Semester

Spring

Date of Graduation

2024

Document Type

Thesis

Degree Type

MS

College

Statler College of Engineering and Mineral Resources

Department

Industrial and Managements Systems Engineering

Committee Chair

Imtiaz Ahmed

Committee Member

Ashish Nimbarte

Committee Member

Christopher Moore

Abstract

In response to the escalating challenges posed by climate change and industrial inefficiency, this thesis presents a comprehensive investigation aimed at advancing the predictive modeling of global CO2 emissions and enhancing operational efficiency in steel manufacturing through Electric Arc Furnace (EAF) temperature optimization. Leveraging a rich dataset sourced from the World Development Indicators database alongside a meticulously curated dataset specific to EAF operations, our study applies an innovative blend of econometric and machine learning techniques, including Pooled Ordinary Least Squares (Pooled OLS), Random Effects (RE), Fixed Effects (FE), and Seasonal Autoregressive Integrated Moving Average with Exogenous Variables (SARIMAX) models. The objective is twofold: to refine global CO2 emission forecasts and to establish a reliable model for predicting the flat bath temperature in EAF steel production, a critical determinant of energy efficiency and product quality. Our analysis elucidates the complex dynamics governing CO2 emissions, identifying key factors such as renewable energy consumption, GDP per unit of energy use, and total greenhouse gas emissions as significant determinants. These insights not only contribute to the academic discourse on environmental sustainability but also provide a solid foundation for policymakers to devise more effective strategies for emission reduction. Concurrently, in the realm of steel manufacturing, the study breaks new ground by harnessing operational data to predict EAF flat bath temperature with unprecedented accuracy. This advancement holds significant implications for energy conservation and operational optimization, addressing the urgent need for sustainability in industrial practices. This thesis not only bridges the gap between theoretical research and practical application but also sets a new benchmark for the utilization of data-driven approaches in environmental science and industrial engineering. By offering a detailed comparison of modeling techniques and their predictive prowess, it guides future research directions and underscores the potential of sophisticated analytical methods in tackling some of the most pressing global challenges. Ultimately, this study underscores the critical role of predictive modeling in achieving a sustainable future, providing valuable insights that can inform both global climate policy and industrial process optimization.

Share

COinS