Prediction of wind turbine blades icing based on feature Selection and 1D-CNN-SBiGRU

Li, Yuanyuan; Hou, Lingyu; Tang, Ming; Sun, Qichun; Chen, Jiahang; Song, Wanqing; Yao, Wei; Cao, Le

doi:10.1007/s11042-021-11700-7

Cited by 24 publications

(6 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning, as a data-driven approach, can overcome these disadvantages. Li et al constructed the hybrid model combined with the 1D-CNN and BiGRU to predict blade icing [23]. A multilevel convolutional RNN was recommended for icing diagnosis using hybrid features by Tian et al [24].…”

Section: Wind Turbine Blade Icing Detectionmentioning

confidence: 99%

Wind turbine blade icing detection using a novel bidirectional gated recurrent unit with temporal pattern attention and improved coot optimization algorithm

Wen-he¹,

Cheng²,

Chang³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

Blade icing detection is significant for the safe operation of wind turbines and for reducing power generation losses. Traditional additional sensors methods for monitoring are limited due to expensive costs and damaging the original mechanical structure. The deep learning model has good performance for icing detection. This paper proposes a temporal pattern attention-based bidirectional gated recurrent unit (BiGRU-TPA). This novel deep learning framework incorporates the TPA module into the BiGRU module to determine the relationship between multiple sensors at different time steps, extracting features from the raw sensor data for discrimination. Meanwhile, its hyperparameters are optimized using an improved coot optimization algorithm (ICOOT) to enhance its recognition performance further. To alleviate the severe imbalance in the dataset, adaptive synthesis (ADASYN) and sliding window upsampling method (SWU) are imported to oversample and sliding window the icing state as a minority class. ICOOT- BiGRU-TPA illustrates its advantages compared with other state-of-art baseline methods, widely used optimization algorithms, and attention mechanisms applied to the real icing dataset. The ablation study and sensitivity analysis also demonstrate the performance of crucial components in the proposed model. Furthermore, its feasibility and practicality are demonstrated by real-time icing detection.

show abstract

Section: Wind Turbine Blade Icing Detectionmentioning

confidence: 99%

Wind turbine blade icing detection using a novel bidirectional gated recurrent unit with temporal pattern attention and improved coot optimization algorithm

Wen-he¹,

Cheng²,

Chang³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…In recent years, deep learning methods for solving TSC tasks have become popular. As a data-driven approach, deep learning can overcome the drawback of manual feature extraction and selection which requires human expertise and efforts, such as Stacked BiGRU [9], CNN-LSTM [16], and Conv-RNN [17]. These pieces of literature concentrate on the structural design of the models for wind turbine blade icing diagnosis.…”

Section: A Wind Turbine Blade Icing Diagnosismentioning

confidence: 99%

“…The deep learning method does not require feature extraction relying on expert experience. It can automatically extract the features and try to model high-level representations using the SCADA data, such as bidirectional gated recurrent unit (BiGRU) [9], and temporal attention convolutional neural network (CNN) [10]. Its performance was more accurate than the shallow machine learning method.…”

mentioning

confidence: 99%

Wind Turbine Blade Icing Diagnosis Using Convolutional LSTM-GRU With Improved African Vultures Optimization

Wen-he

Zhou

Cheng

et al. 2022

IEEE Open J. Instrum. Meas.

View full text Add to dashboard Cite

Wind farms are usually located in plateau mountains and northern coastal areas, bringing a high probability of blade icing. Blade icing even leads to blade cracks and turbine collapse. Traditional methods of blade icing diagnosis increase operating costs and have the potential risk of damaging the original mechanical structure. A data-driven model based on a novel convolutional recurrent neural network is proposed in this paper. The method can effectively extract hidden features for accurate icing diagnosis. The hyperparameters of the proposed model are optimized by the improved African Vultures optimization algorithm (IAVOA). To alleviate the critical data imbalance, the Adaptive Synthetic (ADASYN) is used to oversample the minority classes of icing status. In comparison to the state-of-art classification methods, the proposed method illustrates the outstanding effectiveness in blade icing diagnosis using the sensor data from Supervisory Control and Data Acquisition (SCADA) systems. The effectiveness analysis of variables, ablation study, and sensitivity analysis validate the performance of the proposed method.

show abstract

“…Second, a data imbalance can significantly affect the convergence performance (correctness and speed) of intelligent fault diagnosis models [10]. Approaches have been proposed to address these issues at different levels: the data level [12][13][14][15], model level [16][17][18], and optimization level [19][20][21]. At the data level, data augmentation techniques enable the expansion of scarce data and the balance of imbalanced data [12][13][14][15].…”

Section: Introductionmentioning

confidence: 99%

Generation of high-dimensional vibration signal and its application in fault diagnosis

Ren,

Gao,

Zhu

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Imperfect data, such as data scarcity and imbalance, have a negative impact on intelligent fault diagnosis. Generative adversarial networks (GANs) have proven to be a potential method for augmenting data. However, the overall quality of data generated by GANs still requires improvement. In this study, a multiscale feature-fusion GAN was proposed for generating high-dimensional signals. A strategy that generates signals with dimensionality higher than the desired dimensionality was proposed. The generated signals were resampled to improve the phase diversity of the generated signals. To enhance the feature extraction capability of the GAN for high-dimensional signals, a multiscale feature extraction structure was designed. The integration of multiscale feature extraction and fusion was achieved without a significant increase in the computational burden. To enhance the amplitude diversity of the generated signals, a reconstruction network was designed that directly constrained the spatial distribution of the generated signals. Experimental results show that the model has advantages in terms of the similarity and diversity of the generated signals. The effectiveness of the model in fault diagnosis was verified using two motor datasets, where the fault diagnosis model using the sample set augmented by the proposed model obtained a 36.32% improvement in accuracy compared with using the original sample set. In addition, in comparison experiments, the model achieved a higher diagnostic accuracy improvement of 28.87% compared to four other published models.

show abstract

Prediction of wind turbine blades icing based on feature Selection and 1D-CNN-SBiGRU

Cited by 24 publications

References 26 publications

Wind turbine blade icing detection using a novel bidirectional gated recurrent unit with temporal pattern attention and improved coot optimization algorithm

Wind turbine blade icing detection using a novel bidirectional gated recurrent unit with temporal pattern attention and improved coot optimization algorithm

Wind Turbine Blade Icing Diagnosis Using Convolutional LSTM-GRU With Improved African Vultures Optimization

Generation of high-dimensional vibration signal and its application in fault diagnosis

Contact Info

Product

Resources

About