paper-with-me

Papers

Hybrid Neural Network Augmented Physics-based Models for Nonlinear Filtering

2022-04-13 · Tales Imbiriba, Ahmet Demirkaya, Jindřich Duník, Ondřej Straka, Deniz Erdoğmuş, Pau Closas

In this paper we present a hybrid neural network augmented physics-based modeling (APBM) framework for Bayesian nonlinear latent space estimation. The proposed APBM strategy allows for model adaptation when new operation conditions come into play or the physics-based model is insufficient (or incomplete) to properly describe the latent phenomenon. One advantage of the APBMs and our estimation procedure is the capability of maintaining the physical interpretability of estimated states. Furthermore, we propose a constraint filtering approach to control the neural network contributions to the overall model. We also exploit assumed density filtering techniques and cubature integration rules to present a flexible estimation strategy that can easily deal with nonlinear models and high-dimensional latent spaces. Finally, we demonstrate the efficacy of our methodology by leveraging a target tracking scenario with nonlinear and incomplete measurement and acceleration models, respectively.

📄 PDF Abstract BibTeX arXiv:2204.06471

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Structural Constraints for Physics-augmented Learning

2024-10-07 · Simon Kuang, Xinfan Lin

When the physics is wrong, physics-informed machine learning becomes physics-misinformed machine learning. A powerful black-box model should not be able to conceal misconceived physics. We propose two criteria that can b…

Physics-informed machine learning

Weighted Flow Matching and Physics-Informed Nonlinear Filtering for Parameter Estimation in Digital Twins

2026-05-16 · Yasar Yanik, Himadri Basu, Ricardo G. Sanfelice, Daniele Venturi arxiv

Digital twins (DTs) rely on continuous synchronization between physical systems and their virtual counterparts through online parameter estimation under uncertainty. In many practical settings, however, this task is chal…

Data-Efficient Learning for Complex and Real-Time Physical Problem Solving using Augmented Simulation

2020-11-14 · Kei Ota, Devesh K. Jha, Diego Romeres, Jeroen van Baar 외

Humans quickly solve tasks in novel systems with complex dynamics, without requiring much interaction. While deep reinforcement learning algorithms have achieved tremendous success in many complex tasks, these algorithms…

Deep Reinforcement LearningModel Predictive Controlreinforcement-learningReinforcement Learning (RL)

PiGGO: Physics-Guided Learnable Graph Kalman Filters for Virtual Sensing of Nonlinear Dynamic Structures under Uncertainty

2026-04-29 · Marcus Haywood-Alexander, Gregory Duthé, Eleni Chatzi arxiv

Digital twins provide a powerful paradigm for diagnostic and prognostic tasks in the monitoring and control of engineered systems; however, their deployment for complex structures remains challenged by model-form uncerta…

Nonlinear filtering based on density approximation and deep BSDE prediction

2025-08-14 · Kasper Bågmark, Adam Andersson, Stig Larsson arxiv

A novel approximate Bayesian filter based on backward stochastic differential equations is introduced. It uses a nonlinear Feynman--Kac representation of the filtering problem and the approximation of an unnormalized fil…