Remaining Useful Life Prediction Based on Interpretable Serialized Variational Autoencoder: A Drift-Diffusion Stochastic Equation Perspective
University of Electronic Science and Technology of China · Northwest A&F University · +1 more institution
Abstract
As a proactive maintenance approach, remaining useful life (RUL) prediction plays a key role in smart operation and maintenance of industrial systems. To enhance the interpretability of deep neural network, and to measure the uncertainty of complex systems in the degradation process, an RUL prediction approach based on interpretable serialized variational autoencoder with drift-diffusion stochastic equation (ISVAE-DDSE) is proposed. Specifically, considering a dynamic sequential modeling method, this article proposes a generative deep learning approach to ensure that the model effectively captures the distribution characteristics of degradation data. On this basis, from the perspective of probabilistic deep…
Citation impact
- FWCI
- 85.25
- Percentile
- 100%
- References
- 0
Authors
8- JZJiusi ZhangCorresponding
University of Electronic Science and Technology of China
- KCKai Chen
University of Electronic Science and Technology of China
- RHRenjun He
University of Electronic Science and Technology of China
- THTenglong Huang
Northwest A&F University
- JTJilun Tian
Harbin Institute of Technology
Topics & keywords
- Interpretability
- Autoencoder
- Turbofan
- Representation (politics)
- Probabilistic logic
- Artificial neural network
- Perspective (graphical)
- Dynamic Bayesian network