Pasar al contenido principal

APRENDIZAJE Y DESCUBRIMIENTO DE MODELOS GUIADO POR LA FISICA

PID2020-113463RB-C31

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2020
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD DE ZARAGOZA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 15
Encontrada(s) 1 página(s)

Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Modeling systems from partial observations

  • Champaney, Victor
  • Amores, Víctor J.
  • Garois, Sevan
  • Irastorza-Valera, Luis
  • Ghnatios, Chady
  • Montáns, Francisco J.
  • Cueto, Elías
  • Chinesta, Francisco
Modeling systems from collected data faces two main difficulties: the first one concerns the choice of measurable variables that will define the learnt model features, which should be the ones concerned by the addressed physics, optimally neither more nor less than the essential ones. The second one is linked to accessibility to data since, generally, only limited parts of the system are accessible to perform measurements. This work revisits some aspects related to the observation, description, and modeling of systems that are only partially accessible and shows that a model can be defined when the loading in unresolved degrees of freedom remains unaltered in the different experiments.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

A thermodynamics-informed active learning approach to perception and reasoning about fluids

  • Moya, Beatriz
  • Badías, Alberto
  • González, David
  • Chinesta, Francisco
  • Cueto, Elías
Learning and reasoning about physical phenomena is still a challenge in robotics development, and computational sciences play a capital role in the search for accurate methods able to provide explanations for past events and rigorous forecasts of future situations. We propose a thermodynamics-informed active learning strategy for fluid perception and reasoning from observations. As a model problem, we take the sloshing phenomena of different fluids contained in a glass. Starting from full-field and high-resolution synthetic data for a particular fluid, we develop a method for the tracking (perception) and simulation (reasoning) of any previously unseen liquid whose free surface is observed with a commodity camera. This approach demonstrates the importance of physics and knowledge not only in data-driven (gray-box) modeling but also in real-physics adaptation in low-data regimes and partial observations of the dynamics. The presented method is extensible to other domains such as the development of cognitive digital twins able to learn from observation of phenomena for which they have not been trained explicitly.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Thermodynamics-informed neural networks for physically realistic mixed reality

  • Hernández, Quercus
  • Badías, Alberto
  • Chinesta, Francisco
  • Cueto, Elías
The imminent impact of immersive technologies in society urges for active research in real-time and interactive physics simulation for virtual worlds to be realistic. In this context, realistic means to be compliant to the laws of physics. In this paper we present a method for computing the dynamic response of (possibly non-linear and dissipative) deformable objects induced by real-time user interactions in mixed reality using deep learning. The graph-based architecture of the method ensures the thermodynamic consistency of the predictions, whereas the visualization pipeline allows a natural and realistic user experience. Two examples of virtual solids interacting with virtual or physical solids in mixed reality scenarios are provided to prove the performance of the method.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Physics perception in sloshing scenes with guaranteed thermodynamic consistency

  • Moya, Beatriz
  • Badias, Alberto
  • Gonzalez, David
  • Chinesta, Francisco
  • Cueto, Elías
Physics perception very often faces the problem that only limited data or partial measurements on the scene are available. In this work, we propose a strategy to learn the full state of sloshing liquids from measurements of the free surface. Our approach is based on recurrent neural networks (RNN) that project the limited information available to a reduced-order manifold to not only reconstruct the unknown information but also be capable of performing fluid reasoning about future scenarios in real-time. To obtain physically consistent predictions, we train deep neural networks on the reduced-order manifold that, through the employ of inductive biases, ensure the fulfillment of the principles of thermodynamics. RNNs learn from history the required hidden information to correlate the limited information with the latent space where the simulation occurs. Finally, a decoder returns data to the high-dimensional manifold, to provide the user with insightful information in the form of augmented reality. This algorithm is connected to a computer vision system to test the performance of the proposed methodology with real information, resulting in a system capable of understanding and predicting future states of the observed fluid in real-time.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Port-metriplectic neural networks: thermodynamics-informed machine learning of complex physical systems

  • Hernández, Quercus
  • Badías, Alberto
  • Chinesta, Francisco
  • Cueto, Elías
We develop inductive biases for the machine learning of complex physical systems based on the port-Hamiltonian formalism. To satisfy by construction the principles of thermodynamics in the learned physics (conservation of energy, non-negative entropy production), we modify accordingly the port-Hamiltonian formalism so as to achieve a port-metriplectic one. We show that the constructed networks are able to learn the physics of complex systems by parts, thus alleviating the burden associated to the experimental characterization and posterior learning process of this kind of systems. Predictions can be done, however, at the scale of the complete system. Examples are shown on the performance of the proposed technique.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Regularized regressions for parametric models based on separated representations

