Loading…

A Novel Time Series based Seq2Seq Model for Temperature Prediction in Firing Furnace Process

It is important to maintain the temperature uniformly in the calcining process at the manufacturing site. However, it is not easy to maintain a constant temperature. To predict the temperature, it is necessary to predict the life of the heating element in the calcining process. The breakdown time of...

Full description

Saved in:
Bibliographic Details
Published in:Procedia computer science 2019, Vol.155, p.19-26
Main Authors: Hwang, Soonsung, Jeon, Gunwoo, Jeong, Jongpil, Lee, JunYoul
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:It is important to maintain the temperature uniformly in the calcining process at the manufacturing site. However, it is not easy to maintain a constant temperature. To predict the temperature, it is necessary to predict the life of the heating element in the calcining process. The breakdown time of the process should be reduced by replacing the heating element at an appropriate time before the life of the heating element is reached. In this paper, to predict the temperature of the firing furnace used in the manufacturing process, the temperature of the firing furnace was predicted using the Sequence to Sequence (Seq2Seq) model, which is often used for machine translation. The implemented model proved to have very high accuracy.
ISSN:1877-0509
1877-0509
DOI:10.1016/j.procs.2019.08.007