Energy Consumption Modelling Using Deep Learning Technique — A Case Study of EAF

Abstract

Energy consumption is a global issue which government is taking measures to reduce. Steel plant can have a better energy management once its energy consumption can be modelled and predicted. The purpose of this study is to establish an energy value prediction model for electric arc furnace (EAF) through a data-driven approach using a large amount of real-world data collected from the melt shop in an established steel plant. The data pre-processing and feature selection are carried out. Several data mining algorithms are used separately to build the prediction model. The result shows the predicting performance of the deep learning model is better than the conventional machine learning models, e.g., linear regression, support vector machine and decision tree.