Physics-constrained deep learning of multi-zone building thermal dynamics

J Drgoňa, AR Tuor, V Chandan, DL Vrabie - Energy and Buildings, 2021 - Elsevier
We present a physics-constrained deep learning method to develop control-oriented models
of building thermal dynamics. The proposed method uses systematic encoding of physics …

Differentiable predictive control: Deep learning alternative to explicit model predictive control for unknown nonlinear systems

J Drgoňa, K Kiš, A Tuor, D Vrabie, M Klaučo - Journal of Process Control, 2022 - Elsevier
We present differentiable predictive control (DPC) as a deep learning-based alternative to
the explicit model predictive control (MPC) for unknown nonlinear systems. In the DPC …

Linearly constrained neural networks

J Hendriks, C Jidling, A Wills, T Schön - arXiv preprint arXiv:2002.01600, 2020 - arxiv.org
We present a novel approach to modelling and learning vector fields from physical systems
using neural networks that explicitly satisfy known linear operator constraints. To achieve …

[PDF][PDF] Differentiable predictive control: An mpc alternative for unknown nonlinear systems using constrained deep learning

J Drgona, K Kis, A Tuor, D Vrabie… - arXiv preprint arXiv …, 2020 - researchgate.net
We present an alternative to model predictive control (MPC) for unknown nonlinear systems
in low-resource embedded device settings. The structure of the presented datadriven control …

Constraint learning for control tasks with limited duration barrier functions

M Ohnishi, G Notomista, M Sugiyama, M Egerstedt - Automatica, 2021 - Elsevier
When deploying autonomous agents in unstructured environments over sustained periods
of time, adaptability and robustness oftentimes outweigh optimality as a primary …

Multi-View Majority Vote Learning Algorithms: Direct Minimization of PAC-Bayesian Bounds

M Hennequin, A Zitouni, K Benabdeslem… - arXiv preprint arXiv …, 2024 - arxiv.org
The PAC-Bayesian framework has significantly advanced our understanding of statistical
learning, particularly in majority voting methods. However, its application to multi-view …

Local phasor-based control of DER inverters for voltage regulation on distribution feeders

J Swartz, TG Roberts, A von Meier… - 2020 IEEE Green …, 2020 - ieeexplore.ieee.org
We introduce a new control paradigm termed Phasor-Based Control (PBC) to coordinate
Distributed Energy Resources (DER) for improved voltage regulation and other objectives …

[PDF][PDF] Learning Lie Groups Acting on the Manifolds Generated by Linear Differential Equations

I GURCAN, K USTUN, P CILOGLU, R CINBIS - 2023 - assets-eu.researchsquare.com
Symmetry group is an important construct to understand the behaviour of a pure
mathematical or a physical system including system of differential equations. We develop a …

[图书][B] Design and Control of an Active Ankle-Foot Orthosis

B DeBoer - 2023 - search.proquest.com
Design and Control of an Active Ankle-Foot Orthosis Page 1 Design and Control of an Active
Ankle-Foot Orthosis by Benjamin DeBoer A thesis submitted to the School of Graduate and …

LipFed: Mitigating Subgroup Bias in Federated Learning with Lipschitz Constraints

K Selialia, Y Chandio, J Oke, FM Anwar - openreview.net
Federated learning (FL) has emerged as a promising paradigm for training decentralized
machine learning models with privacy preservation. However, FL models are biased, which …