基于提升卷积神经网络的航空发动机高速轴承智能故障诊断

韩淞宇; 邵海东; 姜洪开; 张笑阳

doi:10.7527/S1000-6893.2021.25479

航空学报 >

2022 , Vol. 43 >Issue 9: 625479 - 625479

DOI: https://doi.org/10.7527/S1000-6893.2021.25479

航空发动机运行安全专栏

基于提升卷积神经网络的航空发动机高速轴承智能故障诊断

韩淞宇 ,
邵海东 ,
姜洪开 ,
张笑阳

展开

1. 湖南大学机械与运载工程学院, 长沙 410082;
2. 西北工业大学民航学院, 西安 710072;
3. 中国航空工业集团公司西安航空计算技术研究所民机事业部, 西安 710065

收稿日期: 2021-03-12

修回日期: 2021-03-30

网络出版日期: 2021-06-18

基金资助

国家重点研发计划(2020YFB1712100);国家自然科学基金(51905160);湖南省自然科学基金(2020JJ5072)

收起

Intelligent fault diagnosis of aero-engine high-speed bearings using enhanced CNN

HAN Songyu ,
SHAO Haidong ,
JIANG Hongkai ,
ZHANG Xiaoyang

Expand

1. College of Mechanical and Vehicle Engineering, Hunan University, Changsha 410082, China;
2. School of Civil Aviation, Northwestern Polytechnical University, Xi'an 710072, China;
3. Civil Aircraft Department, AVIC Xi'an Aeronautics Computing Technique Research Institute, Xi'an 710065, China

Received date: 2021-03-12

Revised date: 2021-03-30

Online published: 2021-06-18

Supported by

National Key Research and Development Program of China (2020YFB1712100); National Natural Science Foundation of China (51905160); Natural Science Foundation of Hunan Province (2020JJ5072)

Fold

摘要

航空发动机轴承长时间工作在高速重载的恶劣条件下, 将不可避免地产生性能衰退甚至引发各种故障, 自动准确的航空发动机高速轴承故障诊断方法有助于提升运行安全性和维修经济性。航空发动机高速轴承的原始振动信号具有强烈的非平稳性, 且其故障样本数量远小于健康样本, 传统的智能诊断方法更容易向大样本偏斜, 从而导致诊断性能的降低。针对上述问题, 提出了一种基于自适应权重和多尺度卷积的提升卷积神经网络(CNN)。首先构造多尺度卷积网络提取故障样本的多尺度特征, 挖掘具有识别性的有用信息; 然后设计自适应权重单元对多尺度特征进行加权融合, 增加重要特征的贡献度, 减少非相关特征的影响; 最后采用Focal Loss作为损失函数, 使训练过程中网络模型更关注故障样本和易混淆样本。通过航空发动机高速轴承振动数据的测试与分析, 证实了所提方法在不平衡数据故障诊断任务中的可行性。

关键词： 航空发动机高速轴承; 智能故障诊断; 提升卷积神经网络; 不平衡数据; 多尺度特征提取; 自适应权重; 损失函数补偿

本文引用格式

韩淞宇 , 邵海东 , 姜洪开 , 张笑阳 . 基于提升卷积神经网络的航空发动机高速轴承智能故障诊断[J]. 航空学报, 2022 , 43(9) : 625479 -625479 . DOI: 10.7527/S1000-6893.2021.25479

Abstract

Aero-engine bearings usually operate for long hours under harsh conditions of high speed and heavy loads, inevitably leading to performance deterioration and even causing various faults, and automatic and accurate fault diagnosis methods for high-speed aero-engine bearings can help to improve operation safety and maintenance economy. The original vibration signals collected from aero-engine high-speed bearings have strong instability and the number of faulty samples is much smaller than that of healthy ones. The traditional intelligent diagnosis method tends to skew to large samples, thereby inducing degradation in diagnosis performance. To solve the above problem, we propose an enhanced convolutional neural network model based on adaptive weight and multi-scale convolution. A multi-scale convolution network is first constructed to extract multi-scale features of fault samples and mine useful identifying information. An adaptive weight unit is then designed to fuse the multi-scale features to increase the contribution of the important features while reducing the influence of unrelated features. Focal Loss is finally used as the loss function to enable the model to consider the small faulty samples and easily confused samples more. The test and analysis of aero-engine high-speed bearing vibration data confirm the feasibility of the proposed method in fault diagnosis tasks with unbalanced data.

