Skip to main navigation Skip to main content
  • E-Submission

JKSPE : Journal of the Korean Society for Precision Engineering

OPEN ACCESS
ABOUT
BROWSE ARTICLES
EDITORIAL POLICIES
FOR CONTRIBUTORS
REGULAR

공기압축기의 이상 진단을 위한 딥러닝 기반 분석

Deep Learning-Based Analysis for Abnormal Diagnosis of Air Compressors

Journal of the Korean Society for Precision Engineering 2022;39(3):209-215.
Published online: March 1, 2022

1 서울과학기술대학교 기계설계로봇공학과

2 ㈜현대로템

1 Department of Mechanical System Design Engineering, Seoul National University of Science & Technology

2 Hyundai-Rotem Co., Ltd.

#E-mail: chibum@seoultech.ac.kr, TEL: +82-2-970-6337
• Received: November 24, 2021   • Revised: December 21, 2021   • Accepted: January 5, 2022

Copyright © The Korean Society for Precision Engineering

This is an Open-Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

  • 114 Views
  • 2 Download
  • 1 Crossref
prev next

Citations

Citations to this article as recorded by  Crossref logo
  • Analysis of Domestic Research Trends on Artificial Intelligence-Based Prognostics and Health Management
    Ye-Eun Jeong, Yong Soo Kim
    Journal of Korean Society for Quality Management.2023; 51(2): 223.     CrossRef

Download Citation

Download a citation file in RIS format that can be imported by all major citation management software, including EndNote, ProCite, RefWorks, and Reference Manager.

Format:

Include:

Deep Learning-Based Analysis for Abnormal Diagnosis of Air Compressors
J. Korean Soc. Precis. Eng.. 2022;39(3):209-215.   Published online March 1, 2022
Download Citation

Download a citation file in RIS format that can be imported by all major citation management software, including EndNote, ProCite, RefWorks, and Reference Manager.

Format:
Include:
Deep Learning-Based Analysis for Abnormal Diagnosis of Air Compressors
J. Korean Soc. Precis. Eng.. 2022;39(3):209-215.   Published online March 1, 2022
Close

Figure

  • 0
  • 1
  • 2
  • 3
  • 4
  • 5
  • 6
  • 7
  • 8
  • 9
Deep Learning-Based Analysis for Abnormal Diagnosis of Air Compressors
Image Image Image Image Image Image Image Image Image Image
Fig. 1 Structure of air compressor
Fig. 2 Method of data processing
Fig. 3 Downtrend, downshift of inner pressure
Fig. 4 Uptrend, upshift of oil temperature
Fig. 5 LSTM-AE architecture
Fig. 6 Abnormal score of the two scoring methodologies
Fig. 7 Result plot of the two scoring methodologies(Downtrend)
Fig. 8 Result plot of the two scoring methodologies (Downshift)
Fig. 9 Result plot of the two scoring methodologies (Uptrend)
Fig. 10 Result plot of the two scoring methodologies (Upshift)
Deep Learning-Based Analysis for Abnormal Diagnosis of Air Compressors
Predicted Normal Abnormal
Actual
Normal TN FP
Abnormal FN TP
Method Maximum
score [%]
Likelihood
score [%]
Pattern
Downtrend Precision 100 100
Recall 18.79 34.92
F1 31.63 51.76
Downshift Precision 100 100
Recall 4.61 53.81
F1 8.81 69.92
Uptrend Precision 100 100
Recall 0.02 3.46
F1 0.04 6.69
Upshift Precision 100 100
Recall 0.01 8.09
F1 0.02 14.87
Table 1 Variable of evaluation criteria
Table 2 The results of the two scoring methodologies