Low-cost and Small-sample Fault Diagnosis for 3D Printers Based on Echo State Networks

Kun He; Lianghua Zeng; Qin Shui; Jianyu Long; Chuan Li; Diego Cabrera

doi:10.1109/PHM-Qingdao46334.2019.8942894

Low-cost and Small-sample Fault Diagnosis for 3D Printers Based on Echo State Networks

Kun He, Lianghua Zeng, Qin Shui, Jianyu Long, Chuan Li, Diego Cabrera

Research and Development Group in Industrial Technologies (GIDTEC)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

With the 3D printing rapidly expanding into various fields, 3D printers, as the equipment, should adopt a low-cost and small-sample fault diagnosis methods. A fault diagnosis method based on echo state networks (ESN) for 3D printers is proposed in this paper. A low-cost attitude sensor installed on the 3D printer is employed to collect raw fault data. Subsequently, feature extraction is carried out on the raw fault data. Using these features, ESN, as a shallow learning network, is modeled to diagnose faults of 3D printers. Experimental results show that the fault diagnosis method based on ESN still effective for 3D printers in low-cost and small-sample, which can make the fault recognition accuracy of 3D printer reach to 97.26%. Furthermore, contrast results indicated that the fault diagnosis accuracy of ESN is higher and most stable when compare with support vector machine (SVM), locality preserving projection support vector machine (LPPSVM) and principal component analysis support vector machine (PCASVM).

Original language	English
Title of host publication	2019 Prognostics and System Health Management Conference, PHAI-Qingdao 2019
Editors	Wei Guo, Steven Li, Qiang Miao
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728108612
DOIs	https://doi.org/10.1109/PHM-Qingdao46334.2019.8942894
State	Published - Oct 2019
Event	10th Prognostics and System Health Management Conference, PHM-Qingdao 2019 - Qingdao, China Duration: 25 Oct 2019 → 27 Oct 2019

Publication series

Name	2019 Prognostics and System Health Management Conference, PHM-Qingdao 2019

Conference

Conference	10th Prognostics and System Health Management Conference, PHM-Qingdao 2019
Country/Territory	China
City	Qingdao
Period	25/10/19 → 27/10/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

3D printer
echo state networks
fault diagnosis
feature extraction
machine learning

Access to Document

10.1109/PHM-Qingdao46334.2019.8942894

Cite this

He, K., Zeng, L., Shui, Q., Long, J., Li, C., & Cabrera, D. (2019). Low-cost and Small-sample Fault Diagnosis for 3D Printers Based on Echo State Networks. In W. Guo, S. Li, & Q. Miao (Eds.), 2019 Prognostics and System Health Management Conference, PHAI-Qingdao 2019 Article 8942894 (2019 Prognostics and System Health Management Conference, PHM-Qingdao 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/PHM-Qingdao46334.2019.8942894

He, Kun ; Zeng, Lianghua ; Shui, Qin et al. / Low-cost and Small-sample Fault Diagnosis for 3D Printers Based on Echo State Networks. 2019 Prognostics and System Health Management Conference, PHAI-Qingdao 2019. editor / Wei Guo ; Steven Li ; Qiang Miao. Institute of Electrical and Electronics Engineers Inc., 2019. (2019 Prognostics and System Health Management Conference, PHM-Qingdao 2019).

@inproceedings{88a6625f85f24139932b85edc2790013,

title = "Low-cost and Small-sample Fault Diagnosis for 3D Printers Based on Echo State Networks",

abstract = "With the 3D printing rapidly expanding into various fields, 3D printers, as the equipment, should adopt a low-cost and small-sample fault diagnosis methods. A fault diagnosis method based on echo state networks (ESN) for 3D printers is proposed in this paper. A low-cost attitude sensor installed on the 3D printer is employed to collect raw fault data. Subsequently, feature extraction is carried out on the raw fault data. Using these features, ESN, as a shallow learning network, is modeled to diagnose faults of 3D printers. Experimental results show that the fault diagnosis method based on ESN still effective for 3D printers in low-cost and small-sample, which can make the fault recognition accuracy of 3D printer reach to 97.26%. Furthermore, contrast results indicated that the fault diagnosis accuracy of ESN is higher and most stable when compare with support vector machine (SVM), locality preserving projection support vector machine (LPPSVM) and principal component analysis support vector machine (PCASVM).",

keywords = "3D printer, echo state networks, fault diagnosis, feature extraction, machine learning",

author = "Kun He and Lianghua Zeng and Qin Shui and Jianyu Long and Chuan Li and Diego Cabrera",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 10th Prognostics and System Health Management Conference, PHM-Qingdao 2019 ; Conference date: 25-10-2019 Through 27-10-2019",

year = "2019",

month = oct,

doi = "10.1109/PHM-Qingdao46334.2019.8942894",

language = "English",

series = "2019 Prognostics and System Health Management Conference, PHM-Qingdao 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Wei Guo and Steven Li and Qiang Miao",

