Predicting and Explaining Pig Iron Production on Charcoal Blast Furnaces: A Machine Learning Approach

References

• Agarwal A, Tewary U, Pettersson F, Das S, Saxén H, Chakraborti N (2010) Analysing blast furnace data using evolutionary neural network and multiobjective genetic algorithms. Ironmaking Steelmaking 37(5):353–359.Google Scholar
• Behe MJ (1996) Darwin’s Black Box: The Biochemical Challenge to Evolution (Simon and Schuster, New York).Google Scholar
• Bendel RB, Afifi AA (1977) Comparison of stopping rules in forward “stepwise” regression. J. Amer. Statist. Assoc. 72(357):46–53.Google Scholar
• Breiman L (1996) Bagging predictors. Machine Learn. 24:123–140.Google Scholar
• Breiman L (2001) Random forests. Machine Learn. 45:5–32.Google Scholar
• Castro LF, Tavares RP (2002) Balanço geral e térmico do alto-forno. (Metalsider, Belo. Horizonte, Brazil), 17–26.Google Scholar
• Chai T, Draxler RR (2014) Root mean square error (RMSE) or mean absolute error (MAE)?—Arguments against avoiding RMSE in the literature. Geoscientific Model Development 7(3):1247–1250.Google Scholar
• Chatterjee S, Deng S, Liu J, Shan R, Jiao W (2018) Classifying facts and opinions in Twitter messages: A deep learning-based approach. J. Bus. Anal. 1(1):29–39.Google Scholar
• Chen J (2001) A predictive system for blast furnaces by integrating a neural network with qualitative analysis. Engrg. Appl. Artificial Intelligence 14(1):77–85.Google Scholar
• Chen T, Guestrin C (2016) Xgboost: A scalable tree boosting system. Proc. 22nd ACM SIGKDD Internat. Conf. Knowledge Discovery Data Mining (ACM, New York), 785–794.Google Scholar
• Chugh T, Chakraborti N, Sindhya K, Jin Y (2017) A data-driven surrogate-assisted evolutionary algorithm applied to a many-objective blast furnace optimization problem. Materials Manufacturing Processes 32(10):1172–1178.Google Scholar
• Craddock PT (1995) Early Metal Mining and Production (Edinburgh University Press, Edinburgh, UK).Google Scholar
• Dayhoff JE, DeLeo JM (2001) Artificial neural networks: Opening the black box. Cancer 91(8):1615–1635.Google Scholar
• Delen D, Cogdell D, Kasap N (2012) A comparative analysis of data mining methods in predicting NCAA bowl outcomes. Internat. J. Forecasting 28(2):543–552.Google Scholar
• Delen D, Sharda R, Bessonov M (2006) Identifying significant predictors of injury severity in traffic accidents using a series of artificial neural networks. Accident Anal. Prevention 38(3):434–444.Google Scholar
• Delen D, Tomak L, Topuz K, Eryarsoy E (2017) Investigating injury severity risk factors in automobile crashes with predictive analytics and sensitivity analysis methods. J. Transport Health 4:118–131.Google Scholar
• De Myttenaere A, Golden B, Le Grand B, Rossi F (2016) Mean absolute percentage error for regression models. Neurocomputing 192:38–48.Google Scholar
• Dreiseitl S, Ohno-Machado L (2002) Logistic regression and artificial neural network classification models: A methodology review. J. Biomedical Informatics 35(5–6):352–359.Google Scholar
• Eryarsoy E, Delen D (2019) Predicting the outcome of a football game: A comparative analysis of single and ensemble analytics methods. Proc. 52nd Hawaii Internat. Conf. System Sci. (University of Hawaii at Manoa, Honolulu, HI), 1107–1115.Google Scholar
• Frank KA (2000) Impact of a confounding variable on a regression coefficient. Sociol. Methods Res. 29(2):147–194.Google Scholar
• Friedman JH (2001) Greedy function approximation: A gradient boosting machine. Ann. Statist. 29(5):1189–1232.Google Scholar
• Gao C, Jian L, Luo S (2011) Modeling of the thermal state change of blast furnace hearth with support vector machines. IEEE Trans. Indust. Electron. 59(2):1134–1145.Google Scholar
• Geurts P, Ernst D, Wehenkel L (2006) Extremely randomized trees. Machine Learn. 63:3–42.Google Scholar
• Hastie T, Tibshirani R, Friedman J (2009) Boosting and additive trees. The Elements of Statistical Learning, Springer Series in Statistics (Springer, New York), 337–387.Google Scholar
• Isnugroho K, Birawidha DC (2018) The production of pig iron from crushing plant waste using hot blast cupola. Alexandria Engrg. J. 57:427–433.Google Scholar
• Jain AK, Chandrasekaran B (1982) 39 dimensionality and sample size considerations in pattern recognition practice. Handbook Statist. 2:835–855.Google Scholar
• Kim G, Khalid HR, Kim H, Lee HK (2017) Alkali activated slag pastes with surface-modified blast furnace slag. Cement Concrete Composites 76:39–47.Google Scholar
• Krauss C, Do XA, Huck N (2017) Deep neural networks, gradient-boosted trees, random forests: Statistical arbitrage on the S&P 500. Eur. J. Oper. Res. 259(2):689–702.Google Scholar
• Kuhn M (2008) Building predictive models in R using the caret package. J. Statist. Software 28(5):1–26.Google Scholar
