Fault Diagnosis of Wind Turbine BladeBased on Cauchy Artificial Bee Colony Algorithm Optimized Support Vector Machine

doi:10.11985/2018.01.003

Abstract

Abstract:

In order to improve the recognition rate of wind turbine blade fault diagnosis, the nonlinear relationship between fault diagnosis and characteristic parameters of wind turbine blade is established by using support vector machine. In the Cauchy artificial bee colony algorithm, a dynamic Cauchy factor is introduced to dynamically adjust the search step in the optimization process of the colony, to improve the perturbation ability of the colony algorithm, and to avoid the colony into the local search. A dynamic support vector machine model for dynamic Cauchy bee colony optimization is established. The model is trained and diagnosed by four conditions of a wind farm in the south. The results show that the support vector machine model can be improved based on the dynamic Cauchy artificial bee colony algorithm. Wind turbine generator fault recognition rate, with a certain engineering reference significance.

Key words: Dynamic Cauchy factor, artificial bee colony algorithm, support vector machine, wind turbine, bladefault diagnosis

CLC Number:

TM15

Yupeng Wang,Zhijie Wang,Qi Liu,Lili Xu,Hong Wang,Yali Cheng. Fault Diagnosis of Wind Turbine BladeBased on Cauchy Artificial Bee Colony Algorithm Optimized Support Vector Machine[J]. Journal of Electrical Engineering, 2018, 13(1): 16-22.

Figures/Tables 11

Fig.1

Fig.2

Fig.3

Fig.5

Tab.1

Fig.6

Tab.2

Tab.3

Fig.7

Fig.8

Tab.4

References 12

[1]	于占龙 . 风力发电机状态监测与故障诊断技术综述[J]. 工程技术:文摘版, 2016,16(10):297-297.
	Yu Zhanlong . A review of condition monitoring and fault diagnosis techniques for wind turbine[J]. Engineering Technology: Digest, 2016,16(10):297-297.
[2]	薛浩然, 张珂珩, 李斌 , 等. 基于布谷鸟算法和支持向量机的变压器故障诊断[J].电力系统保护与控制, 2015(8):8-13.
	Xue Haoran, Zhang Keheng, Li Bin , et al. Transformer fault diagnosis based on cuckoo algorithm and support vector machine[J]. Power System Protection and Control, 2015(8):8-13.
[3]	饶金根 . 基于谐波小波和支持向量机的风电叶片损伤识别研究[D]. 兰州:兰州交通大学, 2014.
[4]	Karaboga D, Basturk B . A powerful and efficient algorithm for numerical function optimization: artificial bee colony(ABC)algorithm[J]. Journal of Global Optimization, 2007,39(3):459-471.
[5]	Hu W, Yu Y, Zhang S . A hybrid artificial bee colony algorithm forparameter identification of uncertain fractional-order chaotic systems[J]. Nonlinear Dynamics, 2015,82(3):1-16.
[6]	吴国诚, 范良忠 . 人工蜂群优化支持向量机的电气故障诊断方法研究[J]. 电网与清洁能源, 2016,32(7):87-91.
	Wu Guocheng, Fan Liangzhong . Study on electrical fault diagnosis of artificial bee colony optimization support vector machine[J]. Power System and Clean Energy, 2016,32(7):87-91.
[7]	叶东毅, 陈昭炯 . 最小属性约简问题的一个有效的组合人工蜂群算法[J]. 电子学报, 2015,43(5):1014-1020.
	Ye Dongyi, Chen Zhaojiong . An effective combination of artificial bee colony algorithm for minimal attribute reduction[J]. Acta Electronica Sinica, 2015,43(5):1014-1020.
[8]	许建华, 张学工 . 经典线性算法的非线性核形式[J]. 控制与决策, 2006,21(1):1-6.
	Xu Jianhua, Zhang Xuegong . Nonlinear kernel form of classical linear algorithm[J]. Control & Decision, 2006,21(1):1-6.
[9]	顾桂梅, 胡让, 李远远 . 果蝇优化算法融合SVM的风机叶片损伤识别研究[J]. 自动化仪表, 2016,37(2):9-12.
	Gu Guimei, Hu Rang, Li Yuanyuan . Description of damage identification of blower vane based on drosophila optimization algorithm combined with SVM[J]. Process Automation Instrumentation, 2016,37(2):9-12.
[10]	肖剑, 周建中, 张孝远 , 等. 基于Levy-ABC优化SVM的水电机组故障诊断方法[J]. 振动、测试与诊断, 2013,33(5):839-844.
	Xiao Jian, Zhou Jianzhong, Zhang Xiaoyuan , et al. A fault diagnosis method based on Levy-ABC SVM for hydroelectric units[J]. Journal of Vibration, Testing and Diagnosis, 2013,33(5):839-844.
[11]	张银雪, 田学民, 曹玉苹 . 改进搜索策略的人工蜂群算法[J]. 计算机应用, 2012,32(12):3326-3330.
	Zhang Yinxue, Tian Xuemin, Cao Yuping . Artificial bee colony algorithm with improved search strategy[J]. Journal of Computer Applications, 2012,32(12):3326-3330.
[12]	张鑫, 陈国初, 公维祥 , 等. 自适应柯西蜂群及其收敛性分析[J]. 计算机系统应用, 2015,24(12):118-124.
	Zhang Xin, Chen Guochu, Gong Weixiang . An adaptive cauchy bee colony and its convergence analysis[J]. Computer Systems & Applications, 2015,24(12):118-124.