  • Sancarlos, Abel
  • Champaney, Víctor
  • Cueto, Elías
  • Chinesta, Francisco
Regressions created from experimental or simulated data enable the construction of metamodels, widely used in a variety of engineering applications. Many engineering problems involve multi-parametric physics whose corresponding multi-parametric solutions can be viewed as a sort of computational vademecum that, once computed offline, can be then used in a variety of real-time engineering applications including optimization, inverse analysis, uncertainty propagation or simulation based control. Sometimes, these multi-parametric problems can be solved by using advanced model order reduction—MOR-techniques. However, solving these multi-parametric problems can be very costly. In that case, one possibility consists in solving the problem for a sample of the parametric values and creating a regression from all the computed solutions. The solution for any choice of the parameters is then inferred from the prediction of the regression model. However, addressing high-dimensionality at the low data limit, ensuring accuracy and avoiding overfitting constitutes a difficult challenge. The present paper aims at proposing and discussing different advanced regressions based on the proper generalized decomposition (PGD) enabling the just referred features. In particular, new PGD strategies are developed adding different regularizations to the s-PGD method. In addition, the ANOVA-based PGD is proposed to ally them.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Optimal velocity planning based on the solution of the Euler-Lagrange equations with a neural network based velocity regression

  • Ghnatios, Chady
  • di Lorenzo, Daniele
  • Champaney, Víctor
  • Cueto, Elías
  • Chinesta, Francisco
Trajectory optimization is a complex process that includes an infinite number of possibilities and combinations. This work focuses on a particular aspect of the trajectory optimization, related to the optimization of a velocity along a predefined path, with the aim of minimizing power consumption. To tackle the problem, a functional formulation and minimization strategy is developed, by means of the Euler-Lagrange equation. The minimization is later performed using a neural network approach. The strategy is deemed Lagrange-Net, as it is based on the minimization of the energy functional, by the means of Lagrange's equation and neural network approximations.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Reseña (Review)

Thermodynamics of Learning Physical Phenomena

  • Cueto, Elias
  • Chinesta, Francisco
Thermodynamics could be seen as an expression of physics at a high epistemic level. As such, its potential as an inductive bias to help machine learning procedures attain accurate and credible predictions has been recently realized in many fields. We review how thermodynamics provides helpful insights in the learning process. At the same time, we study the influence of aspects such as the scale at which a given phenomenon is to be described, the choice of relevant variables for this description or the different techniques available for the learning process.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Conciliating accuracy and efficiency to empower engineering based on performance: a short journey

  • Chinesta, Francisco
  • Cueto, Elias
This paper revisits the different arts of engineering. The art of modeling for describing the behavior of complex systems from the solution of partial differential equations that are expected to govern their responses. Then, the art of simulation concerns the ability of solving these complex mathematical objects expected to describe the physical reality as accurately as possible (accuracy with respect to the exact solution of the models) and as fast as possible. Finally, the art of decision making needs to ensure accurate and fast predictions for efficient diagnosis and prognosis. For that purpose physics-informed digital twins (also known as Hybrid Twins) will be employed, allying real-time physics (where complex models are solved by using advanced model order reduction techniques) and physics-informed data-driven models for filling the gap between the reality and the physics-based model predictions. The use of physics-aware data-driven models in tandem with physics-based reduced order models allows us to predict very fast without compromising accuracy. This is compulsory for diagnosis and prognosis purposes.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

A graph convolutional autoencoder approach to model order reduction for parametrized PDEs

  • Pichi, Federico
  • Moya, Beatriz
  • Hesthaven, Jan S.
The present work proposes a framework for nonlinear model order reduction based on a Graph Convolutional Autoencoder (GCA-ROM). In the reduced order modeling (ROM) context, one is interested in obtaining real-time and many-query evaluations of parametric Partial Differential Equations (PDEs). Linear techniques such as Proper Orthogonal Decomposition (POD) and Greedy algorithms have been analyzed thoroughly, but they are more suitable when dealing with linear and affine models showing a fast decay of the Kolmogorov n-width. On one hand, the autoencoder architecture represents a nonlinear generalization of the POD compression procedure, allowing one to encode the main information in a latent set of variables while extracting their main features. On the other hand, Graph Neural Networks (GNNs) constitute a natural framework for studying PDE solutions defined on unstructured meshes. Here, we develop a non-intrusive and data-driven nonlinear reduction approach, exploiting GNNs to encode the reduced manifold and enable fast evaluations of parametrized PDEs. We show the capabilities of the methodology for several models: linear/nonlinear and scalar/vector problems with fast/slow decay in the physically and geometrically parametrized setting. The main properties of our approach consist of (i) high generalizability in the low-data regime even for complex behaviors, (ii) physical compliance with general unstructured grids, and (iii) exploitation of pooling and un-pooling operations to learn from scattered data.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Casting hybrid twin: physics-based reduced order models enriched with data-driven models enabling the highest accuracy in real-time

