In the copper smelting Flue Gas Sulfuric Acid, accurate prediction of the converter inlet temperature is of great engineering significance for ensuring safe operation, reducing energy consumption, and improving system stability. To address the strong coupling, long time delay, and pronounced nonlinearity inherent in this process, we proposed a data-driven soft-sensing method designed for real-world industrial applications. The proposed approach was validated in an actual "two-conversion–two-absorption" industrial system. First, the Partial Autocorrelation Function was employed to analyze Distributed Control System data, identifying the most relevant input variables and time windows to provide a high-correlation feature foundation for model construction. Then, a Gated Recurrent Unit neural network was utilized to model temporal dependencies, effectively capturing complex dynamic relationships while suppressing noise interference. Furthermore, an Attention Mechanism was incorporated to enhance the model's focus on key temporal features, improving adaptability to process fluctuations and enhancing the interpretability of prediction results. Finally, the proposed model was implemented and verified in an industrial Flue Gas Sulfuric Acid process. The experimental results demonstrated that the method maintains stable predictive performance and accurately captures the dynamic variation of the first-layer converter inlet temperature. It effectively assists operators in adjusting process parameters in real time, thereby improving system safety, continuity, and operational reliability. The findings verify the engineering feasibility and practical applicability of the proposed method, providing strong technical support for the intelligent operation of copper smelting sulfuric acid production systems.
Citation: Chunbo Wang, Xiaoli Li, Kang Wang. A data-driven predictive modeling approach for converter inlet temperature in the copper smelting acid-making process[J]. AIMS Electronics and Electrical Engineering, 2026, 10(2): 240-264. doi: 10.3934/electreng.2026010
In the copper smelting Flue Gas Sulfuric Acid, accurate prediction of the converter inlet temperature is of great engineering significance for ensuring safe operation, reducing energy consumption, and improving system stability. To address the strong coupling, long time delay, and pronounced nonlinearity inherent in this process, we proposed a data-driven soft-sensing method designed for real-world industrial applications. The proposed approach was validated in an actual "two-conversion–two-absorption" industrial system. First, the Partial Autocorrelation Function was employed to analyze Distributed Control System data, identifying the most relevant input variables and time windows to provide a high-correlation feature foundation for model construction. Then, a Gated Recurrent Unit neural network was utilized to model temporal dependencies, effectively capturing complex dynamic relationships while suppressing noise interference. Furthermore, an Attention Mechanism was incorporated to enhance the model's focus on key temporal features, improving adaptability to process fluctuations and enhancing the interpretability of prediction results. Finally, the proposed model was implemented and verified in an industrial Flue Gas Sulfuric Acid process. The experimental results demonstrated that the method maintains stable predictive performance and accurately captures the dynamic variation of the first-layer converter inlet temperature. It effectively assists operators in adjusting process parameters in real time, thereby improving system safety, continuity, and operational reliability. The findings verify the engineering feasibility and practical applicability of the proposed method, providing strong technical support for the intelligent operation of copper smelting sulfuric acid production systems.
| [1] |
Cui H, Cao Y (2023) How can market-oriented environmental regulation improve urban energy efficiency? Evidence from quasi-experiment in China's SO2 trading emissions system. Energy 278: 127660. https://doi.org/10.1016/j.energy.2023.127660 doi: 10.1016/j.energy.2023.127660
|
| [2] |
Zhang T, Peng H, Wu C, Guo Y, Wang J, Chen X, et al. (2023) Process compatible desulfurization of NSP cement production: A novel strategy for efficient capture of trace SO2 and the industrial trial. J Clean Prod 411: 137344. https://doi.org/10.1016/j.jclepro.2023.137344 doi: 10.1016/j.jclepro.2023.137344
|
| [3] |
Córdoba P, Rojas S (2024). Carbon sequestration through mineral carbonation: Using commercial FGD-gypsum from a copper smelter for sustainable waste management and environmental impact mitigation. J Environ Chem Eng 12: 112510. https://doi.org/10.1016/j.jece.2024.112510 doi: 10.1016/j.jece.2024.112510
|
| [4] |
