基于深度自编码网络模型的风电机组齿轮箱故障检测

doi:10.19595/j.cnki.1000-6753.tces.161746

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (769 KB)
输出: BibTeX | EndNote (RIS)

摘要为了实现风机齿轮箱的故障检测分析,提出一种基于风电机组齿轮箱的数据采集与监视控制（SCADA）数据和振动信号的深度自编码网络模型。该模型作为一种典型的深度学习方法,通过逐层智能学习初始样本特征,可以获取数据蕴含的规则与分布特征形成更加抽象的高层表示。首先,利用限制性玻尔兹曼机对网络参数进行预训练和反向传播算法对参数进行调优,建立深度自编码网络模型。然后,通过对齿轮箱的状态变量进行编码和解码,计算重构误差并将其作为齿轮箱的状态检测量。为了有效检测重构误差的趋势变化,选用自适应阈值作为风机齿轮箱故障检测的决策准则。最后,利用对齿轮箱故障前、后记录的数据进行仿真分析,结果验证了深度自编码网络学习方法对齿轮箱故障检测的有效性。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	刘辉海
	赵星宇
	赵洪山
	宋鹏
	邓春

关键词 ：风电机组, 齿轮箱, 故障检测, 深度自编码网络, 自适应阈值

Abstract：In order to achieve the fault detection of wind turbine gearbox, a deep autoencoder network model from deep learning method based on supervisory control and data acquisition (SCADA) data and vibration signals of wind turbine gearbox is proposed in this paper. The deep autoencoder network, as one of the typical deep learning methods, can obtain the underlying rules and distribution characteristics of the data through learning features of original sample by layer-wise intelligent learning to form a more abstract and high-level representation. Firstly, restricted boltzmann machine was used to pre-train parameters and the back-propagation algorithm was used to optimize these parameters to build the deep autoencoder model in this paper. Then through encoding and decoding condition variables of gearbox, reconstruction error was computed as the gearbox condition monitoring variable. In order to monitor the trend change of reconstruction error effectively, the adaptive threshold was chosen as the decision criterion of gearbox fault. Finally, by utilizing the record data before and after fault to simulation, results showed the validity of deep autoencoder model on gearbox fault detection.

Key words： Wind turbine gearbox fault detection deep autoencoder adaptive threshold

收稿日期: 2016-11-04 出版日期: 2017-09-14

PACS:

TM614

基金资助:国家科技支撑计划项目资助（2015BAA06B03）

通讯作者: 刘辉海男,1991年生,硕士研究生,研究方向为风电机组传动链系统故障检测。E-mail：hhliu3@126.com

作者简介: 赵星宇男,1995年生,本科生,研究方向为大数据处理与算法。E-mail：asteroid@126.com

引用本文:

刘辉海, 赵星宇, 赵洪山, 宋鹏, 邓春. 基于深度自编码网络模型的风电机组齿轮箱故障检测[J]. 电工技术学报, 2017, 32(17): 156-163. Liu Huihai, Zhao Xingyu, Zhao Hongshan, Song Peng, Deng Chun. Fault Detection of Wind Turbine Gearbox Based on Deep Autoencoder Network. Transactions of China Electrotechnical Society, 2017, 32(17): 156-163.

链接本文:

https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.161746 https://dgjsxb.ces-transaction.com/CN/Y2017/V32/I17/156