Key words： aero-engine high-speed bearings; intelligent fault diagnosis; enhanced convolutional neural network; unbalanced data; multi-scale feature extraction; adaptive weighting; loss function compensation

参考文献

[1] CHEN X F, WANG S B, CHENG L, et al. Matching synchrosqueezing transform for aero-engine's signals with fast varying instantaneous frequency[J]. Journal of Mechanical Engineering, 2019, 55(13): 13-22(in Chinese). 陈雪峰, 王诗彬, 程礼. 航空发动机快变信号的匹配同步压缩变换研究[J]. 机械工程学报, 2019, 55(13): 13-22.
[2] LIANG J, ZUO H F. Evaluation of maintenance cost for commercial aircraft[J]. Journal of Traffic and Transportation Engineering, 2002, 2(4): 95-98(in Chinese). 梁剑, 左洪福. 民用飞机维修成本评估[J]. 交通运输工程学报, 2002, 2(4): 95-98.
[3] XIE Q H, LIANG J, ZHANG Q. The combination forecasting model of aero-engine maintenance cost based on statistic rough set theory[J]. Acta Armamentaril, 2006, 27(5): 857-861(in Chinese). 谢庆华, 梁剑, 张琦. 基于统计粗集的航空发动机维修成本组合预测模型[J]. 兵工学报, 2006, 27(5): 857-861.
[4] SUN C, HE Z J, ZHANG Z S, et al. Operating reliability assessment for aero-engine based on condition monitoring information[J]. Journal of Mechanical Engineering, 2013, 49(6): 30-37(in Chinese). 孙闯, 何正嘉, 张周锁, 等. 基于状态信息的航空发动机运行可靠性评估[J]. 机械工程学报, 2013, 49(6): 30-37.
[5] ZHANG H, DU Z H, FANG Z W, et al. Sparse decomposition based aero-engine's bearing fault diagnosis[J]. Journal of Mechanical Engineering, 2015, 51(1): 97-105(in Chinese). 张晗, 杜朝辉, 方作为, 等. 基于稀疏分解理论的航空发动机轴承故障诊断[J]. 机械工程学报, 2015, 51(1): 97-105.
[6] CHEN G. Feature extraction and intelligent diagnosis for ball bearing early faults[J]. Acta Aeronautica et Astronautica Sinica, 2009, 30(2): 362-367(in Chinese). 陈果. 滚动轴承早期故障的特征提取与智能诊断[J]. 航空学报, 2009, 30(2): 362-367.
[7] CHEN L S, ZHANG H, CHEN X F. Fault diagnosis of aero-engine bevel gear based on a low rank sparse model[J]. Journal of Vibration and Shock, 2020, 39(12): 103-112(in Chinese). 陈礼顺, 张晗, 陈雪峰. 基于低秩稀疏分解算法的航空锥齿轮故障诊断[J]. 振动与冲击, 2020, 39(12): 103-112.
[8] WANG Z, ZHANG Q, XIONG J, et al. Fault diagnosis of a rolling bearing using wavelet packet denoising and random forests[J]. IEEE Sensors Journal, 2017, 17(5): 5581-5588.
[9] JIN X, ZHAO M, CHOW T W S, et al. Motor bearing fault diagnosis using trace ratio linear discriminant analysis[J]. IEEE Transactions on Industrial Electronics, 2014, 61(5): 2441-2451.
[10] WANG T C, WANG J Y, WU Y, et al. A fault diagnosis model based on weighted extension neural network for turbo-generator sets on samples with noise[J]. Chinese Journal of Aeronautics, 2020, 30(10): 2757-2769.
[11] YUAN L, WANG S Y. A review on intelligent health management technology development of spacecraft control systems[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(4): 525044(in Chinese). 袁利, 王淑一. 航天器控制系统智能健康管理技术发展综述[J]. 航空学报, 2021, 42(4): 525044.
[12] LI H, XIAO D Y. Survey on data driven fault diagnosis methods[J]. Journal of Control and Decision, 2011, 26(1): 1-9, 16(in Chinese). 李晗, 萧德云. 基于数据驱动的故障诊断方法综述[J]. 控制与决策, 2011, 26(1): 1-9, 16.
