网络首发:2026-06-04,
纸质出版:2026
移动端阅览
李练兵, 雒威, 程晴, 等. 基于BIRCH-MSSCN模型的风电叶片结冰故障预警[J]. 太阳能学报, 2026,47(5):341-349.
李练兵, 雒威, 程晴, et al. 基于BIRCH-MSSCN模型的风电叶片结冰故障预警[J]. 2026, 47(5): 341-349.
李练兵, 雒威, 程晴, 等. 基于BIRCH-MSSCN模型的风电叶片结冰故障预警[J]. 太阳能学报, 2026,47(5):341-349. DOI: 10.19912/j.0254-0096.tynxb.2025-0010.
李练兵, 雒威, 程晴, et al. 基于BIRCH-MSSCN模型的风电叶片结冰故障预警[J]. 2026, 47(5): 341-349. DOI: 10.19912/j.0254-0096.tynxb.2025-0010.
为提前预警风电叶片的结冰故障
提出一种基于平衡迭代缩减聚类(BIRCH)、梅尔频谱图、暹罗网络和卷积基础的多尺度注意力机制(CBAM)的BIRCH-MSSCN模型。该模型通过对风电叶片结冰前状态的标记、正常数据的下采样、暹罗网络的相似度度量以及CBAM注意力机制对特征的选择
实现结冰故障的提前预警。对比分析结果表明
在保证较低计算量的同时
该模型能够早在42 min前实现较为准确的结冰故障预警。该模型为风电机组的高效、稳定运行提供了更为可靠的预警信息
具有重要的应用价值。
To provide early warnings for blade icing faults
a BIRCH-MSSCN model is proposed
based on Balanced Iterative Reducing and Clustering using Hierarchies (BIRCH)
Mel spectrograms
Siamese networks
and the Convolutional-based Multi-scale Attention Mechanism (CBAM). The model achieves early fault warnings for blade icing through labeling pre-icing states
down-sampling normal data
measuring similarity using the Siamese network
and selecting features with the CBAM attention mechanism. Comparative analysis results indicate that while maintaining low computational costs
the model can accurately predict icing faults up to 42 minutes in advance. This model provides more reliable early warning information for the efficient and stable operation of wind turbines
showcasing significant application value.
王颉, 刘兴杰, 梁英, 等. 一种基于MGWO-Informer的超短期风电功率预测方法[J]. 太阳能学报, 2024, 45(11): 477-485.
佘应森, 李鹏, 梁俊宇, 等. 基于多尺度排列熵和极限学习机的风机叶片覆冰故障检测方法[J]. 中国安全生产科学技术, 2022, 18(12): 19-25.
GUO P, INFIELD D.Wind turbine blade icing detection with multi-model collaborative monitoring method[J]. Renewable energy, 2021, 179: 1098-1105.
WANG L, HE Y G, HE Y L, et al.Wind turbine blade icing risk assessment considering power output predictions based on SCSO-IFCM clustering algorithm[J]. Renewable energy, 2024, 223: 119969.
李少丽. 基于机器学习的风力机叶片结冰故障诊断模型研究[D]. 西安: 西安理工大学, 2023.
张丹峰. 基于LightGBM, XGBoost, ERT混合模型的风机叶片结冰预测研究[D]. 上海: 上海师范大学, 2018.
王非凡. 基于数据驱动的风机叶片结冰检测方法研究[D]. 株洲: 湖南工业大学, 2023.
杨莹. 基于残差神经网络的风机叶片覆冰预测方法研究[D]. 阜新: 辽宁工程技术大学, 2021.
汤占军, 史小兵, 肖遥, 等. 基于深度学习模型的风机叶片结冰故障诊断[J]. 噪声与振动控制, 2023, 43(4): 96-103.
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.
姜娜, 严蜜, 李柠. 基于时序上采样卷积神经网络的风机叶片结冰检测[J]. 控制与决策, 2022, 37(8): 2017-2025.
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.
沈学利, 杨莹, 秦鑫宇, 等. 基于残差神经网络的风机叶片结冰故障诊断[J]. 噪声与振动控制, 2022, 42(1): 79-87.
BAI X J, TAO T, GAO L Y, et al.Wind turbine blade icing diagnosis using RFECV-TSVM pseudo-sample processing[J]. Renewable energy, 2023, 211: 412-419.
TONG R N, LI P, LANG X, et al.A novel adaptive weighted kernel extreme learning machine algorithm and its application in wind turbine blade icing fault detection[J]. Measurement, 2021, 185: 110009.
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.
孙坚, 杨宇兵. 基于特征提取和最优加权集成策略的风机叶片结冰故障检测[J]. 科学技术与工程, 2024, 24(11): 4501-4509.
XING Z X, GUO S S, CHEN M Y, et al.Icing diagnosis method of wind turbine blade based on mechanism and data driving[J]. Renewable energy, 2025, 255: 123820.
张晓珂, 张辉, 戴小然, 等. 基于层次聚类和BILSTM的光伏短期功率预测模型[J]. 智慧电力, 2024, 52(9): 41-48.
HONG G, SUH D.Mel Spectrogram-based advanced deep temporal clustering model with unsupervised data for fault diagnosis[J]. Expert systems with applications, 2023, 217: 119551.
ZHANG X W, XUAN C Z, MA Y H, et al.High-similarity sheep face recognition method based on a Siamese network with fewer training samples[J]. Computers and electronics in agriculture, 2024, 225: 109295.
赵陆阳, 刘长良, 刘卫亮, 等. 基于CBAM-DSC-UNet模型的时空风速预测算法[J]. 太阳能学报, 2024, 45(10): 497-505.
0
浏览量
14
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621