Energy Consumption Prediction in the Steel Industry Using Principal Component Analysis and Regression Tree Methods

Mery Septiani (1) , Genrawan Hoendarto (2) , Jimmy Tjen (3)
(1) Widya Dharma Pontianak University, Pontianak , Indonesia
(2) Widya Dharma Pontianak University, Pontianak , Indonesia
(3) Widya Dharma Pontianak University, Pontianak , Indonesia

DOI:

https://doi.org/10.18535/sshj.v9i01.1459

##plugins.themes.novelty.article.sidebar##

Issue
Vol. 9 No. 01 (2025)
Published
2025-01-03
Keywords:
    Principal Component Analysis, Regression Tree, Prediction, Energy Consumption, Steel Industry
PDF

Abstract

The steel industry is a major contributor to global energy consumption and greenhouse gas emissions, driving the need for enhanced efficiency. This study explore the use of Principal Component Analysis (PCA) combined with Regression tree (RT) techniques to predict energy consumption in the steel industry. PCA reduces data dimensionality, while RT addresses complex, non-linear relationships. Tested on a Kaggle dataset, the PCA and RT model achieved high accuracy, with a Root Mean Square Error (RMSE) of 0.67 and an accuracy rate of 90.82%, outperforming other methods in a comparative analysis. The model’s moderate training time of 1.18 seconds highlights its efficiency. Visual and comparative analysis confirmed the model’s strong alignment with observed energy consumption values and its balance between accuracy and computational efficiency. The PCA and RT model is an effective tool for predicting energy consumption in the steel industry, offering a practical approach to improving energy efficiency and sustainability. Future research could explore advanced techniques to further enhance predictive accuracy and model robustness.

References

[1] Y. Wang, X. He, and F. Jiang, “The energy conservation and emission reduction potentials in China’s iron and steel industry: Considering the uncertainty factor,” J. Clean. Prod., vol. 413, p. 137519, Aug. 2023, doi: 10.1016/J.JCLEPRO.2023.137519.
[2] J. Kim et al., “Decarbonizing the iron and steel industry: A systematic review of sociotechnical systems, technological innovations, and policy options,” Energy Res. Soc. Sci., vol. 89, Jul. 2022, doi: 10.1016/j.erss.2022.102565.
[3] Y. M. Wei, H. Liao, and Y. Fan, “An empirical analysis of energy efficiency in China’s iron and steel sector,” Energy, vol. 32, no. 12, pp. 2262–2270, Dec. 2007, doi: 10.1016/J.ENERGY.2007.07.007.
[4] I. T. Jollife and J. Cadima, “Principal component analysis: A review and recent developments,” Philos. Trans. R. Soc. A Math. Phys. Eng. Sci., vol. 374, no. 2065, 2016, doi: 10.1098/rsta.2015.0202.
[5] L. Breiman, J. H. Friedman, R. A. Olshen, and C. J. Stone, Classification A nd R egression Trees Leo. 2017.
[6] E. Worrell, “Advanced technologies and energy efficiency in the iron and steel industry in China,” Energy Sustain. Dev., vol. 2, no. 4, pp. 27–40, Nov. 1995, doi: 10.1016/S0973-0826(08)60148-9.
[7] N. Margolis and L. Sousa, “Energy and environmental profile of the U.S. iron and steel industry,” Proc. ACEEE Summer Study Energy Effic. Ind., no. August, pp. 103–113, 1997.
[8] B. Kiss and L. Neij, “The importance of learning when supporting emergent technologies for energy efficiency—A case study on policy intervention for learning for the development of energy efficient windows in Sweden,” Energy Policy, vol. 39, no. 10, pp. 6514–6524, Oct. 2011, doi: 10.1016/J.ENPOL.2011.07.053.
[9] T. T. X. Hasanbeigi, Ali, William R Morrow III, Jayant A Sathaye, Eric R Masanet, “Assessment of Energy Efficiency Improvement and CO2 Emission Reduction Potentials in the Iron and Steel Industry in China,” Lawrence Berkeley Natl. Lab., 2012, [Online]. Available: https://energyanalysis.lbl.gov/publications/assessment-energy-efficiency-2
[10] J. Suer, M. Traverso, and N. Jäger, “Review of Life Cycle Assessments for Steel and Environmental Analysis of Future Steel Production Scenarios,” Sustain., vol. 14, no. 21, 2022, doi: 10.3390/su142114131.
[11] H. W. Kua, “Integrated policies to promote sustainable use of steel slag for construction—A consequential life cycle embodied energy and greenhouse gas emission perspective,” Energy Build., vol. 101, pp. 133–143, Aug. 2015, doi: 10.1016/J.ENBUILD.2015.04.036.
[12] S. Siitonen, M. Tuomaala, and P. Ahtila, “Variables affecting energy efficiency and CO2 emissions in the steel industry,” Energy Policy, vol. 38, no. 5, pp. 2477–2485, May 2010, doi: 10.1016/J.ENPOL.2009.12.042.
[13] World Steel Association (WSA), “Fact Sheet: Energy use in the steel industry,” Worldsteel Assoc. Fact Sheet, no. Lci, pp. 1–3, 2013.
[14] J. De Beer, E. Worrell, and K. Blok, “Future technologies for energy-efficient iron and steel making,” Annu. Rev. Energy Environ., vol. 23, no. 1, pp. 123–205, 1998, doi: 10.1146/annurev.energy.23.1.123.
[15] F. Smarra, J. Tjen, and A. D’Innocenzo, “Learning methods for structural damage detection via entropy-based sensors selection,” Int. J. Robust Nonlinear Control, vol. 32, no. 10, pp. 6035–6067, 2022, doi: 10.1002/rnc.6124.
[16] Kaggle, “Steel Industry Energy Consumption Prediction.” [Online]. Available: https://www.kaggle.com/datasets/joebeachcapital/steel-industry-energy-consumption

Authors

Mery Septiani
Widya Dharma Pontianak University, Pontianak
Genrawan Hoendarto
Widya Dharma Pontianak University, Pontianak
Jimmy Tjen
Widya Dharma Pontianak University, Pontianak
[1]
“Energy Consumption Prediction in the Steel Industry Using Principal Component Analysis and Regression Tree Methods”, Soc. sci. humanities j., vol. 9, no. 01, Jan. 2025, doi: 10.18535/sshj.v9i01.1459.