小训练样本下齿轮箱故障诊断:一种基于改进深度森林的方法

邵怡韦; 陈嘉宇; 林翠颖; 万程; 葛红娟; 石智龙

doi:10.7527/S1000-6893.2021.25429

航空学报 >

2022 , Vol. 43 >Issue 8: 625429 - 625429

DOI: https://doi.org/10.7527/S1000-6893.2021.25429

故障诊断技术在航空航天领域中的应用专栏

小训练样本下齿轮箱故障诊断:一种基于改进深度森林的方法

邵怡韦 ,
陈嘉宇 ,
林翠颖 ,
万程 ,
葛红娟 ,
石智龙

展开

1. 南京航空航天大学民航学院, 南京 211106;
2. 南京航空航天大学民航飞行健康监测与智能维护重点实验室, 南京 211106;
3. 南京航空航天大学电子信息工程学院, 南京 211106;
4. 北京飞机维修工程有限公司杭州分部, 杭州 310000

收稿日期: 2021-02-28

修回日期: 2021-04-30

网络出版日期: 2021-04-29

基金资助

中央高校基本科研业务费专项资金(1007-XZA20017);国家自然科学基金(U1933115)

收起

Gearbox fault diagnosis with small training samples: An improved deep forest based method

SHAO Yiwei ,
CHEN Jiayu ,
LIN Cuiying ,
WAN Cheng ,
GE Hongjuan ,
SHI Zhilong

Expand

1. College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China;
2. Civil Aviation Key Laboratory of Aircraft Health Monitoring and Intelligent Maintenance, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China;
3. College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China;
4. Hangzhou Branch, Aircraft Maintenance and Engineering Coorporation, Hangzhou 310000, China

Received date: 2021-02-28

Revised date: 2021-04-30

Online published: 2021-04-29

Supported by

the Fundamental Research Funds for the Central University (1007-XZA20017);National Natural Science Foundation of China (U1933115)

Fold

摘要

作为航空装备的重要传动部件,齿轮箱的故障诊断对保障装备可靠持续适航具有至关重要的作用。随着人工智能技术的不断发展,基于深度学习的方法成为了领域内的研究热点。然而,深度神经网络对超参数设置和训练数据量有严格的要求,难以满足实际工业中快速、准确与稳定的诊断需求。针对此问题,提出了一种基于改进深度森林的诊断方法,实现小训练样本下齿轮箱的多种类混合故障的高效诊断。针对旋转机械振动信号单样本数据的长特性与深度森林模型数据处理成本高的矛盾,设计了基于主成分分析特征提取的深度森林模型,解决原始模型中的数据计算冗余问题。同时,改进的深度森林模型提高了多粒度扫描与级联森林中的数据传递与处理能力,在保障数据多样性的同时,增强模型内的特征代表性,从而提高算法的运行效率和诊断性能。最后,通过控制数据集与训练样本比例变量,开展小训练样本下齿轮箱故障诊断实验研究。结果表明,在训练-总数据比例为50%和10%条件下,所提方法平均诊断精度高达97.3%和82.8%,验证了所提方法的有效性。同时,通过对比研究,所提方法诊断性能优于现有的齿轮箱智能故障诊断方法。

关键词： 深度学习; 故障诊断; 小训练样本; 深度神经网络; 主成分分析

本文引用格式

邵怡韦 , 陈嘉宇 , 林翠颖 , 万程 , 葛红娟 , 石智龙 . 小训练样本下齿轮箱故障诊断:一种基于改进深度森林的方法[J]. 航空学报, 2022 , 43(8) : 625429 -625429 . DOI: 10.7527/S1000-6893.2021.25429

Abstract

The gearbox is an important transmission part of complex aero-equipment, and fault diagnosis of gearbox plays a vital role in ensuring reliable and continued airworthiness. With the continuous development of artificial intelligence technology, deep learning-based methods have become a research hotspot in this field. However, deep neural networks have strict requirements on hyperparameter settings and training data volume, and are difficult to meet the requirements of fast, accurate and stable diagnosis in the actual industry. To solve these problems, a diagnostic method is proposed based on the improved deep forest to realize the efficient diagnosis of the multiple and mixed faults of gearbox with small training samples. For the contradiction between the long characteristic of the single-sample data in the rotating machinery vibration signal and the high cost of data processing in the deep forest model, a deep forest model is designed based on principal component analysis (PCA) feature extraction to solve redundant calculation of data in the original model. The improved deep forest enhances data transmission and processing capability in multi-grained scanning and cascade forest. While ensuring diversity of data, it enhances the representativeness of the internal features in the model, so as to improve the operating efficiency and diagnostic performance of the algorithm. Experiments on gearbox fault diagnosis under small training samples are carried out by controlling the variable of the ratio of total datasets to training samples. The results show that average diagnostic accuracy of the proposed method reaches 97.3% and 82.8% under the condition of 50% and 10% training-total dataset ratio, respectively, which verifies the effectiveness of the proposed method. The diagnostic performance of the proposed method is found to outperform the existing intelligent diagnostic methods for gearbox.

