基于频域特征的航空轴承智能诊断

李宏宇; 苏越; 陈康; 王俨剀

doi:10.13224/j.cnki.jasp.20220405

基于频域特征的航空轴承智能诊断

doi: 10.13224/j.cnki.jasp.20220405

西北工业大学动力与能源学院，西安 710072

基金项目: 国家科技重大专项（2017-Ⅰ-0006-0007）

详细信息

作者简介:
李宏宇（1997-），男，硕士生，主要从事航空发动机故障诊断领域的研究

中图分类号: V263.6
计量
- 文章访问数: 52
- HTML浏览量: 25
- PDF量: 11
- 被引次数: 0
出版历程
- 收稿日期: 2022-06-05
- 网络出版日期: 2023-11-27

Intelligent diagnosis of aviation bearings based on frequency domain features

School of Power and Energy，Northwestern Polytechnical University，Xi’an 710072，China

摘要

摘要:
针对航空发动机滚动轴承的故障诊断，提出一种基于频域特征的故障诊断模型。将原始振动信号进行包络解调预处理，仅取每段数据处理后的512个点作为故障特征，将其作为双向循环长短期记忆网络（BiLSTM）模型的输入，可对内圈故障、外圈故障、滚动体故障及每种故障所对应3种不同的故障程度进行诊断。该模型不仅弥补完全由原始振动信号输入导致输入数据冗长，特征不明显等缺点，也弥补由人工提取振动特征来进行故障诊断的不确定性。在滚动轴承公开数据集上进行实验，结果表明故障识别的准确度达到99.8%以上。搭建航空轴承实验器来对方法与模型进行检验。基于频域特征的双向循环长短期记忆网络模型能够更准确的对轴承进行故障诊断，所提方法对于航空发动机滚动轴承故障诊断具有重要工程价值。
- 故障诊断 /
- 特征提取 /
- 神经网络 /
- 滚动轴承 /
- 双向循环长短期记忆网络
Abstract:
A fault diagnosis model based on feature extraction was proposed for aeroengine rolling bearing fault diagnosis. The original vibration signals were preprocessed by envelope demodulation, and only 512 points of each segment of data were taken as fault features, and used as input of bidirectional long short-term memory (BiLSTM) model to diagnose the inner ring faults, outer ring faults, rolling body faults and three different fault degrees corresponding to each fault. The model made up for not only the disadvantages of long input data and obscure features caused by the original vibration signal input, but also the uncertainty of fault diagnosis by extracting vibration features manually. Experiments on the open data set of rolling bearings showed that the accuracy of fault identification was above 99.8%. An aero-bearing tester was built to verify the method and model. BiLSTM based on feature extraction can diagnose the bearing faults more accurately. The proposed method has important engineering value for the fault diagnosis of aeroengine rolling bearings.
- fault diagnosis /
- feature extraction /
- neural network /
- rolling bearing /
- bidirectional long short-term memory

HTML

图 1 RNN网络结构

Figure 1. RNN network structure

下载: 全尺寸图片幻灯片

图 2 LSTM内部结构

Figure 2. LSTM internal structure

下载: 全尺寸图片幻灯片

图 3 BiLSTM结构图

Figure 3. BiLSTM structure

下载: 全尺寸图片幻灯片

图 4 模型训练流程

Figure 4. Model training process

下载: 全尺寸图片幻灯片

图 5 凯斯西储大学轴承实验台^[26]

Figure 5. Rolling bearing test-bed of Case Western Reserve University^[26]

下载: 全尺寸图片幻灯片

图 6 原始振动信号

Figure 6. Original vibration signal

下载: 全尺寸图片幻灯片

图 7 包络解调后的特征数据

Figure 7. Characteristic data after envelope demodulation

下载: 全尺寸图片幻灯片

图 8 不同特征值对应训练过程的准确率

Figure 8. Accuracy of different feature numbers corresponding to the training process