[13] LEI Y G, JIA F, KONG D T, et al. Opportunities and challenges of machinery intelligent fault diagnosis in big data era[J]. Journal of Mechanical Engineering, 2018, 54(5): 94-104(in Chinese). 雷亚国, 贾锋, 孔德同, 等. 大数据下机械智能故障诊断的机遇与挑战[J]. 机械工程学报, 2018, 54(5): 94-104.
[14] JIANG H K, SHAO H D, LI X Q, et al. Intelligent fault diagnosis method of aircraft based on deep learning[J]. Journal of Mechanical Engineering, 2019, 55(7): 27-34(in Chinese). 姜洪开, 邵海东, 李兴球, 等. 基于深度学习的飞行器智能故障诊断方法[J]. 机械工程学报, 2019, 55(7): 27-34.
[15] DING B Q, WU J Y, SUN C, et al. Sparsity-Assis-ted Intelligent Condition Monitoring Method for Aero-engine Main Shaft Bearing[J]. Transactions of Nanjing University of Aeronautics and Astronautics, 2020, 37(4): 508-516.
[16] SHAO H D, ZHANG X Y, CHENG J S, et al. Intelligent fault diagnosis of bearing using enhanced deep transfer auto-encoder[J]. Journal of Mechanical Engineering, 2020, 56(9): 84-90(in Chinese). 邵海东, 张笑阳, 程军圣, 等. 基于提升深度迁移自编码器的轴承故障诊断[J]. 机械工程学报, 2020, 56(9): 84-90.
[17] HOU W Q, Y M, LI W H. Rolling element bearing fault classification using improved stacked de-noising auto-encoders[J]. Journal of Mechanical Engineering, 2018, 54(7): 87-96(in Chinese). 侯文擎, 叶鸣, 李巍华. 基于改进堆叠降噪自编码器的滚动轴承故障分类[J]. 机械工程学报, 2018, 54(7): 87-96.
[18] CHI Y W, YANG S X, JIAO W D. A Multi-label fault classification method for rolling bearing based on LSTM-RNN[J]. Journal of Vibration, Measurement & Diagnosis, 2020, 40(3): 563-571, 629(in Chinese). 池永为, 杨世锡, 焦卫东. 基于LSTM-RNN的滚动轴承故障多标签分类方法[J]. 振动. 测试与诊断, 2020, 40(3): 563-571, 629.
[19] ZHANG J Q, SUN Y, GUO L, et al. A new bearing fault diagnosis method based on modified convolutional neural networks[J]. Chinese Journal of Aeronautics, 2020, 33(2): 439-447.
[20] CHEN R X, YANG X, HU X L, et al. Planetary gearbox fault diagnosis method based on deep belief network transfer learning[J]. Journal of Vibration and Shock, 2021, 40(1): 127-133, 150(in Chinese). 陈仁祥, 杨星, 胡小林, 等. 深度置信网络迁移学习的行星齿轮箱故障诊断方法[J]. 振动与冲击, 2021, 40(1): 127-133, 150.
[21] HU N Q, CHEN H P, CHENG Z, et al. Fault diagnosis for planetary gearbox based on EMD and deep convolutional neural networks[J]. Journal of Mechanical Engineering, 2019, 55(7): 9-17(in Chinese). 胡茑庆, 陈徽鹏, 程哲, 等. 基于经验模态分解和深度卷积神经网络的行星齿轮箱故障诊断方法[J]. 机械工程学报, 2019, 55(7): 9-17.
[22] TANG B P, XIONG X Y, ZHAO M H, et al. A Multi-resonance component fusion based convolutional neural network for fault diagnosis of planetary gearboxes[J]. Journal of Vibration, Measurement & Diagnosis, 2020, 40(3): 507-512, 625(in Chinese). 汤宝平, 熊学嫣, 赵明航, 等. 多共振分类融合CNN的行星齿轮箱故障诊断[J]. 振动、测试与诊断, 2020, 40(3): 507-512, 625.
[23] WEI X L, CHAO Q, TAO J F, 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). 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.
