| Autor: |
G. C. Das, Chanchal Biswas, Saugata Dhar, Rajib Dey, Arghya Majumder |
| Rok vydání: |
2021 |
| Předmět: |
|
| Zdroj: |
Learning and Analytics in Intelligent Systems ISBN: 9783030654061 |
| Popis: |
Now a day’s an effective process management system is essential for the sustainability of integrated steel plant. Their effective process enhances quality of product and increases the cost efficiency. The nature of the raw material, its mix proportion, size, chemical composition and process parameter plays a very vital role in sinter mineralogy. The main objective of this study is to optimize the sinter plant process parameters to get the best productivity of Sinter Plant. Sinter has a very vital role for the production of hot metal in blast furnace. A huge number of industrial parameters as large as 106 numbers control the productivity of sinter plant in a very complex manner. As such there is not much study on the prediction of sinter yield as function of those parameters combined. Perhaps it is for the first time an attempt has been made to predict the sinter yield by using Artificial Neural Networking (ANN), with large number of industrial data available at Vizag Steel over a fairly long period of time. One of the most important achievement of this paper is that the reduction in the number of parameters using metallurgical knowledge and experience (without using any sophisticated optimization technique). The prediction of sinter yield with this reduced number of parameters is almost as good as that predicted by using the exhaustive number of 106 parameters within the framework of ANN. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
