Side-by-side Chinese-English

基于光纤布拉格光栅传感的齿轮故障检测方法

陈勇1 陈亚武1 刘志强1 刘焕淋2

(1.重庆邮电大学工业物联网与网络化教育部重点实验室, 重庆 400065)
(2.重庆邮电大学光纤通信重点实验室, 重庆 400065)

【摘要】针对齿轮故障难以识别的问题,提出了一种用于齿轮异常状态识别的自适应噪声补偿聚合经验模态分解方法。利用光纤布拉格光栅(FBG)传感器提取齿轮的振动信号,通过自适应补偿高斯白噪声使振动信号频谱均匀化,以消除经验模态算法分解产生的模态混叠现象。利用相关系数和峭度值组成综合评价指标来选择有效分量,并提取其特征,采用支持向量机对齿轮故障进行识别与分类。实验结果表明:所提方法能有效地识别齿轮的不同状态(正常、轻度磨损、重度磨损、点蚀、裂纹以及断齿等),识别正确率均在90%以上。

【关键词】 光纤光学;齿轮;故障检测;光纤布拉格光栅;经验模态分解;模态混叠;

【DOI】

【基金资助】 国家自然科学基金(51977021);

A Gear Fault Detection Method Based on a Fiber Bragg Grating Sensor

CHEN Yong1 CHEN Yawu1 LIU Zhiqiang1 LIU Huanlin2

(1.Key Laboratory of Industrial Internet of Things and Network Control, Ministry of Education, Chongqing University of Posts and Telecommunications, Chongqing, China 400065)
(2.Key Laboratory of Optical Fiber Communication Technology, Chongqing University of Posts and Telecommunications, Chongqing, China 400065)

【Abstract】In this study, we proposed a gear fault identification method based on empirical mode decomposition of adaptive-noise complementary ensemble to solve the problem associated with the identification of gear faults. Initially, we used the fiber Bragg grating to extract the gear vibration signals and uniformized the spectrum of the vibration signal by adaptively adding Gaussian white noise to eliminate the mode mixing caused by the empirical modal algorithm. Subsequently, we used the correlation coefficient and the kurtosis value to obtain comprehensive evaluation indices for selecting the effective components and extracting the features of the effective components. Finally, we used a support vector machine to identify the gear faults. The experimental results denote that the proposed method can be used to effectively identify the states of gears, including normal, mild-wear, severe-wear, pitting, cracks, and broken teeth. Furthermore, the gear state identification accuracy rate is more than 90%.

【Keywords】 fiber optics; gear; fault detection; fiber Bragg grating; empirical mode decomposition; mode mixing;

【DOI】

【Funds】 National Natural Science Foundation of China (51977021);

Download this article
    References

    [1] Jiang G Q, He H B, Yan J, et al. Multiscale convolutional neural networks for fault diagnosis of wind turbine gearbox [J]. IEEE Transactions on Industrial Electronics, 2019, 66 (4): 3196–3207.

    [2] Yang Q, Hu C Z, Zheng N G. Data-driven diagnosis of nonlinearly mixed mechanical faults in wind turbine gearbox [J]. IEEE Internet of Things Journal, 2018, 5 (1): 466–467.

    [3] Zhou W, Liang Q. Real-time spectrum analysis algorithm for non-stationary signal and it’s implementation on FPGA platforms [J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2018, 30 (5): 633–641 (in Chinese).

    [4] Wang J, Cheng F Z, Qiao W, et al. Multiscale filtering reconstruction for wind turbine gearbox fault diagnosis under varying-speed and noisy conditions [J]. IEEE Transactions on Industrial Electronics, 2018, 65 (5): 4268–4278.

    [5] Zhang M, Wang K S, Wei D D, et al. Amplitudes of characteristic frequencies for fault diagnosis of planetary gearbox [J]. Journal of Sound and Vibration, 2018, 432: 119–132.

    [6] Chen Y, Wu C T, Liu H L. EMD self-adaptive selecting relevant modes algorithm for FBG spectrum signal [J]. Optical Fiber Technology, 2017, 36: 63–67.

    [7] Amarnath M, Praveen Krishna I R. Local fault detection in helical gears via vibration and acoustic signals using EMD based statistical parameter analysis [J]. Measurement, 2014, 58: 154–164.

    [8] Pan P, Xi L X, Zhang X G, et al. Experimental research on polarization mode dispersion measurement based on empirical mode decomposition [J]. Chinese Journal of Lasers, 2018, 45 (1): 0106002 (in Chinese).

    [9] Chen J Y, Zhou D, Liu C, et al. An integrated method based on CEEMD-SampEn and the correlation analysis algorithm for the fault diagnosis of a gearbox under different working conditions [J]. Mechanical Systems and Signal Processing, 2018, 113: 102–111.

    [10] Zhao C R, Jin X F, Ni D C, et al. Optical fiber rotational speed sensor based on plastic optical fiber and optical prism [J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2016, 28 (3): 383–388 (in Chinese).

    [11] Chen Y, Liu B L, Liu H L, et al. Load location and measurement system based on fiber Bragg grating sensor [J]. Chinese Journal of Mechanical Engineering, 2016, 52 (18): 8–15 (in Chinese).

    [12] Chen Y, Zhou L X, Liu H L. A fiber Bragg grating sensor perimeter intrusion localization method optimized by improved particle swarm optimization algorithm [J]. IEEE Sensors Journal, 2018, 18 (3): 1243–1249.

    [13] Liu H L, Wang C J, Chen Y. An improved genetic algorithm for increasing the addressing accuracy of encoding fiber Bragg grating sensor network [J]. Optical Fiber Technology, 2018, 40: 28–35.

    [14] He C B, Cai S K, Sun D K, et al. Fault diagnosis of wind turbine planetary gearbox based on order analysis and divergence index [J]. The Journal of Engineering, 2017, 2017 (13): 1394–1398.

    [15] Huang N E, Shen Z, Long S R, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis [J]. Proceedings of the Royal Society of London Series A: Mathematical, Physical and Engineering Sciences, 1998, 454 (1971): 903–995.

    [16] Lian J J, Rong Q B, Dong X F, et al. Structural model parameter identification method based on an improved HHT for suppressing mode mixing [J]. Journal of Vibration and Shock, 2018, 37 (18): 1–8 (in Chinese).

    [17] Zhang X, Cui W, Liu Y L. Recovery of structured signals with prior information via maximizing correlation [J]. IEEE Transactions on Signal Processing, 2018, 66 (12): 3296–3310.

    [18] Zhang L, Mao Z D, Yang S X, et al. An improved Kurtogram based on band-pass envelope spectral Kurtosis with its application in bearing fault diagnosis [J]. Journal of Vibration and Shock, 2018, 37 (23): 171–179 (in Chinese).

    [19] Pan X L, Yang Z J, Xu Y T, et al. Safe screening rules for accelerating twin support vector machine classification [J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29 (5): 1876–1887.

    [20] Chen Y, Liu Z Q, Liu H L. A method of fiber Bragg grating sensing signal de-noise based on compressive sensing [J]. IEEE Access, 2018, 6: 28318–28327.

    [21] Geng R, Wang X J, Ye N, et al. A fault prediction algorithm based on rough sets and back propagation neural network for vehicular networks [J]. IEEE Access, 2018, 6: 74984–74992.

This Article

ISSN:0258-7025

CN: 31-1339/TN

Vol 47, No. 03, Pages 232-241

March 2020

Downloads:3

Share
Article Outline

Abstract

  • 1 Introduction
  • 2 Method of identification of gear faults
  • 3 Simulation verification
  • 4 Experiment and analysis
  • 5 Conclusions
  • References