• Landsberg PT (2014) Thermodynamics and Statistical Mechanics (Courier Corporation, North Chelmsford, MA).Google Scholar
• Li Y, Zhang S, Yin Y, Xiao W, Zhang J (2017) A novel online sequential extreme learning machine for gas utilization ratio prediction in blast furnaces. Sensors (Basel) 17(8):1847–1856.Google Scholar
• Louppe G, Wehenkel L, Sutera A, Geurts P (2013) Understanding variable importances in forests of randomized trees. Proc. Adv. Neural Inform. Processing Systems (NIPS) (ACM, New York), 431–439.Google Scholar
• Mahanta BK, Chakraborti N (2018) Evolutionary data driven modeling and multi objective optimization of noisy data set in blast furnace iron making process. Steel Res. Internat. 89(9):1800121.Google Scholar
• Olson DL, Delen D (2008) Advanced Data Mining Techniques (Springer Science & Business Media, Berlin).Google Scholar
• Peacey JG, Davenport WG (2016) The Iron Blast Furnace: Theory and Practice (Elsevier, Amsterdam).Google Scholar
• Pettersson F, Chakraborti N, Saxén H (2007) A genetic algorithms based multi-objective neural net applied to noisy blast furnace data. Appl. Soft Comput. 7:387–397.Google Scholar
• Quinlan JR (1986) Induction of decision trees. Machine Learn. 1:81–106.Google Scholar
• Saha B, Goebel K, Christophersen J (2009) Comparison of prognostic algorithms for estimating remaining useful life of batteries. Trans. Inst. Measurement Control 31(3):293–308.Google Scholar
• Sakamoto Y, Ishiguro M, Kitagawa G (1986) Akaike Information Criterion Statistics (Springer Netherlands, Dordrecht, Netherlands).Google Scholar
• Saxén H, Hinnela J (2004) Model for burden distribution tracking in the blast furnace. Mineral Processing Extractive Metallurgy Rev. 25(1):1–27.Google Scholar
• Saxén H, Pettersson F (2007) Nonlinear prediction of the hot metal silicon content in the blast furnace. ISIJ Internat. 47(12):1732–1737.Google Scholar
• Saxén H, Pettersson F, Gunturu K (2007) Evolving nonlinear time-series models of the hot metal silicon content in the blast furnace. Materials Manufacturing Processes 22(5):577–584.Google Scholar
• Schwabacher M (2005) A Survey of Data-Driven Prognostics. Infotech@Aerospace. (AIAA, Reston, VA), 7002–7007.Google Scholar
• Sharda R, Delen D, Turban E (2016) Business Intelligence, Analytics, and Data Science: A Managerial Perspective (Pearson, New York).Google Scholar
• Spanlang A, Wukovits W, Weiss B (2016) Development of a blast furnace model with thermodynamic process depiction by means of the Rist operating diagram. Chemical Engrg. Trans. 52:973–978.Google Scholar
• Spoerl JS (2004) A brief history of iron and steel production. Accessed November 1, 2020, https://www.academia.edu/31060927/A_Brief_History_of_Iron_and_Steel_Production.Google Scholar
• Tang X, Zhuang L, Jiang C (2009) Prediction of silicon content in hot metal using support vector regression based on chaos particle swarm optimization. Expert Systems Appl. 36(9):11853–11857.Google Scholar
• Tunckaya Y, Koklukaya E (2015) Comparative prediction analysis of 600 MWe coal-fired power plant production rate using statistical and neural-based models. J. Energy Inst. 88(1):11–18.Google Scholar
• Ueda S, Natsui S, Nogami H, Yagi J, Ariyama T (2010) Recent progress and future perspective on mathematical modeling of blast furnace. ISIJ Internat. 50(7):914–923.Google Scholar
• Wakelin DH (1999) The Making, Shaping, and Treating of Steel: Ironmaking, vol. 2 (AISE Steel Foundation, Pittsburgh).Google Scholar
• Willmott CJ, Matsuura K (2005) Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate Res. 30(1):79–82.Google Scholar
• Willmott CJ, Matsuura K, Robeson SM (2009) Ambiguities inherent in sums-of-squares-based error statistics. Atmospheric Environment 43(3):749–752.Google Scholar
• Wolpert DH, Macready WG (1995) No free lunch theorems for search. Working paper, Santa Fe Institute, Santa Fe, NM.Google Scholar
• Wu D, Jennings C, Terpenny J, Gao RX, Kumara S (2017) A comparative study on machine learning algorithms for smart manufacturing: Tool wear prediction using random forests. J. Manufacturing Sci. Engrg. 139(7):071018.Google Scholar
• Youyou W, Kosinski M, Stillwell D (2015) Computer-based personality judgments are more accurate than those made by humans. Proc. Natl. Acad. Sci. USA 112(4):1036–1040.Google Scholar
• Zeng J, Gao C (2009) Improvement of identification of blast furnace ironmaking process by outlier detection and missing value imputation. J. Process Control 19(9):1519–1528.Google Scholar
• Zhou D, Cheng S, Wang Y, Jiang X (2017) The production of large blast furnaces during 2016 and future development of ironmaking in China. Ironmaking Steelmaking 44(10):714–720.Google Scholar