[HTML][HTML] Automatic model calibration for coupled HVAC and building dynamics using Modelica and Bayesian optimization

V Martinez-Viol, EM Urbano, M Delgado-Prieto… - Building and …, 2022 - Elsevier
In recent years, increasing the energy efficiency of the building has become one of the
objectives of facility managers. In this sense, monitoring-based commissioning and …

AixLib: an open-source Modelica library for compound building energy systems from component to district level with automated quality management

L Maier, D Jansen, F Wüllhorst, M Kremer… - Journal of Building …, 2024 - Taylor & Francis
Open-source modelling libraries facilitate the standardization and harmonization of model
development. In the context of building energy systems, Modelica is a suitable modelling …

[HTML][HTML] Real-time monitoring and optimization of a large-scale heat pump prone to fouling-towards a digital twin framework

JJ Aguilera, W Meesenburg, WB Markussen… - Applied Energy, 2024 - Elsevier
Large-scale heat pumps are a promising technology for the decarbonisation of heat
supplied in buildings and industries, provided they operate as expected. However, common …

[HTML][HTML] Calibration of a hybrid model for HVAC systems for fault data generation

V Martinez-Viol, F Arellano-Espitia… - Journal of Building …, 2024 - Elsevier
The application of automated fault detection and diagnosis algorithms has proven to be an
effective way to increase the energy efficiency of buildings. While data-driven strategies …

Reduced-dimension Bayesian optimization for model calibration of transient vapor compression cycles

J Ma, D Kim, JE Braun - International Journal of Refrigeration, 2024 - Elsevier
Abstract Development and calibration of first-principles dynamic models of vapor
compression cycles (VCCs) is of critical importance for applications that include control …

Meta-Learning for Physically-Constrained Neural System Identification

A Chakrabarty, G Wichern, VM Deshpande… - arXiv preprint arXiv …, 2025 - arxiv.org
We present a gradient-based meta-learning framework for rapid adaptation of neural state-
space models (NSSMs) for black-box system identification. When applicable, we also …

Online model-based framework for operation and fouling monitoring in a large-scale heat pump

JJ Aguilera, W Meesenburg, WB Markussen… - … on Efficiency, Cost …, 2023 - orbit.dtu.dk
Heat pump systems are a key technology towards the decarbonisation of district heating
systems as they can leverage renewable energy sources and industrial excess heat. Large …

Learning residual dynamics via physics-augmented neural networks: Application to vapor compression cycles

R Chinchilla, VM Deshpande… - 2023 American …, 2023 - ieeexplore.ieee.org
In order to improve the control performance of vapor compression cycles (VCCs), it is often
necessary to construct accurate dynamical models of the underlying thermo-fluid dynamics …

Physics-Constrained Deep Autoencoded Kalman Filters for Estimating Vapor Compression System States

VM Deshpande, A Chakrabarty… - IEEE Control …, 2023 - ieeexplore.ieee.org
Physics-based computational models of vapor compression systems (VCSs) enable high-
fidelity simulations but require high-dimensional state representations. The underlying VCS …

Multi-pass extended Kalman smoother with partially-known constraints for estimation of vapor compression cycles

VM Deshpande, CR Laughman - IFAC-PapersOnLine, 2023 - Elsevier
State and parameter estimation methodologies have the potential to make a significant
impact in the development of broad array of capabilities for widely-used vapor compression …