Prediction of Sinter Productivity Utilizing Deep Learning Frameworks - A Multivariate Analysis
DOI:
https://doi.org/10.30544/MMD42Abstract
The productivity of a sinter machine represents an essential techno-economic factor in the operation of a steel plant. It is contingent upon the careful composition of several constituents agglomerated to form sinter used in blast furnaces. Understanding the interrelationships between these constituents and their effects on sinter productivity presents an opportunity for improvement, and innovative methods can enhance our ability to assess their impact beyond traditional physical experimentation. This paper explores the application of deep learning (DL) methodologies to boost the prediction of sinter plant productivity. By gathering comprehensive industrial data from an integrated steel plant, this study aims to provide valuable insights that can contribute to optimizing operational efficiency. The study outlines a methodology that employs Long Short-Term Memory (LSTM), Bi-directional LSTM (BiLSTM), and Convolutional Neural Network BiLSTM (CNN BiLSTM) to forecast sinter productivity based on an analysis of sixteen input parameters. The novel architecture of the CNN-BiLSTM model is capable of exhibiting better results than baseline models with mean absolute error (MAE) 0.0239 T/m2–hr, mean squared error (MSE)- 0.0009 T/m2–hr, root mean squared error (RMSE)- 0.0301 T/m2–hr; and coefficient of determination (R2) - 0.8982. Finally, the evaluation metrics were validated statistically.
Keywords:
Sinter plant, productivity, dep learning, parameters, evaluation metricsReferences
Arpit, Mallick, Subhra Dhara, and Sushant Rath. “Application of Machine Learning Algorithms for Prediction of Sinter Machine Productivity.” Machine Learning with Applications 6, no. 100186 (2021): 1–13. https://doi.org/10.1016/j.mlwa.2021.100186.
Fathy, Ahmed, Hegazy Rezk, Dalia Yousri, Tamer Kandil, and Ahmed G. Abo-Khalil. “Real-Time Bald Eagle Search Approach for Tracking the Maximum Generated Power of Wind Energy Conversion System.” Energy 249 (2022): 123661. https://doi.org/10.1016/j.energy.2022.123661.
Feng, Yan, Xinmin Zhang, Chunjie Yang, Bing Hu, Weidong Qian, and Zhihuan Song. “Data-Driven Modelling Methods in Sintering Process: Current Research Status and Perspectives.” The Canadian Journal of Chemical Engineering 101 (2023): 4506–4522. https://doi.org/10.1002/cjce.24871.
Harvey, David, Stephen Leybourne, and Paul Newbold. “Testing the Equality of Prediction Mean Squared Errors.” International Journal of Forecasting 13, no. 2 (1997): 281–91. https://doi.org/10.1016/S0169-2070(96)00719-4.
Isibor, Kennedy Ihianle, Augustine O. Nwajana, Solomon Henry Ebenuwa, Richard I. Otuka, and Mobolaji O. “Deep Learning Approach for Human Activities Recognition from Multimodal Sensing Devices.” IEEE Access 8 (2020): 191474–90. https://doi.org/10.1109/ACCESS.2020.3027979.
Jaseena, K. U., and B. C. Kovoor. “Decomposition-Based Hybrid Wind Speed Forecasting Model Using Deep Bidirectional LSTM Networks.” Energy Conversion and Management 234 (2021): 113944. https://doi.org/10.1016/j.enconman.2021.113944.
Karina, Ana A., and Flávio T. Barros. “Optimization of Sintering Machine Parameters Using Simulated Annealing Metaheuristic.” Tecnologia em Metalurgia, Materiais e Mineração 21 (2024): e2965. https://doi.org/10.4322/2176-1523.20242965.
Keras: Deep Learning for humans n.d. https://keras.io/ (accessed June 15, 2024).
Li, Xiaolong, Xin Liu, Heng Li, Ruihang Liu, Zhongwei Zhang, Hongwei Li, Qiang Lyu, and Lei Wen. “Research on Sinter Quality Prediction System Based on Granger Causality Analysis and Stacking Integration Algorithm.” Metals 13, no. 2 (2023): 419. https://doi.org/10.3390/met13020419.
Liao, M. J., J. Lin, and J. Y. Lin. “Fuzzy Neural Networks-Based Quality Prediction System for Sintering Process.” IEEE Transactions on Fuzzy Systems 8, no. 3 (2000): 314–24. https://doi.org/10.1109/91.855919.
Mariano, Roberto S., and Daniel Preve. “Statistical Tests for Multiple Forecast Comparison.” Journal of Econometrics 169, no. 1 (2012): 123–30. https://doi.org/10.1016/j.jeconom.2012.01.014.
Memarzadeh, Golshan, and Farshid Keynia. “A New Short-Term Wind Speed Forecasting Method Based on Fine-Tuned LSTM Neural Network and Optimal Input Sets.” Energy Conversion and Management 213 (2020): 112824. https://doi.org/10.1016/j.enconman.2020.112824.
Rath, Sushant. “Sinter Machine Productivity.” Mendeley Data V1 (2021). https://doi.org/10.17632/72hgnwmsvs.
Reihanian, M., S. R. Asadullahpour, S. Hajarpour, and K. Gheisari. “Application of Neural Network and Genetic Algorithm to Powder Metallurgy of Pure Iron.” Materials & Design 32, no. 6 (2011): 3183–88. https://doi.org/10.1016/j.matdes.2011.02.049.
Singh, Kripash, Pranay Vakkantham, S. H. Nistala, and Venkataramana Runkana. “Multi-Objective Optimization of Integrated Iron Ore Sintering Process Using Machine Learning and Evolutionary Algorithms.” Transactions of the Indian Institute of Metals 73 (2020): 2033–39. https://doi.org/10.1007/s12666-020-01920-0.
Song, Qiang, and Xinyu Guo. “Application of Combined Gray Neural Network (GMNN) for the BTP in Sintering Process.” Academic Journal of Manufacturing Engineering 18, no. 3 (2020): 25–32.
Thiago, Paulo Silva, Alexandre M. Souza, Bruno A. Rocha, and Braulio V. Sousa. “Prediction of Sinter Plant Productivity by Neural Network.” In Proceedings of the 6th International Congress on the Science and Technology of Ironmaking (ICSTI), 42nd Ironmaking and Raw Material Seminar, 13th Brazilian Symposium on Iron Ore, vol. 2, 764–76. Rio de Janeiro: ABM, 2012.
Zhang, Jun, Aidi Xie, and Feng Shen. “Multi-Objective Optimization and Analysis Model of Sintering Process Based on BP Neural Network.” Journal of Iron and Steel Research International 14 (2007): 1–5. https://doi.org/10.1016/S1006-706X(07)60018-1.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Ram Babu Mukkamala, Rajaprasad SVS, Vishnu Namboodiri
This work is licensed under a Creative Commons Attribution 4.0 International License.
