Fault Identification for Wind Turbine Based on Attention Mechanism and RCN-BiLSTM Fusion

doi:10.11930/j.issn.1004-9649.202412081

Abstract

Abstract:

To improve the identification accuracy of wind turbine faults, an RCN-BiLSTM-Attention wind turbine fault identification method based on the attention mechanism (AM) and the fusion of residual capsule network (RCN) and bidirectional long short-term memory (BiLSTM) network is proposed. First, the abnormal values in the wind turbine supervisory control and data acquisition (SCADA) system are eliminated by the density-based spatial clustering of applications with noise (DBSCAN) algorithm. Then, RCN is employed to extract spatial relational features from the fault data, the BiLSTM is performed to dynamically capture the hierarchical temporal dependencies of the spatial features extracted by RCN to obtain the temporal information of multiple faults, and fusion AM assigns different weights to the outputs of BiLSTM to enhance the accuracy of wind turbine fault identification. Finally, the SCADA data of several wind turbines are used to verify that the proposed model provides high identification accuracy and generalization ability compared with other models.

Key words: wind turbine, fault identification, bidirectional long short-term memory

CHEN Xiaoqian, YIN Liang, ZHAN Zonghui, WANG Fang, LI Xutao. Fault Identification for Wind Turbine Based on Attention Mechanism and RCN-BiLSTM Fusion[J]. Electric Power, 2025, 58(8): 94-102.

Add to citation manager EndNote|Ris|BibTeX

URL: https://www.electricpower.com.cn/EN/10.11930/j.issn.1004-9649.202412081

https://www.electricpower.com.cn/EN/Y2025/V58/I8/94

Figures/Tables 10

Fig.1 Residual capsule network model

Fig.2 LSTM network diagram

Fig.3 BiLSTM network diagram

Fig.4 RCN-BiLSTM-Attnetion architecture

Fig.5 Attention mechanism structure

Fig.6 Fault identification process based on RCN-BiLSTM-Attention

Fig.7 Original wind power data curve

Fig.8 Processed wind power data curve

Fig.9 The convergence curve of the RCN-BiLSTM-Attention model

Table 1 Performance comparison of different models 单位：%

模型	平均准确率	平均精确率	平均召回率	平均 F₁值
DT	85.71	70.90	71.43	71.16
LSTM	86.46	72.06	73.68	72.86
BiLSTM	88.68	77.27	76.69	76.98
CNN-BiLSTM	93.88	86.23	89.47	87.82
RCN-BiLSTM	95.73	91.67	90.98	91.32
RCN-BiLSTM- Attention	97.77	94.81	96.24	95.52