  • Ammar, Amine
  • Ben Saada, Mariem
  • Cueto, Elias
  • Chinesta, Francisco
Knowing the thermo-mechanical history of a part during its processing is essential to master the final properties of the product. During forming processes, several parameters can affect it. The development of a surrogate model makes it possible to access history in real time without having to resort to a numerical simulation. We restrict ourselves in this study to the cooling phase of the casting process. The thermal problem has been formulated taking into account the metal as well as the mould. Physical constants such as latent heat, conductivities and heat transfer coefficients has been kept constant. The problem has been parametrized by the coolant temperatures in five different cooling channels. To establish the offline model, multiple simulations are performed based on well-chosen combinations of parameters. The space-time solution of the thermal problem has been solved parametrically. In this work we propose a strategy based on the solution decomposition in space, time, and parameter modes. By applying a machine learning strategy, one should be able to produce modes of the parametric space for new sets of parameters. The machine learning strategy uses either random forest or polynomial fitting regressors. The reconstruction of the thermal solution can then be done using those modes obtained from the parametric space, with the same spatial and temporal basis previously established. This rationale is further extended to establish a model for the ignored part of the physics, in order to describe experimental measures. We present a strategy that makes it possible to calculate this ignorance using the same spatio-temporal basis obtained during the implementation of the numerical model, enabling the efficient construction of processing hybrid twins.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Optimal trajectory planning combining model-based and data-driven hybrid approaches

  • Ghnatios, Chady
  • Di Lorenzo, Daniele
  • Champaney, Victor
  • Ammar, Amine
  • Cueto, Elias
  • Chinesta, Francisco
Trajectory planning aims at computing an optimal trajectory through the minimization of a cost function. This paper considers four different scenarios: (i) the first concerns a given trajectory on which a cost function is minimized by a acting on the velocity along it; (ii) the second considers trajectories expressed parametrically, from which an optimal path and the velocity along it are computed; (iii), the case in which only the departure and arrival points of the trajectory are known, and the optimal path must be determined; and finally, (iv) the case involving uncertainty in the environment in which the trajectory operates. When the considered cost functions are expressed analytically, the application of Euler–Lagrange equations constitutes an appealing option. However, in many applications, complex cost functions are learned by using black-box machine learning techniques, for instance deep neural networks. In such cases, a neural approach of the trajectory planning becomes an appealing alternative. Different numerical experiments will serve to illustrate the potential of the proposed methodologies on some selected use cases.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Structure-preserving formulations for data-driven analysis of coupled multi-physics systems

  • Muixí, Alba
  • González, David
  • Chinesta, Francisco
  • Cueto, Elías
We develop a novel methodology for data-driven simulation of coupled multi-physics systems. The result of the method is a learned numerical integrator of the coupled system dynamics. In order to preserve the fundamental physics of the coupled systems, and thus preserve the geometrical properties of the governing equations—even if they may be completely unknown—we impose a port-metriplectic structure on the system evolution, i.e., a combination of a symplectic evolution for the system energy with a gradient flow for the entropy of each system, which can be exchanged through predefined ports. The resulting method guarantees by construction the satisfaction of the laws of thermodynamics for open systems, leading to accurate predictions of the future states of their dynamics. Examples are given for systems of varying complexity, based on synthetic as well as experimental data.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

Thermodynamics-informed super-resolution of scarce temporal dynamics data

  • Bermejo-Barbanoj, Carlos
  • Moya, Beatriz
  • Badías, Alberto
  • Chinesta, Francisco
  • Cueto, Elías
We present a method to increase the resolution of measurements of a physical system and subsequently predict its time evolution using thermodynamics-aware neural networks. Our method uses adversarial autoencoders, which reduce the dimensionality of the full order model to a set of latent variables that are enforced to match a prior, for example a normal distribution. Adversarial autoencoders are seen as generative models, and they can be trained to generate high-resolution samples from low-resolution inputs, meaning they can address the so-called super-resolution problem. Then, a second neural network is trained to learn the physical structure of the latent variables and predict their temporal evolution. This neural network is known as a structure-preserving neural network. It learns the metriplectic-structure of the system and applies a physical bias to ensure that the first and second principles of thermodynamics are fulfilled. The integrated trajectories are decoded to their original dimensionality, as well as to the higher dimensionality space produced by the adversarial autoencoder and they are compared to the ground truth solution. The method is tested with two examples of flow over a cylinder, where the fluid properties are varied between both examples.
Zaguán. Repositorio Digital de la Universidad de Zaragoza
Publicación Artículo científico (JournalArticle)

A comparison of single and double generator formalisms for thermodynamics-informed neural networks

  • Urdeitx, Pau
  • Alfaro, Icíar
  • González, David
  • Chinesta, Francisco
  • Cueto, Elías
The development of inductive biases has been shown to be a very effective way to increase the accuracy and robustness of neural networks, particularly when they are used to predict physical phenomena. These biases significantly increase the certainty of predictions, decrease the error made and allow considerably smaller datasets to be used. There are a multitude of methods in the literature to develop these biases. One of the most effective ways, when dealing with physical phenomena, is to introduce physical principles of recognised validity into the network architecture. The problem becomes more complex without knowledge of the physical principles governing the phenomena under study. A very interesting possibility then is to turn to the principles of thermodynamics, which are universally valid, regardless of the level of abstraction of the description sought for the phenomenon under study. To ensure compliance with the principles of thermodynamics, there are formulations that have a long tradition in many branches of science. In the field of rheology, for example, two main types of formalisms are used to ensure compliance with these principles: one-generator and two-generator formalisms. In this paper we study the advantages and disadvantages of each, using classical problems with known solutions and synthetic data.