Improving steel making off-gas predictions by mixing classification and regression multi-modal multivariate models
This paper addresses the problem of real-time short-term multi-period off-gas prediction in a steel making batch process, denominated Linz-Donawitz Gas (LDG). Baselines, heuristic statistical methods, multi-modal multivariate Long Short-Term Memory (LSTM) and Ensemble Gradient Boosting Decision Tree (GBDT) strategies were proposed and compared. Proposed methods, mixing classification and regression tasks, achieved good results on recoverable LDG prediction, establishing a benchmark on subject for future works. Experiments suggest improvements from 19.4% to 15.85% on average in mean absolute percentage error (MAPE) over recent reviewed papers within a similar scenario at same steel making plant.
Colla, V. and et. al. (2019). Assessing the efficiency of the off-gas network management in integrated steelworks. Materiaux & Techniques, 107(1):104.
de Oliveira Junior, V. B., Pena, J. G. C., and Salles, J. L. F. (2016). An improved plant-wide multiperiod optimization model of a byproduct gas supply system in the iron and steel-making process. Applied energy, 164:462-474.
Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine. Annals of statistics, pages 1189-1232.
Fruehan, R. J. (1998). The making, shaping and treating of steel: steelmaking and refining volume. AISE steel Foundation.
Gorishniy, Y., Rubachev, I., Khrulkov, V., and Babenko, A. (2021). Revisiting deep learning models for tabular data. Advances in Neural Information Processing Systems, 34.
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.-Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30:3146-3154.
Li, S., Wei, X., and Yu, L. (2011). Numerical simulation of off-gas formation during top-blown oxygen converter steelmaking. Fuel, 90(4):1350-1360.
Luca Avila, R. d. and De Bona, G. (2020). Financial time series forecasting via ceemdan-lstm with exogenous features. In Brazilian Conference on Intelligent Systems, pages 558-572. Springer.
Ofli, F., Alam, F., and Imran, M. (2020). Analysis of social media data using multimodal deep learning for disaster response. arXiv preprint arXiv:2004.11838.
Pena, J. G. C., de Oliveira Junior, V. B., and Salles, J. L. F. (2019). Optimal scheduling of a by-product gas supply system in the iron-and steel-making process under uncertainties. Computers & Chemical Engineering, 125:351-364.
Sala, D. A., Jalalvand, A., Van Yperen-De Deyne, A., and Mannens, E. (2018). Multivariate time series for data-driven endpoint prediction in the basic oxygen furnace. In 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), pages 1419-1426. IEEE.
Staudemeyer, R. C. and Morris, E. R. (2019). Understanding lstm-a tutorial into long short-term memory recurrent neural networks. arXiv preprint arXiv:1909.09586.
Wang, T., Leung, H., Zhao, J., and Wang, W. (2020). Multiseries featural lstm for partial periodic time-series prediction: A case study for steel industry. IEEE Transactions on Instrumentation and Measurement, 69(9):5994-6003.
Zhao, J., Wang, W., and Sheng, C. (2018). Industrial time series prediction. In Data-Driven Prediction for Industrial Processes and Their Applications, pages 53-119. Springer.