ANOMALY DETECTION METHOD FOR WIND TURBINE TOWER BASED ON T-SNE MULTI-FEATURE FUSION

Zhang Wentao; Qin Xianrong; Yang Qiong; Hou Bingning; Zhang Qing

doi:10.19912/j.0254-0096.tynxb.2024-0811

PDF(6095 KB)

Acta Energiae Solaris Sinica ›› 2025, Vol. 46 ›› Issue (9) : 91-97. DOI: 10.19912/j.0254-0096.tynxb.2024-0811

ANOMALY DETECTION METHOD FOR WIND TURBINE TOWER BASED ON T-SNE MULTI-FEATURE FUSION

Zhang Wentao, Qin Xianrong, Yang Qiong, Hou Bingning, Zhang Qing

Author information +

History +

Abstract

An anomaly detection method based on multi-feature fusion and t-distributed stochastic neighbor embedding （t-SNE） is proposed to identify the abnormal state of wind turbine towers based on monitored structural response signals. The method involves evaluating the time domain, frequency domain, and time-frequency domain statistical indicators of the monitored structure response signals to extract high-dimensional multi-feature vectors. The t-SNE algorithm is used for dimensionality reduction and fusion to obtain a visual representation of the data in a low-dimensional space. The K-means clustering algorithm is employed to analyze the data state, and a quantitative analysis of the anomaly index is then constructed to realize structural anomaly detection. The proposed method has been successfully applied to engineering applications of wind turbine towers during typhoon and earthquake periods, demonstrating its effectiveness in detecting abnormal structural responses caused by environmental changes.

Key words

wind turbines / anomaly detection / data visualization / feature fusion / t-distributed stochastic neighbor embedding （t-SNE）

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Zhang Wentao, Qin Xianrong, Yang Qiong, Hou Bingning, Zhang Qing. ANOMALY DETECTION METHOD FOR WIND TURBINE TOWER BASED ON T-SNE MULTI-FEATURE FUSION[J]. Acta Energiae Solaris Sinica. 2025, 46(9): 91-97 https://doi.org/10.19912/j.0254-0096.tynxb.2024-0811

