Skip to main content

Physics-constrained adaptive learning for multi-physics optimization

Objective

About a hundred trillion bytes of data has been created in the world while reading this sentence. Central to big data is machine learning, which is an automated way of transforming information into empirical knowledge. Machine learning techniques have been applied to some fluid mechanics problems with success, but there are still three big open questions: Do machine learning algorithms scale to engineering configurations? (Are they robust?); Can we gain physical insight into the solutions? (Are they interpretable?); Can we extrapolate knowledge to other configurations, such as multi-physics problems? (Are they generalizable?).

Fluid mechanics modelling has been historically enabled by both empirical approaches and physical principles. Machine learning models may not be interpretable and robust, but they excel at empirical modelling. On the other hand, physical principles are governed by equations that do not adaptively change, but they are interpretable and robust. This project will combine physical principles and empirical modelling into a unified approach: physics-constrained adaptive learning for multi-physics optimization of unsteady, unpredictable and uncertain flows. The learned solutions will not violate physical constraints.

The technical objectives are to combine physical principles with machine learning; design adaptive multi-physics models by on-the-fly data assimilation; optimize turbulent flows; quantify the uncertainty; and develop a code that wraps around existing simulation software and experiments. This framework will be applied to maximize energy harvesting from aeroelastic systems to produce clean energy; optimize stable aeroengines with low emissions; and reconstruct high-resolution flow fields from low-resolution experimental measurements. We will rigorously interlace chaos theory, Bayesian inference and artificial intelligence. This project will benefit industries that work with multi-physics flows and artificial intelligence companies.

Field of science

  • /natural sciences/computer and information sciences/software/application software/simulation software
  • /natural sciences/physical sciences/classical mechanics/fluid mechanics
  • /engineering and technology/environmental engineering/energy and fuels/renewable energy
  • /natural sciences/computer and information sciences/data science/big data
  • /natural sciences/physical sciences/plasma physics
  • /natural sciences/computer and information sciences/artificial intelligence/machine learning

Call for proposal

ERC-2020-STG
See other projects for this call

Funding Scheme

ERC-STG - Starting Grant

Host institution

THE CHANCELLOR MASTERS AND SCHOLARSOF THE UNIVERSITY OF CAMBRIDGE
Address
Trinity Lane The Old Schools
CB2 1TN Cambridge
United Kingdom
Activity type
Higher or Secondary Education Establishments
EU contribution
€ 1 500 000

Beneficiaries (1)

THE CHANCELLOR MASTERS AND SCHOLARSOF THE UNIVERSITY OF CAMBRIDGE
United Kingdom
EU contribution
€ 1 500 000
Address
Trinity Lane The Old Schools
CB2 1TN Cambridge
Activity type
Higher or Secondary Education Establishments