A new data-driven transferable remaining useful life prediction approach for bearing under different working conditions

Zhu, Jun; Chen, Nan; Shen, Changqing

doi:10.1016/j.ymssp.2019.106602

Cited by 217 publications

(75 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Table 2 gives a detailed description of the datasets. From the table, we can see that the operating conditions of the three datasets are different, and from the literature (Zhu, Chen & Shen, 2020), we can obtain that the failure modes are also different. This is very suitable for experimenting with the method proposed in this article.…”

Section: Experimental Data Descriptionmentioning

confidence: 81%

“…At the same time, through 4-layer wavelet packet decomposition, we extract the energy of 16 frequency bands as time-frequency domain features. In the literature ( Zhu, Chen & Shen, 2020 ), the frequency resolution of the vibration signal was too low. Therefore, we do not extract the frequency domain features but rather use the features of three trigonometric functions.…”

Section: Methodsmentioning

confidence: 99%

“…They introduced the idea of zero-shot learning into industrial fields and proposed a zero-sample fault diagnosis method based on the attribute transfer method. RUL prediction studies based on TL are still relatively few in number, as far as the authors know ( Fan, Nowaczyk & Rögnvaldsson, 2020 ; Mao, He & Zuo, 2020 ; Sun et al, 2019 ; Zhu, Chen & Shen, 2020 ).…”

Section: Literature Reviewmentioning

confidence: 99%

See 2 more Smart Citations

Data-driven remaining useful life prediction based on domain adaptation

Wen

Xiao

Wang

et al. 2021

PeerJ Computer Science

View full text Add to dashboard Cite

As an important part of prognostics and health management, remaining useful life (RUL) prediction can provide users and managers with system life information and improve the reliability of maintenance systems. Data-driven methods are powerful tools for RUL prediction because of their great modeling abilities. However, most current data-driven studies require large amounts of labeled training data and assume that the training data and test data follow similar distributions. In fact, the collected data are often variable due to different equipment operating conditions, fault modes, and noise distributions. As a result, the assumption that the training data and the test data obey the same distribution may not be valid. In response to the above problems, this paper proposes a data-driven framework with domain adaptability using a bidirectional gated recurrent unit (BGRU). The framework uses a domain-adversarial neural network (DANN) to implement transfer learning (TL) from the source domain to the target domain, which contains only sensor information. To verify the effectiveness of the proposed method, we analyze the IEEE PHM 2012 Challenge datasets and use them for verification. The experimental results show that the generalization ability of the model is effectively improved through the domain adaptation approach.

show abstract

Section: Experimental Data Descriptionmentioning

confidence: 81%

Section: Methodsmentioning

confidence: 99%

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Data-driven remaining useful life prediction based on domain adaptation

Wen

Xiao

Wang

et al. 2021

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…In some studies, more than one feature has been extracted according to the time-domain, frequency-domain, and time-frequency domain. For instance, in [33], 13-time domain features, 16 time-frequency domain features, and features based on trigonometric functions are extracted. In [34], a total of 28 features; 11 time-domain features, 9 frequency-domain features, and 8 time-frequency domain features, have been extracted.…”

Section: Rq15: How Is Feature Extraction Applied When Performing Predictive Maintenance?mentioning

confidence: 99%

Kestirimci Bakım ve Kalan Yararlı Ömür Uygulama için Teknikler: Sistematik Haritalama Çalışması

Ture

Akbulut

Zaim

2021

Bilecik Şeyh Edebali Üniversitesi Fen Bilimleri Dergisi

View full text Add to dashboard Cite

With prognostic activities, it is possible to predict the remaining useful life (RUL) of industrial systems with high accuracy by following the current health status of devices. In this study, we have collected 199 articles on predictive maintenance and remaining useful life. The aim of our systematic mapping study is to determine which techniques and methods are used in the areas of predictive maintenance and remaining useful life. Another thing we aim is to give an idea about the main subject to the researchers who will work in this field. We created our article repository by searching databases such as IEEE and Science Direct with certain criteria and classified the articles we obtained. By applying the necessary inclusion and exclusion criteria in the article pool we collected, the most appropriate articles were determined and our study was carried out through these articles. When we focused on the results, it was learned that the SupportVector Machine algorithm is the most preferred predictive maintenance method. Most studies aimed at evaluating the performance and calculating the accuracy of the results used the Root Mean Square Error algorithm. In our study, every method and algorithm included in the articles are discussed. The articles were examined together with the goals and questions we determined, and results were obtained. The obtained results are explained and shown graphically in the article. According to the results, it is seen that the topics of predictive maintenance and remaining useful lifetime provide functionality and financial gain to the environment they are used in. Our study was concluded by light on many questions about the application of predictive maintenance.

show abstract

“…ese can extract abstract information and features from massive datasets while building and discovering complex functional and temporal relationships from the data [9]. Deep learning approaches have been implemented in a great variety of systems for prognostics purposes, such as lithium-ion batteries state of health (SOH) and state of charge (SOC) estimation, [10][11][12][13], RUL estimation in rolling bearings [14][15][16], and turbofan engines [17][18][19][20].…”

Section: Introductionmentioning

confidence: 99%

Remaining Useful Life Estimation through Deep Learning Partial Differential Equation Models: A Framework for Degradation Dynamics Interpretation Using Latent Variables

Cofre-Martel

Droguett

Modarres

2021

Shock and Vibration

View full text Add to dashboard Cite

Remaining useful life (RUL) estimation is one of the main objectives of prognostics and health management (PHM) frameworks. For the past decade, researchers have explored the application of deep learning (DL) regression algorithms to predict the system’s health state behavior based on sensor readings from the monitoring system. Although the state-of-art results have been achieved in benchmark problems, most DL-PHM algorithms are treated as black-box functions, giving little-to-no control over data interpretation. This becomes an issue when the models unknowingly break the governing laws of physics when no constraints are imposed. The latest research efforts have focused on applying complex DL models to achieve low prediction errors rather than studying how they interpret the data’s behavior and the system itself. This paper proposes an open-box approach using a deep neural network framework to explore the physics of a complex system’s degradation through partial differential equations (PDEs). This proposed framework is an attempt to bridge the gap between statistic-based PHM and physics-based PHM. The framework has three stages, and it aims to discover the health state of the system through a latent variable while still providing a RUL estimation. Results show that the latent variable can capture the failure modes of the system. A latent space representation can also be used as a health state estimator through a random forest classifier with up to a 90% performance on new unseen data.

show abstract

A new data-driven transferable remaining useful life prediction approach for bearing under different working conditions

Cited by 217 publications

References 41 publications

Data-driven remaining useful life prediction based on domain adaptation

Data-driven remaining useful life prediction based on domain adaptation

Kestirimci Bakım ve Kalan Yararlı Ömür Uygulama için Teknikler: Sistematik Haritalama Çalışması

Remaining Useful Life Estimation through Deep Learning Partial Differential Equation Models: A Framework for Degradation Dynamics Interpretation Using Latent Variables

Contact Info

Product

Resources

About