About this Abstract |
| Meeting |
2027 TMS Annual Meeting & Exhibition
|
| Symposium
|
Energy Technologies and CO2 Management: Resource Efficient Processes
|
| Presentation Title |
A Novel Prediction Model for Reheating Furnace Gas Consumption in the Iron and Steel Industry |
| Author(s) |
Jie Huang, Yucong Yang, Wei Li, Pengfan Ren, Hao Wang, Yingqin Wang, Minghui Chi, Zhongheng Chen, Xiancong Zhao, Hao Bai |
| On-Site Speaker (Planned) |
Hao Wang |
| Abstract Scope |
Byproduct gases are important secondary energy sources generated during the iron and steel making process, which account for approximately 30–40% of total energy consumption. Reheating furnaces(RF) are major consumers of byproduct gases.Due to changes in production schedule and heating load, the consumption of byproduct gases for RF fluctuate significantly.Therefore, accurate prediction of RF gas consumption can support the dynamic prediction of byproduct gas demand. In this study, a novel prediction model for RF gas consumption is proposed. Compared with conventional data-driven models, the proposed model can better adapt to changes in production schedule and provide more robust results, thereby supporting the dynamic balancing of byproduct gases in steel enterprises. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
钢铁, 机器学习, 建模与仿真 |