Rolling bearing fault detection using continuous deep belief network with locally linear embedding

Shao, Haidong; Jiang, Hongkai; Li, Xingqiu; Tan, Liang

doi:10.1016/j.compind.2018.01.005

Cited by 159 publications

(61 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…When P G (x) = 0, D * becomes 1 meaning that the discriminator can effectively recognize synthetic data, when P G (x) is close to P data (x), D * tends to the optimal value of 0.5, which means that synthetic data are indistinguishable from real data. Plugging in (17) into (15), one has: (18) As the objective of generative part is to shrink the distance between real and generated data, the loss function of generative model can be defined as…”

Section: Generative Adversarial Networkmentioning

confidence: 99%

See 1 more Smart Citation

Exploiting Generative Adversarial Networks as an Oversampling Method for Fault Diagnosis of an Industrial Robotic Manipulator

Cabrera

Sánchez

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

Data-driven machine learning techniques play an important role in fault diagnosis, safety, and maintenance of the industrial robotic manipulator. However, these methods require data that, more often that not, are hard to obtain, especially data collected from fault condition states and, without enough and appropriated (balanced) data, no acceptable performance should be expected. Generative adversarial networks (GAN) are receiving a significant interest, especially in the image analysis field due to their outstanding generative capabilities. This paper investigates whether or not GAN can be used as an oversampling tool to compensate for an unbalanced data set in an industrial manipulator fault diagnosis task. A comprehensive empirical analysis is performed taking into account six different scenarios for mitigating the unbalanced data, including classical under and oversampling (SMOTE) methods. In all of these, a wavelet packet transform is used for feature generation while a random forest is used for fault classification. Aspects such as loss functions, learning curves, random input distributions, data shuffling, and initial conditions were also considered. A non-parametric statistical test of hypotheses reveals that all GAN based fault-diagnosis outperforms both under and oversampling classical methods while, within GAN based methods, an average accuracy difference as high as 1.68% can be achieved.

show abstract

Section: Generative Adversarial Networkmentioning

confidence: 99%

“…Lee et al [16] proposed a real-time fault diagnosis model using a deep neural network. Shao et al [17] presented a continuous deep belief network (CDBN) for bearings fault detection. Shen et al [8] used a deep belief network with an optimized function of Nesterov momentum (NM) for bearing fault diagnosis.…”

Section: Introductionmentioning

confidence: 99%

Exploiting Generative Adversarial Networks as an Oversampling Method for Fault Diagnosis of an Industrial Robotic Manipulator

Cabrera

Sánchez

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…In order to predict the available remaining life, the effective feature representation of several heath states is required. As proven by many pioneer works in previous studies, [14][15][16][17][18] deep learning techniques are good at extracting discriminative features directly from raw data. Therefore, we plan to exploit proper feature representation for two different health states: normal state and fast degradation.…”

Section: Deep Learning Feature Representationmentioning

confidence: 99%

“…However, this work directly divided the degradation data of multiple bearings into training and test sets without specifying offline and online scenarios. Shao et al 17 used continuous deep belief network (CDBN) with locally linear embedding and deep stacked auto encoder (DSAE) 18 to detect the rolling bearing fault. Shao et al 19 utilized stacked auto encoder (SAE), CNN, and deep belief network (DBN) to extract deep features to further identify health states of bearings.…”

Section: Introductionmentioning

confidence: 99%

Predicting remaining useful life of rolling bearings based on deep feature representation and long short-term memory neural network

Mao

Tang

et al. 2018

Advances in Mechanical Engineering

104

View full text Add to dashboard Cite

For bearing remaining useful life prediction problem, the traditional machine-learning-based methods are generally short of feature representation ability and incapable of adaptive feature extraction. Although deep-learning-based remaining useful life prediction methods proposed in recent years can effectively extract discriminative features for bearing fault, these methods tend to less consider temporal information of fault degradation process. To solve this problem, a new remaining useful life prediction approach based on deep feature representation and long short-term memory neural network is proposed in this article. First, a new criterion, named support vector data normalized correlation coefficient, is proposed to automatically divide the whole bearing life as normal state and fast degradation state. Second, deep features of bearing fault with good representation ability can be obtained from convolutional neural network by means of the marginal spectrum in Hilbert-Huang transform of raw vibration signals and health state label. Finally, by considering the temporal information of degradation process, these features are fed into a long short-term memory neural network to construct a remaining useful life prediction model. Experiments are conducted on bearing data sets of IEEE PHM Challenge 2012. The results show the significance of performance improvement of the proposed method in terms of predictive accuracy and numerical stability.

show abstract

“…DL methods can automatically learn abstract representation features without manually selecting fault features , and yield the best-in-class performance [16]. Various DL algorithms have been used for REB fault diagnosis [17][18][19][20][21][22][23][24][25][26]. Chen et al [27] proposed a fusion method to fuse the vibration signals from time and frequency domains.…”

Section: Introductionmentioning

confidence: 99%

Input Feature Mappings-Based Deep Residual Networks for Fault Diagnosis of Rolling Element Bearing With Complicated Dataset

et al. 2020

View full text Add to dashboard Cite

Most rolling element bearing (REB) fault diagnosis algorithms are evaluated on the Case Western Reserve University (CWRU) bearing dataset for its popularity and simplicity. However, the diagnosis accuracy on CWRU bearing dataset is overly saturated; it is nearly up to 100%. In this study, an input feature mappings (IFMs)-based deep residual network (ResNet) is proposed to conduct detailed and comprehensive fault diagnosis on REB with complicated bearing dataset. Firstly, a new data preprocessing method named as a signal-to-IFMs method is proposed to automatically extract features from raw signals without predefined parameters. Then, a deep ResNet is used as the fault classifier to learn the discriminative features from IFMs and identify the faults of REB. Finally, the proposed model is evaluated on the artificial, real, and mixed damages of the Paderborn university bearing dataset. The proposed method yields the average testing accuracies of 99.7%, 99.7%, and 99.81% in artificial, real, and mixed bearing damages, which outperforms other methods. INDEX TERMS Rolling element bearing, fault diagnosis, signal-to-input feature mappings, deep residual networks.

show abstract

Rolling bearing fault detection using continuous deep belief network with locally linear embedding

Cited by 159 publications

References 47 publications

Exploiting Generative Adversarial Networks as an Oversampling Method for Fault Diagnosis of an Industrial Robotic Manipulator

Exploiting Generative Adversarial Networks as an Oversampling Method for Fault Diagnosis of an Industrial Robotic Manipulator

Predicting remaining useful life of rolling bearings based on deep feature representation and long short-term memory neural network

Input Feature Mappings-Based Deep Residual Networks for Fault Diagnosis of Rolling Element Bearing With Complicated Dataset

Contact Info

Product

Resources

About