June 1, 2020
A two-year NSERC Alliance grant was recently awarded to a consortium of two University of British Columbia research clusters--the Composite Research Network and Data Science Institute--for their project "Data Science & Composite Materials Manufacturing". This project aims to apply breakthroughs in data science, machine learning, and probabilistic programming to innovate and accelerate manufacturing and design of composite materials, specifically for the aerospace sector. This crucial funding will support the consortium's mission to interweave two complementary, yet to-date, poorly connected digital threads: data science with engineering science to advance Canada's position in advanced materials manufacturing.
Over the past two decades, we have witnessed the emergence of the so-called "Big Data" era. This is driven by breakthroughs in learning from massive quantities of rich, complex data, to building sophisticated models and extracting insightful patterns from them. Numerous application domains, such as in finance, medicine, and so on, have benefited from these new methods in data science, machine learning, artificial intelligence, and computational statistics. However, the application domain of advanced manufacturing, particularly in composite materials, has yet to harness and leverage the advances in the aforementioned technologies. In particular, the CRN-DSI consortium is motivated by the problem of composite (e.g., carbon fibre) part autoclave curing in aerospace engineering, and applying advances in data science, machine learning, and probabilistic programming to better understand and predict the physical processes during composites manufacturing, where the primary goals are to:
- Infer the internal states of the composite part as it cures;
- Predict deviations from nominal final part dimensions; and
- Optimize the curing process to minimize defects, cost, and time wasted.
The ultimate outcome is to reduce costly decisions (i.e., time, financial) in the design and manufacturing of composites--ultimately leading to increased efficiency and better products.
This collaborative effort involves a team of faculty and students from UBC Composites Research Network, UBC Data Science Institute, UBC Computer Science, and UBC Statistics. The consortium is partially funded by Convergent Technologies, Canada's Digital Technology Supercluster, and UBC VPRI.