Fault Diagnosis Method of Wind Turbines Based on Wide Deep Convolutional Neural Network With Resampling and Principal Component Analysis

doi:10.12096/j.2096-4528.pgt.22178

Abstract

Abstract:

Fault diagnosis of wind turbines suffers from less training data and noises. A method based on wide deep convolutional neural network with resampling and principal component analysis was presented for the diagnosis of mechanical faults (that is the main fault component of wind turbines). The method adopted a variety of signal preprocessing methods such as resampling wavelet threshold denoising and principal component analysis to increase the information density and ensure the integrity of the information. After being trained with small amount of data, the network which has a powerful feature extraction capability could extract the fault signal in the time domain which will be further used for fault diagnosis. Experimental results were verified based on the real wind turbine data, demonstrating the effectiveness of this method.

Key words: wind turbine, wide deep convolutional neural network, resampling, wavelet threshold denoising, principal component analysis

CLC Number:

TK 83

Zhan LIU, Yanyang BAO, Dazi LI. Fault Diagnosis Method of Wind Turbines Based on Wide Deep Convolutional Neural Network With Resampling and Principal Component Analysis[J]. Power Generation Technology, 2023, 44(6): 824-832.

Figures/Tables 12

Fig. 1 Diagram of WDCNN structure

Fig. 2 Diagram of resampling vibration signal of high-speed shaft tooth breakage in a certain unit

Fig. 3 Comparison before and after wavelet threshold denoising

Fig. 4 Frequency domain diagram of high-speed shaft vibration signal of a certain unit before and after PCA dimensionality reduction

Fig. 5 Frequency domain data of high-speed shaft vibration signal for a certain unit

Fig. 6 Structure diagram based on WDCNN method

Fig. 7 Raw data of drive end of generator

Fig. 8 Raw data of non drive end of generator

Tab. 1 Fault diagnosis results of wind turbine generator at the same speed

类别	测试样本	分类准确率/%
发电机驱动端	50	100
发电机非驱动端	50	98

Tab. 2 Fault diagnosis results of fan generators at different rotational speeds

类别	测试样本	分类准确率/%
发电机驱动端	50	98
发电机非驱动端	50	96

Fig. 9 Raw data of drive end of gearbox

Tab. 3 Results of ablation experiment

风机编号	训练集				测试集
风机编号	第1组	第2组	第3组	第4组	第1组	第2组	第3组	第4组
01	0.956	0.942	0.998	0.985	0.956	0.948	0.984	0.976
02	0.957	0.949	0.997	0.987	0.949	0.943	0.988	0.975
03	0.957	0.937	0.998	0.992	0.956	0.941	0.989	0.978
04	0.952	0.938	0.998	0.989	0.956	0.945	0.983	0.973
05	0.954	0.951	0.996	0.986	0.965	0.941	0.984	0.974
06	0.968	0.949	0.998	0.983	0.957	0.938	0.987	0.972
07	0.953	0.943	0.996	0.987	0.954	0.946	0.985	0.974
08	0.959	0.942	0.998	0.985	0.955	0.942	0.982	0.975
09	0.951	0.945	0.997	0.988	0.953	0.943	0.986	0.968
10	0.957	0.943	0.997	0.990	0.955	0.943	0.984	0.973