References 31

1	李丹, 梁云嫣, 缪书唯, 等. 基于高斯混合聚类和改进条件变分自编码的多风电场功率日场景生成方法[J]. 中国电力, 2024, 57 (12): 17- 29. DOI
	LI Dan, LIANG Yunyan, MIAO Shuwei, et al. Daily power scenario generation method for multiple wind farms based on Gaussian mixture clustering and improved conditional variational autoencoder[J]. Electric Power, 2024, 57 (12): 17- 29. DOI
2	张睿骁, 梁利, 王定美. 新能源场站快速频率响应分析与高效测试装置设计[J]. 中国电力, 2025, 58 (5): 144- 151. DOI
	ZHANG Ruixiao, LIANG Li, WANG Dingmei. Fast frequency response analysis and efficient test device design of new energy station[J]. Electric Power, 2025, 58 (5): 144- 151. DOI
3	徐贤, 朱丹丹, 徐晓春, 等. 海上风电集群AVC子站无功电压灵敏度协同控制策略研究[J]. 电测与仪表, 2025, 62 (4): 53- 64.
	XU Xian, ZHU Dandan, XU Xiaochun, et al. Study on cooperative reactive voltage sensitivity control strategy of AVC substations in clustered offshore wind farm[J]. Electrical Measurement & Instrumentation, 2025, 62 (4): 53- 64.
4	杜谦, 张金龙, 陈武晖. 考虑集电系统元件故障的风电场可靠性评估[J]. 内蒙古电力技术, 2024, 42 (4): 73- 79.
	DU Qian, ZHANG Jinlong, CHEN Wuhui. Reliability evaluation of wind farm considering component faults in collecting system[J]. Inner Mongolia Electric Power, 2024, 42 (4): 73- 79.
5	李令宇, 程浩忠, 张衡, 等. 含高比例新能源电力系统的低碳电源规划方法[J]. 电测与仪表, 2025, 62 (7): 30- 37.
	LI Lingyu, CHENG Haozhong, ZHANG Heng, et al. Low-carbon power planning method for power system with high proportion of renewable energy[J]. Electrical Measurement & Instrumentation, 2025, 62 (7): 30- 37.
6	龙寰, 杨婷, 徐劭辉, 等. 基于数据驱动的风电机组状态监测与故障诊断技术综述[J]. 电力系统自动化, 2023, 47 (23): 55- 69. DOI
	LONG Huan, YANG Ting, XU Shaohui, et al. Review of data-driven condition monitoring and fault diagnosis technologies for wind turbines[J]. Automation of Electric Power Systems, 2023, 47 (23): 55- 69. DOI
7	罗必雄, 胡均亮, 杨亚军, 等. 计及纵向扰动稳定的高空风电系统建模与稳定运行控制方法[J]. 南方能源建设, 2025, 12 (1): 1- 11.
	LUO Bixiong, HU Junliang, YANG Yajun, et al. Modeling and stable operation control method for airborne wind energy system considering longitudinal disturbance stability[J]. Southern Energy Construction, 2025, 12 (1): 1- 11.
8	张秀琦, 胡学超, 李勇. 风电机组设备可靠性分析及提升方法研究[J]. 内蒙古电力技术, 2024, 42 (3): 8- 12.
	ZHANG Xiuqi, HU Xuechao, LI Yong. Research on equipment reliability analysis and improvement methods for wind turbine[J]. Inner Mongolia Electric Power, 2024, 42 (3): 8- 12.
9	张振海, 王维庆, 王海云, 等. 基于改进小波包的风电机组齿轮箱复合故障特征提取研究[J]. 太阳能学报, 2022, 43 (9): 331- 336.
	ZHANG Zhenhai, WANG Weiqing, WANG Haiyun, et al. Research on composite fault feature extraction of wind turbine gearbox based on improved wavelet packet[J]. Acta Energiae Solaris Sinica, 2022, 43 (9): 331- 336.
10	孙群丽, 周瑛, 刘长良. 基于LARS特征选择的风电机组故障诊断的研究[J]. 可再生能源, 2020, 38 (10): 1349- 1354. DOI
	SUN Qunli, ZHOU Ying, LIU Changliang. Research on fault diagnosis of wind turbines based on LARS feature selection[J]. Renewable Energy Resources, 2020, 38 (10): 1349- 1354. DOI
11	AHILAN T, NARASIMHULU ANDRIYA, PRASAD DVSSSV. A self-improved optimizer-based CNN for wind turbine fault detection[J]. Journal of Circuits Systems and Computers, 2023, 32 (14): 2350247. DOI
12	XIE P, ZHANG X M, JIANG G Q, et al. Investigation of deep transfer learning for cross-turbine diagnosis of wind turbine faults[J]. Measurement Science and Technology, 2023, 34 (4): 044009. DOI
13	周凌, 赵前程, 朱岸锋, 等. 基于FISSA-DBN模型的风电机组运行状态监测[J]. 振动·测试与诊断, 2023, 43 (1): 80- 87, 199.
	ZHOU Ling, ZHAO Qiancheng, ZHU Anfeng, et al. Wind turbine operation status monitoring based on FISSA-DBN model[J]. Journal of Vibration, Measurement & Diagnosis, 2023, 43 (1): 80- 87, 199.
14	WANG X, ZHENG Z, JIANG G Q, et al. Detecting wind turbine blade icing with a multiscale long short-term memory network[J]. Energies, 2022, 15 (8): 2864. DOI
15	JIANG G Q, YUE R X, HE Q, et al. Imbalanced learning for wind turbine blade icing detection via spatio-temporal attention model with a self-adaptive weight loss function[J]. Expert Systems with Applications, 2023, 229, 120428. DOI
16	陈庆, 柳雨生, 段练达, 等. 大语言模型融合知识图谱的风电运维问答系统研究[J]. 综合智慧能源, 2024, 46 (9): 61- 68. DOI
	CHEN Qing, LIU Yusheng, DUAN Lianda, et al. Research on a wind power operation and maintenance Q & A system based on large language models and knowledge graphs[J]. Integrated Intelligent Energy, 2024, 46 (9): 61- 68. DOI