References

[1] 陈中培, 邱宇舟, 钱进, 等. 海上风电装备产业基地生产设施设计[J]. 船舶与海洋工程, 2024, 40(1): 20-25.
CHEN Z P, QIU Y Z, QIAN J, et al.Design of production facilities for offshore wind power equipment industry base[J]. Naval architecture and ocean engineering, 2024, 40(1): 20-25.
[2] 李万润, 郭赛聪, 张广隶, 等. 考虑风速风向联合概率分布的风电塔筒结构风致疲劳寿命评估[J]. 太阳能学报, 2022, 43(5): 278-286.
LI W R, GUO S C, ZHANG G L, et al.Assessment on wind-induced fatigue life of wind turbine tower considering joint probability distribution of wind speed and wind direction[J]. Acta energiae solaris sinica, 2022, 43(5): 278-286.
[3] 章培, 唐友刚, 李焱, 等. 基于多目标遗传算法的海上铰接式风力机塔架结构参数优化[J]. 太阳能学报, 2023, 44(8): 460-466.
ZHANG P, TANG Y G, LI Y, et al.Tower structure parameter optimization of offshore articulated wind turbine based on Muti-objective genetic algorithm[J]. Acta energiae solaris sinica, 2023, 44(8): 460-466.
[4] 李学平, 刘伟江, 周民强, 等. 风力发电机组塔架振动异常分析与优化[J]. 噪声与振动控制, 2020, 40(1): 69-73.
LI X P, LIU W J, ZHOU M Q, et al.Abnormal vibration analysis and optimization of wind turbine towers[J]. Noise and vibration control, 2020, 40(1): 69-73.
[5] 苏连成, 朱娇娇, 郭高鑫, 等. 基于LSTM的塔架振动状态监测研究[J]. 燕山大学学报, 2022, 46(5): 437-445.
SU L C, ZHU J J, GUO G X, et al.Research on monitoring of tower vibration condition based on LSTM[J]. Journal of Yanshan University, 2022, 46(5): 437-445.
[6] CASTELLANI F, GARIBALDI L, DAGA A P, et al.Diagnosis of faulty wind turbine bearings using tower vibration measurements[J]. Energies, 2020, 13(6): 1474.
[7] 殷秀丽, 谢丽蓉, 杨欢, 等. 特征选择与t-SNE结合的滚动轴承故障诊断[J]. 机械科学与技术, 2023, 42(11): 1784-1793.
YIN X L, XIE L R, YANG H, et al.Rolling bearing fault diagnosis combined feature selection with t-distributed stochastic neighbor embedding[J]. Mechanical science and technology for aerospace engineering, 2023, 42(11): 1784-1793.
[8] 郑坚钦, 杜渐, 梁永图, 等. 基于CAE-TSNE的成品油管道运行工况识别[J]. 石油科学通报, 2024, 9(1): 148-157.
ZHENG J Q, DU J, LIANG Y T, et al.Research on pipeline operating condition recognition based on CAE-TSNE[J]. Petroleum science bulletin, 2024, 9(1): 148-157.
[9] 曹康栖, 李灿. 基于WPD-tSNE-SVM方法的电站机组主轴故障诊断分析[J]. 机械制造与自动化, 2023, 52(6): 226-228.
CAO K X, LI C.Fault diagnosis analysis of power station spindle based on WPD-tSNE-SVM model[J]. Machine building & automation, 2023, 52(6): 226-228.
[10] 王莉娟. 时域-频域-MEWMA算法在风机发电机轴承监测中的应用[J]. 无线互联科技, 2022, 19(15): 86-88, 136.
WANG L J.Application of time-frequency-MEWMA algorithm in bearing monitoring of wind turbine generator[J]. Wireless Internet technology, 2022, 19(15): 86-88, 136.
[11] 林水泉. 频域分析在风力机轴承故障诊断上的应用[J]. 广东化工, 2020, 47(23): 104-107.
LIN S Q.Application of frequency domain analysis in fault diagnosis of fan bearing[J]. Guangdong chemical industry, 2020, 47(23): 104-107.
[12] 常凯, 许敬能, 吴启东, 等. 基于小波包分解与半监督生成对抗网络的轴流通风机故障诊断[J]. 电力科学与工程, 2023, 39(11): 22-31.
CHANG K, XU J N, WU Q D, et al.Fault diagnosis of axial fan based on wavelet packet decomposition and semi-supervised generation adversarial network[J]. Electric power science and engineering, 2023, 39(11): 22-31.
[13] ANOWAR F, SADAOUI S, SELIM B.Conceptual and empirical comparison of dimensionality reduction algorithms (PCA, KPCA, LDA, MDS, SVD, LLE, ISOMAP, LE, ICA, t-SNE)[J]. Computer science review, 2021, 40: 100378.
[14] IKOTUN A M, EZUGWU A E, ABUALIGAH L, et al.K-means clustering algorithms: a comprehensive review, variants analysis, and advances in the era of big data[J]. Information sciences, 2023, 622: 178-210.
[15] 黄雨薇, 彭道刚, 姚峻, 等. 基于SSA和K均值的TD-BP神经网络超短期光伏功率预测[J]. 太阳能学报, 2021, 42(4): 229-238.
HUANG Y W, PENG D G, YAO J, et al.Ultra-short-term photovoltaic power forecast of TD-BP neural network based on SSA and K-means[J]. Acta energiae solaris sinica, 2021, 42(4): 229-238.
[16] 中国地震台网. 2022年9月18日台湾花莲县6.9级地震信息[EB/OL].(2022-09-18)[2024-04-16]. https://www.ceic.ac.cn.
China Earthquake Networks Center. M 6.9 Earthquake in Hualien County, Taiwan (September 18, 2022)[EB/OL]. https://www.ceic.ac.cn.