booktitle = "2019 Prognostics and System Health Management Conference, PHAI-Qingdao 2019",

address = "United States",

}

He, K, Zeng, L, Shui, Q, Long, J, Li, C & Cabrera, D 2019, Low-cost and Small-sample Fault Diagnosis for 3D Printers Based on Echo State Networks. in W Guo, S Li & Q Miao (eds), 2019 Prognostics and System Health Management Conference, PHAI-Qingdao 2019., 8942894, 2019 Prognostics and System Health Management Conference, PHM-Qingdao 2019, Institute of Electrical and Electronics Engineers Inc., 10th Prognostics and System Health Management Conference, PHM-Qingdao 2019, Qingdao, China, 25/10/19. https://doi.org/10.1109/PHM-Qingdao46334.2019.8942894

Low-cost and Small-sample Fault Diagnosis for 3D Printers Based on Echo State Networks. / He, Kun; Zeng, Lianghua; Shui, Qin et al.
2019 Prognostics and System Health Management Conference, PHAI-Qingdao 2019. ed. / Wei Guo; Steven Li; Qiang Miao. Institute of Electrical and Electronics Engineers Inc., 2019. 8942894 (2019 Prognostics and System Health Management Conference, PHM-Qingdao 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Low-cost and Small-sample Fault Diagnosis for 3D Printers Based on Echo State Networks

AU - He, Kun

AU - Zeng, Lianghua

AU - Shui, Qin

AU - Long, Jianyu

AU - Li, Chuan

AU - Cabrera, Diego

PY - 2019/10

Y1 - 2019/10

N2 - With the 3D printing rapidly expanding into various fields, 3D printers, as the equipment, should adopt a low-cost and small-sample fault diagnosis methods. A fault diagnosis method based on echo state networks (ESN) for 3D printers is proposed in this paper. A low-cost attitude sensor installed on the 3D printer is employed to collect raw fault data. Subsequently, feature extraction is carried out on the raw fault data. Using these features, ESN, as a shallow learning network, is modeled to diagnose faults of 3D printers. Experimental results show that the fault diagnosis method based on ESN still effective for 3D printers in low-cost and small-sample, which can make the fault recognition accuracy of 3D printer reach to 97.26%. Furthermore, contrast results indicated that the fault diagnosis accuracy of ESN is higher and most stable when compare with support vector machine (SVM), locality preserving projection support vector machine (LPPSVM) and principal component analysis support vector machine (PCASVM).

AB - With the 3D printing rapidly expanding into various fields, 3D printers, as the equipment, should adopt a low-cost and small-sample fault diagnosis methods. A fault diagnosis method based on echo state networks (ESN) for 3D printers is proposed in this paper. A low-cost attitude sensor installed on the 3D printer is employed to collect raw fault data. Subsequently, feature extraction is carried out on the raw fault data. Using these features, ESN, as a shallow learning network, is modeled to diagnose faults of 3D printers. Experimental results show that the fault diagnosis method based on ESN still effective for 3D printers in low-cost and small-sample, which can make the fault recognition accuracy of 3D printer reach to 97.26%. Furthermore, contrast results indicated that the fault diagnosis accuracy of ESN is higher and most stable when compare with support vector machine (SVM), locality preserving projection support vector machine (LPPSVM) and principal component analysis support vector machine (PCASVM).

KW - 3D printer

KW - echo state networks

KW - fault diagnosis

KW - feature extraction

KW - machine learning

UR - http://www.scopus.com/inward/record.url?scp=85077988896&partnerID=8YFLogxK

U2 - 10.1109/PHM-Qingdao46334.2019.8942894

DO - 10.1109/PHM-Qingdao46334.2019.8942894

M3 - Conference contribution

AN - SCOPUS:85077988896

T3 - 2019 Prognostics and System Health Management Conference, PHM-Qingdao 2019

BT - 2019 Prognostics and System Health Management Conference, PHAI-Qingdao 2019

A2 - Guo, Wei

A2 - Li, Steven

A2 - Miao, Qiang

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 10th Prognostics and System Health Management Conference, PHM-Qingdao 2019

Y2 - 25 October 2019 through 27 October 2019

ER -

He K, Zeng L, Shui Q, Long J, Li C, Cabrera D. Low-cost and Small-sample Fault Diagnosis for 3D Printers Based on Echo State Networks. In Guo W, Li S, Miao Q, editors, 2019 Prognostics and System Health Management Conference, PHAI-Qingdao 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 8942894. (2019 Prognostics and System Health Management Conference, PHM-Qingdao 2019). doi: 10.1109/PHM-Qingdao46334.2019.8942894

Low-cost and Small-sample Fault Diagnosis for 3D Printers Based on Echo State Networks

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this