基于FNER性能退化指标及IDRSN的滚动轴承寿命状态识别方法

doi:10.3901/JME.2021.15.105

机械工程学报 ›› 2021, Vol. 57 ›› Issue (15): 105-115.doi: 10.3901/JME.2021.15.105

扫码分享

基于FNER性能退化指标及IDRSN的滚动轴承寿命状态识别方法

董绍江^1,2, 裴雪武¹, 汤宝平³, 田科位¹, 朱朋¹, 李洋¹, 赵兴新⁴

1. 重庆交通大学机电与车辆工程学院重庆 400074;
2. 磁悬技术与磁浮列车教育部重点实验室成都 610031;
3. 重庆大学机械传动国家重点实验室重庆 400044;
4. 重庆长江轴承股份有限公司重庆 401336

收稿日期:2020-10-10 修回日期:2021-03-15 出版日期:2021-08-05 发布日期:2021-11-03
通讯作者: 裴雪武(通信作者),男,1995年出生。主要研究方向为机械故障诊断。E-mail:398721763@qq.com
作者简介:董绍江,男,1982年出生,博士,教授,博士研究生导师。主要研究方向为机械故障诊断和机电一体化技术。E-mail:dongshaojiang100@163.com
基金资助:
国家自然科学基金（51775072），重庆市科技创新领军人才支持计划（CSTCCCXLJRC201920）和重庆市高校创新研究群体（CXQT20019）资助项目。

Recognition of Rolling Bearing Life Status Based on FNER Performance Degradation Indicator and IDRSN

DONG Shaojiang^1,2, PEI Xuewu¹, TANG Baoping³, TIAN Kewei¹, ZHU Peng¹, LI Yang¹, ZHAO Xingxin⁴

1. School of Mechantronics and Vehicle Engineering, Chongqing Jiaotong University, Chongqing 400074;
2. Key Laboratory of Magnetic Suspension Technology and Maglev Vehicle, Ministry of Education, Chengdu 610031;
3. The State Key Laboratory of Mechanical Transmission, Chongqing University, Chongqing 400044;
4. Chongqing Changjiang Bearing Co., Ltd, Chongqing 401336

Received:2020-10-10 Revised:2021-03-15 Online:2021-08-05 Published:2021-11-03

摘要/Abstract

摘要： 针对滚动轴承退化性能难以评估、寿命状态难以识别的问题，提出一种基于特征噪声能量比（Feature-to-noise energy ratio，FNER）指标及改进深度残差收缩网络（Improved deep residual shrinkage network，IDRSN）的滚动轴承寿命状态识别新方法。首先，将全寿命轴承信号进行希尔伯特（Hilbert）变换和快速傅里叶变换（Fast fourier transform，FFT）得到包络谱，根据故障特征频率及其倍频计算包络谱幅值的特征能量比（Feature energy ratio，FER）；然后，根据自相关函数（Autocorrelation function，AF）得到包络信号的总能量，将故障特征能量和噪声能量的比值作为轴承性能退化指标，之后按照FNER指标曲线划分轴承寿命状态和实现样本标签化；随后，使用标签化样本训练引入了密集连接网络的IDRSN得到轴承寿命状态识别模型。为了提高抗干扰能力，将DropBlock层引入第一个大型卷积内核，在全局平均池化之前引入Dropout技术。最后，运用两个滚动轴承全寿命周期数据集验证FNER指标和IDRSN模型的实用性和有效性，结果表明所提方法能更准确地实现滚动轴承寿命状态识别。

关键词: 特征噪声能量比, 滚动轴承性能退化评估, 早期故障检测, 改进深度残差收缩网络, 寿命状态识别

Abstract: Aiming at the difficulty in evaluating the degradation performance of rolling bearing and identifying bearing running state, a new method based on feature-to-noise energy ratio (FNER) indicator and improved deep residual shrinkage network (IDRSN) model is proposed. Firstly, Hilbert transform and fast fourier transform (FFT) are used to obtain the envelope spectrum of bearing run-to-failure test signal and the fault feature energy of the envelope spectrum amplitude is calculated. The feature energy ratio of the envelope spectrum amplitude is calculated according to the fault characteristic frequency and its frequency multiplication. Subsequently, the total energy of the signal is obtained according to the autocorrelation function (AF). After that, the ratio of the fault feature energy and the noise energy is used as the bearing performance degradation indicator. Moreover, the bearing running state is divided according to FNER indicator and tagged bearing samples realized. Then, tagged samples are used to train the IDRSN which introduces the densely connected network to obtain the bearing running state recognition model. In order to improve the anti-interference ability, the DropBlock layer is introduced into the first large convolution kernel and the Dropout technique is introduced before the global average pooling layer (GPA). Finally, two life cycle data sets of rolling bearings are used to verify the practicability and validity of FNER indicator and IDRSN model. The results show that the proposed method can more accurately identify the life state of rolling bearings.

Key words: feature-to-noise energy ratio, rolling bearing performance degradation assessment, early fault detection, improved deep residual shrinkage network, life state recognition

中图分类号:

TH17
TN911

董绍江, 裴雪武, 汤宝平, 田科位, 朱朋, 李洋, 赵兴新. 基于FNER性能退化指标及IDRSN的滚动轴承寿命状态识别方法[J]. 机械工程学报, 2021, 57(15): 105-115.

DONG Shaojiang, PEI Xuewu, TANG Baoping, TIAN Kewei, ZHU Peng, LI Yang, ZHAO Xingxin. Recognition of Rolling Bearing Life Status Based on FNER Performance Degradation Indicator and IDRSN[J]. Journal of Mechanical Engineering, 2021, 57(15): 105-115.

