• 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.

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.

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.

Wavelet Integrated CNNs for Noise-Robust Image Classification

WaveCNets, the wavelet integrated versions of VGG, ResNets, and DenseNet, achieve higher accuracy and better noise-robustness than their vanilla versions.

Investigation of Machine Learning Models for a Time Series Classification Task in Radial–Axial Ring Rolling

The next step to further investigate the suitability of different machine learning models for a classification task regarding the ovality of a formed ring is taken by implementing several models of the time series classification domain in machine learning and training them on actual production data of thyssenkrupp rothe erde Germany.

Bearing Fault Diagnosis with Denoising Autoencoders in Few Labeled Sample Case

  • Yuan ZengXiaojun WuJinlong Chen
  • Computer Science
    2020 5th IEEE International Conference on Big Data Analytics (ICBDA)
  • 2020
A bearing fault diagnosis model with a small number of labeled samples and several optimizations are proposed on the dassic AE fault diagnosis method, and the effectiveness of the optimization content is verified in the experimental stage.



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.

Multi-Frequency Decomposition with Fully Convolutional Neural Network for Time Series Classification

Compared with the existing state-of-the-art methods, the proposed FCN structure based on the multi-frequency decomposition (MFD) method is effectively verified through some datasets in UCR Time Series Classification archive.

Forecasting Wavelet Transformed Time Series with Attentive Neural Networks

This paper proposes to explicitly disclose frequency-domain information from a univariate time series using wavelet transform, towards improving forecasting accuracy and leverages different neural networks to capture local time-frequency features and global long-term trend simultaneously.

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