Li L, Zhang X, Lian X, Zhang L, Zhang Z, Liu X, et al. (2025) Flue gas desulfurization and SO2 recovery within a flexible hydrogen-bonded organic framework. Nature Chemistry 17: 727‒733. https://doi.org/10.1038/s41557-025-01744-9 doi: 10.1038/s41557-025-01744-9
|
| [5] |
Zhou Z, Lu J, Ma X (2024) SO3/sulfuric acid mist removal in simulated flue gas: Multi-factor study based on two-film theory mass transfer process. Fuel 357: 129698. https://doi.org/10.1016/j.fuel.2023.129698Get rights and content doi: 10.1016/j.fuel.2023.129698Getrightsandcontent
|
| [6] |
Li X, Han J, Liu Y, Dou Z, Zhang T (2022) Summary of research progress on industrial flue gas desulfurization technology. Sep Purif Technol 281: 119849. https://doi.org/10.1016/j.seppur.2021.119849 doi: 10.1016/j.seppur.2021.119849
|
| [7] |
Wang X, Li H (2018) Soft sensor based on stacked auto-encoder deep neural network for air preheater rotor deformation prediction. Adv eng inform 36: 112‒119. https://doi.org/10.1016/j.aei.2018.03.003 doi: 10.1016/j.aei.2018.03.003
|
| [8] |
Weng Q, Tian X, Wang H, Wu X, Wang S, Zhuo Y, et al. (2022) Comprehensive effect of oxidant addition in an FGD slurry on the removal and distribution of selenium: a field study. Environ Sci Technol 56: 3544‒3551. https://pubs.acs.org/doi/10.1021/acs.est.1c07708 doi: 10.1021/acs.est.1c07708
|
| [9] |
Qiao Z, Wang X, Gu H, Tang Y, Si F, Romero C, et al. (2019) An investigation on data mining and operating optimization for wet flue gas desulfurization systems. Fuel 258: 116178. https://doi.org/10.1016/j.fuel.2019.116178 doi: 10.1016/j.fuel.2019.116178
|
| [10] |
Hou P, Bai J, Yin J (2013) On-line monitoring and optimization of performance indexes for limestone wet desulfurization technology. Applied Mechanics and Materials 295: 1020‒1028. https://doi.org/10.4028/www.scientific.net/AMM.295-298.1020 doi: 10.4028/www.scientific.net/AMM.295-298.1020
|
| [11] |
Li X, Dong J, Wang K (2023) Constrained nonlinear model predictive control of pH value in wet flue gas desulfurization process. Optim Contr Appl Meth 44: 1523‒1539. https://doi.org/10.1002/oca.2763 doi: 10.1002/oca.2763
|
| [12] |
Darake S, Hatamipour M, Rahimi A, Hamzeloui P (2016) SO2 removal by seawater in a spray tower: Experimental study and mathematical modeling. Chem Eng Res Des 109: 180‒189. https://doi.org/10.1016/j.cherd.2015.11.027 doi: 10.1016/j.cherd.2015.11.027
|
| [13] |
Zhao Z, Zhang Y, Gao W, Baleta J, Liu C, Li W, et al. (2021) Simulation of SO2 absorption and performance enhancement of wet flue gas desulfurization system. Process Saf Environ Prot 150: 453‒463. https://doi.org/10.1016/j.psep.2021.04.032 doi: 10.1016/j.psep.2021.04.032
|
| [14] |
Liu C, Zhao Z, Gao W, Baleta J, Li W, Li Q, et al. (2021). Process optimization of S (Ⅳ) oxidation in flue gas desulfurization scrubbers. Process saf environ prot 149: 610‒618. https://doi.org/10.1016/j.psep.2021.03.020 doi: 10.1016/j.psep.2021.03.020
|
| [15] |
Xin J, Zhou C, Jiang Y, Tang Q, Yang X, Zhou J (2023) A signal recovery method for bridge monitoring system using TVFEMD and encoder-decoder aided LSTM. Measurement 214: 112797. https://doi.org/10.1016/j.measurement.2023.112797 doi: 10.1016/j.measurement.2023.112797
|
| [16] |
Ren C, An N, Wang J, Li L, Hu B, Shang D (2014) Optimal parameters selection for BP neural network based on particle swarm optimization: A case study of wind speed forecasting. Knowledge-based systems 56: 226‒239. https://doi.org/10.1016/j.knosys.2013.11.015 doi: 10.1016/j.knosys.2013.11.015
|
| [17] |
Yuan X, Li L, Shardt Y, Wang Y, Yang C (2020) Deep learning with spatiotemporal attention-based LSTM for industrial soft sensor model development. IEEE T Ind Electron 68: 4404‒4414. https://doi.org/10.1109/TIE.2020.2984443 doi: 10.1109/TIE.2020.2984443
|
| [18] |
Lui C, Liu Y, Xie M (2022) A supervised bidirectional long short-term memory network for data-driven dynamic soft sensor modeling. IEEE T Instrum Meas 71: 1‒13. https://doi.org/10.1109/TIM.2022.3152856 doi: 10.1109/TIM.2022.3152856
|
| [19] |
Yuan X, Ou C, Wang Y, Yang C, Gui W (2019) A layer-wise data augmentation strategy for deep learning networks and its soft sensor application in an industrial hydrocracking process. IEEE T Neur Net Lear Syst 32: 3296‒3305. https://doi.org/10.1109/TNNLS.2019.2951708 doi: 10.1109/TNNLS.2019.2951708
|
| [20] | Yang Y, Yu H, Liu X (2022) A Variable Attention-Based Gated GRU Approach for Soft Sensor Models. In 2022 34th Chinese Control and Decision Conference (CCDC), 92‒96. https://doi.org/10.1109/CCDC55256.2022.10033933 |
Figures(9) / Tables(2)
Chunbo Wang, Xiaoli Li, Kang Wang. A data-driven predictive modeling approach for converter inlet temperature in the copper smelting acid-making process[J]. AIMS Electronics and Electrical Engineering, 2026, 10(2): 240-264. doi: 10.3934/electreng.2026010
DownLoad: