Descripción del proyecto
Un aprendizaje automático que tiene en cuenta la física para la mecánica de fluidos
Tanto los principios físicos como los enfoques empíricos permiten que la modelización de la mecánica de fluidos prevea la evolución de un fluido. Por un lado, los principios físicos (por ejemplo, las leyes de conservación) se pueden extrapolar: ofrecen predicciones sobre fenómenos que no han sido observados. Por otro lado, la modelización empírica ofrece funciones de correlación en los datos. La inteligencia artificial y el aprendizaje automático resultan excelentes en cuanto a la modelización empírica. El proyecto PhyCo, financiado con fondos europeos, combinará principios físicos y la modelización empírica en un enfoque unificado: métodos basados en datos y acotados a la física para la optimización multifísica. Las soluciones de aprendizaje automático no incumplirán las restricciones físicas. El marco informático se aplicará para reconstruir flujos de imágenes de alta resolución a partir de datos de baja resolución, minimizar las emisiones de los motores aeroespaciales con flujos de reacción basados en hidrógeno y maximizar la recolección de energía con cero emisiones a partir de las oscilaciones entre fluido y estructura.
Objetivo
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.
Ámbito científico
- natural sciencescomputer and information sciencesdata sciencebig data
- natural sciencesmathematicsapplied mathematicsstatistics and probabilitybayesian statistics
- natural sciencescomputer and information sciencescomputational sciencemultiphysics
- natural sciencescomputer and information sciencesartificial intelligencemachine learning
- natural sciencescomputer and information sciencessoftwaresoftware applicationssimulation software
Palabras clave
- adjoint equations in stability
- least square shadowing
- computational fluid dynamics
- reacting flows
- machine learning in fluid mechanics
- virtualization of flows
- gas turbines
- reduced-order models of fluids
- thermoacoustic instabilities
- aeroelastic instabilities
- combustion instabilities
- acoustic-flow interaction
- proper orthogonal decomposition
- dynamic mode decomposition
- dimensionality reduction
- flow state estimator
- uncertainty quantification in fluid dynamics
- turbule
Programa(s)
Régimen de financiación
ERC-STG - Starting GrantInstitución de acogida
10129 Torino
Italia