针对变工况复杂环境下风电机组轴承的早期故障潜隐性高且故障阈值设置困难的问题,提出一种基于多层深度互信息变分网络的轴承故障超前预警方法。该网络在变分自编码器的架构上进行多层编码拓展,采用解码信号的二次编码增强了变分网络对输入信号中噪声的鲁棒性,通过隐层变量与输入信号间最大化互信息以及与二次编码特征间的最大化互信息,提高了网络对轴承正常状态空间的建模能力。以二次编码特征与隐层变量的重构误差为基础,构建健康指数,结合三次递推指数加权移动平均模型设置与风电机组轴承工况环境相适应的健康基线。在2个风电机组轴承故障检测试验中的应用结果表明,该方法对比传统的基于模型重构的轴承早期故障检测方法,具有更高故障预警准确率和抗干扰能力。
Abstract
For the wind turbine in variable working conditions and complex environment,the fault monitoring and early warning of its bearing faces the problems of high latent characteristics of and the difficulty in fault threshold setting. Aiming to the problems,an early warning method based on multi-layer deep mutual information variational network（MDMIVN） is proposed. The coding layer of variational auto-coder is extended to multi-layer encoding, and the decoded signal is encoded again to improve the network robustness to the noise in the original fault signal. To improve the ability of modeling the bearing normal state space, the maximum mutual information between the latent variables and the input signal, between the latent variables and the secondary coding features are introduced as the loss functions. The health index is established based on the reconstruction errors between the secondary coding features and the latent variables. And then,the health baseline is adaptively set, by combining the triple exponential weighted moving average model and the updating iteration of the health indexes. The experimental results on two wind turbine bearing vibration data sets show that compared with the traditional early fault detection method based on model reconstruction, the proposed method has high fault warning accuracy, anti-interference ability.
关键词
风电机组 /
故障检测 /
状态监测 /
多层互信息 /
健康指数构建 /
健康基线设置
Key words
wind turbines /
fault detection /
condition monitoring /
multi-layer mutual information /
health index construction /
health baseline setting
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 王波, 王志乐, 熊鑫州, 等. 一种改进的MRVM方法及其在风电机组轴承诊断中的应用[J]. 太阳能学报, 2021, 42(1): 215-221.
WANG B, WANG Z L, XIONG X Z, et al.An improved MRVM method and its application in wind turbine bearing diagnosis[J]. Acta solaris energiae sinica, 2021, 42(1): 215-221.
[2] 孟宗, 刘东, 岳建辉, 等. 基于DEMD局部时频熵和SVM 的风电齿轮箱故障诊断方法研究[J]. 计量学报, 2017, 38(4): 449-452.
MENG Z, LIU D, YUE J H,et al.Research on fault diagnosis method of wind turbine gearbox based on DEMD local time-frequency entropy and SVM[J]. Acta metrologica sinica , 2017, 38(4): 449-452.
[3] 王晓龙, 唐贵基, 何玉灵, 等. 变转速工况下基于改进奇异谱分解和1.5维包络阶次谱的风电机组轴承损伤识别[J]. 太阳能学报, 2021, 42(1): 241-246.
WANG X L, TANG G J, HE Y L, et al.Identification of bearing damage in wind turbines based on improved singular spectrum decomposition and 1.5-dimensional enveloped order spectrum in variable speed conditions[J]. Acta solaris energiae sinica, 2021, 42(1): 241-246.
[4] 赵光权, 刘小勇, 姜泽东, 等. 基于深度学习的轴承健康因子无监督构建方法[J]. 仪器仪表学报, 2018, 39(6): 82-88.
ZHAO G Q, LIU X Y, JIANG Z D,et al.Unsupervised construction method of bearing health factors based on deep learning[J]. Chinese journal of scientific instrument, 2018, 39(6): 82-88.
[5] RAI A, UPADHYAY S H.Bearing performance degradation assessment based on a combination of empirical mode decomposition and k-medoids clustering[J]. Mechanical systems and signal processing, 2017, 93(1): 16-29.
[6] LIM R, MBA D.Diagnosis and prognosis of AH64D tail rotor gearbox bearing degradation[C]//ASME Power Transmission & Gearing Conference, Portland, OR, USA, 2013.
