Hybrid State Estimation: Integrating Physics-Informed Neural Networks with Adaptive UKF for Dynamic Systems

This article belongs to the Special Issue Cyber-Physical Systems: Recent Developments and Emerging Trends

Detalles Bibliográficos
Autores: Curtò i Díaz, Joaquim de, Zarzà i Cubero, Irene de
Tipo de recurso: artículo
Fecha de publicación:2024
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/411789
Acceso en línea:https://hdl.handle.net/2117/411789
https://dx.doi.org/10.3390/electronics13112208
Access Level:acceso abierto
Palabra clave:Neural networks (Computer science)
Physics-Informed Neural Networks
Unscented Kalman Filter (UKF)
State estimation
Simulació per ordinador
Àrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica::Aplicacions informàtiques a la física i l‘enginyeria
id ES_caa6fe65d9ede686f60694bc6cf26e91
oai_identifier_str oai:upcommons.upc.edu:2117/411789
network_acronym_str ES
network_name_str España
repository_id_str
spelling Hybrid State Estimation: Integrating Physics-Informed Neural Networks with Adaptive UKF for Dynamic SystemsCurtò i Díaz, Joaquim deZarzà i Cubero, Irene deNeural networks (Computer science)Physics-Informed Neural NetworksUnscented Kalman Filter (UKF)State estimationSimulació per ordinadorÀrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica::Aplicacions informàtiques a la física i l‘enginyeriaThis article belongs to the Special Issue Cyber-Physical Systems: Recent Developments and Emerging TrendsIn this paper, we present a novel approach to state estimation in dynamic systems by combining Physics-Informed Neural Networks (PINNs) with an adaptive Unscented Kalman Filter (UKF). Recognizing the limitations of traditional state estimation methods, we refine the PINN architecture with hybrid loss functions and Monte Carlo Dropout for enhanced uncertainty estimation. The Unscented Kalman Filter is augmented with an adaptive noise covariance mechanism and incorporates model parameters into the state vector to improve adaptability. We further validate this hybrid framework by integrating the enhanced PINN with the UKF for a seamless state prediction pipeline, demonstrating significant improvements in accuracy and robustness. Our experimental results show a marked enhancement in state estimation fidelity for both position and velocity tracking, supported by uncertainty quantification via Bayesian inference and Monte Carlo Dropout. We further extend the simulation and present evaluations on a double pendulum system and state estimation on a quadcopter drone. This comprehensive solution is poised to advance the state-of-the-art in dynamic system estimation, providing unparalleled performance across control theory, machine learning, and numerical optimization domains.The work is developed under the following projects at BARCELONA Supercomputing Center: ‘TIFON’. This work has also received funding from the ‘NEXTBAT’ project funded by the EUROPEAN Union’s HORIZON EUROPE research and innovation programme under grant agreement No. 101103983. The work is also developed under UFV R&D pre-competitive project ‘OpenMaas: Open Manufacturing as a Service’.Peer ReviewedMDPI20242024-01-0120242024-07-16journal articlehttp://purl.org/coar/resource_type/c_6501AMhttp://purl.org/coar/version/c_ab4af688f83e57aainfo:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/2117/411789https://dx.doi.org/10.3390/electronics13112208reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)InglésengEuropean Commission http://doi.org/10.13039/501100000780 HE 101103983 Next generation technologies for battery systems in transport electrification based on novel design approach to increase performance and reduce carbon footprintopen accesshttp://purl.org/coar/access_right/c_abf2Attribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/4117892026-05-27T15:37:01Z
dc.title.none.fl_str_mv Hybrid State Estimation: Integrating Physics-Informed Neural Networks with Adaptive UKF for Dynamic Systems
title Hybrid State Estimation: Integrating Physics-Informed Neural Networks with Adaptive UKF for Dynamic Systems
spellingShingle Hybrid State Estimation: Integrating Physics-Informed Neural Networks with Adaptive UKF for Dynamic Systems
Curtò i Díaz, Joaquim de
Neural networks (Computer science)
Physics-Informed Neural Networks
Unscented Kalman Filter (UKF)
State estimation
Simulació per ordinador
Àrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica::Aplicacions informàtiques a la física i l‘enginyeria
title_short Hybrid State Estimation: Integrating Physics-Informed Neural Networks with Adaptive UKF for Dynamic Systems
title_full Hybrid State Estimation: Integrating Physics-Informed Neural Networks with Adaptive UKF for Dynamic Systems
title_fullStr Hybrid State Estimation: Integrating Physics-Informed Neural Networks with Adaptive UKF for Dynamic Systems
title_full_unstemmed Hybrid State Estimation: Integrating Physics-Informed Neural Networks with Adaptive UKF for Dynamic Systems
title_sort Hybrid State Estimation: Integrating Physics-Informed Neural Networks with Adaptive UKF for Dynamic Systems
dc.creator.none.fl_str_mv Curtò i Díaz, Joaquim de
Zarzà i Cubero, Irene de
author Curtò i Díaz, Joaquim de
author_facet Curtò i Díaz, Joaquim de
Zarzà i Cubero, Irene de
author_role author
author2 Zarzà i Cubero, Irene de
author2_role author
dc.subject.none.fl_str_mv Neural networks (Computer science)
Physics-Informed Neural Networks
Unscented Kalman Filter (UKF)
State estimation
Simulació per ordinador
Àrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica::Aplicacions informàtiques a la física i l‘enginyeria
topic Neural networks (Computer science)
Physics-Informed Neural Networks
Unscented Kalman Filter (UKF)
State estimation
Simulació per ordinador
Àrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica::Aplicacions informàtiques a la física i l‘enginyeria
description This article belongs to the Special Issue Cyber-Physical Systems: Recent Developments and Emerging Trends
publishDate 2024
dc.date.none.fl_str_mv 2024
2024-01-01
2024
2024-07-16
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
AM
http://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/411789
https://dx.doi.org/10.3390/electronics13112208
url https://hdl.handle.net/2117/411789
https://dx.doi.org/10.3390/electronics13112208
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv European Commission http://doi.org/10.13039/501100000780 HE 101103983 Next generation technologies for battery systems in transport electrification based on novel design approach to increase performance and reduce carbon footprint
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv MDPI
publisher.none.fl_str_mv MDPI
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869419498171269120
score 15,81155

Similares en LA Referencia