[24] ZHANG M D, LU J H, MA J H. Fault diagnosis of rolling bearing based on multi-scale convolution strategy CNN[J]. Journal of Chongqing University of Technology (Natural Science), 2020, 34(6): 102-110(in Chinese). 张明德, 卢建华, 马婧华. 基于多尺度卷积策略CNN得滚动轴承故障诊断[J]. 重庆理工大学学报(自然科学), 2020, 34(6): 102-110.
[25] PENG P, KE L L, WANG J G. Fault diagnosis of RV reducer with noise interference[J]. Journal of Mechanical Engineering, 2020, 56(1): 30-36(in Chinese). 彭鹏, 柯梁亮, 汪久根. 噪声干扰下的RV减速器故障诊断[J]. 机械工程学报, 2020, 56(1): 30-36.
[26] SHEN C Q, WANG X, WANG D, et al. Multi-scale convolution intra-class transfer learning for train bearing fault diagnosis[J]. Journal of Traffic and Transportation Engineering, 2020, 20(5): 151-164(in Chinese). 沈长青, 王旭, 王东, 等. 基于多尺度卷积类迁移学习的列车轴承故障诊断[J]. 交通与运输工程学报, 2020, 20(5): 151-164.
[27] MATEUSZ B, ATSUTO M, MACIEJ A, et al. A systematic study of the class imbalance problem in convolutional neural networks[J]. Neural Networks, 2018, 106: 249-259.
[28] GUO Q, LI Y, SONG Y, et al. Intelligent fault diagnosis method based on full 1-D convolutional generative adversarial network[J]. IEEE Transactions on Industrial Informatics, 2020, 16(3): 2044-2053.
[29] HUANG N, CHEN Q, CAI G, et al. Fault diagnosis of bearing in wind turbine gearbox under actual operating conditions driven by limited data with noise labels[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70(1): 1-10.
[30] MATHEW J, PANG C K, LUO M, et al. Classification of imbalanced data by oversampling in kernel space of support vector machines[J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(9): 4065-4076.
[31] HUANG H S, WEI J A, REN Z P, et al. Rolling bearing fault diagnosis based on imbalanced sample characteristics oversampling algorithm and SVM[J]. Journal of Vibration and Shock, 2020, 39(10): 65-74, 132(in Chinese). 黄海松, 魏建安, 任竹鹏, 等. 基于失衡样本特性过采样算法与SVM的滚动轴承故障诊断[J]. 振动与冲击, 2020, 39(10): 65-74, 132.
[32] TAO X M, LIU F R, DONG Z J, et al. Novel fault detection method based on SVM with unbalanced datasets[J]. Journal of Vibration and Shock, 2010, 29(12): 8-12, 29(in Chinese). 陶新民, 刘福荣, 董智靖, 等. 不均衡数据下基于SVM的故障检测新算法[J]. 振动与冲击, 2010, 29(12): 8-12, 29.
[33] LU L, SHIN Y, SHU Y, et al. Dying ReLU and initialization: Theory and numerical examples[EB/OL]. (2020-10-26)[2021-2-26]. http://export.arxiv.org/abs/1903.06733.
[34] RAMACHANDRAN P, ZOPH B, QUOC V L. Searching for activation functions[EB/OL]. (2017-10-27)[2021-2-26]. https://arxiv.org/abs/1710.05941.
[35] ARROA V, MAHLA S K, LEEKHA R S, et al. Intervention of artificial neural network with an improved activation function to predict the performance and emission characteristics of a biogas powered dual fuel engine[J]. Electronics, 2021, 10(5): 584.
[36] DAGA A P, FASANA A, MARCHESIELLO S, et al. The Politecnico di Torino rolling bearing test rig: Description and analysis of open access data[J]. Mechanical Systems and Signal Processing, 2019, 120: 252-273.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献