What is this project about?
As a Turing Fellow, Kit Windows-Yule has led and contributed to a number of Data Study Groups (DSGs) run by the Alan Turing Institute. DSGs are a unique sprint research activity in which a group of around ten PhD-level data science and AI experts from diverse fields come together to address a significant challenge proposed by an industrial or governmental “Challenge Owner”.
In one of the more notable projects, the Challenge Owner was Rolls-Royce, and the aim of the challenge was to use AI methods to develop new ideas for ways to optimise the production of turbine blades — minimising the waste and cost associated with defective parts.
In order to operate optimally, a whole turbine blade must be formed from a single crystal: all its constituent atoms must be organised neatly into a single crystalline lattice. Without such single crystal components, which are capable of operating in the very hottest parts of an aeroplane engine, it is impossible to manufacture the modern jet engine. Despite decades of advances, challenges remain in identifying and overcoming the reasons for failure to achieve a single crystal in each and every casting. Because multiple mechanisms result in the formation and growth of secondary grains, the experiments required to separate them are too costly and too slow to perform in practice. A data-driven approach to solving this problem could prove transformative.
During the DSG, a variety of AI and data science methods were tested, including convolutional neural networks (CNNs), generative adversarial networks (GANs), and topological data analysis. While a complete solution could not realistically be obtained within the DSG timeframe, several approaches showed significant promise. As a result, funding was secured to continue exploring these methods in a PhD project stemming from the initial exploratory work.
Why was Baskerville chosen?
Baskerville was chosen for two main reasons: the scale of the challenge, and the sensitivity of the data.
The data provided by Rolls-Royce included over 3 GB of process data and around 185 GB of 3D images. In order to process these data and develop and train novel AI models within the restrictive one-week DSG timeframe, significant compute power was required. Baskerville’s 208 NVIDIA A100 GPUs provided the ideal solution.
Regarding the latter, despite being desensitised, the data used for the study represented real Rolls-Royce process data and was decidedly commercially sensitive. The secure environment provided by Baskerville allowed the data to be handled and processed safely, without fear of data leaks. Without the security assurances offered by Baskerville, this project could not have gone ahead.
How has Baskerville been useful?
In addition to the extreme compute power and data security described above, the system’s flexibility and ease of use were also pivotal to the project’s success. Due to the nature of the DSG, researchers from different institutions around the world had to learn to use an HPC they had never worked on before within a very limited timeframe. The extensive documentation and training resources available, as well as the excellent support provided by the Advanced Research Computing (ARC) team, ensured that participants could get up to speed quickly and make full use of the time and resources available to them.