基于HO-CNN-BiLSTM-Transformer模型的风机叶片结冰故障诊断

doi:10.16088/j.issn.1001-6600.2024101701

摘要/Abstract

摘要： 针对风力发电机叶片运行监测数据在时序性分析与数据不平衡性研究方面的不足,本文提出一种基于特征工程和HO-CNN-BiLSTM-Transformer(Hippopotamus optimization-CNN-BiLSTM-Transformer)的风机叶片结冰故障检测方法。首先通过借助叶片结冰的机理模型进行特征工程,构建叶片结冰的机理变量;其次,构建CNN-BiLSTM-Transformer检测模型,挖掘监控与数据采集系统(supervisory control and data acquisition, SCADA)数据之间的时序信息,最后利用Hippopotamus optimization(HO)算法优化模型的超参数,提高模型的诊断性能和泛化性。实验结果表明,该检测方法的精确率、召回率、F₁分数分别达到0.983 8、0.990 2、0.987 0,优于其他对比模型和优化算法,可以为风电场运营提供优化维护策略的信息,确保风机在寒冷条件下安全高效运行。

关键词: 风机叶片, 叶片结冰, 故障诊断, 特征工程, 不平衡数据, 河马优化算法, 深度学习

Abstract: To address the shortcomings in time-series analysis and data imbalance research for operational monitoring data of wind turbine blades, this paper proposes a fault detection method for blade icing based on feature engineering and a HO-CNN-BiLSTM-Transformer framework. Firstly, feature engineering is employed by using the blade icing mechanism model to construct mechanism variables for blade icing. Secondly, a CNN-BiLSTM-Transformer detection model is developed to explore the temporal information in supervisory control and data acquisition (SCADA) system data. Finally, the Hippopotamus optimization (HO) algorithm is utilized to optimize the model’s hyperparameters, enhancing its diagnostic performance and generalization ability. Experimental results demonstrate that this detection method achieves precision, recall, and F₁ scores of 0.983 8, 0.990 2, and 0.987 0, respectively, outperforming other comparative models and optimization algorithms. This method provides valuable insights for optimizing maintenance strategies in wind farms, ensuring safe and efficient operation of wind turbines under cold conditions.

Key words: wind turbines, blade icing, fault diagnosis, feature engineering, imbalanced data, hippopotamus optimization algorithm, deep learning

中图分类号: TM315;TP18

韩华彬, 高丙朋, 蔡鑫, 孙凯. 基于HO-CNN-BiLSTM-Transformer模型的风机叶片结冰故障诊断[J]. 广西师范大学学报（自然科学版）, 2025, 43(6): 13-28.

HAN Huabin, GAO Bingpeng, CAI Xin, SUN Kai. Fault Diagnosis of Wind Turbine Blade Icing Based on HO-CNN-BiLSTM-Transformer Model[J]. Journal of Guangxi Normal University(Natural Science Edition), 2025, 43(6): 13-28.

