为实现对风电齿轮箱健康评估、发现齿轮箱部件早期故障,提出一种基于条件卷积自编码高斯混合模型的风电齿轮箱健康评估网络。在编码器部分,同时对传感器信息和时序信息进行编码解码并提取压缩特征,根据高斯混合模型设计基于信号本身概率分布的能量设计评价指标进行健康评估。根据核密度估计确定阈值,并利用某真实风电场数据进行实验,验证方法的有效性。
Abstract
To achieve health evaluation and detect wary faults of wind turbine gearboxes, a new conditional convolutional autoencoding Gaussian mixture model is proposed. The sensor information and temporal information are first encoded and decoded at the same time, and the compressed features are extracted. Then, the extracted features are input to the Gaussian mixture model to calculate the energy index based on the probability distribution as the health index for health assessment. Finally, the threshold is determined using the kernel density estimation algorithm. The effectiveness of the proposed method is verified with the supervisory control and data acquisition（SCADA） data from a real wind farm.
关键词
风电机组 /
自编码网络 /
健康评估 /
高斯混合模型 /
数据采集与监控系统
Key words
wind turbines /
conditional autoencoding network /
health assessment /
Gaussian mixture model /
SCADA
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Global wind report 2017: annual market update[R]. report 2017: annual market update[R]. Global Wind Energy Council, 2018.
[2] 金晓航, 孙毅, 单继宏, 等. 风力发电机组故障诊断与预测技术研究综述[J]. 仪器仪表学报, 2017, 38(5): 1041-1053.
JIN X H, SUN Y, SHAN J H, et al.Fault diagnosis and prognosis for wind turbines: an overview[J]. Chinese journal of scientific instrument, 2017, 38(5): 1041-1053.
[3] JIN X H, XU Z W, QIAO W.Condition monitoring of wind turbine generators using SCADA data analysis[J]. IEEE transactions on sustainable energy, 2021, 12: 202-210.
[4] 何群, 尹飞飞, 武鑫, 等. 基于长短期记忆网络的风电机组齿轮箱故障预测[J]. 计量学报, 2020, 41(10): 1284-1290.
HE Q, YIN F F, WU X, et al.Fault prediction of wind turbine gearbox based on long short-term memory network[J]. Acta metrologica sinica, 2020, 41(10): 1284-1290.
[5] 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, 2864.
[6] 金晓航, 许壮伟, 孙毅, 等. 基于SCADA数据分析和稀疏自编码神经网络的风电机组在线运行状态监测[J]. 太阳能学报, 2021, 42(6): 321-328.
JIN X H, XU Z W, SUN Y, et al.Online condition monitoring for wind turbines based on scada data analysis and sparse auto-encoder neural network[J]. Acta energiae solaris sinica, 2021, 42(6): 321-328.
[7] 赵洪山, 刘辉海. 基于深度学习网络的风电机组主轴承故障检测[J]. 太阳能学报, 2018, 39(3): 588-595.
ZHAO H S, LIU H H.Fault detection of wind turbine main bear based on deep learning network[J]. Acta energiae solaris sinica, 2018, 39(3): 588-595.
[8] 褚景春, 王飞, 汪杨, 等. 基于故障树和概率神经网络的风电机组故障诊断方法[J]. 太阳能学报, 2018, 39(10): 2901-2907.
CHU J C, WANG F, WANG Y, et al.Fault diagnosis method of wind turbine based on fault tree and probabilistic neural network[J]. Acta energiae solaris sinica, 2018, 39(10): 2901-2907.
[9] 任建亭, 汤宝平, 雍彬, 等. 基于深度变分自编码网络融合SCADA数据的风电齿轮箱故障预警[J]. 太阳能学报, 2021, 42(4): 403-408.
REN J T, TANG B P, YONG B, et al.Wind turbine gearbox fault warning based on depth variational autoencoders network fusion scada data[J]. Acta energiae solaris sinica, 2021, 42(4): 403-408.
[10] QI S. Deep autoencoding Gaussian mixture model for unsupervised anomaly detection[EB/OL].2018-2015,https://sites.cs.ucsb.edu/~bzong/doc/iclr18-dagmm.pdf.
[11] YANG L X, ZHANG Z J.A Conditional convolutional autoencoder-based method for monitoring wind turbine blade breakages[J]. IEEE transactions on industrial informatics, 2020, 17(9): 6390-6398.
[12] JIANG G Q, XIE P, HE H B, et al.Wind turbine fault detection using a denoising autoencoder with temporal information[J]. IEEE/ASME transactions on mechatronics, 2018, 23(1): 89-100.
基金
河北省自然科学基金（F2021203009）; 国家自然科学基金（62273299; 61803329）; 中央引导地方科技发展资金（216Z2101G）; 河北省重点研发计划（19214306D）
PDF(28052 KB)
