Semi-supervised learning for industrial fault detection and diagnosis: A systemic review
ISA Transactions · 2023-12 · 143 · 255-270
DOI: 10.1016/j.isatra.2023.09.027 ↗Kurz gefasst
Fachartikel in der Zeitschrift ISA Transactions, 2023-12. Verfasst von José Miguel Ramírez-Sanz und 3 weiteren Autor:innen. Beteiligte Einrichtung: Universidad de Burgos, Avda. Cantabria s/n, Burgos, 09006, Burgos, Spain. Die Arbeit wurde bisher 124-mal zitiert (Crossref) und nennt 182 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Commission, Federación Española de Enfermedades Raras, Ministerio de Ciencia e Innovación.
Abstract (Originalsprache)
The automation of Fault Detection and Diagnosis (FDD) is a central task for many industries today. A myriad of methods are in use, although the most recent leading contenders are data-driven approaches and especially Machine Learning (ML) methods. ML algorithms fall into two main categories: supervised and unsupervised methods, depending on whether or not the instances are labeled with the expected outputs. However, a new approach called Semi-Supervised Learning (SSL) has recently emerged that uses a few labeled instances together with other unlabeled instances for the training process. This new approach can significantly improve the accuracy of conventional ML models for industrial environments where labeled data are scarce. SSL has been tested as a promising solution over the past few years for several FDD problems, although there have been no systemic reviews of this sort of approach up until the present review. In this study, an attempt to organize the existing literature on SSL for FDD using the taxonomy of van Engelen & Hoos is reported. The most and the least frequently used SSL algorithms are identified and considered in terms of different fault detection tasks and their most common dataset structure. Moreover, a set of best practices are proposed in the conclusions of this work for implementation under real industrial conditions, so as to avoid some of the most common faults.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Universidad de Burgos, Avda. Cantabria s/n, Burgos, 09006, Burgos, Spain.
- Universidad de Burgos, Avda. Cantabria s/n, Burgos, 09006, Burgos, Spain. Electronic address: alvarag@ubu.es.
Förderung
- European Commission
- Federación Española de Enfermedades Raras
- Ministerio de Ciencia e Innovación
- European Social Fund Plus
- Consejería de Educación, Junta de Castilla y León
- Gobierno de España Ministerio de Ciencia e Innovación
- Junta de Castilla y León
Zitieren
APA
Ramírez-Sanz, J. M., Maestro-Prieto, J. A., Arnaiz-González, Á., & Bustillo, A. (2023). Semi-supervised learning for industrial fault detection and diagnosis: A systemic review. ISA Transactions, 143, 255-270. https://doi.org/10.1016/j.isatra.2023.09.027
Vancouver
Ramírez-Sanz JM, Maestro-Prieto JA, Arnaiz-González Á, Bustillo A. Semi-supervised learning for industrial fault detection and diagnosis: A systemic review. ISA Transactions. 2023;143:255-270. doi:10.1016/j.isatra.2023.09.027
BibTeX
@article{RamrezSanz2023,
author = {Ramírez-Sanz, José Miguel and Maestro-Prieto, Jose-Alberto and Arnaiz-González, Álvar and Bustillo, Andrés},
title = {Semi-supervised learning for industrial fault detection and diagnosis: A systemic review},
journal = {ISA Transactions},
year = {2023},
volume = {143},
pages = {255--270},
doi = {10.1016/j.isatra.2023.09.027}
}
EUVIMED