PhD for AI in Aerospace Manufacturing
Updated: 13 May 2021
Problem to be solved:
The space, aerospace, and other precision manufacturing industries rely on tightly controlled, closely monitored processes to ensure that materials and structures are built with the highest reliability possible. Artificial Intelligence (AI) is evolving to create a number of industry-changing improvements across the material design and structure manufacturing process. Unfortunately, many forms of AI are complex, obtuse, and deliver volatile results unless specific care is used to ensure stability.
Because of this challenge, AI must be developed in a way that matches the strategic directives of key regulatory organizations. EASA and ESA have released their roadmaps for incorporating AI into the aerospace/space industries, noting the risks and necessary mitigations.
Potential areas of research for this position:
The TU Delft Aerospace Engineering Faculty is developing a number of projects to directly address this challenge. A key to using AI for space-related certification is developing a true digital twin; we are working to develop processes that incorporate the high fidelity finite element modelling currently used for certification, develop more robust modelling through neural networks, then create a feedback loop through experimental prototyping that improves the new modelling parameters. We are also working with neural networks to expand the purpose and capability of coupon-level testing to component-level testing, with similar confidence levels.
As the design of materials are complete and the manufacturing process begins, another key opportunity for AI-enabled certification is through inspection. We propose the development of a comprehensive sensor suite to be used specifically for space-rated requirements. The sensors collect data both during and after manufacture (especially in the additive manufacturing area), measuring through optical, IR, thermal, CT, X-ray, induction, temp/humidity, shock/vibe, load, strain, and other measurements depending on the material. Doing so would help establish a very specific set of environmental and material requirements to be considered certified right on the first build. It would also enable a much more sensitive level of determining potential errors or defects in the manufacturing process with the use of machine learning algorithms. This data package could also act as a certification pedigree, allowing auditors to review the entire manufacturing process after the fact, which may enable more flexible and modular manufacturing processes to maintain certification.
We are also looking beyond the manufacturing process to create a wealth of product life-cycle data that could be monitored and used to continuously improve the materials and structures developed for a given mission. We are researching methods to incorporate sensor grids into manufactured composites, which would allow benefits such as predictive maintenance, continuous monitoring, and rich amounts of on-mission data to better enable the design modelling and manufacturing processes, thus developing a continuously improving feedback loop.
Strong experience in artificial intelligence (AI), machine learning (ML), and data science.
Research focus has been in the area of manufacturing; preferably in the aerospace, space, or other precision manufacturing industries.
- Desired Experience:
- Additive Manufacturing
- Augmented Reality
- AI/ML hardware and software builds
- Python or similar programming language
- Data visualization
TU Delft offers PhD-candidates a 4-year contract, with an official go/no go progress assessment after one year. Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities, increasing from € 2395 per month in the first year to € 3061 in the fourth year. As a PhD candidate you will be enrolled in the TU Delft Graduate School. The TU Delft Graduate School provides an inspiring research environment with an excellent team of supervisors, academic staff and a mentor. The Doctoral Education Programme is aimed at developing your transferable, discipline-related and research skills.
The TU Delft offers a customisable compensation package, discounts on health insurance and sport memberships, and a monthly work costs contribution. Flexible work schedules can be arranged. For international applicants we offer the Coming to Delft Service and Partner Career Advice to assist you with your relocation.
38 hours per week