17	马嘉晨, 袁满, 杨德友, 等. 用于提升风电消纳能力的高载能负荷调度策略研究[J]. 东北电力大学学报, 2024, 44 (2): 79- 87.
	MA Jiachen, YUAN Man, YANG Deyou, et al. Research on high-energy load dispatching strategy usedto improve wind power ability[J]. Journal of Northeast Electric Power University, 2024, 44 (2): 79- 87.
18	骆尧涵, 汤皓环, 李金裕, 等. 基于电压迭代的直驱风电场短路电流计算方法[J]. 浙江电力, 2024, 43 (10): 75- 84.
	LUO Yaohan, TANG Haohuan, LI Jinyu, et al. A short-circuit current calculation method for direct-driven wind farms based on voltage iteration[J]. Zhejiang Electric Power, 2024, 43 (10): 75- 84.
19	尹子康, 林忠伟, 吕广华, 等. 基于数据驱动的风电机组变桨系统故障诊断与健康状态预测研究[J]. 东北电力大学学报, 2023, 43 (5): 1- 11, 17.
	YIN Zikang, LIN Zhongwei, LV Guanghua, et al. Research on fault diagnosis and health state prediction of wind turbine variable pitch system based on data drive[J]. Journal of Northeast Electric Power University, 2023, 43 (5): 1- 11, 17.
20	毛煜, 尚海昆, 于卓琦. 基于长短期记忆网络的电网同调机群快速辨识[J]. 电气工程学报, 2022, 17 (2): 201- 207.
	MAO Yu, SHANG Haikun, YU Zhuoqi. A fast prediction method of coherent generators based on long short-term memory network[J]. Journal of Electrical Engineering, 2022, 17 (2): 201- 207.
21	任建吉, 位慧慧, 邹卓霖, 等. 基于CNN-BiLSTM-Attention的超短期电力负荷预测[J]. 电力系统保护与控制, 2022, 50 (8): 108- 116.
	REN Jianji, WEI Huihui, ZOU Zhuolin, et al. Ultra-short-term power load forecasting based on CNN-BiLSTM-Attention[J]. Power System Protection and Control, 2022, 50 (8): 108- 116.
22	武煜昊, 王永生, 徐昊, 等. 风电输出功率预测技术研究综述[J]. 计算机科学与探索, 2022, 16 (12): 2653- 2677. DOI
	WU Yuhao, WANG Yongsheng, XU Hao, et al. Survey of wind power output power forecasting technology[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16 (12): 2653- 2677. DOI
23	DASZYKOWSKI M, WALCZAK B, MASSART D L. Looking for natural patterns in data[J]. Chemometrics and Intelligent Laboratory Systems, 2001, 56 (2): 83- 92. DOI
24	JIA X D, JIN C, BUZZA M, et al. Wind turbine performance degradation assessment based on a novel similarity metric for machine performance curves[J]. Renewable Energy, 2016, 99, 1191- 1201. DOI
25	慕宗君, 邱俊宏, 李振兴, 等. 多类型故障影响下柔直线路故障机理分析及单端保护方法[J]. 中国电力, 2025, 58 (1): 107- 114.
	MU Zongjun, QIU Junhong, LI Zhenxing, et al. Fault mechanism analysis and one-terminal protection method of flexible DC transmission line under the influence of multi-type faults[J]. Electric Power, 2025, 58 (1): 107- 114.
26	曹力潭, 魏华兵, 黄智, 等. 基于LSTM神经网络的电抗器故障声纹识别方法[J]. 浙江电力, 2023, 42 (4): 114- 120.
	CAO Litan, WEI Huabing, HUANG Zhi, et al. Research on voiceprint recognition of reactor fault based on LSTM neural network[J]. Zhejiang Electric Power, 2023, 42 (4): 114- 120.
27	金恩淑, 张弼弘, 胡晓晨, 等. 基于限流电抗器电压的柔性直流配电线路单端量保护新方法[J]. 东北电力大学学报, 2024, 44 (3): 64- 73.
	JIN Enshu, ZHANG Bihong, HU Xiaochen, et al. A new method of single-terminal protection for flexible DC distribution lines based on current-limiting reactor voltage[J]. Journal of Northeast Electric Power University, 2024, 44 (3): 64- 73.
28	皮俊波, 齐世雄, 孙文多, 等. 基于UIE框架的电网故障处置预案实体和事件识别方法[J]. 中国电力, 2023, 56 (12): 138- 146. DOI
	PI Junbo, QI Shixiong, SUN Wenduo, et al. Entity and event recognition method for power grid fault handling plan based on UIE framework[J]. Electric Power, 2023, 56 (12): 138- 146. DOI
29	黄雯, 张紫凡, 梁展弘, 等. 基于小波算法的小电流接地系统高阻接地故障的识别[J]. 内蒙古电力技术, 2023, 41 (4): 60- 65.
	HUANG Wen, ZHANG Zifan, LIANG Zhanhong, et al. Identification of high resistance grounding fault in small current earthing system based on wavelet algorithm[J]. Inner Mongolia Electric Power, 2023, 41 (4): 60- 65.
30	冯骥, 杨国华, 史磊, 等. 基于并行融合深度残差收缩网络的有源配电网故障诊断[J]. 综合智慧能源, 2024, 46 (6): 8- 15. DOI
	FENG Ji, YANG Guohua, SHI Lei, et al. Research on fault diagnosis of active distribution network based on parallel fusion deep residual shrinkage network[J]. Integrated Intelligent Energy, 2024, 46 (6): 8- 15. DOI
31	罗美玲, 李紫肖, 郑涛, 等. 基于模糊多判据融合的单端暂态量保护新方案[J]. 中国电力, 2024, 57 (3): 60- 72.
	LUO Meiling, LI Zixiao, ZHENG Tao, et al. Single terminal transient protection scheme based on fuzzy multi-criteria fusion[J]. Electric Power, 2024, 57 (3): 60- 72.

