.png){kind=icon}
.png){kind=icon}
Return
A deep patch network with spatiotemporal meta-parameter learning for soft sensor modeling of industrial processes
.png){kind=icon}
PRE
AI
DOI：10.1016/j.engappai.2025.112155.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Propose a novel deep patch network with spatiotemporal meta-parameter learning for soft sensor modeling. • Devise an unified framework that enables explicit and simultaneous extraction of complex features under varying spatiotemporal contexts. • Develop learnable spatiotemporal embeddings incorporating patch information, time intervals, and spatiotemporal coupling characteristics. • Enhance context-aware feature extraction for industrial time-series data.
Journal
IF:
8
Papers:
5.3K
Citations:
3.5W