Hybrid modelling and identification of mechanical systems using Physics-Enhanced Machine Learning
| dc.contributor.author | Merino Olagüe, Mikel | |
| dc.contributor.author | Iriarte Goñi, Xabier | |
| dc.contributor.author | Castellano Aldave, Jesús Carlos | |
| dc.contributor.author | Plaza Puértolas, Aitor | |
| dc.contributor.department | Ingeniería | es_ES |
| dc.contributor.department | Ingeniaritza | eu |
| dc.contributor.department | Institute of Smart Cities - ISC | en |
| dc.contributor.department | Ingeniería Eléctrica, Electrónica y de Comunicación | es_ES |
| dc.contributor.department | Ingeniaritza Elektrikoa, Elektronikoa eta Telekomunikazio Ingeniaritza | eu |
| dc.contributor.funder | Universidad Pública de Navarra / Nafarroako Unibertsitate Publikoa | |
| dc.date.accessioned | 2025-07-23T10:54:41Z | |
| dc.date.available | 2025-07-23T10:54:41Z | |
| dc.date.issued | 2025-11-15 | |
| dc.date.updated | 2025-07-23T10:46:54Z | |
| dc.description.abstract | Obtaining mathematical models for mechanical systems is a key subject in engineering. These models are essential for calculation, simulation and design tasks, and they are usually obtained from physical principles or by fitting a black-box parametric input-output model to experimental data. However, both methodologies have some limitations: physics based models may not take some phenomena into account and black-box models are complicated to interpretate. In this work, we develop a novel methodology based on discrepancy modelling, which combines physical principles with neural networks to model mechanical systems with partially unknown or unmodelled physics. Two different mechanical systems with partially unknown dynamics are successfully modelled and the values of their physical parameters are obtained. Furthermore, the obtained models enable numerical integration for future state prediction, linearization and the possibility of varying the values of the physical parameters. The results show how a hybrid methodology provides accurate and interpretable models for mechanical systems when some physical information is missing. In essence, the presented methodology is a tool to obtain better mathematical models, which could be used for analysis, simulation and design tasks. | en |
| dc.description.sponsorship | This paper has been supported by the Public University of Navarre under grant PJUPNA2024-11690, and also by the Spanish Research Agency under grants PDC2023-145876-C22, PID2022-138510OB-C21, TED2021-131052B-C21. Open access funding provided by Universidad Pública de Navarra. | |
| dc.format.mimetype | application/pdf | |
| dc.identifier.citation | Merino-Olagüe, M., Iriarte, X., Castellano-Aldave, C., Plaza, A. (2025) Hybrid modelling and identification of mechanical systems using Physics-Enhanced Machine Learning. Engineering Applications of Artificial Intelligence, 159(Part C), 1-15. https://doi.org/10.1016/j.engappai.2025.111762 | |
| dc.identifier.doi | 10.1016/j.engappai.2025.111762 | |
| dc.identifier.issn | 0952-1976 | |
| dc.identifier.uri | https://academica-e.unavarra.es/handle/2454/54436 | |
| dc.language.iso | eng | |
| dc.publisher | Elsevier | |
| dc.relation.ispartof | Engineering Applications of Artificial Intelligence, 159(Part C), 1-15 | |
| dc.relation.projectID | info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023/PDC2023-145876-C22/ES/ | |
| dc.relation.projectID | info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023/PID2022-138510OB-C21/ES/ | |
| dc.relation.projectID | info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023/TED2021-131052B-C21/ | |
| dc.relation.publisherversion | https://doi.org/10.1016/j.engappai.2025.111762 | |
| dc.rights | © 2025 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY license. | |
| dc.rights.accessRights | info:eu-repo/semantics/openAccess | |
| dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
| dc.subject | Mechanical system identification | en |
| dc.subject | Hybrid modelling | en |
| dc.subject | Physics-enhanced neural networks | en |
| dc.subject | Parameter estimation | en |
| dc.title | Hybrid modelling and identification of mechanical systems using Physics-Enhanced Machine Learning | en |
| dc.type | info:eu-repo/semantics/article | |
| dc.type.version | info:eu-repo/semantics/publishedVersion | |
| dspace.entity.type | Publication | |
| relation.isAuthorOfPublication | 9a84c795-6aa6-4431-8574-d5614ef6ef3f | |
| relation.isAuthorOfPublication | e7d5cd2e-5e19-4ef9-ba9b-7e3505379d96 | |
| relation.isAuthorOfPublication | 5a798097-8d20-4352-bc05-5139619aeb41 | |
| relation.isAuthorOfPublication | 236809d6-78a4-4e83-b534-b3981785886e | |
| relation.isAuthorOfPublication.latestForDiscovery | 9a84c795-6aa6-4431-8574-d5614ef6ef3f |