参考文献

[1] WU Dengyun, WANG Jianwen, WANG Hong, et al. An automatic bearing fault diagnosis method based on characteristics frequency ratio[J]. Sensors, 2020, 20(5):15-27.
[2] WANG Hengdi, DENG Sier, YANG Jianxi, et al. Parameter-adaptive VMD method based on BAS optimization algorithm for incipient bearing fault diagnosis[J]. Mathematical Problems in Engineering, 2020, 2020:5659618.
[3] DONG Shaojiang, WU Wenliang, HE Kun, et al. Rolling bearing performance degradation assessment based on improved convolutional neural network with anti-interference[J]. Measurement, 2020, 151:107219.
[4] ZHENG Jinde, PAN Haiyang, CHENG Junsheng. Rolling bearing fault detection and diagnosis based on composite multiscale fuzzy entropy and ensemble support vector machines[J]. Mechanical Systems and Signal Processing, 2017, 85:746-759.
[5] ZIMROZ R, BARTELMU W, BARSZCZ T, et al. Diagnostics of bearings in presence of strong operating conditions non stationarity-a procedure of load dependent features processing with application to wind turbine bearings[J]. Mechanical Systems and Signal Processing, 2014, 46(1):16-27.
[6] JACEK D. Diagnosing of rolling-element bearings using amplitude level-based decomposition of machine vibration signal[J]. Measurement, 2018, 126:143-155.
[7] YU Jianbo. Bearing performance degradation assessment using locality preserving projections[J]. Expert Systems with Applications, 2011, 38(6):7440-7450.
[8] ZHOU Jianmin, GUO Huijuan, ZHANG Long, et al. Bearing performance degradation assessment using lifting wavelet packet symbolic entropy and SVDD[J]. Shock and Vibration, 2016, 2016:1-10.
[9] ALI J B, FNAIECH N, SAIDI L, et al. Application of empirical mode decomposition and artificial neural network for automatic bearing fault diagnosis based on vibration signals[J]. Applied Acoustics, 2015, 89:16-27.
[10] XU Xiaoqiang, ZHAO Ming, LIN Jing, et al. Envelope harmonic-to-noise ratio for periodic impulses detection and its application to bearing diagnosis[J]. Measurement, 2016, 91:385-397.
[11] SACHAN S, SHUKLA S, SINGH S K. Two level de-noising algorithm for early detection of bearing fault using wavelet transform and zero frequency filter[J]. Tribology International, 2020, 143:106088.
[12] 程珩, 励文艳, 权龙, 等. 基于VMD-MDE和ELM的柱塞泵微弱故障诊断[J]. 振动.测试与诊断, 2020, 40(4):635-642, 818. CHENG Heng, LI Wenyan, QUAN Long, et al. Diagnosis of weak fault of plunger pump based on VMD-MDE and ELM[J]. Vibration. Test and Diagnosis, 2020, 40(4):635-642, 818.
[13] ZHANG Bin, ZHANG Shaohui, LI Weihua. Bearing performance degradation assessment using long short-term memory recurrent network[J]. Computers in Industry, 2019, 106:14-29.
[14] CHEGINI S N, MANJILI M J H, BAGHERI A. New fault diagnosis approaches for detecting the bearing slight degradation[J]. Meccanica, 2020, 55(1):261-286.
[15] PANG Bin, HE Yuling, TANG Guiji, et al. Rolling bearing fault diagnosis based on optimal notch filter and enhanced singular value decomposition[J]. Entropy, 2018, 20(7):482.
[16] ZHAO Minghang, ZHONG Shisheng, FU Xuyun, et al. Deep residual shrinkage networks for fault diagnosis[J]. IEEE Transactions on Industrial Informatics, 2020, 16(7):4681-4690.
[17] LIEW S S, KHALIL-HANI M, BAKHTERI R. Bounded activation functions for enhanced training stability of deep neural networks on visual pattern recognition problems[J]. Neurocomputing, 2016, 216(5):718-734.
[18] GHIASI G, LIN T Y, QUOC V L. DropBlock:A regularization method for convolutional networks[C]//Neural Information Processing Systems Conference, Monteral:NIPS. 2018.
[19] ZHANG Wei, LI Chuanhao, PENG Gaoliang, et al. A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load[J]. Mechanical Systems and Signal Processing, 2018, 100:439-453.
[20] HUANG Gao, LIU Zhang, MAATEN L V D, et al. Densely connected convolutional networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu:IEEE, 2017:2261-2269.
[21] XU Kun, LI Shunming, WANG Jinrui, et al. A novel adaptive and fast deep convolutional neural network for bearing fault diagnosis under different working conditions[J]. Proceedings of the Institution of Mechanical Engineers. Part D:Journal of Automobile Engineering, 2019, 234(4):1167-1182.
[22] 雷亚国, 韩天宇, 王彪, 等. XJTU-SY滚动轴承加速寿命试验数据集解读[J]. 机械工程学报, 2019, 55(16):1-6. LEI Yaguo, HAN Tianyu, WANG Biao, et al. XJTU-SY rolling bearing accelerated life test data set interpretation[J]. Journal of Mechanical Engineering, 2019, 55(16):1-6.

基于FNER性能退化指标及IDRSN的滚动轴承寿命状态识别方法

Recognition of Rolling Bearing Life Status Based on FNER Performance Degradation Indicator and IDRSN

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价

[1]	卞文彬, 邓艾东, 刘东川, 赵敏, 刘洋, 李晶. 基于改进深度残差收缩网络的风电机组滚动轴承故障诊断方法[J]. 机械工程学报, 2023, 59(12): 202-214.
[2]	王庆锋, 卫炳坤, 刘家赫, 马文生, 许述剑. 一种数据驱动的旋转机械早期故障检测模型构建和应用研究[J]. 机械工程学报, 2020, 56(16): 22-32.