Logo do repositório
 
Publicação

The use of Natural Language Processing (NLP) in aviation

2026Artigo científico Acesso aberto
Ver registo simples
dc.contributor.authorLopes, Mariana M.
dc.contributor.authorDinis, Duarte
dc.contributor.authorSala, Roberto
dc.contributor.authorPirola, Fabiana
dc.contributor.institutionUNIDEMI - Unidade de Investigação e Desenvolvimento em Engenharia Mecânica e Industrial
dc.contributor.institutionDEMI - Departamento de Engenharia Mecânica e Industrial
dc.contributor.pblElsevier
dc.date.accessioned2026-09-14T15:44:03Z
dc.date.available2026-09-14T15:44:03Z
dc.date.issued2026
dc.descriptionDuarte Dinis acknowledges the Portuguese Fundação para a Ciência e a Tecnologia (FCT) for its financial support via the project UIDB/00667/2025 and UIDP/00667/2025 (UNIDEMI). Duarte Dinis also acknowledges FCT for the financial support under the project UIDB/00097/2025 and UIDP/00097/2025 (CEGIST). Publisher Copyright: © 2026 Elsevier B.V.. All rights reserved.
dc.description.abstractIn the aircraft Maintenance, Repair and Overhaul (MRO) industry the high uncertainty of resources needed for a given operation is a very recurrent problem. This implies that being able to collect and analyse data from past events to forecast future ones provides a company with more stability of outcomes and a competitive advantage in the industry. However, the heterogeneous manner in which data is collected and stored causes it to be often disregarded or at least not used in all its potential. This paper presents the development and evaluation of a BERT-based Natural Language Processing (NLP) model designed to classify aircraft zones from free-text maintenance reports. Using maintenance reports of 372 maintenance projects from a Portuguese MRO, the model achieved an accuracy of 85.69%. While developing the model a sensitivity analysis was performed to examine the impact of learning rate, warm-up period, and dropout probability on performance, allowing considerations for future model development in this area. In addition, the added value of this paper includes recommendations for maintenance management in companies intending to implement such model.en
dc.description.versionpublishersversion
dc.description.versionpublished
dc.format.extent10
dc.format.extent1051234
dc.identifier.doi10.1016/j.procs.2026.02.050
dc.identifier.issn1877-0509
dc.identifier.otherPURE: 173321825
dc.identifier.otherPURE UUID: 4c4e230f-8bc0-4898-ae92-6180b9e6381c
dc.identifier.otherScopus: 105040145170
dc.identifier.urihttp://hdl.handle.net/10362/206371
dc.identifier.urlhttps://www.scopus.com/pages/publications/105040145170
dc.language.isoeng
dc.peerreviewedyes
dc.subjectAircraft Maintenance
dc.subjectBERT
dc.subjectMaintenance Management
dc.subjectNatural Language Processing
dc.subjectGeneral Computer Science
dc.titleThe use of Natural Language Processing (NLP) in aviationen
dc.title.subtitleA case study using BERTen
dc.typejournal article
degois.publication.firstPage91
degois.publication.lastPage100
degois.publication.titleProcedia Computer Science
degois.publication.volume277
dspace.entity.typePublication
rcaap.rightsopenAccess

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
Lopes_et_al._2026_.pdf
Tamanho:
1 MB
Formato:
Adobe Portable Document Format
Ver/Abrir

Coleções

Home collection (FCT)