Energy Consumption Analysis in SCADA: A Case Study in the Glass Container Industry

Abstract

Given the present geopolitical scenario and global energy crisis, there is a growing demand to cut energy use, particularly in industry. The glass package manufacturing business has been severely hit by the rise in energy prices in recent years, and most likely this trend will continue. There is a lack of instruments for effiectively anticipating furnace usage when it comes to managing the infrastructure's energy expenditure in the glass industry, which is the case of the BA Glass Avintes company. Because the furnaces are the key energy expenditure source in the plant, getting a thorough understanding of their energy consumption is an important step towards making educated decisions. The purpose of this study is to undertake a detailed analysis of gas and electricity usage for the three furnaces at the BA Glass Avintes facility using data obtained from PowerStudio SCADA. It was investigated which regression model produced the best accurate results when precisely adjusted to the BA Glass Avintes shop-floor setting. The findings indicate that linear regression models may not be appropriate for this application, however tree-based methods, notably the decision tree model, provide promising outcomes. Furthermore, for increased model performance, the study emphasises the necessity of a bigger training dataset and a shorter prediction interval.