Indice
Letteratura scientifica selezionata sul tema "Apprentissage automatique informé par la physique"
Cita una fonte nei formati APA, MLA, Chicago, Harvard e in molti altri stili
Consulta la lista di attuali articoli, libri, tesi, atti di convegni e altre fonti scientifiche attinenti al tema "Apprentissage automatique informé par la physique".
Accanto a ogni fonte nell'elenco di riferimenti c'è un pulsante "Aggiungi alla bibliografia". Premilo e genereremo automaticamente la citazione bibliografica dell'opera scelta nello stile citazionale di cui hai bisogno: APA, MLA, Harvard, Chicago, Vancouver ecc.
Puoi anche scaricare il testo completo della pubblicazione scientifica nel formato .pdf e leggere online l'abstract (il sommario) dell'opera se è presente nei metadati.
Tesi sul tema "Apprentissage automatique informé par la physique"
Deng, Weikun. "Amélioration du diagnostic et du pronostic dans des conditions de données rares et de connaissances limitées par l'apprentissage automatique informé par la physique et auto-supervisé". Electronic Thesis or Diss., Université de Toulouse (2023-....), 2024. http://www.theses.fr/2024TLSEP107.
Testo completoThis thesis addresses the critical challenge of “sparse data and scarce knowledge” in developing a generic Prognostics and Health Management (PHM) model. A comprehensive literature review highlights the efficacy of hybrid models combining physics-based modeling with machine learning, focusing on Physics-Informed Machine Learning (PIML) and Self-Supervised Learning (SSL) for enhanced learning from unlabeled data. Thereby, this thesis contributes to advancing both PIML and SSL theories and their practical applications in PHM.The first contribution is developing a generic architectural and learning strategy solution for PIML. Various informed approaches are analyzed, and the mimetic theory is proposed to design flexible, physically consistent neurons and interlayer connections. This novel approach leads to the development of the Rotor Finite Elements Mimetic Neural Network (RFEMNN), which mimics rotor finite element-based dynamics to adjust weight distribution and data flow within the neural network. RFEMNN effectively localizes and recognizes compound faults across multiple rotor structures and conditions. To enhance RFEMNN's few-shot diagnostic capability, constraint projection theory and a reinforcement learning strategy are proposed, aligning the learning process with physics. A generic PIML architecture with parallel, independent PI and data-driven branches is proposed, involving a three-stage training process: pre-training the data-driven branch, freezing it to train the PI branch, and joint training of both branches. This method combines optimized local branches into a comprehensive global model, ensuring the PIML model's performance exceeds original data-driven models under spare data context. Moreover, the solid electrolyte interphase growth-informed Dilated CNN model using this approach showcases its superiority, surpassing leading models in predicting lithium-ion battery RUL with small-cycle data.The second contribution is developing an innovative SSL strategy for unlabeled data learning, introducing a Siamese CNN-LSTM model with a custom contrastive loss function. This model extracts robust feature representations by maximizing differences in the same samples presented in varied sequential orders. Variants of downstream tasks are proposed as intermediate objectives in SSL pretext learning, integrating downstream structures into the pre-training model to align representations with downstream requirements. Under this strategy, the proposed Siamese CNN-LSTM excels at predicting RUL on PRONOSTIA-bearing dataset and remains stable even as training data sparsity increases.The final contribution extends PIML concepts for active knowledge discovery on unlabeled data and integrates SSL into the second phase of PIML's three-step training, utilizing both labeled and unlabeled data. A novel Liquid PI structure and an end-to-end Liquid PI-CNN-Selective state space model (CNN-SSM) are developed. The Liquid PI design introduces gated neurons and liquid interlayer connections that adapt dynamically, acquiring physics knowledge through an optimized search within a predefined operator pool. Demonstrated in torque monitoring of robot manipulators, this approach efficiently discovers knowledge using basic physical operators and dynamic weights from unlabeled data. The Liquid PI CNN-SSM processes variable-length input sequences without signal preprocessing, optimizing resources by requiring only 600 KB to handle 23.9 GB of data. It achieves state-of-the-art performance in mixed prognostic tasks, including bearing degradation, tool wear, battery aging, and CFRP tube fatigue, showcasing the originality and versatility of the proposed approach.Future work will apply PHM-specific scaling laws and train on extensive synthetic and industry datasets to build a cross-modal macro-model. It could integrate diagnostic-prognostic capabilities with infinite sequence length processing, continuing to transform PHM methodologies and solutions
Quattromini, Michele. "Graph Neural Networks for fluid mechanics : data-assimilation and optimization". Electronic Thesis or Diss., université Paris-Saclay, 2024. http://www.theses.fr/2024UPAST161.
