Integration of machine learning and first principles models
L Rajulapati, S Chinta, B Shyamala… - AIChE …, 2022 - Wiley Online Library
Abstract Model building and parameter estimation are traditional concepts widely used in
chemical, biological, metallurgical, and manufacturing industries. Early modeling …
chemical, biological, metallurgical, and manufacturing industries. Early modeling …
Universal differential equations for scientific machine learning
In the context of science, the well-known adage" a picture is worth a thousand words" might
well be" a model is worth a thousand datasets." In this manuscript we introduce the SciML …
well be" a model is worth a thousand datasets." In this manuscript we introduce the SciML …
[HTML][HTML] Quasi-newton methods for partitioned simulation of fluid–structure interaction reviewed in the generalized broyden framework
N Delaissé, T Demeester, R Haelterman… - … Methods in Engineering, 2023 - Springer
Fluid–structure interaction simulations can be performed in a partitioned way, by coupling a
flow solver with a structural solver. However, Gauss–Seidel iterations between these solvers …
flow solver with a structural solver. However, Gauss–Seidel iterations between these solvers …
Physics-integrated variational autoencoders for robust and interpretable generative modeling
N Takeishi, A Kalousis - Advances in Neural Information …, 2021 - proceedings.neurips.cc
Integrating physics models within machine learning models holds considerable promise
toward learning robust models with improved interpretability and abilities to extrapolate. In …
toward learning robust models with improved interpretability and abilities to extrapolate. In …
Physics-guided Bayesian neural networks by ABC-SS: Application to reinforced concrete columns
This manuscript proposes a physics-guided Bayesian neural network, which combines
Approximate-Bayesian-Computation training with physics-based models. This hybrid …
Approximate-Bayesian-Computation training with physics-based models. This hybrid …
[HTML][HTML] Physics-guided recurrent neural network trained with approximate Bayesian computation: A case study on structural response prognostics
A new physics-guided Bayesian recurrent neural network is proposed in this manuscript.
This hybrid algorithm benefits from the knowledge in physics-based models, the capability of …
This hybrid algorithm benefits from the knowledge in physics-based models, the capability of …
[HTML][HTML] Magnetic nanoparticles in theranostic applications
A Coene, J Leliaert - Journal of Applied Physics, 2022 - pubs.aip.org
Nanomedicine research recently started exploring the combination of therapy and
diagnostics, so-called theranostics, as an approach to offer a more flexible, personal, and …
diagnostics, so-called theranostics, as an approach to offer a more flexible, personal, and …
Dual regularized policy updating and shiftpoint detection for automated deployment of reinforcement learning controllers on industrial mechatronic systems
V Vantilborgh, T Staessens, W De Groote… - Control Engineering …, 2024 - Elsevier
We propose an algorithmic pipeline enabling deep reinforcement learning controllers to
detect when a significant change in system characteristics has occurred and update the …
detect when a significant change in system characteristics has occurred and update the …
Evolutionary sparse data-driven discovery of multibody system dynamics
E Askari, G Crevecoeur - Multibody System Dynamics, 2023 - Springer
The value of unknown parameters of multibody systems is crucial for prediction, monitoring,
and control, sometimes estimated using a biased physics-based model leading to incorrect …
and control, sometimes estimated using a biased physics-based model leading to incorrect …
Adaptive learning control of robot manipulators via incremental hybrid neural network
S Xu, Z Wu - Neurocomputing, 2024 - Elsevier
A novel hybrid neural network based learning control method is proposed to improve
trajectory tracking accuracy for complex robot manipulators in this paper. Firstly, a hybrid …
trajectory tracking accuracy for complex robot manipulators in this paper. Firstly, a hybrid …