One-shot fault diagnosis of 3D printers through improved feature space learning

Signal acquisition from mechanical systems working in faulty conditions is normally expensive. As a consequence, supervised learning-based approaches are hardly applicable. To address this problem, a one-shot learning-based approach is proposed for multi-class classification of signals coming from a...

Descripción completa

Detalles Bibliográficos
Autores: Li, Chuan, Cabrera, Diego, Sancho Caparrini, Fernando, Sánchez, René-Vinicio, Cerrada, Mariela, Oliveira, José Valente de
Tipo de recurso: artículo
Estado:Versión enviada para evaluación y publicación
Fecha de publicación:2020
País:España
Institución:Universidad de Sevilla (US)
Repositorio:idUS. Depósito de Investigación de la Universidad de Sevilla
OAI Identifier:oai:idus.us.es:11441/107272
Acceso en línea:https://hdl.handle.net/11441/107272
https://doi.org/10.1109/TIE.2020.3013546
Access Level:acceso abierto
Palabra clave:Deep learning
Fault diagnosis
One-shot learning
3D printer
Descripción
Sumario:Signal acquisition from mechanical systems working in faulty conditions is normally expensive. As a consequence, supervised learning-based approaches are hardly applicable. To address this problem, a one-shot learning-based approach is proposed for multi-class classification of signals coming from a feature space created only from healthy condition signals and one single sample for each faulty class. First, a transformation mapping between the input signal space and a feature space is learned through a bidirectional generative adversarial network. Next, the identification of different health condition regions in this feature space is carried out by means of a single input signal per fault. The method is applied to three fault diagnosis problems of a 3D printer and outperforms other methods in the literature.