Prediction of Wind Turbine Blades Icing Based on CJBM With Imbalanced Data

Supervisory control and data acquisition (SCADA) is widely used in wind farms as an effective data acquisition system for wind turbines (WTs). However, in practical engineering applications, it is difficult for us to have adequate conditions to collect enough WT blade icing data, which leads to data imbalance and uneven distribution in the feature space. Using the classical synthetic minority oversampling technique (SMOTE) to balance the data may increase the overlap of positive and negative samples, or produce some redundant samples without useful information. A center jumping boosting machine (CJBM) method is proposed that combines an improved clustering-based oversampling (γ mini density peaks clustering SMOTE, γMiniDPC-SMOTE) and light gradient boosting machine (LightGBM) for blade icing prediction. First, to solve the problem of imbalanced and uneven distribution of WT data, a <inline-formula> <tex-math notation="LaTeX">${\gamma }$ </tex-math></inline-formula>MiniDPC-SMOTE method is proposed, which divides icing samples into multiple clusters, then increases icing samples, and alleviates uneven distribution in feature space. Second, calculating the intercept distance <inline-formula> <tex-math notation="LaTeX">${d}_{c}$ </tex-math></inline-formula> based on the binary search method and the adaptive selection of DPC parameters based on the step phenomenon of <inline-formula> <tex-math notation="LaTeX">$\gamma $ </tex-math></inline-formula> parameters and verified by <inline-formula> <tex-math notation="LaTeX">$\gamma $ </tex-math></inline-formula>-step of two WT icing data are proposed. Then, for the problem of low operating efficiency of the model under a large amount of imbalanced data, LightGBM is used for model training and icing prediction. Finally, validation was performed on two SCADA datasets. The results showed that the accuracy, precision, recall, F1-measure, and running times increased significantly, proving the superiority of the CJBM.

[1]  Chu Jian,et al.  Imbalanced fault diagnosis based on semi-supervised ensemble learning , 2022, Journal of Intelligent Manufacturing.

[2]  H. Abu-Rub,et al.  Intrusion Detection Method Based on SMOTE Transformation for Smart Grid Cybersecurity , 2022, 2022 3rd International Conference on Smart Grid and Renewable Energy (SGRE).

[3]  Zhenyu Wu,et al.  Imbalanced bearing fault diagnosis under variant working conditions using cost-sensitive deep domain adaptation network , 2022, Expert Syst. Appl..

[4]  Ling Xie,et al.  Prediction of wind turbine blade icing fault based on selective deep ensemble model , 2022, Knowl. Based Syst..

[5]  D. Infield,et al.  Wind turbine blade icing detection with multi-model collaborative monitoring method , 2021 .

[6]  Xuefeng Yan,et al.  Imbalanced Classification Based on Minority Clustering Synthetic Minority Oversampling Technique With Wind Turbine Fault Detection Application , 2021, IEEE Transactions on Industrial Informatics.

[7]  Xiufeng Liu,et al.  A Novel Deep Class-Imbalanced Semisupervised Model for Wind Turbine Blade Icing Detection , 2021, IEEE Transactions on Neural Networks and Learning Systems.

[8]  Nitesh V. Chawla,et al.  DeepSMOTE: Fusing Deep Learning and SMOTE for Imbalanced Data , 2021, IEEE Transactions on Neural Networks and Learning Systems.

[9]  Shuilong He,et al.  Intelligent fault diagnosis of machines with small & imbalanced data: A state-of-the-art review and possible extensions. , 2021, ISA transactions.

[10]  Wei Qiao,et al.  Condition Monitoring of Wind Turbine Generators Using SCADA Data Analysis , 2021, IEEE Transactions on Sustainable Energy.

[11]  Jia Li,et al.  Blades icing identification model of wind turbines based on SCADA data , 2020 .

[12]  Jipu Li,et al.  A Robust Weight-Shared Capsule Network for Intelligent Machinery Fault Diagnosis , 2020, IEEE Transactions on Industrial Informatics.

[13]  Yaning Liu,et al.  Prediction of protein crotonylation sites through LightGBM classifier based on SMOTE and elastic net. , 2020, Analytical biochemistry.

[14]  Xinpan Yuan,et al.  Research on Fault Diagnosis of Wind Power Generator Blade Based on SC-SMOTE and kNN , 2020, J. Inf. Process. Syst..

[15]  Xu Li,et al.  Domain generalization in rotating machinery fault diagnostics using deep neural networks , 2020, Neurocomputing.

[16]  Lei Deng,et al.  Condition monitoring of wind turbines based on spatio-temporal fusion of SCADA data by convolutional neural networks and gated recurrent units , 2020 .

[17]  Yixiong Liang,et al.  Learning to autofocus based on Gradient Boosting Machine for optical microscopy , 2019 .

[18]  Wei Su,et al.  Improving Classification of Imbalanced Datasets Based on KM++ SMOTE Algorithm , 2019, 2019 2nd International Conference on Safety Produce Informatization (IICSPI).

[19]  Guanghua Xu,et al.  Learning deep representation of imbalanced SCADA data for fault detection of wind turbines , 2019, Measurement.

[20]  Rui Liu,et al.  Self-adaptive cost weights-based support vector machine cost-sensitive ensemble for imbalanced data classification , 2019, Inf. Sci..

[21]  Hong Wang,et al.  Shared-nearest-neighbor-based clustering by fast search and find of density peaks , 2018, Inf. Sci..

[22]  Philip S. Yu,et al.  An Introduction to Image Synthesis with Generative Adversarial Nets , 2018, ArXiv.

[23]  Dong Yue,et al.  Prediction of wind turbine blades icing based on MBK-SMOTE and random forest in imbalanced data set , 2017, 2017 IEEE Conference on Energy Internet and Energy System Integration (EI2).

[24]  Vincent Dumoulin,et al.  Generative Adversarial Networks: An Overview , 2017, 1710.07035.

[25]  Chi-Hyuck Jun,et al.  Instance categorization by support vector machines to adjust weights in AdaBoost for imbalanced data classification , 2017, Inf. Sci..

[26]  Sean Hughes,et al.  Clustering by Fast Search and Find of Density Peaks , 2016 .

[27]  Ole Winther,et al.  Autoencoding beyond pixels using a learned similarity metric , 2015, ICML.

[28]  Junlong Fang,et al.  A SCADA-Data-Driven Condition Monitoring Method of Wind Turbine Generators , 2022, IEEE Access.

[29]  Xudong Lai,et al.  C-SASO: A Clustering-Based Size-Adaptive Safer Oversampling Technique for Imbalanced SAR Ship Classification , 2022, IEEE Transactions on Geoscience and Remote Sensing.

[30]  Jipu Li,et al.  Deep Adversarial Capsule Network for Compound Fault Diagnosis of Machinery Toward Multidomain Generalization Task , 2021, IEEE Transactions on Instrumentation and Measurement.

[31]  Islam Elgedawy,et al.  AB-SMOTE: An Affinitive Borderline SMOTE Approach for Imbalanced Data Binary Classification , 2020 .