下载: 全尺寸图片幻灯片

图 9 诊断结果混淆矩阵图

Figure 9. Confusion matrix diagram of diagnosis results

下载: 全尺寸图片幻灯片

图 10 训练过程损失值对比

Figure 10. Comparison of loss values during training

下载: 全尺寸图片幻灯片

图 11 训练过程准确率对比

Figure 11. Comparison of accuracy during training

下载: 全尺寸图片幻灯片

图 12 航空发动机滚动轴承实验器

Figure 12. Aero engine rolling bearing tester

下载: 全尺寸图片幻灯片

图 13 实验器数据集训练过程损失值对比

Figure 13. Comparison of the loss value in the training process of the experimental device data set

下载: 全尺寸图片幻灯片

图 14 实验器数据集训练过程准确率对比

Figure 14. Comparison of accuracy in training process of experimental device data set

下载: 全尺寸图片幻灯片

表 1 详细实验数据

Table 1. Detailed experimental data

序号	故障类型	故障直径/mm	样本长度	特征长度	训练样本数	测试样本数	标记标签值
1	正常	0	2048	512	278	70	0
2	内圈	0.1778	2048	512	278	70	1
3	外圈六点钟	0.1778	2048	512	278	70	2
4	滚动体	0.1778	2048	512	278	70	3
5	内圈	0.3556	2048	512	278	70	4
6	外圈六点钟	0.3556	2048	512	278	70	5
7	滚动体	0.3556	2048	512	278	70	6
8	内圈	0.5334	2048	512	278	70	7
9	外圈六点钟	0.5334	2048	512	278	70	8
10	滚动体	0.5334	2048	512	278	70	9

下载: 导出CSV

表 2 故障模拟方案

Table 2. Fault simulation scheme mm

序号	故障类型	损伤长	损伤宽度	损伤深度
1	内圈	0.3	0.1	1
2	外圈	0.3	0.1	1
3	滚动体	0.3	0.1	1

下载: 导出CSV

表 3 实验器详细数据表

Table 3. Detailed data sheet of tester

序号	故障类型	训练样本数	测试样本数	标记标签值
1	正常	188	48	0
2	内圈	188	48	1
3	外圈	188	48	2
4	滚动体	188	48	3

下载: 导出CSV

表 4 实验器数据验证结果

Table 4. Results of tester data validation

序号	故障类型	诊断准确率/%	标记标签值
1	正常	100	0
2	内圈	98	1
3	外圈	100	2
4	滚动体	100	3

下载: 导出CSV

参考文献(26)

