Overviews of grey-box models

A spectrum of physics-informed Gaussian processes for regression in engineering
E.J. Cross, T.J. Rogers, D.J. Pitchforth, S.J. Gibson & M.R. Jones
preprint (submitted)
arXiv, September 23
Open access: https://arxiv.org/abs/2309.10656

Physics-informed machine learning for structural health monitoring
E.J. Cross, S.J. Gibson, M.R. Jones, D.J. Pitchforth, S. Zhang, T.J. Rogers
Book Chapter
Structural Health Monitoring Based on Data Science Techniques, October 21
Open access: https://arxiv.org/pdf/2206.15303.pdf
DOI: https://doi.org/10.1007/978-3-030-81716-9_17

Combining physics-based and machine learning models

Grey-box models for wave loading prediction
D.J. Pitchforth, T.J. Rogers, U.T. Tygesen, E.J. Cross
Mechanical Systems and Signal Processing, October 21
DOI: https://doi.org/10.1016/j.ymssp.2021.107741
Open access: https://arxiv.org/pdf/2105.13813.pdf

Grey-Box Modelling via Gaussian Process Mean Functions for Mechanical Systems
S. Zhang, T.J. Rogers, E.J. Cross
Data Science in Engineering, Volume 9, October 21
DOI: https://doi.org/10.1007/978-3-030-76004-5_19

Gaussian Process Based Grey-Box Modelling for SHM of Structures Under Fluctuating Environmental Conditions
S. Zhang & E.J. Cross
EWSHM 2020: European Workshop on Structural Health Monitoring, January 21
DOI: https://doi.org/10.1007/978-3-030-64908-1_6

Semi-physical modelling

Distributions of fatigue damage from data-driven strain prediction using Gaussian process regression
S.J. Gibson, T.J. Rogers & E.J. Cross
Structural Health Monitoring, 2023 Open access: https://journals.sagepub.com/doi/full/10.1177/14759217221140080

On evolutionary system identification with applications to nonlinear benchmarks
K. Worden, R.J. Barthorpe, E.J. Cross, N. Dervilis, G.R. Holmes, G. Manson, T.J. Rogers
Mechanical Systems and Signal Processing, 2018
DOI: https://doi.org/10.1016/j.ymssp.2018.04.001
Open access:https://eprints.whiterose.ac.uk/130344/

On a grey box modelling framework for nonlinear system identification
T.J. Rogers, G.R. Holmes, E.J. Cross & K. Worden
Special Topics in Structural Dynamics, Volume 6, 2017
DOI: http://dx.doi.org/10.1007/978-3-319-53841-9_15

Aircraft parametric structural load monitoring using Gaussian process regression
R Fuentes, E.J. Cross, A. Halfpenny, K. Worden, R.J. Barthorpe
EWSHM - 7th European Workshop on Structural Health Monitoring, 2014
Open access: https://hal.inria.fr/hal-01022048/document

Physics-informed kernels

Incorporation of partial physical knowledge within Gaussian processes
D.J. Pitchforth, T.J. Rogers, U.T. Tygesen & E.J. Cross
In Proceedings of the 30th International Conference on Noise and Vibration Engineering (ISMA-USD 2022), 2022

Integrating Physical Knowledge into Gaussian Process Regression Models for Probabilistic Fatigue Assessment
S.J. Gibson, T.J. Rogers, & E.J. Cross
10th European Workshop on Structural Health Monitoring (EWSHM), 2023
DOI: https://doi.org/10.1007/978-3-031-07322-9_48

Physics-derived covariance functions for machine learning in structural dynamics
E.J. Cross & T.J. Rogers
IFAC Papers online, 19th IFAC Symposium on System Identification (SYSID) 2021
DOI: https://doi.org/10.1016/j.ifacol.2021.08.353
Open access: https://eprints.whiterose.ac.uk/178485/1/1-s2.0-S2405896321011277-main.pdf

Physical covariance functions for dynamic systems with time-dependent parameters
M.R. Jones, T.J. Rogers & E.J. Cross
10th European Workshop on Structural Health Monitoring (EWSHM), 2023
DOI: https://doi.org/10.1007/978-3-031-07322-9_39

Constrained machine learners

Constraining Gaussian processes for physics-informed acoustic emission mapping
M.R. Jones, T.J. Rogers & E.J. Cross
Mechanical Systems and Signal Processing, 2023
Open access: https://www.sciencedirect.com/science/article/pii/S0888327022010524

Constraining Gaussian processes for grey-box acoustic emission source localisation
M.R. Jones, T.J. Rogers, P.A. Gardner, E.J. Cross
ISMA 2020 - International Conference on Noise and Vibration Engineering

Grey-box modelling for structural health monitoring: Physical constraints on machine learning
E.J. Cross, T.J. Rogers, T.J. Gibbons
IWSHM 2019 - International Workshop on Structural Health Monitoring
DOI: http://doi.org/10.12783/shm2019/32349

State space models for grey-box learning

Bayesian joint input-state estimation for nonlinear systems
T.J. Rogers, K. Worden, E.J. Cross
Vibration, 2020
DOI: https://doi.org/10.3390/vibration3030020
Open access: https://eprints.whiterose.ac.uk/165393/1/vibration-03-00020%20%281%29.pdf

On the application of Gaussian process latent force models for joint input-state-parameter estimation: With a view to Bayesian operational identification
T.J. Rogers, K. Worden, E.J. Cross
Mechanical Systems and Signal Processing, 2018
DOI: https://doi.org/10.1016/j.ymssp.2019.106580
Open access: https://eprints.whiterose.ac.uk/157049/1/mssp19_1540_accepted_manuscript.pdf