Discovering causal relations and equations from data

G Camps-Valls, A Gerhardus, U Ninad, G Varando… - Physics Reports, 2023 - Elsevier
Physics is a field of science that has traditionally used the scientific method to answer
questions about why natural phenomena occur and to make testable models that explain the …

Physics-informed machine learning for structural health monitoring

EJ Cross, SJ Gibson, MR Jones, DJ Pitchforth… - … Health Monitoring Based …, 2022 - Springer
The use of machine learning in structural health monitoring is becoming more common, as
many of the inherent tasks (such as regression and classification) in developing condition …

A sparse Bayesian framework for discovering interpretable nonlinear stochastic dynamical systems with Gaussian white noise

T Tripura, S Chakraborty - Mechanical Systems and Signal Processing, 2023 - Elsevier
Extracting governing physics from data is a key challenge in many areas of science and
technology. The existing techniques for equation discovery are mostly applicable to …

On spike-and-slab priors for Bayesian equation discovery of nonlinear dynamical systems via sparse linear regression

R Nayek, R Fuentes, K Worden, EJ Cross - Mechanical Systems and Signal …, 2021 - Elsevier
This paper presents the use of spike-and-slab (SS) priors for discovering governing
differential equations of motion of nonlinear structural dynamic systems. The problem of …

Sparse Bayesian learning of explicit algebraic Reynolds-stress models for turbulent separated flows

S Cherroud, X Merle, P Cinnella, X Gloerfelt - International Journal of Heat …, 2022 - Elsevier
Abstract A novel Sparse Bayesian Learning (SBL) framework is introduced for generating
stochastic Explicit Algebraic Reynolds Stress (EARSM) closures for the Reynolds-Averaged …

Sparse identification for ball-screw drives considering position-dependent dynamics and nonlinear friction

X Liu, Y Li, Y Cheng, Y Cai - Robotics and Computer-Integrated …, 2023 - Elsevier
Establishing accurate dynamic models in a form that is suitable for integration with model-
based control methods, is of great significance for further improving the dynamic motion …

Koopman operator learning using invertible neural networks

Y Meng, J Huang, Y Qiu - Journal of Computational Physics, 2024 - Elsevier
In Koopman operator theory, a finite-dimensional nonlinear system is transformed into an
infinite but linear system using a set of observable functions. However, manually selecting …

MAntRA: A framework for model agnostic reliability analysis

YC Mathpati, KS More, T Tripura, R Nayek… - Reliability Engineering & …, 2023 - Elsevier
We propose a novel model-agnostic data-driven reliability analysis framework for time-
dependent reliability analysis. The proposed approach–referred to as MAntRA–combines …

[HTML][HTML] Sparse Bayesian machine learning for the interpretable identification of nonlinear structural dynamics: Towards the experimental data-driven discovery of a …

T Chatterjee, AD Shaw, MI Friswell… - Mechanical Systems and …, 2023 - Elsevier
Data-driven discovery of governing laws for complex nonlinear structural dynamic systems
remains a challenging issue of paramount importance. This work addresses the above issue …

Discussing the spectra of physics-enhanced machine learning via a survey on structural mechanics applications

M Haywood-Alexander, W Liu, K Bacsa, Z Lai… - CoRR, 2023 - openreview.net
The intersection of physics and machine learning has given rise to the physics-enhanced
machine learning (PEML) paradigm, aiming to improve the capabilities and reduce the …