[1]	LIU Han, LIU Jindong, LI He, LI Yanli, YU Qiyuan, ZHAO Yuan, GENG Yanan. Leakage Fault Identification of PV-Integrated Distribution Networks Based on CEEMDAN and NRBO-XGBoost [J]. Electric Power, 2025, 58(9): 23-32.
[2]	JI Zhanyang, HU Yang, KONG Lingxing, SONG Ziqiu, DENG Dan, LIU Jizhen. Dynamic Modeling and Simulation of Wind Turbine Unit Primary Frequency Regulation Considering Multi-domain Coupling Characteristics [J]. Electric Power, 2025, 58(4): 56-67.
[3]	WANG Xiaodong, LI Qing, FU Deyi, LIU Yingming, WANG Ruojin. Fatigue Load Prediction of Wind Turbine Drive Train Based on CNN-BiLSTM [J]. Electric Power, 2025, 58(4): 90-97.
[4]	Penghui YANG, Guochao QIAN, Hao BAI, Hongwen LIU, Wanxian YANG, Xiao SHI. High Resistance Grounding Fault Perception and Identification Method in Asymmetric Distribution Network [J]. Electric Power, 2025, 58(2): 22-32.
[5]	YANG Xiaofeng, FANG Yihang, ZHAO Pengzhen, WANG Chengmin, XIE Ning. State Recognition of Wind Turbines Based on K-means and BPNN [J]. Electric Power, 2023, 56(6): 158-166,175.
[6]	LI Bohao, GUO Kunli, LV Jiajun, CAI Weizheng, LIU Luhao, LIU Fengyi, HAO Yifan. Inhibition of Subsynchronous Oscillation of Direct-Drive Wind Turbine by Improved LADRC in Weak Grids [J]. Electric Power, 2023, 56(4): 56-67.
[7]	Bing LI, Yunshan BAI, Kuan ZHAO, Congbin GUO, Yongjie ZHAI. Surface Defect Detection Algorithm for Wind Turbine Blades Based on HSCA-YOLOv7 [J]. Electric Power, 2023, 56(10): 43-52.
[8]	Haifei MA, Wei TENG, Dikang PENG, Yibing LIU, Tao JIN. Compound Fault Feature Extraction of Wind Power Gearbox Based on DRS and Improved Autogram [J]. Electric Power, 2023, 56(10): 71-79.
[9]	Lei WANG, Yibing LIU, Wei TENG, Xinwei HUANG, Jiantao LIU. Research and Development of Nondestructive Detection Technology for Wind Turbine Blades [J]. Electric Power, 2023, 56(10): 80-95.
[10]	Yuhui WU, Yangfan ZHANG, Feng GAO, Yu WANG, Yaohan WANG, Weixin YANG, Hong ZHANG. Research on Online Monitoring of Crack Damage of Wind Turbine Blades Based on Working Modal Analysis [J]. Electric Power, 2023, 56(10): 106-114.
[11]	LI Qian, GOU Luyang, LI Fan, ZHANG Anan, ZHENG Yadi, ZHOU Xipeng. System Flexibility-Oriented Optimized Unit Operation in Wind Farms [J]. Electric Power, 2022, 55(8): 23-30.
[12]	ZHOU Shijia, YANG Guangyuan, PENG Guangqiang, WU Jiyang, XIN Qingming. Fault-Tolerant Control Strategy Based on Multi-Phase Wind Power System [J]. Electric Power, 2022, 55(7): 134-141.
[13]	WANG Yuhang, WANG Wenling, ZHOU Xuhong, WANG Kang, LUO Yintao. Optimization and Response Analysis of Floating Truss Foundation for Offshore Wind Turbine [J]. Electric Power, 2022, 55(5): 21-31.
[14]	SUN Sujuan, HUO Qiantao, SUN Lixin, GUO Liang, WANG Rui, KONG Xiangmei. Mechanism Analysis and Suppression Strategy of Torsional Vibrations of DFIG Shaft System Considering Torque Control of Wind Turbine [J]. Electric Power, 2022, 55(5): 39-46.
[15]	CAI Weizheng, GUO Kunli, LIU Luyu, WU Chaojun. Subsynchronous Oscillation Mitigation Strategy Based on First-Order LADRC for Direct-Drive Wind Turbines [J]. Electric Power, 2022, 55(4): 175-184.