References 19

1	AWADALLAH M A， VENKATESH B ．Energy storage in distribution system planning and operation：current status and outstanding challenges[J]．Canadian Journal of Electrical and Computer Engineering，2019，42(1)：10-19． doi:10.1109/cjece.2018.2878321
2	辛保安，单葆国，李琼慧，等．“双碳”目标下“能源三要素”再思考[J]．中国电机工程学报，2022，42(9)：3117-3125．
	XIN B A， SHAN B G， LI Q H，et al ．Rethinking of the “three elements of energy” toward carbon peak and carbon neutrality[J]．Proceedings of the CSEE，2022，42(9)：3117-3125．
3	董文博，顾秀芳，陈艳宁．风电并网价值分析[J]．发电技术，2020，41(3)：320-327． doi:10.12096/j.2096-4528.pgt.19117
	DONG W B， GU X F， CHEN Y N ．Value analysis of wind power integration[J]．Power Generation Technology，2020，41(3)：320-327． doi:10.12096/j.2096-4528.pgt.19117
4	中丹可再生能源发展项目管理办公室．中国可再生能源发展路线图 2050[EB/OL]．(2014-12-16) [2022-11-15]．
089	Zhongdan Renewable Energy Development Project Management Office ．China’s roadmap for renewable energy development 2050[EB\OL]．(2014-12-16)[2022-11-15]．. doi:10.1023/a:1010650624155
	c3d5bbfd0a79563c1ec4dad77e.‍html？‍‍_wkts_‍=16914621. doi:10.1023/a:1010650624155
	84089． doi:10.1023/a:1010650624155
5	刘展．MW级变速变桨风力发电机组系统振动故障诊断技术与减振降载方法研究[D]．北京：北京交通大学，2019．
	LIU Z ．Study on vibration fault diagnosis technology and vibration reduction and load reduction method of MW variable speed variable pitch wind turbine system[D]．Beijing：Beijing Jiaotong University，2019．
6	李亚光，李蒙．基于深度小世界神经网络的风电机组异常检测[J]．发电技术，2021，42(3)：313-321． doi:10.12096/j.2096-4528.pgt.20091
	LI Y G， LI M ．Anomaly detection of wind turbines based on deep small-world neural network[J]．Power Generation Technology，2021，42(3)：313-321． doi:10.12096/j.2096-4528.pgt.20091
7	马海飞，滕伟，彭迪康，等．基于DRS与改进Autogram的风电齿轮箱复合故障特征提取[J]．中国电力，2023，56(10)：71-79．
	MA H F， TENG W， PENG D K，et al ．Compound fault feature extraction of wind power gearbox based on DRS and improved autogram[J]．Electric Power，2023，56(10)：71-79．
8	康佳乐，余浩，段瑶，等．风电场次同步振荡等值建模方法研究[J]．发电技术，2022，43(6)：880-891． doi:10.12096/j.2096-4528.pgt.21121
	KANG J L， YU H， DUAN Y，et al ．Equivalent modeling method of sub-synchronous oscillation in wind farm[J]．Power Generation Technology，2022，43(6)：880-891． doi:10.12096/j.2096-4528.pgt.21121
9	周超，朱熀秋，魏杰，等．我国风力发电发展现状和问题分析[J]．能源研究与信息，2012，28(2)：69-75． doi:10.3969/j.issn.1008-8857.2012.02.004
	ZHOU C， ZHU H Q， WEI J，et al ．Status quo and problems analysis of wind power generation in China[J]．Energy Research and Information，2012， 28(2)：69-75． doi:10.3969/j.issn.1008-8857.2012.02.004
10	杨晓峰，方逸航，赵鹏臻，等．风电机组状态识别的非机理性建模方法[J/OL]．中国电力：1-9[2022-08-29]．．
	YANG X F， FANG Y H， ZHAO P Z，et al ．Non-mechanical modeling method for state identification of wind turbines[J/OL]．Electric Power：1-9[2023-08-29]．．
11	QIAO W， LU D G ．A wurvey on wind turbine condition monitoring and fault diagnosis-part I：components and subsystems[J]．IEEE Transactions on Industrial Electronics，2015，62(10)：6536-6545． doi:10.1109/tie.2015.2422112
12	LI Z G， YAN B J ．Fault diagnosis of hoist gearbox based on time-domain analysis of EMD and fuzzy clustering[J]．Advanced Materials Research，2011，328/330：1717-1720． doi:10.4028/www.scientific.net/amr.328-330.1717
13	ZHANG Z， WANG Y， WANG K ．Intelligent fault diagnosis and prognosis approach for rotating machinery integrating wavelet transform， principal component analysis，and artificial neural networks[J]．The International Journal of Advanced Manufacturing Technology，2013，68(1/2/3/4)：763-773． doi:10.1007/s00170-013-4797-0
14	LI J M， CHEN X F， DU Z H，et al ．A new noise-controlled second-order enhanced stochastic resonance method with its application in wind turbine drivetrain fault diagnosis[J]．Renewable Energy，2013，60：7-19． doi:10.1016/j.renene.2013.04.005
15	CHEN J L， PAN J， LI Z P，et al ．Generator bearing fault diagnosis for wind turbine via empirical wavelet transform using measured vibration signals[J]．Renewable Energy，2016，89：80-92． doi:10.1016/j.renene.2015.12.010
16	HUSSAIN H S ．A review of artificial intelligence techniques in image steganography domain[J]．Journal of Engineering Science and Technology，2017，12(1)：1835-1845．
17	LONG X F， YANG P， GUO H X，et al ．A CBA-KELM-based recognition method for fault diagnosis of wind turbines with time-domain analysis and multisensor data fusion[J]．Shock and Vibration，2019(13)：1-14． doi:10.1155/2019/7490750
18	HU W F， CHANG H， GU X S ．A novel fault diagnosis technique for wind turbine gearbox[J]．Applied Soft Computing，2019，82：1-11． doi:10.1016/j.asoc.2019.105556
19	KRIZHEVSKY A， SUTSKEVER I， HINTON G E ．Imagenet classification with deep convolutional neural networks[J]．Communications of the ACM，2017，60(6)：84-90． doi:10.1145/3065386

