复杂工况下的直升机行星传动轮系故障诊断

孙灿飞; 黄林然; 沈勇

doi:10.7527/S1000-6893.2021.25480

航空学报 >

2022 , Vol. 43 >Issue 8: 625480 - 625480

DOI: https://doi.org/10.7527/S1000-6893.2021.25480

故障诊断技术在航空航天领域中的应用专栏

复杂工况下的直升机行星传动轮系故障诊断

孙灿飞 ,
黄林然 ,
沈勇

展开

1. 航空工业上海航空测控技术研究所研究中心, 上海 201601;
2. 故障诊断与健康管理技术航空科技重点实验室试验与验证中心, 上海 201601

收稿日期: 2021-03-12

修回日期: 2021-06-21

网络出版日期: 2021-06-18

基金资助

航空科学基金(20183352031)

收起

Fault diagnosis of helicopter planetary gear transmission system under complex operating conditions

SUN Canfei ,
HUANG Linran ,
SHEN Yong

Expand

1. Research Center, AVIC Shanghai Aero Measurement Controlling Research Institute, Shanghai 201601, China;
2. Testing and Verification Center, Aviation Key Laboratory of Science and Technology on Fault Diagnosis and Health Management, Shanghai 201601, China

Received date: 2021-03-12

Revised date: 2021-06-21

Online published: 2021-06-18

Supported by

Aeronautical Science Foundation of China (20183352031)

Fold

摘要

行星传动轮系是直升机动力传动系统的核心部件,是直升机健康和使用监测系统重要的监测对象。针对复杂工况下直升机行星传动轮系的故障诊断难题,提出了结合域对抗与深度编码网络的自适应域对抗深度迁移故障诊断方法。方法输入归一化频谱数据,基于堆栈收缩自动编码网络建立训练负载与测试负载编码网络,从训练域数据进行有监督学习提取高质量深度故障特征,并结合参数迁移和对抗学习策略,通过测试域数据无监督自适应优化测试域深度故障特征提取网络,以适应负载条件变化引起的样本数据分布差异以及恶劣噪声环境引起的样本数据波动的影响。方法在直升机行星传动轮系实验平台上通过故障注入试验进行了对比验证,证明了方法的有效性与健壮性。

关键词： 直升机; 行星齿轮; 变工况; 故障诊断; 深度学习; 域对抗迁移

本文引用格式

孙灿飞 , 黄林然 , 沈勇 . 复杂工况下的直升机行星传动轮系故障诊断[J]. 航空学报, 2022 , 43(8) : 625480 -625480 . DOI: 10.7527/S1000-6893.2021.25480

Abstract

The planetary transmission system as the core component of the helicopter power transmission system is an important monitoring object for the helicopter health and use monitoring system. In view of the problem of fault diagnosis of the helicopter planetary transmission wheel system under complex working conditions, a method for fault diagnosis of the adaptive domain against deep migration combined with domain adversity and deep coding networks is proposed. Inputting normalized spectrum data and establishing a training load and test load coding network based on the stack shrink automatic encoding network, this method extracts high-quality in-depth fault characteristics from the training domain data with supervised learning, and the network from the test domain data by unsupervised self-adaptively optimized test domain in-depth fault characteristics combining parameter migration and the anti-learning strategy to adapt to the differences in sample data distribution caused by changes in load conditions and the impact of sample data fluctuations caused by harsh noisy environments. The validity and robustness of the method are verified by comparison analysis through fault injection tests on the experimental platform of the helicopter planetary transmission wheel system.

Key words： helicopters; planetary gear transmission; variable conditions; fault diagnosis; deep learning; domain-adversarial transfer