[1]	刘朋,王黎钦,张传伟,等. 航空发动机主轴轴承状态监测研究现状与发展趋势[J]. 航空动力学报,2022,37(2): 330-343. LIU Peng,WANG Liqin,ZHANG Chuanwei,et al. Research status and development trend of condition monitoring on main-shaft bearings used in aircraft engines[J]. Journal of Aerospace Power,2022,37(2): 330-343. (in Chinese doi: 10.13224/j.cnki.jasp.20210083 LIU Peng, WANG Liqin, ZHANG Chuanwei, et al. Research status and development trend of condition monitoring on main-shaft bearings used in aircraft engines[J]. Journal of Aerospace Power, 2022, 37(2): 330-343. (in Chinese) doi: 10.13224/j.cnki.jasp.20210083
[2]	ZHANG Weitao,JI Xiaofan,HUANG Ju,et al. Compound fault diagnosis of aero-engine rolling element bearing based on CCA blind extraction[J]. IEEE Access,2021,9: 159873-159881. doi: 10.1109/ACCESS.2021.3130637
[3]	韩磊,洪杰,王冬. 基于小波包分析的航空发动机轴承故障诊断[J]. 推进技术,2009,30(3): 328-331,341. HAN Lei,HONG Jie,WANG Dong. Fault diagnosis of aero-engine bearings based on wavelet package analysis[J]. Journal of Propulsion Technology,2009,30(3): 328-331,341. (in Chinese doi: 10.3321/j.issn:1001-4055.2009.03.014 HAN Lei, HONG Jie, WANG Dong. Fault diagnosis of aero-engine bearings based on wavelet package analysis[J]. Journal of Propulsion Technology, 2009, 30(3): 328-331, 341. (in Chinese) doi: 10.3321/j.issn:1001-4055.2009.03.014
[4]	李先锋,颉潭成,徐彦伟,等. 轴承故障智能诊断专家系统的研究[J]. 制造业自动化,2020,42(1): 7-9,14. LI Xianfeng,XIE Tancheng,XU Yanwei,et al. The research on the intelligent diagnosis expert system for bearing fault[J]. Manufacturing Automation,2020,42(1): 7-9,14. (in Chinese LI Xianfeng, XIE Tancheng, XU Yanwei, et al. The research on the intelligent diagnosis expert system for bearing fault[J]. Manufacturing Automation, 2020, 42(1): 7-9, 14. (in Chinese)
[5]	BEN ALI J,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. doi: 10.1016/j.apacoust.2014.08.016
[6]	王平,廖明夫. 滚动轴承故障诊断的自适应共振解调技术[J]. 航空动力学报,2005,20(4): 606-612. WANG Ping,LIAO Mingfu. Adaptive demodulated resonance technique for the rolling bearing fault diagnosis[J]. Journal of Aerospace Power,2005,20(4): 606-612. (in Chinese doi: 10.3969/j.issn.1000-8055.2005.04.015 WANG Ping, LIAO Mingfu. Adaptive demodulated resonance technique for the rolling bearing fault diagnosis[J]. Journal of Aerospace Power, 2005, 20(4): 606-612. (in Chinese) doi: 10.3969/j.issn.1000-8055.2005.04.015
[7]	叶亮,邓四二,崔永存,等. 滚动轴承振动性能状态演变的非线性特征和不确定性特征的灰关系分析[J]. 航空动力学报,2022,37(6): 1121-1133. YE Liang,DENG Sier,CUI Yongcun,et al. Grey relation analysis on nonlinear characteristics and uncertainty characteristics of evolution of rolling bearing vibration performance state[J]. Journal of Aerospace Power,2022,37(6): 1121-1133. (in Chinese YE Liang, DENG Sier, CUI Yongcun, et al. Grey relation analysis on nonlinear characteristics and uncertainty characteristics of evolution of rolling bearing vibration performance state[J]. Journal of Aerospace Power, 2022, 37(6): 1121-1133. (in Chinese)
[8]	王晓龙,唐贵基. 一种基于连续小波变换的滚动轴承早期故障诊断新方法[J]. 推进技术,2016,37(8): 1431-1437. WANG Xiaolong,TANG Guiji. A new diagnosis method based on continuous wavelet transform for incipient fault of rolling bearing[J]. Journal of Propulsion Technology,2016,37(8): 1431-1437. (in Chinese doi: 10.13675/j.cnki.tjjs.2016.08.004 WANG Xiaolong, TANG Guiji. A new diagnosis method based on continuous wavelet transform for incipient fault of rolling bearing[J]. Journal of Propulsion Technology, 2016, 37(8): 1431-1437. (in Chinese) doi: 10.13675/j.cnki.tjjs.2016.08.004