测试函数	DCABC			ABC
测试函数	最优值	平均值	收敛时间/s	最优值	平均值	收敛时间/s
Rastrigin	0	0.008 1	4.231 4	0.000 4	0.009 1	5.523 1
Sphere	5.001 2×10^-7	0.053 2	4.136 9	2.256 4×10^-6	0.062 3	5.813 7
Ackley	1.846 5×10^-12	0.002 75	5.196 4	1.156 4×10^-11	0.0052	6.315 9
Griewank	0	2.584 1×10^-5	5.169 8	0.000 4	4.621 4×10^-5	6.412 8

	正常	前缘开裂	后缘开裂	蒙皮开裂
训练样本	60	40	40	40
实验样本	25	20	20	20
总数据	85	60	60	60

故障类型	前缘温度x₁	后缘温度x₂	前缘湿度x₃	后缘湿度x₄	前缘光亮度x₅	后缘光亮度x₆	前缘音量x₇	后缘音量x₈
正常	0.75	0.84	2.03	2.12	0.51	0.53	0.87	0.84
正常	0.67	0.94	2.04	2.24	0.61	0.58	0.78	0.91
蒙皮开裂	0.45	1.06	0.48	0.45	1.04	1.05	2.73	2.58
蒙皮开裂	0.52	1.06	0.59	0.52	1.05	1.04	2.75	2.55
前缘开裂	1.72	0.99	1.89	0.88	2.43	1.65	2.98	1.14
前缘开裂	1.66	1.05	1.83	1.08	2.27	1.62	2.92	1.16
后缘开裂	0.92	1.80	1.19	1.97	1.66	2.36	1.06	2.68
后缘开裂	1.04	1.76	1.08	1.87	1.52	2.25	1.09	2.88

方法	C	γ	训练时间/s	准确率(%)
ABC-SVM	13.254	0.231	50.40	95.29
DCABC-SVM	11.241	0.104	37.54	97.65

[1]	HE Erming, XIONG Bo, YANG Jiajia. Study on Active-passive Integrated Vibration Control of Offshore Floating Wind Turbine Based on TMD-HMD [J]. Journal of Mechanical Engineering, 2020, 56(3): 73-79.
[2]	TANG Xinzi, LI Pengcheng, PENG Ruitao, LU Xinyu. Aerodynamic Characteristics and Robust Optimization of Small Wind Turbine Airfoil under Turbulence Condition [J]. Journal of Mechanical Engineering, 2020, 56(2): 192-200.
[3]	PEI Hong, HU Changhua, SI Xiaosheng, ZHANG Jianxun, PANG Zhenan, ZHANG Peng. Review of Machine Learning Based Remaining Useful Life Prediction Methods for Equipment [J]. Journal of Mechanical Engineering, 2019, 55(8): 1-13.
[4]	CHEN Xu, ZHU Caichao, SONG Chaosheng, TAN Jianjun, ZHU Yongchao. Dynamic Characteristics Analysis of Wind Turbine under Emergency Shutdown Events [J]. Journal of Mechanical Engineering, 2019, 55(5): 82-88.
[5]	Zhipeng SUN,Zhilong SUN,Jian WEI. Research on Power Transformer Fault Diagnosis Based on Decision Tree Support Vector Machine Algorithm [J]. Journal of Electrical Engineering, 2019, 14(4): 42-45.
[6]	ZHANG Fan, LIU Deshun, DAI Juchuan, WANG Chao, SHEN Xiangbing. An Operating Condition Recognition Method of Wind Turbine Based on SCADA Parameter Relations [J]. Journal of Mechanical Engineering, 2019, 55(4): 1-9.
[7]	BAO Guangqing,LI Yuan,MA Ming,WANG Ningbo. Virtual Synchronization Control Strategy of Direct Drive Permanent Magnet Wind Turbine under Load Shedding Operation Mode [J]. Journal of Electrical Engineering, 2019, 14(3): 47-53.
[8]	ZHENG Dazhou,ZENG Dong,LI Guanglei,LU Rui. Building and Simulation Research on the Electrical Model of DFIG [J]. Journal of Electrical Engineering, 2019, 14(3): 81-89.
[9]	ZHU Daye, DING Xiaohong, WANG Shenlong, WANG Haihua, YU Huijie. Uncertainty Evaluation Method of Complex Nonlinear System Test Based on Support Vector Machine Model [J]. Journal of Mechanical Engineering, 2018, 54(8): 177-184.
[10]	Chen Ming,Chen Yongjun,Li Lisen. Study of Heat Dissipation of Frequency Converter of Wind Turbine Tower Bottom [J]. Journal of Electrical Engineering, 2018, 13(5): 33-39.
[11]	Wei Qiao, Liyan Qu. Prognostic Condition Monitoring for Wind Turbine Drivetrains via Generator Current Analysis [J]. Chinese Journal of Electrical Engineering, 2018, 4(3): 80-89.
[12]	ZHAO Zhenzhou, YAN Chang, WANG Tongguang, SHEN Wenzhong, ZHENG Yuan, XU Bofeng. Parametric Model of Vortex Generators of Wind Turbine Considering Inter-effect of Winglets [J]. Journal of Mechanical Engineering, 2018, 54(2): 201-208.
[13]	CHI Zhiqiang, XIA Hongjian, LI Deyuan, ZHANG Xiangwei. Study on Modal Aerodynamic Damping Analysis Method for Wind Turbine Blade [J]. Journal of Mechanical Engineering, 2018, 54(2): 176-183.
[14]	HOU Yali, WANG Jianwen, WANG Qiang, WANG Xinting. Influence of Roof Shape on Micrositing of Rooftop Wind Turbine in the Building Group [J]. Journal of Mechanical Engineering, 2018, 54(2): 191-200.
[15]	SHAN Zhongde, ZHU Fuxian. Wear Mechanism and Prediction Model of Polycrystalline Diamond Tool in Milling Sand Mould [J]. Journal of Mechanical Engineering, 2018, 54(17): 124-132.