Abstract
In the steel industry, there are some parameters that are difficult to measure online due to technical difficulties. In these scenarios, soft-sensors, which are online tools that aim forecasting of certain variables, play an indispensable role for quality control. In this investigation, different soft sensors are developed to address the problem of predicting the slag quantity and composition in an electric arc furnace process. The results provide evidence that the models perform better for simulated data than for real data. They also reveal higher accuracy in predicting the composition of the slag than the measured quantity of the slag.
| Original language | English |
|---|---|
| Pages (from-to) | 178-183 |
| Number of pages | 6 |
| Journal | Procedia Manufacturing |
| Volume | 54 |
| DOIs | |
| Publication status | Published - 2021 |
| Event | 10th CIRP Sponsored Conference on Digital Enterprise Technologies - Digital Technologies as Enablers of Industrial Competitiveness and Sustainability, DET 2020 - Budapest, Hungary Duration: 12 Oct 2020 → 14 Oct 2020 |
Keywords
- Slag prediction model
- Soft-sensors
- Electric arc furnace process
- Machine Learning
Project and Funding Information
- Project ID
- info:eu-repo/grantAgreement/EC/H2020/820670/EU/Innovative and efficient solution, based on modular, versatile, smart process units for energy and resource flexibility in highly energy intensive processes/CIRMET
- Funding Info
- The project leading to this research work has received funding from the European Unions Horizon 2020 research and innovation programme under grant agreement No 820670.