为在不平衡数据上得到准确分类的故障诊断模型,提出将SMOTETomek过采样方法与领域自适应迁移学习相结合的故障诊断算法框架。首先利用滑动窗口采样技术将数据采样成二维时空窗口数据,然后执行SMOTETomek过采样操作,可保留并丰富完整的时序故障特征。针对过采样算法引入噪声信息的问题,引入领域自适应迁移学习算法在原始数据与过采样后的数据之间提取不变特征,使得过采样算法的引入的噪声信息可被过滤掉。在中国某实际风电场的实验结果显示,所提方法可在高度不平衡的数据上完成模型训练,准确识别各类型故障并精确辨识故障过程对应的时间窗口,诊断性能显著优于基于先前用于应对数据不平衡所普遍使用的过采样方法得到的模型。
Abstract
The installed capacity of wind power has grown significantly in recent years, and wind power accounts for an increasing proportion of the total generation capacity, while its fault process can pose a greater threat to the safety and stability of grid operation, so it is important to accurately diagnose and predict the faults occurring on wind turbines. SCADA data-driven fault diagnosis algorithms have been widely researched and applied, however, the high imbalance in the distribution of the number of SCADA normal and fault data poses a major challenge for establishing a high-performance fault diagnosis model. In order to obtain a fault diagnosis model that can accurately give fault categories on unbalanced data, this paper proposes a fault diagnosis algorithm framework that combines SMOTETomek oversampling method with domain adaptive migration learning. The data is first sampled into two-dimensional temporal window data using sliding window sampling technique, and then SMOTETomek oversampling operation is executed on this basis to retain and enrich the complete temporal fault features. To address the problem of noise information introduced by the oversampling algorithm, this paper introduces a domain adaptive migration learning algorithm to extract invariant features between the original data and the oversampled data, so that the noise information introduced by the oversampling algorithm can be filtered out. Experimental results in a real wind farm in China show that the proposed method can complete model training on highly unbalanced data, accurately identify each type of fault and accurately give the time window of the fault process, and the diagnostic performance is significantly better than that of the model obtained based on the previously commonly used oversampling method.
关键词
风电机组 /
故障诊断 /
监督控制和数据采集系统 /
深度学习 /
SMOTE过采样方法 /
领域自适应
Key words
wind turbines /
fault diagnosis /
SCADA /
deep learning /
SMOTE oversampling method /
domain adaptation
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] G W E Council. Global wind report 2021. No. 5[R]. 2021.
[2] ZOU L, LI Y, XU F Y.An adversarial denoising convolutional neural network for fault diagnosis of rotating machinery under noisy environment and limited sample size case[J]. Neurocomputing, 2020, 407: 105-120.
[3] MARUGÁN A P, MÁRQUEZ F P G, PEREZ J M P, et al. A survey of artificial neural network in wind energy systems[J]. Applied energy, 2018, 228: 1822-1836.
[4] ZHAO X L, JIA M P.A new local-global deep neural network and its application in rotating machinery fault diagnosis[J]. Neurocomputing, 2019, 366(C): 215-233.
[5] JIA F, LEI Y G, LIN J, et al.Deep neural networks: a promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data[J]. Mechanical systems and signal processing, 2016, 72: 303-315.
[6] PANG Y H, HE Q, JIANG G Q, et al.Spatio-temporal fusion neural network for multi-class fault diagnosis of wind turbines based on SCADA data[J]. Renewable energy, 2020, 161: 510-524.
[7] WEN L, LI X Y, GAO L, et al.A new convolutional neural network-based data-driven fault diagnosis method[J]. IEEE transactions on industrial electronics, 2018, 65(7): 5990-5998.
[8] 苏向敬, 山衍浩, 周汶鑫, 等. 基于GRU和注意力机制的海上风机齿轮箱状态监测[J]. 电力系统保护与控制, 2021, 49(24): 141-149.
SU X J, SHAN Y H, ZHOU W X, et al.GRU and attention mechanism-based condition monitoring of an offshore wind turbine gearbox[J]. Power system protection and control, 2021, 49(24): 141-149.
[9] 王思华, 王恬, 周丽君, 等. 基于批标准化的堆叠自编码网络风电机组变桨系统故障诊断[J]. 太阳能学报, 2022, 43(2): 394-401.
WANG S H, WANG T, ZHOU L J, et al.Fault diagnosis of pitch system of wind turbine based on standardized stacked autoencoder network[J]. Acta energiae solaris sinica, 2022, 43(2): 394-401.
[10] SHAO H D, JIANG H K, ZHANG H Z, et al.Rolling bearing fault feature learning using improved convolutional deep belief network with compressed sensing[J]. Mechanical systems and signal processing, 2018, 100: 743-765.
[11] 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.
[12] 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.
[13] 滕伟, 丁显, 史秉帅, 等. 基于WGAN-GP的风电机组传动链故障诊断[J]. 电力系统自动化, 2021, 45(22): 167-173.
TENG W, DING X, SHI B S, et al.Fault diagnosis of wind turbine drivetrain based on Wasserstein generative adversarial network-gradient penalty[J]. Automation of electric power systems, 2021, 45(22): 167-173.
[14] LI Y T, JIANG W B, ZHANG G Y, et al.Wind turbine fault diagnosis based on transfer learning and convolutional autoencoder with small-scale data[J]. Renewable energy, 2021, 171: 103-115.
[15] 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(1): 202-210.
[16] WEI L, QIAN Z, ZAREIPOUR H.Wind turbine pitch system condition monitoring and fault detection based on optimized relevance vector machine regression[J]. IEEE transactions on sustainable energy, 2020, 11(4): 2326-2336.
[17] WANG L, ZHANG Z J, XU J, et al.Wind turbine blade breakage monitoring with deep autoencoders[J]. IEEE transactions on smart grid, 2018, 9(4): 2824-2833.
[18] CHEN H S, LIU H, CHU X N, et al.Anomaly detection and critical SCADA parameters identification for wind turbines based on LSTM-AE neural network[J]. Renewable energy, 2021, 172: 829-840.
[19] LIN T Y, GOYAL P, GIRSHICK R, et al.Focal loss for dense object detection[J]. IEEE transactions on pattern analysis and machine intelligence, 2020, 42(2): 318-327.
[20] HE Q, PANG Y H, JIANG G Q, et al.A spatio-temporal multiscale neural network approach for wind turbine fault diagnosis with imbalanced SCADA data[J]. IEEE transactions on industrial informatics, 2021, 17(10): 6875-6884.
[21] YI H K, JIANG Q C, YAN X F, et al.Imbalanced classification based on minority clustering synthetic minority oversampling technique with wind turbine fault detection application[J]. IEEE transactions on industrial informatics, 2021, 17(9): 5867-5875.
[22] DING S Y, WANG Z J, ZHANG J, et al.A PCC-Ensemble-TCN model for wind turbine icing detection using class-imbalanced and label-missing SCADA data[J]. International journal of distributed sensor networks, 2021, 17(11): 155014772110577.
[23] LIU J H, QU F M, HONG X W, et al.A small-sample wind turbine fault detection method with synthetic fault data using generative adversarial nets[J]. IEEE transactions on industrial informatics, 2019, 15(7): 3877-3888.
[24] 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.
[25] WANG Z, WU C H, ZHENG K F, et al.SMOTETomek-based resampling for personality recognition[J]. IEEE access, 2019, 7: 129678-129689.
[26] BAI S, KOLTER J Z, KOLTUN V.An empirical evaluation of generic convolutional and recurrent networks for sequence modeling[M/OL]. http://arxiv.org/abs/1803.01271.
[27] HE K M, ZHANG X Y, REN S Q, et al.Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA, 2016: 770-778.
[28] SUN B C, FENG J S, SAENKO K.Return of frustratingly easy domain adaptation[C]//Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence. Phoenix, Arizona, USA, 2016: 2058-2065.
基金
国家自然科学基金（51777121）; 2021年辽宁省揭榜挂帅科技攻关专项（2021JH/10400009）
PDF(1517 KB)
