Sinter machine productivity

Published: 12 October 2021| Version 1 | DOI: 10.17632/72hgnwmsvs.1
Contributor:
Sushant Rath

Description

This datasets contains Sinter Machine Productivity as out put and 16 input parameters: (1) I/O Fines Total, Fe % (2) I/O Fines SiO2, % (3)I/O Fines Al2O3, % (4)I/O Fines CaO, % (5)Flux CaO, % (6)Flux MgO, % (7)Flux Crushing Index, % (8)Coke Crushing Index, % (9)Sinter Total Fe, % (10)Sinter FeO, % (11)Sinter SiO2, % (12)Sinter Al2O3, % (13) Sinter CaO, % (14)Sinter MgO, % (15)Sinter +40mm Size, % (16)Drum Tumbling Index (DTI), % The objective is to correlate the input parameters with sinter plant productivity and suggest prescriptive analytics.

Files

Steps to reproduce

Two Machine Learning Algorithms are used for the prediction of Sinter Machine Productivity. For Linear regression Lr.py file can be used. For ANN, ANN.mat file can be used.

Institutions

Steel Authority of India Ltd

Categories

Steel, Machine Learning, Sintering

Licence