• Corpus ID: 62985907

WaveletFCNN: A Deep Time Series Classification Model for Wind Turbine Blade Icing Detection

  title={WaveletFCNN: A Deep Time Series Classification Model for Wind Turbine Blade Icing Detection},
  author={Binhang Yuan and Chen Wang and Fei Jiang and Mingsheng Long and Philip S. Yu and Yuan Liu},
Wind power, as an alternative to burning fossil fuels, is plentiful and renewable. Data-driven approaches are increasingly popular for inspecting the wind turbine failures. In this paper, we propose a novel classification-based anomaly detection system for icing detection of the wind turbine blades. We effectively combine the deep neural networks and wavelet transformation to identify such failures sequentially across the time. In the training phase, we present a wavelet based fully… 

Figures and Tables from this paper

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

This paper proposes a temporal pattern attention-based bidirectional gated recurrent unit (BiGRU-TPA), which 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.

Temporal Attention Convolutional Neural Network for Estimation of Icing Probability on Wind Turbine Blades

This novel data-driven model introduces a temporal attention module into a convolutional neural network, with the goal of determining the importance of sensors and timesteps and automatically identifying discriminative features from raw sensor data.

Detecting Wind Turbine Blade Icing with a Multiscale Long Short-Term Memory Network

Blade icing is one of the main problems of wind turbines installed in cold climate regions, resulting in increasing power generation loss and maintenance costs. Traditional blade icing detection

Intelligent Icing Detection Model of Wind Turbine Blades Based on SCADA data

This paper explores the possibility that using convolutional neural networks, generative adversarial networks and domain adaption learning to establish intelligent diagnosis frameworks under different training scenarios can achieve more accurate detection on the same wind turbine and more generalized capability on a new wind turbine, compared with other machine learning models and conventional CNNs.

Gated Convolutional Neural Network for Wind Turbine Blade Icing Detection

A GRU-gated Convolutional Neural Network (GCNN) is proposed to better fuse the information between sensors and temporal information for icing detection and the experimental results verify the feasibility and effectiveness of the proposed GCNN.

A Class-Imbalanced Heterogeneous Federated Learning Model for Detecting Icing on Wind Turbine Blades

This article proposes a heterogeneous federated learning (FL) model for wind turbine blade icing detection that addresses the class imbalance problem in the training data and compares it with two state-of-the-art FL models and five well-known class imbalance methods.

SCADA data-driven blade icing detection for wind turbines: an enhanced spatio-temporal feature learning approach

An enhanced spatio-temporal feature learning approach, called multi-task temporal spatial attention network (MT-STAN), consisting of both deep metric learning and classification learning tasks, to further enhance the discriminative ability of the learned representations and improve the performance of fault detection.

Detecting Surface Defects of Wind Tubine Blades Using an Alexnet Deep Learning Algorithm

The point shows that it is feasible to apply the UAV image acquisition and the deep learning classifier to diagnose the damages of wind turbine blades in service automatically.

A Novel Method of Bearing Fault Diagnosis in Time-Frequency Graphs Using InceptionResnet and Deformable Convolution Networks

This work proposes a novel model by combining InceptionResnetV2 with Deformable Convolution Networks, named DeIN, which replaces the basic form of convolution with deformable convolution in specific layers, and achieves highest-precision fault classification results comparing with other state-of-the-art CNN models.

Rolling bearing fault diagnosis based on multiscale texture statistical convolutional neural network

A bearing fault diagnosis algorithm based on multiscale texture statistical convolutional neural network (MSCNN) is proposed and a series of ablation experiments and comparative experiments have verified the effectiveness and superiority of the proposed method.



Learning Deep Representation for Blades Icing Fault Detection of Wind Turbines

The results show that the proposed DNN outperforms the traditional method named normal behavior modeling based on artificial neural network in terms of effectiveness and generalization ability.

Multilevel Wavelet Decomposition Network for Interpretable Time Series Analysis

A wavelet-based neural network structure called multilevel Wavelet Decomposition Network (mWDN) is proposed for building frequency-aware deep learning models for time series analysis and an importance analysis method is proposed to identify those time-series elements and mWDN layers that are crucially important to time seriesAnalysis.

A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data

This paper proposes a Multi-Scale Convolutional Recurrent Encoder-Decoder (MSCRED), to perform anomaly detection and diagnosis in multivariate time series data and demonstrates that MSCRED can outperform state-of-the-art baseline methods.

Fast and Accurate Time Series Classification with WEASEL

On the popular UCR benchmark of 85 TS datasets, WEASEL is more accurate than the best current non-ensemble algorithms at orders-of-magnitude lower classification and training times, and it is almost as accurate as ensemble classifiers, whose computational complexity makes them inapplicable even for mid-size datasets.

Analyzing bearing faults in wind turbines: A data-mining approach

A review of recent advances in wind turbine condition monitoring and fault diagnosis

The state-of-the-art advancement in wind turbine condition monitoring and fault diagnosis for the recent several years is reviewed. Since the existing surveys on wind turbine condition monitoring

Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network

The core idea is to capture the normal patterns of multivariate time series by learning their robust representations with key techniques such as stochastic variable connection and planar normalizing flow, reconstruct input data by the representations, and use the reconstruction probabilities to determine anomalies.

Time Series Classification with Shallow Learning Shepard Interpolation Neural Networks

This paper leverages the novel SINN architecture on a popular benchmark TSC data set achieving state-of-the-art accuracy on several of its test sets while being competitive against the other established algorithms.