[7] TONG L, GUO C, OUYANG W L, et al.Hyper-spherical distance discrimination: a novel data description method for aero-engine rolling bearing fault detection[J]. Mechanical systems and signal processing, 2018, 109(1): 330-351.
[8] DEMPSEY P J, MOSHER M, HUFF E M.Threshold assessment of gear diagnostic tools on flight and test rig data[R]. NASA/TM—2003-212220/REV1.
[9] MORELANDE M R, KREUCHER C M, KASTELLA K.A Bayesian approach to multiple target detection and tracking[J]. IEEE transactions on signal processing, 2007, 55(5): 1589-1604.
[10] DEMPSEY P J, AFJEH A A.Integrating oil debris and vibration gear damage measurement technologies using fuzzy logic[R]. NASA/TM—2002-211126.
[11] DEMPSEY P J, KELLER J A, WADE D R, et al.Signal detection theory applied to helicopter transmission diagnostic thresholds[R]. NASA/TM—2008-215262, National Aeronautics and Space Administration.
[12] NIKLAS R, PRAMOD B, EDMUND H.System-wide anomaly detection in wind turbines using deep autoencoders[J]. Renewable energy, 2020, 157: 647-659.
[13] ZHAO H S, LIU H H, HU W J, et al.Anomaly detection and fault analysis of wind turbine components based on deep learning network[J]. Renewable energy, 2018, 127:825-834.
[14] YANG W G, LIU C, JIANG D X.An unsupervised spatiotemporal graphical modeling approach for wind turbine condition monitoring[J]. Renewable energy, 2018, 127: 230-241.
[15] 戴俊, 王俊, 朱忠奎, 等. 基于生成对抗网络和自动编码器的机械系统异常检测[J]. 仪器仪表学报, 2019, 40(9): 19-29.
DAI J, WANG J, ZHU Z K, et al.Mechanical system anomaly detection based on generative countermeasure network and automatic encoder[J]. Chinese journal of scientific instrument, 2019, 40(9): 19-29.
[16] 郝忠. 基于双判别对抗学习的异常检测方法[D]. 天津: 河北工业大学, 2020.
HAO Z.Anomaly detection method based on dual discriminant antagonistic learning[D]. Tianjin: Hebei University of Technology, 2020.
[17] 秦婉亭, 老松杨, 汤俊, 等. 基于变分自编码器的飓风轨迹异常检测方法[J]. 系统仿真学报, 2021, 33(9): 2191-2201.
QIN W T, LAO S Y, TANG J, et al.Anomaly detection method of hurricane track based on variational autoencoder[J]. Journal of system simulation, 2021, 33(9): 2191-2201.
[18] KINGMA D P, WELLING M.Auto-encoding variational Bayes[EB/OL]. [2013-12-20]. https://arxiv.org/abs/1312.61 14v10
[19] BELGHAZI M I, BARATIN A, RAJESWAR S, et al.Mutual information neural estimation[C]//Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden, 2018, 80: 531-540.
[20] SAIDI L, BECHHOEFER E, ALI J B, et al.Wind turbine high-speed shaft bearing degradation analysis for run-to-failure testing using spectral kurtosis[C]//16th International Conference on Sciences and Techniques of Automatic Control and Computer Engineering(STA), Monastir, Tunisia, 2015.
[21] DOMINGUES R, FILIPPONE M, MICHIARDI P, et al.A comparative evaluation of outlier detection algorithms: experiments and analyses[J]. Pattern recognition, 2018, 74: 406-421.
[22] MA H H, HU Y, SHI H B.Fault detection and identification based on the neighborhood standardized local outlier factor method[J]. Industrial & Engineering chemistry research, 2013, 52(6): 2389-2402.
[23] MAO J X, WANG H, SPEMCER B F.Toward data anomaly detection for automated structural health monitoring: exploiting generative adversarial nets and autoencoders[J]. Structural health monitoring, 2020, DOI: 10.1177/1475921720924601.
基金
国家自然科学基金（52175077; 51975067）; 中央高校基本科研业务费（2020CDCGJX022）
PDF(2120 KB)