[1] 赵洪山, 郭伟, 邵玲, 等．基于子空间方法的风机齿轮箱故障预测算法[J]．电力自动化设备, 2015, 35(3): 27-32.
Zhao Hongshan, Guo Wei, Shao Ling, et al．Gearbox fault prediction algorithm based on subspace method for wind turbine[J]．Electric Power Automation Equipment, 2015, 35(3): 27-32.
[2] 杭俊, 张建忠, 程明, 等. 风力发电系统状态监测和故障诊断技术综述[J]. 电工技术学报, 2013, 28(4): 262-271.
Hang Jun, Zhang Jianzhong, Cheng Ming, et al. An overview of condition monitoring and fault diagnostic for wind energy conversion system[J]. Transactions of China Electrotechnical Society, 2013, 28(4): 261-271.
[3] 杨明, 董传洋, 徐殿国. 基于电机驱动系统的齿轮故障诊断方法研究综述[J]. 电工技术学报, 2016, 31(4): 58-63.
Yang Ming, Dong Chuanyang, Xu Dianguo. Review of gear fault diagnosis methods based on motor drive system[J]. Transactions of China Electrotechnical Society, 2016, 31(4): 58-63.
[4] 孙娟. 基于模型的风电齿轮箱故障检测[D]. 南京: 南京理工大学, 2015.
[5] 冯志鹏, 范寅夕, Liang Ming, 等. 行星齿轮箱故障诊断的非平稳振动信号分析方法[J]. 中国电机工程学报, 2013, 33(17): 105-110.
Feng Zhipeng, Fan Yinxi, Liang Ming, et al. A nonstationary vibration signal analysis method for fault diagnosis of planetary gearboxes[J]. Proceedings of the CSEE, 2013, 33(17): 105-110.
[6] 顾煜炯, 宋磊, 徐天金, 等. 变工况条件下的风电机组齿轮箱故障预警方法[J]. 中国机械工程, 2014, 25(10): 1346-1452.
Gu Yujiong, Song Lei, Xu Tianjin, et al. Research on wind turbine gearbox fault warning method under variable working condition[J]. China Mechanical Egineering, 2014, 25(10): 1346-1452.
[7] Liu B, Riemenschneider S, Xu Y. Gearbox fault diagnosis using empirical mode decomposition and Hilbert spectrum[J]. Mechanical Systems and Signal Processing, 2006, 20(3): 718-734.
[8] 杨茂, 陈郁林. 基于EMD分解和集对分析的风电功率实时预测[J]. 电工技术学报, 2016, 31(21): 86-93.
Yang Mao, Chen Yulin. Real-time prediction for wind power based on EMD and set pair analysis[J]. Transactions of China Electrotechnical Society, 2016, 31(21): 86-93.
[9] 于生宝, 何建龙, 王睿家, 等. 基于小波包分析和概率神经网络的电磁法三电平变换器故障诊断方法[J]. 电工技术学报, 2016, 31(17): 102-112.
Yu Shengbao, He Jianlong, Wang Ruijia, et al. Fault diagnosis of electromagnetic three-level inverter based on wavelet packet analysis and probabilistic neural networks[J]. Transactions of China Electrotechnical Society, 2016, 31(17): 102-112.
[10] 陈学峰, 梁培钧. 油液分析技术在齿轮箱故障诊断中的应用[J]. 机械工程与自动化, 2011(1): 114-115.
Chen Xuefeng, Liang Peijun. Application of oil analysis technology in gearbox fault diagnosis[J]. Mechanical Engineering & Automation, 2011(1): 114-115.
[11] 杨明, 董传洋, 徐殿国. 基于电机驱动系统的齿轮故障诊断方法综述[J]. 电工技术学报, 2016, 31(4): 132-140.
Yang Ming, Dong Chuanyang, Xu Dianguo. Review of gear fault diagnosis methods based on motor drive system[J]. Transactions of China Electrotechnical Society, 2016, 31(4): 132-140.
[12] 赵洪山, 胡庆春, 李志为. 基于统计过程控制的风机齿轮箱故障预测[J]. 电力系统保护与控制, 2012, 40(13): 67-73.
Zhao Hongshan, Hu Qingchun, Li Zhiwei. Failure prediction of wind turbine gearbox based on statistical process control[J]. Power System Protection and Control, 2012, 40(13): 67-73.
[13] 郭鹏, David Infield, 杨锡运. 风电机组齿轮箱温度趋势状态监测及分析方法[J]. 中国电机工程学报, 2011, 31(32): 129-136.
Guo Peng, David Infield, Yang Xiyun. Wind turbine gearbox condition monitoring using temperature trend analysis[J]. Proceedings of the CSEE, 2011, 31(32): 129-136.
[14] 周国亮, 朱永利, 王桂兰, 等. 实时大数据处理技术在状态监测领域中的应用[J]. 电工技术学报, 2014, 29(1): 432-437.
Zhou Guoliang, Zhu Yongli, Wang Guilan, et al. Real-time big data processing technology application in the field of state monitoring[J]. Transactions of China Electrotechnical Society, 2014, 29(1): 432-437.
15 . 电力系统自动化, 2016, 40(14): 129-134.
16 Zhang Shaomin, Mao Dong, Wang Baoyi. Application of big data processing technology in fault diagnosis and early warning of wind turbine gearbox[J]. Automation of Electric Power Systems, 2016, 40(14): 129-134.
[16] Yang Wenxian, Court R, Jiang Jiesheng. Wind turbine condition monitoring by the approach of SCADA data analysis[J]. Renewable Energy, 2013, 53(9): 365-376.
[17] 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, 39(7): 1946-1953.
Zhao Guangquan, Ge Qiangqiang, Liu Xiaoyong, et al. Fault feature extraction and diagnosis method based on deep belief network[J]. Chinese Journal of Scientific Instrument, 2016, 39(7): 1946-1953.
[18] 雷亚国, 贾峰, 周昕, 等. 基于深度学习理论的机械装备大数据健康监测方法[J]. 机械工程学报, 2015, 51(21): 49-56.
Lei Yaguo, Jia Feng, Zhou Xin, et al. A deep learning-based method for machinery health monitoring[J]. Journal of Mechanical Engineering, 2015, 51(21): 49-56.
[19] Lecun Y, Bengio Y, Hinton G. Deep learning[J]. Nature, 2015, 521(7553): 436-444.
[20] Chen Yushi, Lin Zhouhan, Zhao Xing, et al. Deep learning-based classification of hyperspectral data[J]. IEEE Journal of Selected Topics in Applied Earth Observation and Remote Sensing, 2014, 7(6): 2094-2107.
[21] Hinton G, Osindero S, Teh Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554.
[22] Salakhutdinov R, Murray I. On the quantitative analysis of deep belief networks[C]//Proceedings of the 25th International Conference on Machine Learning, New York, USA, 2008: 872-879.
[23] Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(1): 504-507.
[24] Bengio Y, Lamblin P, Popovici D, et al. Greedy layer-wise training of deep network[J]. Advances in Neural Information Processing Systems, 2007, 19: 153-160.
[25] Rumelhart D E, Hinton G E, Williams R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323(6008): 533-536.