Health Indicator for Low-Speed Axial Bearings Using Variational Autoencoders

Hemmer, Martin; Klausen, Andreas; Khang, Huynh Van; Robbersmyr, Kjell G.; Waag, Tor Inge

doi:10.1109/access.2020.2974942

Cited by 31 publications

(9 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many HIs in the literature are based on out-of-distribution detection [15], [49]- [51]. To our knowledge, no previous work has exploited the out-of-distribution detection in the standard Nataf space.…”

Section: Health Index In For Out-of-distribution Detectionmentioning

confidence: 99%

System Condition Monitoring Based on a Standardized Latent Space and the Nataf Transform

Oliveira-Filho,

Zemouri,

Pelletier

et al. 2024

IEEE Access

View full text Add to dashboard Cite

This work introduces a new condition monitoring approach for complex systems based on a standardized latent space representation. Latent variable models such as the variational autoencoders are widely used to analyze systems described by a high-dimensional physical space. The encoding of such space defines a low-dimensional and physically representative latent space. Of note, however, the latent space obtained for complex systems operating under multiple conditions is often difficult to exploit in defining an efficient Health Index, thanks to the non-deterministic and hyperparameter-dependent nature of the latent space. In addition, the distribution of the healthy cluster is not known a priori. The original contribution of this paper is to use the Nataf isoprobabilistic transform to map the latent space into a standardized space. This normalizes the spatial structure of the latent space and relaxes the model's sensitivity to

show abstract

Section: Health Index In For Out-of-distribution Detectionmentioning

confidence: 99%

System Condition Monitoring Based on a Standardized Latent Space and the Nataf Transform

Oliveira-Filho,

Zemouri,

Pelletier

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…7 VAER architecture. NN structure visualization inspired by Hemmer et al (2020) subset. In other words, when the validation subset calculated loss starts to increase, the training process is halted.…”

Section: Diminishing Overfittingmentioning

confidence: 99%

Predicting the quality of a machined workpiece with a variational autoencoder approach

et al. 2021

View full text Add to dashboard Cite

In this article, it is shown that a machine learning approach based only on data from sensors (vibration and current consumption) can be used to predict the geometric dimensioning and tolerancing quality measurement values of machined workpieces in an industrial context. First, a methodology based on a variational autoencoder approach is used, and then a metric based on the concept of Euclidean distance and the 2D latent space produced by the variational autoencoder is proposed. The proposed variational autoencoder regression model is shown capable of predicting the quality measurement values, with a mean square error of 5.2573 × 10 −4 mm. The proposed measurement system also displays a confidence interval of ± 0.05 mm. Moreover, the resulting 2D latent space is capable of distributing and structuring data based on the quality level and of providing a quick visual support. Compared to the t-SNE method, this latent space displays a better structure. Furthermore, the proposed Euclidean distance metric is correlated to the quality level in both the predicted and observed subsets. This work is also based on an industrial dataset, thus increasing its potential for technological transfer; that in turn allows a better monitoring of the machining process, as well as the prediction of the workpiece quality.

show abstract

“…In [13], a novel remaining useful life prediction model was proposed based on VAE, in which LSTM network and Gaussian mixture model were utilized as building blocks. Health indicator for low-speed axial rolling element bearing was calculated by utilizing the latent representation obtained via VAE [14]. An unsupervised anomaly detection method named variable cumulative error anomaly detection model was proposed in [15], which was constructed based on autoencoders and temporal convolutional networks.…”

Section: Introductionmentioning

confidence: 99%

Blade fouling fault detection based on shaft orbit generative adversarial network

Huang,

Ma,

Shao

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

The precision and stability of anomaly detection methods are vital for the secure and efficient operation of machinery. In this paper, finite element model is firstly used to analyze the shaft orbit of cantilever rotor from the perspective of fault mechanism. Then shaft orbit generative adversarial network is proposed and applied to detect the blade fouling fault. Variational autoencoder is used as the foundational network architecture for extracting high-dimensional latent features from shaft orbit images. Concurrently, the seventh-order moment of shaft orbit images is extracted and embedded into a bypass within the generator, thereby enhancing the accuracy of fault detection. Two sets of real-world blade fouling fault data are collected and meticulously analyzed. The results demonstrate that the proposed method exhibits higher accuracy and more robust generalization capability in anomaly detection. Additionally, the utilization of gradient information for the localization and visual analysis of anomalies dynamically tracks the spatial evolution of the rotor shaft orbit throughout its entire lifecycle. The data generation capability and interpretability of the proposed model can effectively support the digital twin modeling and health management of rotating machinery.

show abstract

Health Indicator for Low-Speed Axial Bearings Using Variational Autoencoders

Cited by 31 publications

References 39 publications

System Condition Monitoring Based on a Standardized Latent Space and the Nataf Transform

System Condition Monitoring Based on a Standardized Latent Space and the Nataf Transform

Predicting the quality of a machined workpiece with a variational autoencoder approach

Blade fouling fault detection based on shaft orbit generative adversarial network

Contact Info

Product

Resources

About