[9]	向丹,岑健. 基于EMD熵特征融合的滚动轴承故障诊断方法[J]. 航空动力学报,2015,30(5): 1149-1155. XIANG Dan,CEN Jian. Method of roller bearing fault diagnosis based on feature fusion of EMD entropy[J]. Journal of Aerospace Power,2015,30(5): 1149-1155. (in Chinese doi: 10.13224/j.cnki.jasp.2015.05.016 XIANG Dan, CEN Jian. Method of roller bearing fault diagnosis based on feature fusion of EMD entropy[J]. Journal of Aerospace Power, 2015, 30(5): 1149-1155. (in Chinese) doi: 10.13224/j.cnki.jasp.2015.05.016
[10]	KHAKIPOUR M H,SAFAVI A A,SETOODEH P. Bearing fault diagnosis with morphological gradient wavelet[J]. Journal of the Franklin Institute,2017,354(6): 2465-2476. doi: 10.1016/j.jfranklin.2016.11.013
[11]	WANG Yi,XU Guanghua,ZHANG Qing,et al. Rotating speed isolation and its application to rolling element bearing fault diagnosis under large speed variation conditions[J]. Journal of Sound and Vibration,2015,348: 381-396. doi: 10.1016/j.jsv.2015.03.018
[12]	李巍华,单外平,曾雪琼. 基于深度信念网络的轴承故障分类识别[J]. 振动工程学报,2016,29(2): 340-347. LI Weihua,SHAN Waiping,ZENG Xueqiong. Bearing fault identification based on deep belief network[J]. Journal of Vibration Engineering,2016,29(2): 340-347. (in Chinese doi: 10.16385/j.cnki.issn.1004-4523.2016.02.020 LI Weihua, SHAN Waiping, ZENG Xueqiong. Bearing fault identification based on deep belief network[J]. Journal of Vibration Engineering, 2016, 29(2): 340-347. (in Chinese) doi: 10.16385/j.cnki.issn.1004-4523.2016.02.020
[13]	LU Chen,WANG Zhenya,ZHOU Bo. Intelligent fault diagnosis of rolling bearing using hierarchical convolutional network based health state classification[J]. Advanced Engineering Informatics,2017,32: 139-151. doi: 10.1016/j.aei.2017.02.005
[14]	王坤,侯树贤. 基于深度学习的辅助动力装置性能参数预测方法研究[J]. 推进技术,2022,43(1): 290-299. WANG Kun,HOU Shuxian. Prediction method of auxiliary power unit performance parameter based on deep learning[J]. Journal of Propulsion Technology,2022,43(1): 290-299. (in Chinese doi: 10.13675/j.cnki.tjjs.200580 WANG Kun, HOU Shuxian. Prediction method of auxiliary power unit performance parameter based on deep learning[J]. Journal of Propulsion Technology, 2022, 43(1): 290-299. (in Chinese) doi: 10.13675/j.cnki.tjjs.200580
[15]	周飞燕,金林鹏,董军. 卷积神经网络研究综述[J]. 计算机学报,2017,40(6): 1229-1251. ZHOU Feiyan,JIN Linpeng,DONG Jun. Review of convolutional neural network[J]. Chinese Journal of Computers,2017,40(6): 1229-1251. (in Chinese ZHOU Feiyan, JIN Linpeng, DONG Jun. Review of convolutional neural network[J]. Chinese Journal of Computers, 2017, 40(6): 1229-1251. (in Chinese)
[16]	魏晓良,潮群,陶建峰,等. 基于LSTM和CNN的高速柱塞泵故障诊断[J]. 航空学报,2021,42(3): 423876. WEI Xiaoliang,CHAO Qun,TAO Jianfeng,et al. Cavitation fault diagnosis method for high-speed plunger pumps based on LSTM and CNN[J]. Acta Aeronautica et Astronautica Sinica,2021,42(3): 423876. (in Chinese WEI Xiaoliang, CHAO Qun, TAO Jianfeng, et al. Cavitation fault diagnosis method for high-speed plunger pumps based on LSTM and CNN[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(3): 423876. (in Chinese)
[17]	张鹏,束小曼,厉雪衣,等. 基于LSTM的交流电机系统故障诊断方法研究[J]. 电机与控制学报,2022,26(3): 109-116. ZHANG Peng,SHU Xiaoman,LI Xueyi,et al. LSTM-based fault diagnosis of AC electric machine system[J]. Electric Machines and Control,2022,26(3): 109-116. (in Chinese ZHANG Peng, SHU Xiaoman, LI Xueyi, et al. LSTM-based fault diagnosis of AC electric machine system[J]. Electric Machines and Control, 2022, 26(3): 109-116. (in Chinese)
