Contrastive Adversarial Domain Adaptation for Machine Remaining Useful Life Prediction

Ragab, Mohamed; Chen, Zhenghua; Wu, Min; Foo, Chuan Sheng; Kwoh, Chee Keong; Yan, Ruqiang; Li, Xiaoli

doi:10.1109/tii.2020.3032690

Cited by 84 publications

(21 citation statements)

References 36 publications

(62 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hinchi et al used convolutional layers to directly extract local features from sensor data, combined them with LSTM layers to capture the degradation process of the bearing, and finally output the prediction values [23]. Whereas LSTM solves the problem of gradient disappearance of traditional RNN to some extent, the deliberate design of LSTM for RUL prediction is very time consuming [24,25].…”

Section: Prediction Modelmentioning

confidence: 99%

SACGNet: A Remaining Useful Life Prediction of Bearing with Self-Attention Augmented Convolution GRU Network

Duan

Chen³

et al. 2022

Lubricants

View full text Add to dashboard Cite

In recent years, the development of deep learning-based remaining useful life (RUL) prediction methods of bearings has flourished because of their high accuracy, easy implementation, and lack of reliance on a priori knowledge. However, there are two challenging issues concerning the prediction accuracy of existing methods. The run-to-failure sequential data and its RUL labels are almost inaccessible in real-world scenarios. Meanwhile, the existing models usually capture the general degradation trend of bearings while ignoring the local information, which restricts the model performance. To tackle the aforementioned problems, we propose a novel health indicator derived from the original vibration signals by combining principal components analysis with Euclidean distance metric, which was motivated by the desire to resolve the dependency on RUL labels. Then, we design a novel self-attention augmented convolution GRU network (SACGNet) to predict the RUL. Combining a self-attention mechanism with a convolution framework can both adaptively assign greater weights to more important information and focus on local information. Furthermore, Gated Recurrent Units are used to parse the long-term dependencies in weighted features such that SACGNet can utilize the important weighted features and focus on local features to improve the prognostic accuracy. The experimental results on the PHM 2012 Challenge dataset and the XJTU-SY bearing dataset have demonstrated that our proposed method is superior to the state of the art.

show abstract

Section: Prediction Modelmentioning

confidence: 99%

SACGNet: A Remaining Useful Life Prediction of Bearing with Self-Attention Augmented Convolution GRU Network

Duan

Chen³

et al. 2022

Lubricants

View full text Add to dashboard Cite

show abstract

“…Figure 32 shows the working principle of TL [198]. The authors of [180] propose a novel transfer learning technique based on multiple layer perceptron (MLP) for dissimilar data distribution problems in RUL prediction of bearing machinery. However, many scopes to use selfsupervised learning [199] and self-supervised contrastive learning [200] algorithms are fine-tuned on limited data.…”

Section: Transfer Learning (Tl)mentioning

confidence: 99%

Data-Driven Remaining Useful Life Estimation for Milling Process: Sensors, Algorithms, Datasets, and Future Directions

et al. 2021

View full text Add to dashboard Cite

An increase in unplanned downtime of machines disrupts and degrades the industrial business, which results in substantial credibility damage and monetary loss. The cutting tool is a critical asset of the milling machine; the failure of the cutting tool causes a loss in industrial productivity due to unplanned downtime. In such cases, a proper predictive maintenance strategy by real-time health monitoring of cutting tools becomes essential. Accurately predicting the useful life of equipment plays a vital role in the predictive maintenance arena of industry 4.0. Many active research efforts have been done to estimate tool life in varied directions. However, the consolidated study of the implemented techniques and future pathways is still missing. So, the purpose of this paper is to provide a systematic and comprehensive literature survey on the data-driven approach of Remaining Useful Life (RUL) estimation of cutting tools during the milling process. The authors have summarized different monitoring techniques, feature extraction methods, decision-making models, and available sensors currently used in the data-driven model. The authors have also presented publicly available datasets related to milling under various operating conditions to compare the accuracy of the prediction model for tool wear estimation. Finally, the article concluded with the challenges, limitations, recent advancements in RUL prognostics techniques using Artificial Intelligence (AI), and future research scope to explore more in this area.

show abstract

“…Generally, the degradation trends are not the same for different bearings under the same conditions, resulting in significant data distribution discrepancies between entities. To overcome these problems, adversarial domain adaptation approaches and CNN-based health stage prediction methods have been proposed for RUL prediction [17,18,19,24]. The adversarial domain adaptation approaches have been proposed to generalize the feature extraction of bearing wear.…”

Section: Deep Learning and Adversarial Domain Adaptation For Rulmentioning

confidence: 99%

“…Da Costa et al [17] proposed a deep domain adaptation method for the RUL prediction by integrating the LSTM model with domain classification loss to reduce the deviation between source and target domains. Ragab et al [18,19] proposed a contrastive adversarial domain adaptation approach that enables automatic feature extraction and the RUL prediction from a source domain to a target domain. However, these approaches predict the RUL without determining the HS and FPT and only focus on the single-source single-target adaptation setting which is impractical because the network of domain adaptation should be trained for data from different domains with different distributions.…”

Section: Deep Learning and Adversarial Domain Adaptation For Rulmentioning

confidence: 99%

“…(3) For accurate RUL prediction, it is essential to properly determine the health stage (HS) of the machinery; because the machine in a healthy state would not have any remarkable difference in the run-to-failure training dataset. However, extant conventional methods predict the RUL without determining the first predicting time (FPT) [17,18,19], which is the start time of the unhealthy stage.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Generalized multiscale feature extraction for remaining useful life prediction of bearings with generative adversarial networks

Suh¹,

Lukowicz²,

Lee³

2021

Preprint

View full text Add to dashboard Cite

Bearing is a key component in industrial machinery and its failure may lead to unwanted downtime and economic loss. Hence, it is necessary to predict the remaining useful life (RUL) of bearings. Conventional data-driven approaches of RUL prediction require expert domain knowledge for manual feature extraction and may suffer from data distribution discrepancy between training and test data. In this study, we propose a novel generalized multiscale feature extraction method with generative adversarial networks. The adversarial training learns the distribution of training data from different bearings and is introduced for health stage division and RUL prediction. To capture the sequence feature from a one-dimensional vibration signal, we adapt a U-Net architecture that reconstructs features to process them with multiscale layers in the generator of the adversarial network. To validate the proposed method, comprehensive experiments on two rotating machinery datasets have been conducted to predict the RUL. The experimental results show that the proposed feature extraction method can effectively predict the RUL and outperforms the conventional RUL prediction approaches based on deep neural networks.

show abstract

Contrastive Adversarial Domain Adaptation for Machine Remaining Useful Life Prediction

Abstract: Contrastive adversarial domain adaptation for machine remaining useful life prediction.

Cited by 84 publications

References 36 publications

SACGNet: A Remaining Useful Life Prediction of Bearing with Self-Attention Augmented Convolution GRU Network

SACGNet: A Remaining Useful Life Prediction of Bearing with Self-Attention Augmented Convolution GRU Network

Data-Driven Remaining Useful Life Estimation for Milling Process: Sensors, Algorithms, Datasets, and Future Directions

Generalized multiscale feature extraction for remaining useful life prediction of bearings with generative adversarial networks

Contact Info

Product

Resources

About