Key words： deep learning; fault diagnosis; small training samples; deep neural network; principal component analysis

参考文献

[1] 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): 2756-2765. SUN C F, WANG Y R, SHEN Y, et al. Fault diagnosis of planetary gearbox based on adaptive parameter variational mode decomposition[J]. Journal of Aerospace Power, 2018, 33(11): 2756-27659 (in Chinese).
[2] 周兴康, 余剑波. 基于深度一维残差卷积自编码网络的齿轮箱故障诊断[J]. 机械工程学报, 2020, 56(7):96-108. ZHOU X K, YU J B. Gearbox fault diagnosis based on one-dimension residual convolutional auto-encoder[J]. Journal of Mechanical Engineering, 2020, 56(7): 96-108 (in Chinese).
[3] 姜洪开, 邵海东, 李兴球. 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. JIANG H K, SHAO H D, LI X Q. Deep learning theory with application in intelligent fault diagnosis of aircraft[J]. Journal of Mechanical Engineering, 2019, 55(7): 27-34 (in Chinese).
[4] 何俊. 齿轮箱振动特性分析与智能故障诊断方法研究[D]. 杭州: 浙江大学, 2018: 5-9. HE J. Vibration characteristic analysis and intelligent fault diagnosis of gearboxes[D]. Hangzhou: Zhejiang University, 2018: 5-9 (in Chinese).
[5] 井陆阳. 基于深度卷积模型的旋转机械故障诊断方法研究[D]. 天津: 天津大学, 2017: 39-66. JING L Y. Fault diagnosis method of rotating machinery based on deep convolution model[D]. Tianjin: Tianjin University, 2017: 39-66 (in Chinese).
[6] 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):111-124. SUN C F, WANG Y R. Advance in study of fault diagnosis of helicopter planetary gears[J]. Acta Aeronautica et Astronautica Sinica, 2017, 38(7): 111-124 (in Chinese).
[7] 雷亚国, 雷锋, 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. LEI Y G, LEI 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).
[8] 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): 9-18. HU N Q, CHEN H P, CHENG Z, et al. Fault diagnosis for planetary gearbox based on EMD and deep convolution neural networks[J]. Journal of Mechanical Engineering, 2019, 55(7): 9-18 (in Chinese).
[9] SAUFI S R, BIN AHMAD Z A, LEONG M S, et al. Challenges and opportunities of deep learning models for machinery fault detection and diagnosis: A review[J]. IEEE Access, 2019, 7: 122644-122662.
[10] ZHOU Z H, JI F, Deep forest: Towards an alternative to deep neural networks[J]. National Science Review, 2019, 6(1): 74-86.
[11] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998,86(11): 2278-2324.
[12] KRIZHEVSKY A. ImageNet classification with deep convolutional neural networks[C]//Advances in Neural Information Processing Systems, 2012:1097-1105.
[13] ZHANG Y, CHAN W, JAITLY N. Very deep convolutional networks for end to end speech recognition[C]//2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017:4845-4849.
[14] XIA J S, MING Z H, IWASAKI A. Multiple sources data fusion via deep forest[C]//IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium, 2018: 1722-1725.
[15] SHEN J H, WANG S C, WANG Z Y. Growing deep forests efficiently with soft routing and learned connectivity[C]//2018 IEEE International Conference on Data Mining Workshops (ICDMW), 2018: 399-402.
[16] FAN Y M, QI L, TIE Y. The cascade improved model based deep forest for small-scale datasets classification[C]//2019 8th International Symposium on Next Generation Electronics (ISNE), 2019: 1-3.
[17] DING J M, LUO Q B, JIA L Y, et al. Deep forest-based fault diagnosis method for chemical process[J]. Mathematical Problems in Engineering, 2020, 2020:1-15.
[18] LIU X L, TIAN Y, LEI X H, et al. Deep forest based intelligent fault diagnosis of hydraulic turbine[J]. Journal of Mechanical Science and Technology, 2019, 33(5): 2049-2058.
