Proceedings of Conference on Coal Science
Online ISSN : 2423-8309
Print ISSN : 2423-8295
ISSN-L : 2423-8295
[volume title in Japanese]
Conference information

1-03 Prediction of Coke strength with AI
Kotaro SakaiYuki kimuraYuko NishibataMasahito Kitao
Author information
CONFERENCE PROCEEDINGS FREE ACCESS

Pages 6-7

Details
Abstract

Coke is manufactured by blending more than 15 types of coal. The coke strength (DI) depends on coal blend ratio. Consequently, it is important to predict coke strength at the time to decide coal blend. The conventional prediction method of DI has been obtained by an inductive model from the average coal properties. However, this prediction has often larger error because there is no additivity in some coal properties. Therefore, we try to predict DI with AI which makes deductive model from coal blending ratio. As the result, AI prediction is more accurate than the conventional prediction for consideration of coal compatibility.

Content from these authors
© 2021 The Japan Institute of Energy
Previous article Next article
feedback
Top