A Multidomain Spatiotemporal Deep Convolutional Autoencoder for Health Indicator Construction in Rotating Machinery
IEEE Sensors Journal · 15.05.2026 · 26 (10) · 15629-15642
DOI: 10.1109/jsen.2026.3676675 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Sensors Journal, erschienen am 15.05.2026. Verfasst von Yong Duan und 3 weiteren Autor:innen. Gefördert von: National Natural Science Foundation of China, Projects of Shaanxi Provincial Science and Technology Department, Postdoctoral Research Funding Program of Shaanxi Province.
Abstract (Originalsprache)
Rotating machinery is widely used in industrial production. Constructing an accurate health indicator (HI) can reveal the degradation process and capture the health status, which is of great significance. However, most existing HI construction methods have problems such as a single form of sample input, poor nonlinear expression ability, difficulty in extracting degenerative features, and capturing early signs of degradation. To overcome these issues, this article proposes a multidomain omnidimensional spatiotemporal collaborative deep convolutional autoencoder (CAE) (MOSCDCAE) for automatically constructing the HI of rotating machinery. The multidomain 2-D weight samples of the vibration signal are introduced to enhance the expression of signal features. An HI construction deep CAE network integrating omnidimensional dynamic convolution (ODConv), bidirectional gated recurrent unit (BiGRU), and attention mechanism (AM) is proposed to generate high-performance HI. This network incorporates newly proposed spatial, temporal, and fusion modules, which can deeply explore the internal deep relationships of the data. On this basis, an exponential function that fits the root mean square (rms) is proposed, and a new loss function is constructed to enhance the HI’s comprehensive performance. The validity of the method is verified by the standard bearing dataset, and the proposed method improves the comprehensive score by an average of 0.1253 compared with other methods. On the reducer accelerated degradation dataset, this method improves the comprehensive score by an average of 0.1465 compared with other methods. It is also able to detect early degradation points earlier and predict remaining useful life (RUL) more precisely.
Förderung
- National Natural Science Foundation of China
- Projects of Shaanxi Provincial Science and Technology Department
- Postdoctoral Research Funding Program of Shaanxi Province
- Key Project of Shaanxi Provincial Key Research and Development Program
Zitieren
APA
Duan, Y., Wei, T., Li, M., & Cao, X. (2026). A Multidomain Spatiotemporal Deep Convolutional Autoencoder for Health Indicator Construction in Rotating Machinery. IEEE Sensors Journal, 26(10), 15629-15642. https://doi.org/10.1109/jsen.2026.3676675
Vancouver
Duan Y, Wei T, Li M, Cao X. A Multidomain Spatiotemporal Deep Convolutional Autoencoder for Health Indicator Construction in Rotating Machinery. IEEE Sensors Journal. 2026;26(10):15629-15642. doi:10.1109/jsen.2026.3676675
BibTeX
@article{Duan2026,
author = {Duan, Yong and Wei, Tao and Li, Man and Cao, Xiangang},
title = {A Multidomain Spatiotemporal Deep Convolutional Autoencoder for Health Indicator Construction in Rotating Machinery},
journal = {IEEE Sensors Journal},
year = {2026},
volume = {26},
number = {10},
pages = {15629--15642},
doi = {10.1109/jsen.2026.3676675}
}
EUVIMED