THERMAL SCIENCE

International Scientific Journal

RESEARCH ON LIME ROTARY KILN TEMPERATURE PREDICTION BY MULTI-MODEL FUSION NEURAL NETWORK BASED ON DYNAMIC TIME DELAY ANALYSIS

ABSTRACT
The lime rotary kiln systems are widely used in the metallurgical industry, where the combustion state is exceptionally complex, and it is difficult to predict and control the calcined zone’s temperature. The lime rotary kiln system uses the entropy and grey correlation model, combining the lime rotary kiln operation process to determine the input and output characteristics of the model. Then, it analyzes the time lag and inertia in the lime rotary kiln combustion system to compensate for the temperature prediction in the lime rotary kiln by using the CNN-BILSTM-OC model. Correcting the expected output results with the actual situation. The experimental analysis shows that the proposed model has a higher prediction accuracy than others. The maximum relative error calculated for the future temperature prediction is 0.2098%, while the generalized average of the root mean square error of the model under different working conditions is 0.9639. The generalized average of the mean absolute error is 0.6683, which shows that the model has a strong generalization ability to meet practical applications.
KEYWORDS
PAPER SUBMITTED: 2023-09-02
PAPER REVISED: 2023-10-26
PAPER ACCEPTED: 2023-11-02
PUBLISHED ONLINE: 2023-12-10
DOI REFERENCE: https://doi.org/10.2298/TSCI230902264L
CITATION EXPORT: view in browser or download as text file
THERMAL SCIENCE YEAR 2024, VOLUME 28, ISSUE Issue 3, PAGES [2703 - 2715]
REFERENCES
  1. Hu, Y., et al., Working Condition Recognition Based on Transfer Learning and Attention Mechanism for a Rotary Kiln, Entropy, 24 (2022), 9, 1186
  2. Urbano, J. J., et al., Dynamic Modelling of the Heat Transfer Process in Rotary Kilns with Indirect Oil Heating: Parametric Analysis of Gypsum Calcination Case, Thermal Science, 26 (2022), 2C, pp. 1637-1648
  3. Li, J., et al., The DTDR-ALSTM: Extracting Dynamic Time-Delays to Reconstruct Multivariate Data for Improving Attention-Based LSTM Industrial Time Series Prediction Models, Knowledge-Based Systems, 211 (2021), 106508
  4. Tian, Z. D., et al., The SVM Predictive Control for Calcination Zone Temperature in Lime Rotary Kiln with Improved PSO Algorithm, Transactions of the Institute of Measurement and Control, 40 (2018), 10, pp. 3134-3146
  5. Zhang, R. F., et al., Recognition Method of Cement Rotary Kiln Burning State Based on Otsu-Kmeans flame Image Segmentation and SVM, Optik, 243 (2021), 167418
  6. Chen, H., et al., Recognition of the Temperature Condition of a rotary kiln Using Dynamic Features of a Series of Blurry Flame Images, IEEE Transactions on Industrial Informatics, 12 (2016), 1, pp. 148-157
  7. Hu, W. Y., Mao, Z. Z., Forecasting for Chaotic Time Series Based on GRP-lstmGAN Model: Application Temperature Series of Rotary Kiln, Entropy, 25 (2022), 1, 52
  8. Xu, K. K., et al., Cement Rotary Kiln Temperature Prediction Based on Time-Delay Calculation and Residual Network and Bidirectional Novel Gated Recurrent Unit Multi-Model Fusion, Measurement, 218 (2023), 113123
  9. Zheng, J. Q., et al., Hybrid Model of a Cement Rotary Kiln Using an Improved Attention-Based Recurrent Neural Network, ISA Transactions, 129 (2022), Part B, pp. 631-643
  10. Wang, W., et al., A Soft Sensor Modelling Method with Dynamic Time-Delay Estimation and Its Application in Wastewater Treatment Plant, Biochemical Engineering Journal, 172 (2021), 108048
  11. Okoji, A. I., et al., Energetic Assessment Of A Precalcining Rotary Kiln In A Cement Plant Using Process Simulator And Neural Networks, Alexandria Engineering Journal, 61 (2022), 7, pp. 5097-5109
  12. Li, P., et al., A Synergy Model of Material and Energy Flow Analysis for the Calcination Process of Green Petroleum Coke in Rotary Kiln, Thermal Science, 26 (2022), 2C, pp. 1809-1823
  13. Xue, H. B., et al., Data Quality Evaluation of Photovoltaic Power Station based on Entropy Weight Method and Grey Comprehensive Evaluation Method, Journal of Physics: Conference Series, 2399 (2022), 1, 012001
  14. Edmund, W. M., Numerical Calculus, Princeton University Press., Princeton, N. J., USA, 2015
  15. Alzahrani, S., et al., Continuous Mobile User Authentication Using a Hybrid CNN-Bi-LSTM Approach, CMC-Computers Materials and Continua, 75 (2023), 1, pp. 651-667
  16. Guo, Y. L., Mao, Z. Z., Long-Term Prediction Model for NOx Emission Based on LSTM - Transformer, Electronics, 12 (2023), 18, 3929
  17. Tao, L., et al., Rotary kiln Combustion State Recognition Based on Convolutional Neural Network, Journal of Physics:Conference Series, 1575 (2020), 1, 012030
  18. Wang, N. E., Li, Z. M., Short Term Power Load Forecasting Based on BES-VMD and CNN-Bi-LSTM Method with Error Correction, Frontiers in Energy Research, 10 (2023), 1076529
  19. Xiong, W. L., et al., The JITL based MWGPR Soft Sensor For Multi-Mode Process with Dual-Updating Strategy, Computers and Chemical Engineering, 90 (2016), July, pp. 260-267
  20. Guo, X. F., et al., The RUL Prediction of Lithium Ion Battery Based on CEEMDAN-CNN BiLSTM Model, Energy Reports, 9 (2023), Suppl. 10, pp. S1299-S1306

© 2024 Society of Thermal Engineers of Serbia. Published by the Vinča Institute of Nuclear Sciences, National Institute of the Republic of Serbia, Belgrade, Serbia. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International licence