulation, engineers can evaluate the safety of vehicle designs across various crash scenarios. However, simulating crashes using high-res Finite Element methods requires significant computational resources and usually take a considerable amount of time (hours/days). Therefore, predicting the propagation of a crash (simulation) with a data-driven approach can provide engineers with an opportunity to make informed decisions in real-time. The main objective of this thesis is to develop advanced deep learning predictive architectures that can accurately predict the propagation of a crash simulation over time by effectively handling available sequential data.
Tasks:
The spectrum of tasks will follow an end-to-end CRISP-DM cycle, with tasks varying in intensity according to preferences and resource allocation. Key tasks include:
- Researching and evaluating existing deep learning architectures suitable for the application at hand.
- Developing and implementing custom deep learning models tailored for predicting crash simulation propagation over time building on existing solutions.
- Designing and conducting experiments to optimize model hyperparameters and architecture.
- Evaluating model performance using appropriate metrics and validation techniques.
- Investigating techniques to improve model interpretability and explainability.
- Collaborating with domain experts to validate model predictions and refine the predictive capabilities.
- Documenting research findings, methodologies, and results for dissemination and publication.
- Exploring opportunities to integrate the developed models into existing crash simulation frameworks.
What you bring to the table
- Enrolled in a Master’s program in Engineering, Physics or Mathematics.
- Prior knowledge and research experience in the field of structural mechanics, finite element simulations, and passive safety engineering is highly desirable.
- Prior knowledge and research experience in Data Analysis and Machine Learning (RNNs & Transformers) is highly desirable.
- Proficiency in programming languages such as Python and experience with deep learning frameworks (e.g. TensorFlow).
- Analytical thinking and a proactive, innovative approach to problem-solving
- Excellent communication skills and ability to work collaboratively in a team
- Reliable and independent work approach
What you can expect
- Very good supervision by experienced scientists who will support you in your work.
- Interdisciplinary collaboration with colleagues from different fields.
- Very good working atmosphere in a state-of-the-art working environment equipped with the latest technologies and resources.
- Opportunity to participate in groundbreaking research projects.
The weekly working time is 39 hours. We value and promote the diversity of our employees' skills and therefore welcome all applications - regardless of age, gender, nationality, ethnic and social origin, religion, ideology, disability, sexual orientation and identity. Severely disabled persons are given preference in the event of equal suitability. Remuneration according to the general works agreement for employing assistant staff.
With its focus on developing key technologies that are vital for the future and enabling the commercial utilization of this work by business and industry, Fraunhofer plays a central role in the innovation process. As a pioneer and catalyst for groundbreaking developments and scientific excellence, Fraunhofer helps shape society now and in the future.
Interested? Apply online now. We look forward to getting to know you!
Please apply online with your complete application documents (cover letter, CV, certificate of enrollment, work permit if applicable)!
For questions about this position, please contact:
Katriya Seitz
Recruiting
Katriya.Seitz@emi.fraunhofer.de
Fraunhofer Institute for High-Speed Dynamics, Ernst-Mach-Institut EMI
Requisition Number: 72964