Evolutionary LSTM-FCN networks for pattern classification in industrial processes

Simple item page
dc.contributor.authorOrtego, Patxi
dc.contributor.authorDiez-Olivan, Alberto
dc.contributor.authorDel Ser, Javier
dc.contributor.authorVeiga, Fernando
dc.contributor.authorPenalva, Mariluz
dc.contributor.authorSierra, Basilio
dc.contributor.institutionTecnalia Research & Innovation
dc.contributor.institutionIA
dc.contributor.institutionFABRIC_INTEL
dc.date.accessioned2024-07-24T12:02:48Z
dc.date.available2024-07-24T12:02:48Z
dc.date.issued2020-05
dc.descriptionPublisher Copyright: © 2020 Elsevier B.V.
dc.description.abstractThe Industry 4.0 revolution allows gathering big amounts of data that are used to train and deploy Artificial Intelligence algorithms to solve complex industrial problems, optimally and automatically. From those, Long-Short Term Memory Fully Convolutional Network (LSTM-FCN) networks are gaining a lot of attention over the last decade due to their capability of successfully modeling nonlinear feature interactions. However, they have not been yet fully applied for pattern classification tasks in time series data within the digital industry. In this paper, a novel approach based on an evolutionary algorithm for optimizing the networks hyperparameters and on the resulting deep learning model for pattern classification is proposed. In order to demonstrate the applicability of this method, a test scenario that involves a process related to blind fastener installation in the aeronautical industry is provided. The results achieved with the proposed approach are compared with shallow models and it is demonstrated that the proposed method obtains better results with an accuracy value of 95%.en
dc.description.sponsorshipThis project has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 686827. This project has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 686827 .
dc.description.statusPeer reviewed
dc.identifier.citationOrtego , P , Diez-Olivan , A , Del Ser , J , Veiga , F , Penalva , M & Sierra , B 2020 , ' Evolutionary LSTM-FCN networks for pattern classification in industrial processes ' , Swarm and Evolutionary Computation , vol. 54 , 100650 . https://doi.org/10.1016/j.swevo.2020.100650
dc.identifier.doi10.1016/j.swevo.2020.100650
dc.identifier.issn2210-6502
dc.identifier.urihttps://hdl.handle.net/11556/3283
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85078973550&partnerID=8YFLogxK
dc.language.isoeng
dc.relation.ispartofSwarm and Evolutionary Computation
dc.relation.projectIDHorizon 2020 Framework Programme, H2020
dc.relation.projectIDHorizon 2020, 686827
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.subject.keywordsEvolutionary computation
dc.subject.keywordsFully convolutional neural network
dc.subject.keywordsIndustry 4.0
dc.subject.keywordsLong short term memory recurrent neural network
dc.subject.keywordsPattern classification
dc.subject.keywordsGeneral Computer Science
dc.subject.keywordsGeneral Mathematics
dc.subject.keywordsSDG 9 - Industry, Innovation, and Infrastructure
dc.titleEvolutionary LSTM-FCN networks for pattern classification in industrial processesen
dc.typejournal article
Files