Testo completoThis PhD thesis investigates the application of Graph Neural Networks (GNNs) in the field of Computational Fluid Dynamics (CFD), with a focus on data-assimilation and optimization. The work is structured into three main parts: data-assimilation for Reynolds-Averaged Navier-Stokes (RANS) equations based on GNN models; data-assimilation augmented by GNN and adjoint-based enforced physical constraint; fluid systems optimization by ML techniques. In the first part, the thesis explores the potential of GNNs to bypass traditional closure models, which often require manual calibration and are prone to inaccuracies. By leveraging high-fidelity simulation data, GNNs are trained to directly learn the unresolved flow quantities, offering a more flexible framework for the RANS closure problem. This approach eliminates the need for manually tuned closure models, providing a generalized and data-driven alternative. Moreover, in this first part, a comprehensive study of the impact of data quantity on GNN performance is conducted, designing an Active Learning strategy to select the most informative data among those available. Building on these results, the second part of the thesis addresses a critical challenge often faced by ML models: the lack of guaranteed physical consistency in their predictions. To ensure that the GNNs not only minimize errors but also produce physically valid results, this part integrates physical constraints directly into the GNN training process. By embedding key fluid mechanics principles into the machine learning framework, the model produces predictions that are both reliable and consistent with the underlying physical laws, enhancing its applicability to real-world problems. In the third part, the thesis demonstrates the application of GNNs to optimize fluid dynamics systems, with a particular focus on wind turbine design. Here, GNNs are employed as surrogate models, enabling rapid predictions of various design configurations without the need for performing a full CFD simulation at each iteration. This approach significantly accelerates the design process and demonstrates the potential of ML-driven optimization in CFD workflows, allowing for more efficient exploration of design spaces and faster convergence toward optimal solutions. On the methodology side, the thesis introduces a custom GNN architecture specifically tailored for CFD applications. Unlike traditional neural networks, GNNs are inherently capable of handling unstructured mesh data, which is common in fluid mechanics problems involving irregular geometries and complex flow domains. To this end, the thesis presents a two-fold interface between Finite Element Method (FEM) solvers and the GNN architecture. This interface transforms FEM vector fields into numerical tensors that can be efficiently processed by the neural network, allowing data exchange between the simulation environment and the learning model
Elhawary, Mohamed. "Apprentissage profond informé par la physique pour les écoulements complexes". Electronic Thesis or Diss., Paris, ENSAM, 2024. http://www.theses.fr/2024ENAME068.
Testo completoThis PhD work investigates two specific problems concerning turbomachinery using machine learning algorithms. The first focuses on the axial flow compressor, addressing the issues of rotating stall and surge which is unstable phenomena that limit the operational range of compressors. Recent advancements include the development of flow control techniques, such as jets at the casing and leading edge of the rotor, which have shown promise in extending compressor operating ranges. However, optimizing these control strategies poses a challenge due to the large number of parameters and configurations, including the number of jets, the injection velocity, and the injection angle in the fixed frame. This raises the question: can ML algorithms assist in exploring this extensive parameter space and optimizing the control strategy? To this end, a comprehensive database of experimental results from various control parameters and compressor performance evaluations on an axial flow compressor has been utilized, with tests conducted on the CME2 test bench at LMFL laboratory. The second problem examines the radial vaneless diffuser, an annular stator component positioned downstream of the rotor in radial pumps and compressors. Its primary role is to decelerate the fluid while increasing static pressure and enthalpy. Despite its seemingly straightforward function, predicting the flow behaviour within the diffuser is quite challenging due to the lack of fluid guidance, the complex jet wake flow structure at the inlet, flow instabilities, three-dimensional nature of the flow. This leads to the inquiry: can ML algorithms effectively predict this flow? For this analysis, we utilize a database consisting of numerical simulations (URANS) obtained on a radial flow pump geometry performed at LMFL laboratory. We employed two machine learning approaches to investigate these distinct topics related to turbomachinery devices. The first approach utilizes Neural Networks (NNs) and Genetic Algorithms (GAs) to explore active flow control strategies in an axial compressor. The second approach applies Physics-Informed Neural Networks (PINNs) to model 2D turbulent flow in the vaneless diffuser of a radial pump
Brandão, Eduardo. "Complexity Methods in Physics-Guided Machine Learning". Electronic Thesis or Diss., Saint-Etienne, 2023. http://www.theses.fr/2023STET0062.
