Advanced search
2 files | 3.71 MB

Deep learning for infrared thermal image based machine health monitoring

Olivier Janssens (UGent), Rik Van de Walle (UGent), Mia Loccufier (UGent) and Sofie Van Hoecke (UGent)
Author
Organization
Abstract
The condition of a machine can automatically be identified by creating and classifying features that summarize characteristics of measured signals. Currently, experts, in their respective fields, devise these features based on their knowledge. Hence, the performance and usefulness depends on the expert's knowledge of the underlying physics or statistics. Furthermore, if new and additional conditions should be detectable, experts have to implement new feature extraction methods. To mitigate the drawbacks of feature engineering, a method from the subfield of feature learning, i.e., deep learning (DL), more specifically convolutional neural networks (NNs), is researched in this paper. The objective of this paper is to investigate if and how DL can be applied to infrared thermal (IRT) video to automatically determine the condition of the machine. By applying this method on IRT data in two use cases, i.e., machinefault detection and oil-level prediction, we show that the proposed system is able to detect many conditions in rotating machinery very accurately (i.e., 95 and 91.67% accuracy for the respective use cases), without requiring any detailed knowledge about the underlying physics, and thus having the potential to significantly simplify condition monitoring using complex sensor data. Furthermore, we show that by using the trained NNs, important regions in the IRT images can be identified related to specific conditions, which can potentially lead to new physical insights.
Keywords
FAULT-DIAGNOSIS, ROTATING MACHINERY, CLASSIFICATION, Fault detection, machine learning algorithms, neural networks, preventive maintenance

Downloads

    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 938.59 KB
  • DS110 i.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 2.77 MB

Citation

Please use this url to cite or link to this publication:

Chicago
Janssens, Olivier, Rik Van de Walle, Mia Loccufier, and Sofie Van Hoecke. 2018. “Deep Learning for Infrared Thermal Image Based Machine Health Monitoring.” Ieee-asme Transactions on Mechatronics 23 (1): 151–159.
APA
Janssens, O., Van de Walle, R., Loccufier, M., & Van Hoecke, S. (2018). Deep learning for infrared thermal image based machine health monitoring. IEEE-ASME TRANSACTIONS ON MECHATRONICS, 23(1), 151–159.
Vancouver
1.
Janssens O, Van de Walle R, Loccufier M, Van Hoecke S. Deep learning for infrared thermal image based machine health monitoring. IEEE-ASME TRANSACTIONS ON MECHATRONICS. Piscataway: Ieee-inst Electrical Electronics Engineers Inc; 2018;23(1):151–9.
MLA
Janssens, Olivier, Rik Van de Walle, Mia Loccufier, et al. “Deep Learning for Infrared Thermal Image Based Machine Health Monitoring.” IEEE-ASME TRANSACTIONS ON MECHATRONICS 23.1 (2018): 151–159. Print.
@article{8559058,
  abstract     = {The condition of a machine can automatically be identified by creating and classifying features that summarize characteristics of measured signals. Currently, experts, in their respective fields, devise these features based on their knowledge. Hence, the performance and usefulness depends on the expert's knowledge of the underlying physics or statistics. Furthermore, if new and additional conditions should be detectable, experts have to implement new feature extraction methods. To mitigate the drawbacks of feature engineering, a method from the subfield of feature learning, i.e., deep learning (DL), more specifically convolutional neural networks (NNs), is researched in this paper. The objective of this paper is to investigate if and how DL can be applied to infrared thermal (IRT) video to automatically determine the condition of the machine. By applying this method on IRT data in two use cases, i.e., machinefault detection and oil-level prediction, we show that the proposed system is able to detect many conditions in rotating machinery very accurately (i.e., 95 and 91.67\% accuracy for the respective use cases), without requiring any detailed knowledge about the underlying physics, and thus having the potential to significantly simplify condition monitoring using complex sensor data. Furthermore, we show that by using the trained NNs, important regions in the IRT images can be identified related to specific conditions, which can potentially lead to new physical insights.},
  author       = {Janssens, Olivier and Van de Walle, Rik and Loccufier, Mia and Van Hoecke, Sofie},
  issn         = {1083-4435},
  journal      = {IEEE-ASME TRANSACTIONS ON MECHATRONICS},
  keyword      = {FAULT-DIAGNOSIS,ROTATING MACHINERY,CLASSIFICATION,Fault detection,machine learning algorithms,neural networks,preventive maintenance},
  language     = {eng},
  number       = {1},
  pages        = {151--159},
  publisher    = {Ieee-inst Electrical Electronics Engineers Inc},
  title        = {Deep learning for infrared thermal image based machine health monitoring},
  url          = {http://dx.doi.org/10.1109/TMECH.2017.2722479},
  volume       = {23},
  year         = {2018},
}

Altmetric
View in Altmetric
Web of Science
Times cited: