Performance degradation trend prediction method for rotating machinery based on QWGRUNN

被引：0
|
作者：
Li F. [1 ]
Xiang W. [1 ]
Wang J. [2 ]
Tang B. [3 ]
机构：
[1] School of Manufacturing Science and Engineering, Sichuan University, Chengdu
[2] School of Aeronautics and Astronautics, Sichuan University, Chengdu
[3] State Key Lab of Mechanical Transmission, Chongqing University, Chongqing
来源：
Zhendong yu Chongji/Journal of Vibration and Shock | 2019年 / 38卷 / 01期
关键词：
Permutation entropy; Quantum computation; Quantum weighted gated recurrent unit neural network (QWGRUNN); Rotating machinery; Trend prediction;
D O I：
10.13465/j.cnki.jvs.2019.01.018
中图分类号：
学科分类号：
摘要：
A novel performance degradation trend prediction method of rotating machinery was proposed based on the quantum weighted gated recurrent unit neural network (QWGRUNN). Firstly, the performance degradation index set for rotating machinery was constructed by using the wavelet denoise-permutation entropy method. Then, this index set was input in to QWGRUNN to accomplish the performance degradation trend prediction of rotating machinery. On the basis of gated recurrent unit (GRU), qubits were introduced in QWGRUNN to represent network weights and activity values, quantum phase-shift gates were constructed to update weight-qubits and activity-qubits, and improve the network generalization capacity and the performance degradation trend prediction accuracy of the proposed method. Finally, the dynamic learning parameter appropriate to the structure of QWGRUNN was adopted to improve the network convergence speed and the computation efficiency of the proposed method. The example of performance degradation trend prediction for rolling bearing verified the effectiveness of the proposed method. © 2019, Editorial Office of Journal of Vibration and Shock. All right reserved.
引用
收藏
页码：123 / 129and158
相关论文
共 14 条
  • [1] Xu Y., Yuan P., Yang W., Study on condition of automobile engine performance prediction based on Kovmogolov entropy, Journal of Vibration and Shock, 23, 3, pp. 101-104, (2004)
  • [2] Xia F., Jiao J., Ma C., Et al., Forecast the miacrohardnesses of the NI-TIN nanocoatings by AR model, Journal of Functional Materials, 43, 2, pp. 140-143, (2012)
  • [3] Du Z., Li X., Fault estimation and prediction based on multiple fading factors strongtracking UKF and constrained AR model, Control and Decision, 29, 9, pp. 1667-1672, (2014)
  • [4] Ma X., Ren S., Zuo H., Et al., Prediction method of aero-engine life on wing based on LS-SVM algorithm and performance reliability, Journal of Traffic and Transportation Engineering, 15, 3, pp. 92-99, (2015)
  • [5] Chen F., Yang Y., Ma J., Et al., Fuzzy granulation prediction for bearing performance degradation based on information entropy and optimized LS-SVM, Chinese Journal of Scientific Instrument, 37, 4, pp. 779-787, (2016)
  • [6] Xiao T., Tang B., Qin Y., Et al., Degradation trend prediction of rolling bearing based on manifold learning and least squares support vector machine, Journal of Vibration and Shock, 34, 9, pp. 149-153, (2015)
  • [7] Liu H., Wu X., Wang Y., Et al., Power prediction for centrifugal pumps at shut off condition based on BP neural network, Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 28, 11, pp. 45-49, (2012)
  • [8] Qin G., Zhang Y., Ye H., A neural network-based prediction method of machining deformation for thin-walled workpiece, Acta Armamentarii, 34, 7, pp. 840-845, (2013)
  • [9] Guo L., Li N., Jia F., Et al., A recurrent neural network based health indicator for remaining useful life prediction of bearings, Neurocomputing, 240, pp. 98-109, (2017)
  • [10] Cho K., Van Merienboer B., Gulcehre C., Et al., Learning phrase repre-sentations using RNN ecoder-decoder for statistical machine translation, Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, (2014)
12