参考文献

[1] 孙灿飞, 王友仁. 直升机行星传动轮系故障诊断研究进展[J]. 航空学报, 2017, 38(7): 106-119. SUN C F, WANG Y R. Advance in the study on fault diagnosis of helicopter planetary gears[J]. Chinese Journal of Aeronautics, 2017, 38(7): 106-119 (in Chinese).
[2] 孙灿飞, 王友仁, 沈勇, 等. 基于参数自适应变分模态分解的行星齿轮箱故障诊断[J]. 航空动力学报, 2018, 33(11):205-214. SUN C F, WANG Y, SHEN Y, et al. Fault diagnosis of planetary gearbox based on adaptive parameter variational mode decomposition[J]. Journal of Aerospace Power, 2018, 33(11):2756-2765 (in Chinese).
[3] ZHU Y, CHEN Y, LU Z, et al. Heterogeneous transfer learning for image classification[C]//Proceedings of the Twenty-Fifth AAAI Conference on Artificial Intelligence, 2011.
[4] YANG P, GAO W. Information-theoretic multi-view domain adaptation: A theoretical and empirical study[J]. Journal of Artificial Intelligence Research, 2014, 49(1): 501-525.
[5] PAN S J, YANG Q. A survey on transfer learning[J]. IEEE Transactions on Knowledge & Data Engineering, 2010, 22(10): 1345-1359.
[6] SHELL J, COUPLAND S. Fuzzy transfer learning: methodology and application[J]. Information Sciences, 2015, 293(2):59-79.
[7] 康守强, 胡明武, 王玉静, 等. 基于特征迁移学习的变工况下滚动轴承故障诊断方法[J]. 中国电机工程学报, 2019, 39(3):764-772. KANG S Q, HU M W, WANG Y J, et al. Fault diagnosis method of a rolling bearing under variable working conditions based on feature transfer learning[J]. Proceedings of the Chinese Society of Electrical Engineering, 2019, 39(3):764-772 (in Chinese).
[8] 金余丰, 刘晓锋, 姚美常, 等. 基于域对抗迁移的变工况滚动轴承故障诊断模型[J]. 自动化仪表, 2019, 40(12):55-60, 65. JIN Y F, LIU X F, YAO M C, et al. Fault diagnosis model of rolling bearing under variable working conditions based on domain adversarial transfer mechanism[J]. Process Automation Instrumentation, 2019, 40(12): 55-60, 65(in Chinese).
[9] WEN L, GAO L, LI X. A new deep transfer learning based on sparse auto-encoder for fault diagnosis[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2019, 49(1): 136-144.
[10] 庄福振, 罗平, 何清, 等. 迁移学习研究进展[J]. 软件学报,2015,26(1):26-39. ZHUANG F Z, LUO P, HE Q, et al. Survey on transfer learning research[J]. Journal of Software, 2015, 26(1):26-39 (in Chinese).
[11] 金棋, 王友仁, 王俊. 基于深度学习多样性特征提取与信息融合的行星齿轮箱故障诊断方法[J]. 中国机械工程, 2019, 30(2):74-82. JIN Q, WANG Y R, WANG J. Planetary gearbox fault diagnosis based on multiple feature extraction and information fusion combined with deep learning[J]. China Mechanical Engineering, 2019, 30(2):74-82 (in Chinese).
[12] LU C, WANG Z Y, QIN W L, et al. Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification[J]. Signal Processing, 2017, 130:377-388.
[13] XIA M, LI T, LIU L, et al. Intelligent fault diagnosis approach with unsupervised feature learning by stacked denoising autoencoder[J]. IET Science, Measurement & Technology, 2017, 11(6): 687-695.
[14] TAMILSELVAN P, WANG P F. Failure diagnosis using deep belief learning based health state classification[J]. Reliability Engineering and System Safety, 2013, 115: 124-135.
[15] CHEN Z, LI C, SANCHEZ R V. Multi-layer neural network with deep belief network for gearbox fault diagnosis[J]. Journal of Vibro-Engineering, 2015, 17(5): 2379-2392.
[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 X L, CHAO Q, TAO J F, et al. Cavitation fault diagnosis method for high-speed plunger pumps based on LSTM and CNN[J]. Chinese Journal of Aeronautics, 2021, 42(3): 423876 (in Chinese).
[17] RIFAI S, VINCENT P, MULLER X, et al. Contractive auto-encoders: Explicit invariance during feature extraction[C]//Proceeding of the Twenty-Eighth International Conference on Machine Learning, 2011.
[18] GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial networks[C]//Advances in Neural Information Processing Systems, 2014: 2672-2680.
[19] HONG L, DHUPIA J S, SHENG S W. An explanation of frequency features enabling detection of faults in equally spaced planetary gearbox[J]. Mechanism and Machine Theory, 2014, 73: 169-183.
[20] 赵光权, 葛强强, 刘小勇,等. 基于DBN的故障特征提取及诊断方法研究[J].仪器仪表学报, 2016, 37(9):1946-1953. ZHANG G Q, GE Q Q, LIU X Y, et al. Fault feature extraction and diagnosis method based on deep belief network[J]. Chinese Journal of Scientific Instrument, 2016, 37(9):1946-1953 (in Chinese).

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献