Testo completoComplexity is easy to recognize but difficult to define: there are a host of measures of complexity, each relevant for a particular application.In Surface engineering, self-organization drives the formation of patterns on matter by femtosecond laser irradiation, which have important biomedical applications. Pattern formation details are not fully understood. In work leading to two publications [1,2], via a complexity argument and a physics-guided machine learning framework, we show that the severely constrained problem of learning the laser-matter interaction with few data and partial physical knowledge is well-posed in this context. Our model allows us to make useful predictions and suggests physical insights.In another contribution [3] we propose a new formulation of the Minimum Description Length principle, defining model and data complexity in a single step, by taking into account signal and noise in training data. Experiments indicate that Neural Network classifiers that generalize well follow this principle.In unpublished work, we propose Taylor entropy, a novel measure of dynamical system complexity which can be estimated via a single SEM image. This approach could facilitate learning the physical process in new materials through domain adaptation.This thesis paves the way for a unified representation of complexity in data and physical knowledge, which can be used in the context of Physics-guided machine learning.[1] Brandao, Eduardo, et al. "Learning PDE to model self-organization of matter." Entropy 24.8 (2022): 1096.[2] Brandao, Eduardo, et al. "Learning Complexity to Guide Light-Induced Self-Organized Nanopatterns." Physical Review Letters 130.22 (2023): 226201.[3] Brandao, Eduardo, et al. "Is My Neural Net Driven by the MDL Principle?." Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Cham: Springer Nature Switzerland, 2023
Houssein, Aya. "Pléthysmographie respiratoire par magnétométrie ˸ Evaluation de la ventilation et de la dépense énergétique à partir d'algorithmes d'apprentissage automatique". Thesis, Rennes, École normale supérieure, 2021. http://www.theses.fr/2021ENSR0026.
Testo completoRegular physical activity (PA) is essential to maintain and improve health. The quantification of PA has become a major focus in scientific research studying the relationship between PA and its effects on health. PA is generally quantified in terms of energy expenditure (EE). Reference methods used to measure EE are cumbersome and invasive. To overcome the problems associated with the use of reference methods, portable and non-invasive devices have been developed. Among these devices, respiratory magnetometer plethysmography (RMP) has recently developed. PRM is based on the measurement of the longitudinal and transversal thoracic and abdominal distances.The objective of this thesis is to evaluate the ability of PRM to estimate V˙E and EE during low to high intensity PA using machine learning algorithms. The main results of our work demonstrate 1) That RMP is suitable to estimate ˙VE and DE during low to high PA. 2) A nonlinear model is more relevant than a linear model to estimate V˙E. 3) The individualization of the models provides better performance for V˙E and EE estimation.4) RMP can accurately estimate EE at any intensity, including the highest ones. 4) An activity-specific approach is more relevant to estimate EE ,and a step of PA recognition is necessary before EE estimation.Further studies are still needed to evaluate RMP on a large population and under free-living conditions
Buhot, Arnaud. "Etude de propriétés d'apprentissage supervisé et non supervisé par des méthodes de Physique Statistique". Phd thesis, Université Joseph Fourier (Grenoble), 1999. http://tel.archives-ouvertes.fr/tel-00001642.
Testo completoGarnotel, Maël. "Apport de la reconnaissance des postures et des activités par accélérométrie à la caractérisation du comportement de mouvement chez l’humain : application à l’étude de la transition épidémiologique chez les Peuls". Thesis, Lyon, 2019. https://n2t.net/ark:/47881/m6kk9b3r.