[19] ZHANG Z Z, LI B, XU T H, et al. Deep forest-based fault diagnosis for railway turnout system in the case of limited fault data[C]//The 31 st Chinese Control and Decision Conference (CCDC), 2019: 2636-2641.
[20] HU G Z, LI H F, XIA Y Q, et al. A deep Boltzmann machine and multi-grained scanning forest ensemble collaborative method and its application to industrial fault diagnosis[J]. Computers in Industry, 2018, 100: 287-296.
[21] 高绪伟. 核PCA特征提取方法及其应用研究[D]. 南京: 南京航空航天大学, 2009: 1-6. GAO X W. Kernel PCA feature extraction method and its application[D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2009: 1-6 (in Chinese).
[22] YAN H M, MU H N, YI X J, et al. Fault diagnosis of wind turbine based on PCA and GSA-SVM[C]//2019 Prognostics and System Health Management Conference (PHM-Paris), 2019: 13-17.
[23] BERBACHE S, HARKAT M F, KARTZ F. Sensor fault detection and isolation techniques based on PCA[C]//2019 International Conference on Advanced Electrical Engineering (ICAEE), 2019: 1-7.
[24] CARTOCCI N, COSTANTE G, NAPOLITANO M R, et al. PCA methods and evidence based filtering for robust aircraft sensor fault diagnosis[C]//2020 28th Mediterranean Conference on Control and Automation (MED), 2020: 550-555.
[25] 郭莹莹, 张磊, 肖成, 等. 基于改进深度森林算法的风电机组故障诊断技术研究[J]. 可再生能源, 2019, 37(11): 1720-1725. GUO Y Y, ZHANG L, XIAO C, et al, Research on fault diagnosis technology of wind turbine based on improved deep forest algorithm[J]. Renewable energy, 2019, 37(11): 1720-1725 (in Chinese).
[26] 孙春林, 范作民. 发动机故障诊断的主成分算法[J]. 航空学报, 1998(3): 87-90. SUN C L, FAN Z M. Principal components analysis algorithm for engine fault diagnosis[J]. Acta Aeronautica et Astronautica Sinica, 1998(3): 87-90 (in Chinese).
[27] 周志华. 机器学习[M]. 北京: 清华大学出版社, 2016: 229-232. ZHOU Z H. Machine learning[M]. Beijing: Tsinghua University Press, 2016: 229-232 (in Chinese).
[28] PEIXOTO S A, FILHO P R, KUMAR N A, et al. Automatic classification of pulmonary diseases using a structural co-occurrence matrix[J]. Neural Comput & Applic, 2020, 32: 10935-10945.
[29] ZHOU M, WANG K, WANG Y, LUO K J, et al. Online condition diagnosis for a two-stage gearbox machinery of an aerospace utilization system using an ensemble multi-fault features indexing approach[J]. Chinese Journal of Aeronautics,2019,32(5):1100-1110.
[30] NJOCK P G A, SHEN S L, ZHOU A, et al. Evaluation of soil liquefaction using AI technology incorporating a coupled ENN/t-SNE model[J]. Soil Dynamics and Earthquake Engineering, 2020, 130: 0267-7261.
[31] LI Y B, DU X Q, WAN F Y, et al. Rotating machinery fault diagnosis based on convolutional neural network and infrared thermal imaging[J]. Chinese Journal of Aeronautics,2020,33(2):427-438.
[32] 杜小磊, 陈志刚, 许旭, 等. 基于小波卷积自编码器和LSTM网络的轴承故障诊断研究[J].机电工程, 2019, 36(7):663-668. DOU X L, CHEN Z G, XU X, et al. Fault diagnosis of bearing based on wavelet convolutional auto-encoder and LSTM network[J]. Journal of Mechanical & Electrical Engineering, 2019,36(7):663-668 (in Chinese).
[33] ZHANG B, LI W, LI X L, et al. Intelligent fault diagnosis under varying working conditions based on domain adaptive convolutional neural networks[J]. IEEE Access, 2018,6: 66367-66384.
[34] JING L Y, ZHAO M, LI P, et al. A convolutional neural network based feature learning and fault diagnosis method for the condition monitoring of gearbox[J]. Measurement, 2017,111: 1-10.
[35] 张立智, 徐卫晓, 井陆阳, et al. 基于二维深度卷积模型的旋转机械故障诊断[J]. 机械强度, 2020, 42(5): 1039-1044. ZHANG L Z, XU W X, JING L Y, et al. Rotating machinery fault diagnosis based on two-dimensional convolutional neural network[J]. Journal of Mechanical Strength, 2020, 42(5): 1039-1044 (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