전이 학습과 진동 신호를 이용한 설비 고장 진단 및 분석
Fault Diagnosis and Analysis Based on Transfer Learning and Vibration Signals
0
조회
0
다운로드
7
인용
0
참고문헌
키워드
초록
With the automation of production lines in the manufacturing industry, the importance of real-time fault diagnosis of facility is increasing. In this paper, we propose a fault diagnosis algorithm of LM (Linear Motion)-guide based on deep learning using vibration signals. Generally, in order to guarantee the performance of the deep learning, it is necessary to have a sufficient amount of data, but in a manufacturing industry, it is often difficult to obtain enough data due to physical and time constraints. To solve this problem, we propose a convolutional neural networks (CNN) model based on transfer learning. In addition, the spectrogram image is input to the CNN to reflect the frequency characteristic of the vibration signals with time. The performance of fault diagnosis according to various load condition and transfer learning method was compared and evaluated by experiments. The results showed that the proposed algorithm exhibited an excellent performance.
Abstract
With the automation of production lines in the manufacturing industry, the importance of real-time fault diagnosis of facility is increasing. In this paper, we propose a fault diagnosis algorithm of LM (Linear Motion)-guide based on deep learning using vibration signals. Generally, in order to guarantee the performance of the deep learning, it is necessary to have a sufficient amount of data, but in a manufacturing industry, it is often difficult to obtain enough data due to physical and time constraints. To solve this problem, we propose a convolutional neural networks (CNN) model based on transfer learning. In addition, the spectrogram image is input to the CNN to reflect the frequency characteristic of the vibration signals with time. The performance of fault diagnosis according to various load condition and transfer learning method was compared and evaluated by experiments. The results showed that the proposed algorithm exhibited an excellent performance.
참고문헌 (22)
- Analysis of Market Prospect, "R&D Information Center, Smart Factory Construction Technology", Knowledge Industry Information Institute, ~ (2016)
- J. Chen, "Robust Model-based Fault Diagnosis for Dynamic Systems", International Series on Asian Studies in Computer and Information Science, 3 (1990), Springer
- Z. Gao, "A Survey of Fault Diagnosis and Fault-tolerant Techniques - Part 1 : Fault Diagnosis with Model-based and Signal-based Approaches", Journal of IEEE Transsactions on Industrial Electronics, 62(6), pp.3757~3767 (2015)
- 최주호, "예지기술의 연구동향 및 모델기반 예지기술 비교연구", 제어.로봇.시스템학회 논문지, 17(11), pp.1095~1100 (2011), 제어·로봇·시스템학회
- J.Rafiee, "Application of Mother Wavelet Functions for Automatic Gear and Bearing Fault Diagnosis", Journal of Expert Systems with Applications, 37(6), pp.4568~4579 (2010)
- P. Konar, "Bearing Fault Detectin of Induction Motor Using Wavelet and Support Vector Machines (SVMs)", Journal of Applied Soft Computing, 11(6), pp.4203~4211 (2011)
- M. Zhao, "Deep Residual Networks with Dynamically Weighted Wavelet Coefficients for Fault Diagnosis of Planetary Gearboxes", Journal of IEEE Transactions on Industrial Electronics, 65(5), pp.4290~4300 (2018)
- N.E. Huang, "The Empirical Mode Decomposition and the Hilbert Spectrum for Nonlinear and Non-stationary Time Series Analysis", Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences, 454(1971), pp.903~995 (1998)
- R. Yan, "Waelets for Fault Diagnosis of Rotary Machines: A Review with Applications", Proceedings of Signal Processing, 96, pp.1~15 (2014)
- D. You, "WPD-PCA-based Laser Welding Process Monitoring and Defects Diagnosis by Using FNN and SVM", Journal of IEEE Transactions on Industrial Electronics, 62(1), pp.628~638 (2015)
- T. Ince, "Real-time Motor Fault Detection by 1-D Convolutional Neural Networks", Journal of IEEE Transactions on Industrial Electronics, 53(11), pp.7067~7075 (2016)
- R. Liu, "Dislocated Time Series Convolutional Neural Architecture: an Intelligent Fault Diagnosis Approach for Electric Machine", Journal of IEEE Transactions on Industrial informatics, 13(3), pp.1310~1320 (2017)
- 정성종, "LM 볼가이드의 마찰력 정식화", 대한기계학회논문집 A, 40(2), pp.199~206 (2016), 대한기계학회
- Won Gi Lee, "Analysis of Vibration for Fault Diagnosis of Linearly Reciprocating Machinery", Proceedings of Korean Society for Precision Engineering 2011 Autumn Conference, pp.451~452 (2011)
- K. Simonyan, "Very Deep Convolutional Networks for Large-scale Image Recognition", International Conference on Learning Representations (2015)
- H. Liu, "Rolling Bearning Fault Diagnosis based on STFT-Deep Learning and Sound Signal", Journal of Mechanical Engineering, 30(6), pp.1357~1368 (2017)
- I. Goodfellow, "Deep learning" (2016), MIT
- M. Bojarski, "VisualBackProp: Efficient Visualization of CNNs" (2016)
- M.D. Zeiler, "Visualizing and Understanding Convolutional Networks", Proceedings of European Conference on Computer Vision, pp.818~833 (2014)
- J.T. Springenberg, "Striving for Simplicity: the all Convolutional net" (2015), International Conference on Learning Representations
- B. Zhou, "Learning Deep Features for Discriminative Localization", Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp.2921~2929 (2016)
- R.R. Selvaraju, "Learning Deep Features for Discriminative Localization", Proceedings of IEEE Conference on Computer Vision, pp.2921~2929 (2016)