Multiscale Convolutional Attention Network for Predicting Remaining Useful Life of Machinery

Wang, Biao; Lei, Yaguo; Li, Naipeng

doi:10.1109/tie.2020.3003649

Cited by 185 publications

(46 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [16], a recurrent convolutional network is adopted [17] and Monte-Carlo Dropout [18] is used as a simple and effective way of representing the uncertainty in the predictions. In [19], instead of recurrent connections, as applied in [17], attention layers are used to enhance the performance of CNNs. All aforementioned approaches are not appropriate for arbitrarily spaced data, as there is no explicit representation of the time between the observations.…”

Section: Arxiv:201111740v1 [Cslg] 23 Nov 2020mentioning

confidence: 99%

“…In [ 37 ], a recurrent convolutional network is adopted [ 38 ] and Monte-Carlo Dropout [ 39 ] is used as a simple and effective way of representing the uncertainty in the predictions. In [ 40 ], instead of recurrent connections, as applied in [ 38 ], attention layers are used to enhance the performance of CNNs. Chen et al [ 41 ] propose an RNN-based architecture comprising an encoder–decoder structure with attention mechanism.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Remaining Useful Life Estimation for Engineered Systems Operating under Uncertainty with Causal GraphNets

Mylonas¹,

Chatzi²

2021

Sensors

View full text Add to dashboard Cite

In this work, a novel approach, termed GNN-tCNN, is presented for the construction and training of Remaining Useful Life (RUL) models. The method exploits Graph Neural Networks (GNNs) and deals with the problem of efficiently learning from time series with non-equidistant observations, which may span multiple temporal scales. The efficacy of the method is demonstrated on a simulated stochastic degradation dataset and on a real-world accelerated life testing dataset for ball-bearings. The proposed method learns a model that describes the evolution of the system implicitly rather than at the raw observation level and is based on message-passing neural networks, which encode the irregularly sampled causal structure. The proposed approach is compared to a recurrent network with a temporal convolutional feature extractor head (LSTM-tCNN), which forms a viable alternative for the problem considered. Finally, by taking advantage of recent advances in the computation of reparametrization gradients for learning probability distributions, a simple, yet efficient, technique is employed for representing prediction uncertainty as a gamma distribution over RUL predictions.

show abstract

Section: Arxiv:201111740v1 [Cslg] 23 Nov 2020mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Remaining Useful Life Estimation for Engineered Systems Operating under Uncertainty with Causal GraphNets

Mylonas¹,

Chatzi²

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Compared with traditional ML methods, deep learning (DL) methods have more powerful learning capabilities, and possess the capability of establishing more complex mapping relationships [7] between monitoring data and RUL. Therefore, deep learning is now widely used in the field of RUL prediction [8][9][10] . Among various deep learning technologies, recurrent neural network (RNN) [11] [12] and its variant, e.g., long short-term memory (LSTM) network [13][14][15] , are able to effectively capture the time dependence hidden in the degradation process, and have become the promising tool in RUL prediction.…”

Section: Introductionmentioning

confidence: 99%

Residual Convolution Long Short-Term Memory Network for Machines Remaining Useful Life Prediction and Uncertainty Quantification

Wang

Lei

Yan

et al. 2021

JDMD

Self Cite

View full text Add to dashboard Cite

Recently, deep learning is widely used in the field of remaining useful life (RUL) prediction. Among various deep learning technologies, recurrent neural network (RNN) and its variant, e.g., long short-term memory (LSTM) network, are gaining more attention because of their capability of capturing temporal dependence. Although the existing RNN-based approaches have demonstrated their RUL prediction effectiveness, they still suffer from the following two limitations: 1) it is difficult for RNN to extract directly degradation features from original monitoring data, and 2) most of the RNN-based prognostics methods are unable to quantify the uncertainty of prediction results. To address the above limitations, this paper proposes a new method named Residual convolution LSTM (RC-LSTM) network. In RC-LSTM, a new ResNet-based convolution LSTM (Res-ConvLSTM) layer is stacked with convolution LSTM (ConvLSTM) layer to extract degradation representations from monitoring data. Then, predicated on the RUL following a normal distribution, an appropriate output layer is constructed to quantify the uncertainty of the forecast result. Finally, the effectiveness and superiority of RC-LSTM is verified using monitoring data from accelerated degradation tests of rolling element bearings.

show abstract

“…Wind power has become an important source of global renewable energy [1,2]. As wind turbines (WTs) often fail in extreme environments, including sleet, wind gusts, and lightning strikes [3], wind turbine blades (WTBs) monitoring, such as fault prognostics, health monitoring, and early failure warning, etc., is deemed an important task to ensure their maintenance of normal operation [4][5][6][7][8]. Since machine vision techniques have shown great advantages in object detection and recognition, installing visual systems onboard unmanned aerial vehicles (UAVs) is a promising labor-saving and remote sensing approach for WTB surface inspection [5,9].…”

Section: Introductionmentioning

confidence: 99%

Motion Blur Removal for Uav-Based Wind Turbine Blade Images Using Synthetic Datasets

et al. 2021

View full text Add to dashboard Cite

Unmanned air vehicle (UAV) based imaging has been an attractive technology to be used for wind turbine blades (WTBs) monitoring. In such applications, image motion blur is a challenging problem which means that motion deblurring is of great significance in the monitoring of running WTBs. However, an embarrassing fact for these applications is the lack of sufficient WTB images, which should include better pairs of sharp images and blurred images captured under the same conditions for network model training. To overcome the challenge of image pair acquisition, a training sample synthesis method is proposed. Sharp images of static WTBs were first captured, and then video sequences were prepared by running WTBs at different speeds. The blurred images were identified from the video sequences and matched to the sharp images using image difference. To expand the sample dataset, rotational motion blurs were simulated on different WTBs. Synthetic image pairs were then produced by fusing sharp images and images of simulated blurs. Finally, a total of 4000 image pairs were obtained. To conduct motion deblurring, a hybrid deblurring network integrated with DeblurGAN and DeblurGANv2 was deployed. The results show that the integration of DeblurGANv2 and Inception-ResNet-v2 provides better deblurred images, in terms of both metrics of signal-to-noise ratio (80.138) and structural similarity (0.950) than those obtained from the comparable networks of DeblurGAN and MobileNet-DeblurGANv2.

show abstract

Multiscale Convolutional Attention Network for Predicting Remaining Useful Life of Machinery

Cited by 185 publications

References 19 publications

Remaining Useful Life Estimation for Engineered Systems Operating under Uncertainty with Causal GraphNets

Remaining Useful Life Estimation for Engineered Systems Operating under Uncertainty with Causal GraphNets

Residual Convolution Long Short-Term Memory Network for Machines Remaining Useful Life Prediction and Uncertainty Quantification

Motion Blur Removal for Uav-Based Wind Turbine Blade Images Using Synthetic Datasets

Contact Info

Product

Resources

About