参考文献

[1] ROGA S, BARDHAN S, KUMAR Y, et al. Recent technology and challenges of wind energy generation: a review[J]. Sustainable Energy Technologies and Assessments, 2022, 52: 102239. DOI: 10.1016/j.seta.2022.102239.
[2] 全球发展与碳中和课题组. 引领全球气候治理和推进能源转型的战略思考[J]. 国际经济评论, 2024(5): 39-54, 5.
[3] GAO L Y, DASARI T, HONG J R. Wind farm icing loss forecast pertinent to winter extremes[J]. Sustainable Energy Technologies and Assessments, 2022, 50: 101872. DOI: 10.1016/j.seta.2021.101872.
[4] 杜文杰, 关梦茜, 江源, 等. 新疆风力发电减碳效益全生命周期评估[J]. 生态学报, 2024, 44(8): 3293-3302. DOI: 10.20103/j.stxb.202306301400.
[5] WEI K X, YANG Y, ZUO H Y, et al. A review on ice detection technology and ice elimination technology for wind turbine[J]. Wind Energy, 2020, 23(3): 433-457. DOI: 10.1002/we.2427.
[6] KIM D G, UMESH S, SONG M,et al. A fiber-optic ice detection system for large-scale wind turbine blades[EB/OL]. (2017-09-06)[2024-12-18]. https://www.spiedigitallibrary.org/conference-proceedings-of-spie/10374/2273664/A-fiber-optic-ice-detection-system-for-large-scale-wind/10.1117/12.2273664.short. DOI: 10.1117/12.2273664.
[7] GÓMEZ MUÑOZ C Q, GARCÍA MÁRQUEZ F P, SÁNCHEZ TOMÁS J M. Ice detection using thermal infrared radiometry on wind turbine blades[J]. Measurement, 2016, 93: 157-163. DOI: 10.1016/j.measurement.2016.06.064.
[8] TAUTZ-WEINERT J, WATSON S J. Using SCADA data for wind turbine condition monitoring-a review[J]. IET Renewable Power Generation, 2017, 11(4): 382-394. DOI: 10.1049/iet-rpg.2016.0248.
[9] ZHANG L J, LIU K, WANG Y F, et al. Ice detection model of wind turbine blades based on random forest classifier[J]. Energies, 2018, 11(10): 2548. DOI: 10.3390/en11102548.
[10] 海涛, 范恒, 王楷杰, 等. 基于PSO-SVM算法的风电机组结冰故障诊断[J]. 智慧电力, 2021, 49(4): 1-6, 74. DOI: 10.3969/j.issn.1673-7598.2021.04.002.
[11] TAO T, LIU Y Q, QIAO Y H, et al. Wind turbine blade icing diagnosis using hybrid features and Stacked-XGBoost algorithm[J]. Renewable Energy, 2021, 180: 1004-1013. DOI: 10.1016/j.renene.2021.09.008.
[12] YANG X Y, HUANG X X, GAO X X, et al. Icing diagnosis model for wind turbine blade based on feature optimization and 1D-convolutional neural network[J]. Journal of Renewable and Sustainable Energy, 2022, 14(3): 033303. DOI: 10.1063/5.0078364.
[13] TAO C, TAO T, HE S K, et al. Wind turbine blade icing diagnosis using B-SMOTE-Bi-GRU and RFE combined with icing mechanism[J]. Renewable Energy, 2024, 221: 119741. DOI: 10.1016/j.renene.2023.119741.
[14] 刘俊, 姚邹静, 赵春晖. 基于慢特征分析的风机多模型叶片结冰检测[J]. 控制工程, 2020, 27(11): 1987-1994. DOI: 10.14107/j.cnki.kzgc.20190349.
[15] LI M L, HE X. An accurate detection method for turbine icing issues using LSTM network[J]. IOP Conference Series: Earth and Environmental Science, 2019, 237: 032109. DOI: 10.1088/1755-1315/237/3/032109.
[16] WANG L, HE Y G, ZHOU Y Z, et al. A novel approach to wind turbine blade icing detection with limited sensor data via spatiotemporal attention Siamese network[J]. IEEE Transactions on Industrial Informatics, 2024, 20(6): 8993-9005. DOI: 10.1109/TII.2024.3378775.
[17] YUE R X, JIANG G Q, JIN X H, et al. Spatio-temporal feature alignment transfer learning for cross-turbine blade icing detection of wind turbines[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73: 3507717. DOI: 10.1109/TIM.2024.3350147.
[18] 薛建凯. 一种新型的群智能优化技术的研究与应用: 麻雀搜索算法[D]. 上海: 东华大学, 2020. DOI: 10.27012/d.cnki.gdhuu.2020.000178.
[19] KENNEDY J, EBERHART R. Particle swarm optimization[C] //Proceedings of ICNN′95-International Conference on Neural Networks. Piscataway, NJ: IEEE, 2002: 1942-1948. DOI: 10.1109/ICNN.1995.488968.
[20] MIRJALILI S, MIRJALILI S M, LEWIS A. Grey wolf optimizer[J]. Advances in Engineering Software, 2014, 69: 46-61. DOI: 10.1016/j.advengsoft.2013.12.007.
[21] ABDOLLAHZADEH B, GHAREHCHOPOGH F S, MIRJALILI S. African vultures optimization algorithm: a new nature-inspired metaheuristic algorithm for global optimization problems[J]. Computers & Industrial Engineering, 2021, 158: 107408. DOI: 10.1016/j.cie.2021.107408.
[22] 蒋丽英, 高铭悦, 李贺. 基于SSA-VMD和SDP的双通道CNN轴承故障识别方法[J]. 机电工程, 2025, 42(2): 257-266.
[23] GUO J C, SONG X W, TANG S F, et al. Fault diagnosis of wind turbine blade icing based on feature engineering and the PSO-ConvLSTM-transformer[J]. Ocean Engineering, 2024, 302: 117726. DOI: 10.1016/j.oceaneng.2024.117726.
[24] 栾孝驰, 徐石, 沙云东, 等. 基于GWO-NLM与CEEMDAN的滚动轴承故障诊断方法[J]. 航空动力学报, 2023, 38(5): 1185-1197. DOI: 10.13224/j.cnki.jasp.20210547.
[25] 陈闻鹤, 程龙生, 常志朋, 等. 改进BiLSTM-GRU-DMD的风机叶片结冰故障检测与状态评估模型[J]. 工业工程与管理, 2023, 28(5): 108-118. DOI: 10.19495/j.cnki.1007-5429.2023.05.012.
[26] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780. DOI: 10.1162/neco.1997.9.8.173.
[27] VASWANI A, SHAZEER N, PARMAR N, et al. Attention Is All You Need[EB/OL]. (2017-07-12-06)[2024-12-18]. https://arxiv.org/abs/1706.03762.
[28] LIN T Y, GOYAL P, GIRSHICK R et al. Focal Loss for Dense Object Detection[EB/OL].(2017-08-07)[2024-12-18]. https://arxiv.org/abs/1708.02002.
[29] CHAWLA N V, BOWYER K W, HALL L O, et al. SMOTE: synthetic minority over-sampling technique[J]. Journal of Artificial Intelligence Research, 2002, 16: 321-357. DOI: 10.1613/jair.953.
[30] AMIRI M H, MEHRABI HASHJIN N, MONTAZERI M, et al. Hippopotamus optimization algorithm: a novel nature-inspired optimization algorithm[J]. Scientific Reports, 2024, 14(1): 5032. DOI: 10.1038/s41598-024-54910-3.
[31] MAKKONEN L. Models for the growth of rime, glaze, icicles and wet snow on structures[J]. Philosophical Transactions of the Royal Society of London Series A: Mathematical, Physical and Engineering Sciences, 2000, 358(1776): 2913-2939. DOI: 10.1098/rsta.2000.0690.
[32] RAHIMI E, RABIEE A, AGHAEI J, et al. On the management of wind power intermittency[J]. Renewable and Sustainable Energy Reviews, 2013, 28: 643-653. DOI: 10.1016/j.rser.2013.08.034.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed