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

시계열 데이터를 이용한 인공신경망 기반 공작기계 가공상태 모니터링

Monitoring the Machining State of Machine Tools Using Artificial Neural Networks with Time-series Data

Journal of the Korean Society for Precision Engineering 2024;41(8):617-624.
Published online: August 1, 2024

1 부산대학교 부품소재산학협력연구소

2 부산대학교 나노에너지공학과

1 ILIC, Pusan National University

2 Department of Nano Energy Engineering, Pusan National University

#E-mail: dwoolee@pusan.ac.kr, TEL: +82-51-510-3129
• Received: February 25, 2024   • Revised: June 1, 2024   • Accepted: June 17, 2024

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.

  • 7 Views
  • 0 Download
  • 2 Crossref
  • 1 Scopus
prev next

Citations

Citations to this article as recorded by  Crossref logo
  • Development of AI-based Bearing Machining Process Defect Monitoring System
    Dae-Youn Kim, Dongwoo Go, Seunghoon Lee
    Journal of Society of Korea Industrial and Systems Engineering.2025; 48(3): 112.     CrossRef
  • A Review of Intelligent Machining Process in CNC Machine Tool Systems
    Joo Sung Yoon, Il-ha Park, Dong Yoon Lee
    International Journal of Precision Engineering and Manufacturing.2025; 26(9): 2243.     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:

Monitoring the Machining State of Machine Tools Using Artificial Neural Networks with Time-series Data
J. Korean Soc. Precis. Eng.. 2024;41(8):617-624.   Published online August 1, 2024
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:
Monitoring the Machining State of Machine Tools Using Artificial Neural Networks with Time-series Data
J. Korean Soc. Precis. Eng.. 2024;41(8):617-624.   Published online August 1, 2024
Close

Figure

  • 0
  • 1
  • 2
  • 3
  • 4
  • 5
  • 6
  • 7
  • 8
  • 9
  • 10
  • 11
  • 12
  • 13
Monitoring the Machining State of Machine Tools Using Artificial Neural Networks with Time-series Data
Image Image Image Image Image Image Image Image Image Image Image Image Image Image
Fig. 1 Training process of machine learning and deep learning
Fig. 2 CNN architecture comprised of input, hidden, and output layer
Fig. 3 The architecture of the LSTM cell
Fig. 4 Cutting process conducted at machine line center and type of cutting tool
Fig. 5 Installation of gap sensor at the machine line center
Fig. 6 11 holes of drilled and wear tool used in drilling process
Fig. 7 Gap sensor signals for each tool conditions
Fig. 8 Flowchart of the signal analysis through machine learning
Fig. 9 Flowchart of the signal analysis through deep learning
Fig. 10 Architecture of CNN, LSTM and MLP for deep learning
Fig. 11 Training score and model loss curve by test data (Machine learning)
Fig. 12 Confusion matrix of machine learning model plotted based on true and predicted data
Fig. 13 Training score and model loss curve by test data (deep learning)
Fig. 14 Confusion matrix of deep learning model plotted based on true and predicted data
Monitoring the Machining State of Machine Tools Using Artificial Neural Networks with Time-series Data

Evaluation metrics of the confusion matrix for each case

Epoch Number of hidden layers Nodes Macro sensitivity [%] Macro recall [%] Macro F1-score [%]
3,000 3 200 87 86 86
4 150 91 90 90
200 94 93 93
5,000 3 150 90 89 89
200 90 89 89
4 100 90 90 90
150 96 96 96
200 95 95 95

Evaluation metrics of the confusion matrix plotted in Fig. 14

Epoch Macro precision [%] Macro recall [%] Macro F1-score [%] Accuracy [%]
30 97 97 97 96.7
Table 1 Evaluation metrics of the confusion matrix for each case
Table 2 Evaluation metrics of the confusion matrix plotted in Fig. 14