A Temporal Network Based on Characterizing and Extracting Time Series in Copper Smelting for Predicting Matte Grade
Junjia Zhang, Zhuorui Li, Enzhi Wang, Bin Yu, Jiangping Li, Jun Ma, Jongmyon Kim · 2024
Read A Temporal Network Based on Characterizing and Extracting Time Series in Copper Smelting for Predicting Matte Grade by Junjia Zhang, Zhuorui Li, Enzhi Wang, Bin Yu, Jiangping Li, Jun Ma, Jongmyon Kim (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11644727.txt.
Description
Junjia Zhang and six co-authors predict the grade of copper matte during smelting with a temporal neural network, in a two thousand twenty-four industrial informatics paper. Traditional prediction models lean on input and assay data, giving weak accuracy and little interpretability.
Their model first selects process sensors whose signals track matte grade strongly. A Time2Vec module extracts the process's periodic patterns, then a temporal convolutional network with multi-head attention weighs the important time steps. The combined design respects the smelting process's time structure instead of flattening it. Experiments show clearly better prediction accuracy than existing models, with the coefficient of determination improving by roughly two to twelve percent.
Catalog record
| CREATOR | Junjia Zhang, Zhuorui Li, Enzhi Wang, Bin Yu, Jiangping Li, Jun Ma, Jongmyon Kim |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 64 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |