One-Shot Fault Diagnosis of Three-Dimensional Printers through Improved Feature Space Learning

Chuan Li; Diego Cabrera; Fernando Sancho; Rene Vinicio Sanchez; Mariela Cerrada; Jose Valente De Oliveira

doi:10.1109/TIE.2020.3013546

One-Shot Fault Diagnosis of Three-Dimensional Printers through Improved Feature Space Learning

Chuan Li, Diego Cabrera, Fernando Sancho, Rene Vinicio Sanchez, Mariela Cerrada, Jose Valente De Oliveira

Research output: Contribution to journal › Article › peer-review

13 Scopus citations

Abstract

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 multiclass 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 three-dimensional printer and outperforms other methods in the literature.

Original language	English
Article number	9161402
Pages (from-to)	8768-8776
Number of pages	9
Journal	IEEE Transactions on Industrial Electronics
Volume	68
Issue number	9
DOIs	https://doi.org/10.1109/TIE.2020.3013546
State	Published - Sep 2021

Bibliographical note

Funding Information:
Manuscript received March 3, 2020; revised May 28, 2020; accepted July 11, 2020. Date of publication August 6, 2020; date of current version June 16, 2021. This work was supported in part by GIDTEC Research Group of Universidad Politecnica Salesiana, in part by the National Natural Science Foundation of China under Grant 51775112, in part by the Science and Technology Partnership Program under Grant KY201802006, in part by the Chongqing Natural Science Foundation under Grant cstc2019jcyj-zdxmX0013, and in part by the CTBU Project under Grant KFJJ2018107 and Grant KFJJ2018075. (Chuan Li and Diego Cabrera are co-first authors.) (Corresponding author: Diego Cabr-era.) Chuan Li is with the National Research Base of Intelligent Manufacturing Service, Chongqing Technology and Business University, Chongqing 400067, China (e-mail: chuanli@ctbu.edu.cn).

Publisher Copyright:
© 1982-2012 IEEE.

Keywords

Deep learning
fault diagnosis
one-shot learning
three-dimensional (3-D) printer

Access to Document

10.1109/TIE.2020.3013546

Cite this

@article{a81b4e5fb1fd49a686186efa93fdb88a,

title = "One-Shot Fault Diagnosis of Three-Dimensional Printers through Improved Feature Space Learning",

abstract = "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 multiclass 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 three-dimensional printer and outperforms other methods in the literature. ",

keywords = "Deep learning, fault diagnosis, one-shot learning, three-dimensional (3-D) printer",

author = "Chuan Li and Diego Cabrera and Fernando Sancho and Sanchez, {Rene Vinicio} and Mariela Cerrada and {De Oliveira}, {Jose Valente}",

note = "Publisher Copyright: {\textcopyright} 1982-2012 IEEE.",

year = "2021",

month = sep,

doi = "10.1109/TIE.2020.3013546",

language = "English",

volume = "68",

pages = "8768--8776",

journal = "IEEE Transactions on Industrial Electronics",

issn = "0278-0046",

publisher = "IEEE Industrial Electronics Society",

number = "9",

}

TY - JOUR

T1 - One-Shot Fault Diagnosis of Three-Dimensional Printers through Improved Feature Space Learning

AU - Li, Chuan

AU - Cabrera, Diego

AU - Sancho, Fernando

AU - Sanchez, Rene Vinicio

AU - Cerrada, Mariela

AU - De Oliveira, Jose Valente

PY - 2021/9

Y1 - 2021/9

N2 - 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 multiclass 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 three-dimensional printer and outperforms other methods in the literature.

AB - 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 multiclass 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 three-dimensional printer and outperforms other methods in the literature.

KW - Deep learning

KW - fault diagnosis

KW - one-shot learning

KW - three-dimensional (3-D) printer

UR - http://www.scopus.com/inward/record.url?scp=85099574407&partnerID=8YFLogxK

U2 - 10.1109/TIE.2020.3013546

DO - 10.1109/TIE.2020.3013546

M3 - Article

AN - SCOPUS:85099574407

SN - 0278-0046

VL - 68

SP - 8768

EP - 8776

JO - IEEE Transactions on Industrial Electronics

JF - IEEE Transactions on Industrial Electronics

IS - 9

M1 - 9161402

ER -

One-Shot Fault Diagnosis of Three-Dimensional Printers through Improved Feature Space Learning

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this