A Two-Stage Learning Method For Fault Detection of Machines Using Mechanical Big Data
DOI:
https://doi.org/10.26438/ijcse/v6i5.387391Keywords:
Mechanical big data, unsupervised feature learning, sparse filtering, softmax regression, intelligent fault diagnosisAbstract
Intelligent fault diagnosis is a promising instrument to deal with mechanical big data because of its capacity in quickly and proficiently handling gathered signals and giving exact diagnosis outcomes. Feature extraction is done manually in most of the traditional techniques which required previous knowledge along with diagnostic expertise. Such procedures take favourable position of human inventiveness is tedious and work escalated. The main possibility of unsupervised component discovering that utilization of intelligence systems to learn raw data, a two-stage learning technique is proposed for intelligent analysis of machines. In the first stage vibration signal is utilized to get a grasp on features from mechanical vibration signals. In the next stage, softmax regression is used to classify the health conditions depends on the studied features. The approach is verified by a motor bearing dataset and a locomotive bearing dataset. It can be seen that using this method high diagnosis accuracy can be obtained. Also, the proposed method reduces the need of human labour making it preferable than the existing methods.
References
X. Wu, X. Zhu, G.-Q. Wu, and W. Ding, “Data mining with big data,” IEEE Trans. Knowl. Data Eng., vol. 26, no. 1, pp. 97-107, Jan. 2014.
S. Yin, and O. Kaynak, “Big data for modern industry: challenges and trends,” Proc. IEEE, vol. 103, no. 2, pp. 143-146, Feb. 2015.
W. Qiao, and D. Lu, “A survey on wind turbine condition monitoring and fault diagnosis, ” IEEE Trans. Ind. Electron., vol. 62, no. 10, pp. 6536-6545, Oct. 2015.
Y. Lei, J. Lin, M. J. Zuo, and Z. He, “Condition monitoring and fault diagnosis of planetary gearboxes: A review,” Measurement, vol. 48, pp. 292-305, Feb. 2014.
D. You, X. Gao, and S. Katayama, “WPD-PCA-based laser welding process monitoring and defects diagnosis by using FNN and SVM,” IEEE Trans. Ind. Electron., vol. 62, no. 1, pp. 628-638, Jan. 2015.
Y. Lei, Z. He, Y. Zi, and X. Chen, “New clustering algorithm-based fault diagnosis using compensation distance evaluation technique,” Mech. Syst. Signal Process., vol. 22, no. 2, pp. 419-435, Feb. 2008.
S. Yin, S. X. Ding, X. Xie, and H. Luo, “A review on basic data-driven approaches for industrial process monitoring,” IEEE Trans. Ind. Electron., vol. 61, no. 11, pp. 6418-6428, Nov. 2014.
Y. Lei, Z. He, Y. Zi, and Q. Hu, “Fault diagnosis of rotating machinery based on multiple ANFIS combination with GAs,” Mech. Syst. Signal Process., vol. 21, no. 5, pp. 2280-2294, Jul. 2007.
M. Kang, J. Kim, J.-M. Kim, A. C. Tan, E. Y. Kim, and B.-K. Choi, “Reliable Fault Diagnosis for Low-Speed Bearings Using Individually Trained Support Vector Machines With Kernel Discriminative Feature Analysis,” IEEE Trans. Power Electron., vol. 30, no. 5, pp. 2786-2797, May 2015.
Yaguo Lei, Member, IEEE, Feng Jia, Jing Lin, Saibo Xing, and Steven X. Ding,” An Intelligent Fault Diagnosis Method Using Unsupervised Feature Learning Towards Mechanical Big Data.”, IEEE Transctions on Industrial Electronics, 2016.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