[1]	Fangfang WANG, Pengwei YANG, Guangjin ZHAO, Qi LI, Xiaona LIU, Shuangchen MA. Development and Challenge of Flexible Operation Technology of Thermal Power Units Under New Power System [J]. Power Generation Technology, 2024, 45(2): 189-198.
[2]	Ang FAN, Luping LI, Rui LIU, Minnan OUYANG, Shangnian CHEN. Research on Dynamic Characteristics of Monopile Offshore Wind Turbine Tower Under Different Wind Speed Conditions [J]. Power Generation Technology, 2024, 45(2): 312-322.
[3]	Xinrong YAN, Ningning ZHANG, Kuichao MA, Chao WEI, Shuai YANG, Binbin PAN. Overview of Current Situation and Trend of Offshore Wind Power Development in China [J]. Power Generation Technology, 2024, 45(1): 1-12.
[4]	Zhipeng QIN, Gaosheng WEI, Liu CUI, Xiaoze DU. Study on Aerodynamic Performance of Wind Turbine Airfoil With Combined S-Slot and Trailing Edge Flap Control [J]. Power Generation Technology, 2024, 45(1): 24-31.
[5]	Caixin SUN, Bo ZHANG, Wei TANG, Yiming ZHOU, Mingzhi FU, Meng QIN, Xiaojiang GUO. Research and Practice on Localization of Offshore Wind Turbines [J]. Power Generation Technology, 2023, 44(5): 696-702.
[6]	Lifeng ZHANG, Jing LI, Zhi WANG. Reconstruction of Temperature Distribution by Acoustic Tomography Based on Principal Component Analysis and Deep Neural Network [J]. Power Generation Technology, 2023, 44(3): 399-406.
[7]	Ang FAN, Luping LI, Shihai ZHANG, Minnan OUYANG, Xiankui WEN, Shangnian CHEN. A Review on Dynamic Characteristics and Life Loss of Large Wind Turbine Towers [J]. Power Generation Technology, 2022, 43(3): 421-430.
[8]	Zheng LI, Xiaojiang GUO, Xuhui SHEN, Haiyan TANG. Summary of Technologies for the Development of Offshore Wind Power Industry in China [J]. Power Generation Technology, 2022, 43(2): 186-197.
[9]	Danmei HU, Li ZENG, Yunhao CHEN. Analysis of Fluid-Structure Coupling Characteristics of Semi-submersible Offshore Wind Turbines [J]. Power Generation Technology, 2022, 43(2): 218-226.
[10]	Xiaoyang ZOU, Weiguo PAN. Research Progress on Dynamic Simulation Analysis of Floating Offshore Wind Turbine [J]. Power Generation Technology, 2022, 43(2): 249-259.
[11]	Zhiwei ZHANG, Jianping ZHANG, Ming LIU, Haipeng JI, Haojun ZHU, Shengdi ZHOU. Analysis on Variation Characteristics of Offshore Wind Resources in Luchao Port [J]. Power Generation Technology, 2022, 43(2): 260-267.
[12]	Lei ZHANG, Jiying LI, Qinwei LI, Mince ZHANG, Yunfeng GUO, Lidong ZHANG. Status and Prospect of Yaw System Control Strategy for Wind Turbines [J]. Power Generation Technology, 2021, 42(3): 306-312.
[13]	Yaguang LI, Meng LI. Anomaly Detection of Wind Turbines Based on Deep Small-World Neural Network [J]. Power Generation Technology, 2021, 42(3): 313-321.
[14]	Haichuan ZHAO, Yandong LU, Haokang ZHENG, Zuoxia XING. Research on Low Voltage Ride Through for Small Direct-driven Permanent Magnet Wind Turbine in Low Voltage Microgrid [J]. Power Generation Technology, 2020, 41(6): 659-666.
[15]	Changxing YANG, Luping LI. Research Progress on Blade Damage Fault Detection Technology of Wind Turbine [J]. Power Generation Technology, 2020, 41(6): 599-607.