Testo completoFacing the rise of non-communicable diseases, physical activity and sedentary behavior are a major health issue. Evaluating the synergies of movement behavior dimensions in order to establish its link with health emerges is a key challenge. The development of accelerometry has revolutionized the understanding of these links, traditionally studied using declarative data, associated with well-established biases. The classical accelerometry approach allows continuous measurement over long periods in free living conditions but encounters limitations inherent in signal processing and in the non-linear relationship between accelerometry and energy expenditure to characterize human movement in a satisfactory way. My first objective was to clarify the limits of the current approach and to contribute to the improvement of the phenotyping of movement behavior through new analytic methods relying on the automatic activity recognition of postures and activities. In the second part of my thesis, I applied these new approaches to the study of the Fulani of Senegal, a population in epidemiological transition. My work has clarified the limitations of traditional approaches to accelerometry and the value of activities recognition through automatic learning algorithms to overcome the difficulties encountered. For the first time, they show the contribution of this approach to the detailed characterization of a population's physical activity and sedentary behaviors, in relation to its environment. It should contribute in a useful way to the development of future recommendations that are more appropriate for the general population
Melnyk, Artem. "Perfectionnement des algorithmes de contrôle-commande des robots manipulateur électriques en interaction physique avec leur environnement par une approche bio-inspirée". Thesis, Cergy-Pontoise, 2014. http://www.theses.fr/2014CERG0745/document.
Testo completoAutomated production lines integrate robots which are isolated from workers, so there is no physical interaction between a human and robot. In the near future, a humanoid robot will become a part of the human environment as a companion to help or work with humans. The aspects of coexistence always presuppose physical and social interaction between a robot and a human. In humanoid robotics, further progress depends on knowledge of cognitive mechanisms of interpersonal interaction as robots physically and socially interact with humans. An illustrative example of interpersonal interaction is an act of a handshake that plays a substantial social role. The particularity of this form of interpersonal interaction is that it is based on physical and social couplings which lead to synchronization of motion and efforts. Studying a handshake for robots is interesting as it can expand their behavioral properties for interaction with a human being in more natural way. The first chapter of this thesis presents the state of the art in the fields of social sciences, medicine and humanoid robotics that study the phenomenon of a handshake. The second chapter is dedicated to the physical nature of the phenomenon between humans via quantitative measurements. A new wearable system to measure a handshake was built in Donetsk National Technical University (Ukraine). It consists of a set of several sensors attached to the glove for recording angular velocities and gravitational acceleration of the hand and forces in certain points of hand contact during interaction. The measurement campaigns have shown that there is a phenomenon of mutual synchrony that is preceded by the phase of physical contact which initiates this synchrony. Considering the rhythmic nature of this phenomenon, the controller based on the models of rhythmic neuron of Rowat-Selverston, with learning the frequency during interaction was proposed and studied in the third chapter. Chapter four deals with the experiences of physical human-robot interaction. The experimentations with robot arm Katana show that it is possible for a robot to learn to synchronize its rhythm with rhythms imposed by a human during handshake with the proposed model of a bio-inspired controller. A general conclusion and perspectives summarize and finish this work
Desbordes, Paul. "Méthode de sélection de caractéristiques pronostiques et prédictives basée sur les forêts aléatoires pour le suivi thérapeutique des lésions tumorales par imagerie fonctionnelle TEP". Thesis, Normandie, 2017. http://www.theses.fr/2017NORMR030/document.
Testo completoRadiomics proposes to combine image features with those extracted from other modalities (clinical, genomic, proteomic) to set up a personalized medicine in the management of cancer. From an initial exam, the objective is to anticipate the survival rate of the patient or the treatment response probability. In medicine, classical statistical methods are generally used, such as theMann-Whitney analysis for predictive studies and analysis of Kaplan-Meier survival curves for prognostic studies. Thus, the increasing number of studied features limits the use of these statistics. We have focused our works on machine learning algorithms and features selection methods. These methods are resistant to large dimensions as well as non-linear relations between features. We proposed two features selection strategy based on random forests. Our methods allowed the selection of subsets of predictive and prognostic features on 2 databases (oesophagus and lung cancers). Our algorithms showed the best classification performances compared to classical statistical methods and other features selection strategies studied
Philippeau, Jérémy. "Apprentissage de similarités pour l'aide à l'organisation de contenus audiovisuels". Toulouse 3, 2009. http://thesesups.ups-tlse.fr/564/.
Testo completoIn the perspective of new usages in the field of the access to audiovisual archives, we have created a semi-automatic system that helps a user to organize audiovisual contents while performing tasks of classification, characterization, identification and ranking. To do so, we propose to use a new vocabulary, different from the one already available in INA documentary notices, to answer needs which can not be easily defined with words. We have conceived a graphical interface based on graph formalism designed to express an organisational task. The digital similarity is a good tool in respect with the handled elements which are informational objects shown on the computer screen and the automatically extracted audio and video low-level features. We have made the choice to estimate the similarity between those elements with a predictive process through a statistical model. Among the numerous existing models, the statistical prediction based on the univaried regression and on support vectors has been chosen. H)