Applications for this job are now closed
You would develop key technologies enabling the next generation electric ducted fans for advanced air mobility applications (AAM).
The role
The AAM market is booming and there are more than a hundred active startups on the market, most of them are considering options of propulsion modules for their products. As a propulsor manufacturer, the industrial partner sponsoring the project needs to deliver the most efficient and reliable product in a matter of weeks, whereas a benchmark for the development process would be 6-12 months.
For this to happen, your job would be to integrate two key technologies and implement them to the electric ducted fan design. First, there are many Machine Learning algorithms available and there are several cases of successful adoption of these into aerospace engineering. However, they normally require a large quantity of data, but the number of experimental cases usually available is limited to single digits or maximum of 10. This is why the second technology developed at the Whittle Laboratory is a capability for rapid testing of fans and compressors. Currently, it allows us to print one blade set overnight and test it in a day, therefore allowing to reach more than a hundred trial geometries tested during the project under real operating conditions.
Your role would focus on the application of the Machine Learning algorithms to the limited set of experimental data points and obtain physical understanding of the key mechanisms limiting the performance of electric ducted fans.
The post holder will be located at the Whittle Laboratory, Cambridgeshire, UK.
Responsibilities
The key responsibilities and duties are:
- Develop ML-based tool to predict electric ducted fan performance based on its design parameters. The tool is to be trained on limited experimental data points in 3-4 iterations.
- Post-processing experimental data
- Running and processing various ML algorithms
- Comparing with CFD or other low-order design methods
- Designing the next set of trial designs to be tested
- Determining first order understanding of flow physics and design principles
- Writing research publications and attending conferences
- Writing project reports and attending meetings with project partners
About you
The skills, qualifications and experience required to perform the role are:
- Knowledge of turbomachinery aerodynamics
- Experience in managing your own workload and working with initiative
- Excellent communication skills
- Experience of experimental testing in wind tunnels or rotating rigs
- Experience of CFD simulations in turbomachinery
- Experience of using machine learning tools
Fixed-term: The funds for this post are available until 31 March 2025 in the first instance.
Please ensure that you upload your Curriculum Vitae (CV) and a covering letter and publications list in the Upload section of the online application. If you upload any additional documents which have not been requested, we will not be able to consider these as part of your application. Please submit your application by midnight on the closing date.
If you have any questions of a technical nature related to the role, contact James Taylor at jvt24@cam.ac.uk, and for all other questions about the application process, please contact: Juliet Teather email jet63@cam.ac.uk
