A large language model empowered multi-scale fusion attention network for industrial temperature prediction
Measurement Science and Technology · 19.06.2026 · 37 (25) · 256205
DOI: 10.1088/1361-6501/ae7aa5 ↗Kurz gefasst
Fachartikel in der Zeitschrift Measurement Science and Technology, online erschienen am 23.06.2026. Verfasst von Xuefeng Fu und 4 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jiangsu Province, Yangtze River Delta Sci-Tech Innovation Community Joint Research Project.
Abstract (Originalsprache)
Accurate extraction tank temperature prediction is essential for ensuring product quality and process reliability in pharmaceutical manufacturing. This task remains challenging due to concealed temporal patterns, long-range dependencies, and heterogeneous dynamics arising from coexisting continuous process variables and binary valve-state signals. To address these problems, this study develops an ensemble model integrating a pre-trained large language model (LLM) with a multi-scale fusion attention network by leveraging the sequence modeling capability of LLMs. Firstly, a multi-perspective refiner attention module is introduced to capture critical spatial and channel features, while a multi-scale feature fusion module is presented to extract heterogeneous characteristics across different temporal resolutions. Secondly, the pre-trained LLM module is designed to capture intricate temporal dynamics and long-term dependencies in industrial time series. Finally, an improved Adaboost ensemble strategy further enhances prediction accuracy and stability. Experiments on six real-world extraction tank datasets show that the proposed model outperforms state-of-the-art baselines, demonstrating its effectiveness for industrial temperature prediction.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Jiangsu Province
- Yangtze River Delta Sci-Tech Innovation Community Joint Research Project
Zitieren
APA
Fu, X., Wang, Y., Liu, X., Zhang, X., & Ji, Z. (2026). A large language model empowered multi-scale fusion attention network for industrial temperature prediction. Measurement Science and Technology, 37(25), 256205. https://doi.org/10.1088/1361-6501/ae7aa5
Vancouver
Fu X, Wang Y, Liu X, Zhang X, Ji Z. A large language model empowered multi-scale fusion attention network for industrial temperature prediction. Measurement Science and Technology. 2026;37(25):256205. doi:10.1088/1361-6501/ae7aa5
BibTeX
@article{Fu2026,
author = {Fu, Xuefeng and Wang, Yan and Liu, Xiang and Zhang, Xin and Ji, Zhicheng},
title = {A large language model empowered multi-scale fusion attention network for industrial temperature prediction},
journal = {Measurement Science and Technology},
year = {2026},
volume = {37},
number = {25},
pages = {256205},
doi = {10.1088/1361-6501/ae7aa5}
}
EUVIMED