Next Article in Journal
Research Progress of Small Molecule Fluorescent Probes for Detecting Hypochlorite
Next Article in Special Issue
Structural Response Prediction for Damage Identification Using Wavelet Spectra in Convolutional Neural Network
Previous Article in Journal
Thermal Characterization of New 3D-Printed Bendable, Coplanar Capacitive Sensors
Previous Article in Special Issue
Image Motion Extraction of Structures Using Computer Vision Techniques: A Comparative Study
Article

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

Department of Civil, Environmental and Geomatic Engineering, Stefano-Franscini-Platz 5, 8093 Zürich, Switzerland
*
Author to whom correspondence should be addressed.
Academic Editors: Tzu-Kang Lin, Chia-Ming Chang and Dimitrios Chronopoulos
Sensors 2021, 21(19), 6325; https://doi.org/10.3390/s21196325
Received: 19 July 2021 / Revised: 13 September 2021 / Accepted: 15 September 2021 / Published: 22 September 2021
(This article belongs to the Special Issue Sensors in Structural Health Monitoring and Smart Structural Control)
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. View Full-Text
Keywords: ball bearings; condition monitoring; forecast uncertainty; Graph Neural Networks (GNNs); Recurrent Neural Networks (RNNs); non-uniform sampling; Remaining Useful Life (RUL) ball bearings; condition monitoring; forecast uncertainty; Graph Neural Networks (GNNs); Recurrent Neural Networks (RNNs); non-uniform sampling; Remaining Useful Life (RUL)
Show Figures

Figure 1

MDPI and ACS Style

Mylonas, C.; Chatzi, E. Remaining Useful Life Estimation for Engineered Systems Operating under Uncertainty with Causal GraphNets. Sensors 2021, 21, 6325. https://doi.org/10.3390/s21196325

AMA Style

Mylonas C, Chatzi E. Remaining Useful Life Estimation for Engineered Systems Operating under Uncertainty with Causal GraphNets. Sensors. 2021; 21(19):6325. https://doi.org/10.3390/s21196325

Chicago/Turabian Style

Mylonas, Charilaos, and Eleni Chatzi. 2021. "Remaining Useful Life Estimation for Engineered Systems Operating under Uncertainty with Causal GraphNets" Sensors 21, no. 19: 6325. https://doi.org/10.3390/s21196325

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop