About this Abstract |
Meeting |
2022 TMS Annual Meeting & Exhibition
|
Symposium
|
12th International Symposium on High Temperature Metallurgical Processing
|
Presentation Title |
Study on Burden Mineral Phase Identification System and Prediction Model of Metallurgical Properties Based on BP Neural Network |
Author(s) |
Qingqing Hu, Donglai Ma, Yue Wang, Zhixiong You, Xuewei Lv |
On-Site Speaker (Planned) |
Qingqing Hu |
Abstract Scope |
Sinter and pellet are the main burden of blast furnace ironmaking process, and their phase composition plays an important role on the metallurgical properties. It is of great significance to investigate the influence of phase composition on metallurgical properties. In this paper, based on the optical micrographs and image analysis, the gray range of each mineral is preliminarily determined. Then, the composition and content of different mineral in burden can be calculated by reflectance calculation model. Furthermore, BP neural network method is used to study the mapping relationship between mineral phase composition and metallurgical properties. A high-precision prediction model of burden mineral phase-metallurgical properties is established, and the influence of the content of each phase on metallurgical properties is qualitatively analyzed. The model has reached a certain accuracy, and in order to improve the accuracy of the model, it is necessary to enrich the database and improve the modeling method. |
Proceedings Inclusion? |
Planned: |
Keywords |
Iron and Steel, Pyrometallurgy, Machine Learning |