A Physics-Informed Multi-Task Soft Sensor for Uncertainty-Aware Slag Tin Content Prediction in Top-Blown Tin Smelting
Sensors · 14.08.2026 · 26 (16) · 5157
DOI: 10.3390/s26165157 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 14.08.2026. Verfasst von Zhaojun Ma und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Resources and Environment, Yunnan University, Kunming 650500, China. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Yunnan Fundamental Research Projects.
Abstract (Originalsprache)
Slag tin content is a key indicator of reduction efficiency and metal recovery in top-blown tin smelting, but delayed and sparse laboratory assays hinder online monitoring. This study proposes a physics-informed multi-task soft sensor (PI-MTSS) combining a shared temporal convolutional encoder, self-supervised future state reconstruction, a soft monotonicity constraint based on a simplified CO–temperature reduction-potential indicator, and Monte Carlo dropout for epistemic uncertainty estimation. The model was evaluated on a continuous 30-day dataset comprising 43,200 one-minute process observations and 240 laboratory assays, including 40 chronologically held-out test labels. Across five random seeds, PI-MTSS achieved an RMSE of 0.198, an MAE of 0.145, and an R2 of 0.889. Across three rolling-origin evaluations, it obtained a mean RMSE of 0.199 and maintained the lowest RMSE among the evaluated methods. The complete model reduced the physical violation rate to 3.5%. At 95% nominal coverage, its epistemic intervals achieved a PICP of 96.5% and an NMPIW of 0.245; the ACE across six nominal levels was 0.021, and uncertainty correlated positively with absolute error (ρs=0.691). These results support the potential of PI-MTSS for minute-scale monitoring and operator decision support under sparse labels, although validation remains limited to one month from a single furnace.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Resources and Environment, Yunnan University, Kunming 650500, China.
- Yunnan Tin Group (Holding) Co., Ltd., No. 471 Minhang Road, Guandu District, Kunming 650200, China.
- School of Automation, Central South University, Changsha 410083, China.
Förderung
- National Natural Science Foundation of China
- Yunnan Fundamental Research Projects
Zitieren
APA
Ma, Z., Peng, J., Zhou, X., Xie, K., & Zhang, Z. (2026). A Physics-Informed Multi-Task Soft Sensor for Uncertainty-Aware Slag Tin Content Prediction in Top-Blown Tin Smelting. Sensors, 26(16), 5157. https://doi.org/10.3390/s26165157
Vancouver
Ma Z, Peng J, Zhou X, Xie K, Zhang Z. A Physics-Informed Multi-Task Soft Sensor for Uncertainty-Aware Slag Tin Content Prediction in Top-Blown Tin Smelting. Sensors. 2026;26(16):5157. doi:10.3390/s26165157
BibTeX
@article{Ma2026,
author = {Ma, Zhaojun and Peng, Jubo and Zhou, Xiaojun and Xie, Kui and Zhang, Zhang},
title = {A Physics-Informed Multi-Task Soft Sensor for Uncertainty-Aware Slag Tin Content Prediction in Top-Blown Tin Smelting},
journal = {Sensors},
year = {2026},
volume = {26},
number = {16},
pages = {5157},
doi = {10.3390/s26165157}
}
EUVIMED