[18]	曹正志,叶春明. 改进CNN-LSTM模型在滚动轴承故障诊断中的应用[J]. 计算机系统应用,2021,30(3): 126-133. CAO Zhengzhi,YE Chunming. Application of improved CNN-LSTM model in fault diagnosis of rolling bearings[J]. Computer Systems & Applications,2021,30(3): 126-133. (in Chinese doi: 10.15888/j.cnki.csa.007830 CAO Zhengzhi, YE Chunming. Application of improved CNN-LSTM model in fault diagnosis of rolling bearings[J]. Computer Systems & Applications, 2021, 30(3): 126-133. (in Chinese) doi: 10.15888/j.cnki.csa.007830
[19]	GRAVES A,SCHMIDHUBER J. Framewise phoneme classification with bidirectional LSTM and other neural network architectures[J]. Neural Networks,2005,18(5/6): 602-610.
[20]	查文舒,乔奇,刘子雄,等. 基于相关性分析的Bi-LSTM测井曲线预测方法[J]. 合肥工业大学学报(自然科学版),2022,45(5): 700-706. ZHA Wenshu,QIAO Qi,LIU Zixiong,et al. A method for well log prediction using bidirectional long short-term memory based on correlation analysis[J]. Journal of Hefei University of Technology (Natural Science),2022,45(5): 700-706. (in Chinese ZHA Wenshu, QIAO Qi, LIU Zixiong, et al. A method for well log prediction using bidirectional long short-term memory based on correlation analysis[J]. Journal of Hefei University of Technology (Natural Science), 2022, 45(5): 700-706. (in Chinese)
[21]	ERRO D,NAVAS E,SAINZ I,et al. Efficient spectral envelope estimation from harmonic speech signals[J]. Electronics Letters,2012,48(16): 1019-1021. doi: 10.1049/el.2012.0756
[22]	景新,曹宏瑞,陈雪峰. 保持架打滑对航空发动机主轴承故障特征频率的影响[J]. 航空动力学报,2019,34(5): 1145-1152. JING Xin,CAO Hongrui,CHEN Xuefeng. Effect of cage slipping on fault characteristic frequencies of aeroengine main-shaft bearings[J]. Journal of Aerospace Power,2019,34(5): 1145-1152. (in Chinese JING Xin, CAO Hongrui, CHEN Xuefeng. Effect of cage slipping on fault characteristic frequencies of aeroengine main-shaft bearings[J]. Journal of Aerospace Power, 2019, 34(5): 1145-1152. (in Chinese)
[23]	刘西洋,陈果,郝腾飞,等. 基于卷积双向长短期记忆网络的轴承故障尺寸估计[J]. 航空动力学报,2023,38(4): 1005-1016. LIU Xiyang,CHEN Guo,HAO Tengfei,et al. Bearing fault size estimation based on convolutional bidirectional long and short term memory networks[J]. Journal of Aerospace Power,2023,38(4): 1005-1016. (in Chinese doi: 10.13224/j.cnki.jasp.20210292 LIU Xiyang, CHEN Guo, HAO Tengfei, et al. Bearing fault size estimation based on convolutional bidirectional long and short term memory networks[J]. Journal of Aerospace Power, 2023, 38(4): 1005-1016. (in Chinese) doi: 10.13224/j.cnki.jasp.20210292
[24]	马奇友,刘可薇,杜坚,等. 基于深度长短期记忆网络的发动机叶片剩余寿命预测[J]. 推进技术,2021,42(8): 1888-1897. MA Qiyou,LIU Kewei,DU Jian,et al. Prediction of residual life of engine blades based on deep short term memory network[J]. Journal of Propulsion Technology,2021,42(8): 1888-1897. (in Chinese MA Qiyou, LIU Kewei, DU Jian, et al. Prediction of residual life of engine blades based on deep short term memory network[J]. Journal of Propulsion Technology, 2021, 42(8): 1888-1897. (in Chinese)
[25]	CHANDRIAH K K,NARAGANAHALLI R V. RNN/LSTM with modified Adam optimizer in deep learning approach for automobile spare parts demand forecasting[J]. Multimedia Tools and Applications,2021,80(17): 26145-26159. doi: 10.1007/s11042-021-10913-0
[26]	GUSTAFSSON O G,TALLIAN T. Detection of damage in assembled rolling element bearings[J]. ASLE Transactions,1962,5(1): 197-209. doi: 10.1080/05698196208972466