A conscious lab-based approach for modelling and investigating the impact of influential parameters on feed rate and differential pressure in cement vertical roller mills

Document Type : Research Paper

Authors

School of Mining Engineering, College of Engineering, University of Tehran, Tehran, Iran

10.22059/ijmge.2025.395567.595253

Abstract

Vertical Roller Mills (VRMs) are widely used in energy-intensive industries like cement, steel, and chemicals due to their efficiency in grinding, drying, and material transport. However, two critical aspects remain underexplored: the correlation between operational variables and differential pressure (dp) and the influence of key parameters, such as feed rate, on mill performance. To address these gaps, this study utilized advanced machine learning methods, including Random Forest (RF), LightGBM, and Shapley Additive Explanations (SHAP), integrated within a Conscious Lab-based (CL) framework. The study focused on modelling feed rate as a manipulated and dp as a controlled variable, with SHAP employed to analyze variable interactions. Findings identified operational factors such as working pressure, dp, counter pressure, and mill fan speed as significant determinants of feed rate setpoints. Working pressure emerged as the most influential variable impacting both dp and feed rate, establishing its critical role in stabilizing operations and regulating performance. Key variables, such as working pressure, mill fan speed, and feed rate, were also identified as primary contributors to dp, reflecting the principles of the CL framework for dynamic control. Validation tests revealed LightGBM as the best-performing algorithm, achieving the highest R² values (0.98 and 0.97) and lowest RMSE (1.34 and 0.16) for feed rate and dp prediction, respectively, making it the optimal model for predicting feed rate and dp. This study highlighted the potential of combining machine learning with the CL framework to accurately model complex relationships among variables, optimize VRM operations, and advance sustainable energy-efficient practices in the cement industry.

Keywords

Main Subjects

References

[1] Altun, D. (2017). Mathematical modelling of vertical roller mills.
[2] Altun, D., Benzer, H., Aydogan, N., & Gerold, C. (2017). Operational parameters affecting the vertical roller mill performance. Minerals Engineering, 103, 67-71.
[3] Altun, D., Gerold, C., Benzer, H., Altun, O., & Aydogan, N. (2015). Copper ore grinding in a mobile vertical roller mill pilot plant. International Journal of Mineral Processing, 136, 32-36.
[4] Authenrieth, M., Hyttrek, T., Reintke, A., & McGarel, S. (2012). ILM-master for VRMs. Int. Cement Rev.
[5] Barani, K., Azadi, M., & Fatahi, R. (2022). An approach to measuring and modelling the residence time distribution of cement clinker in vertical roller mills. Mineral Processing and Extractive Metallurgy, 131(2), 158-165.
[6] Belmajdoub, F., & Abderafi, S. (2023). Efficient machine learning model to predict fineness, in a vertical raw meal of Morocco cement plant. Results in Engineering, 17, 100833.
[7] Breiman, L. (1996). Bagging predictors. Machine learning, 24, 123-140.
[8] Bussmann, N., Giudici, P., Marinelli, D., & Papenbrock, J. (2021). Explainable machine learning in credit risk management. Computational Economics, 57(1), 203-216.
[9] Chelgani, S. C., Homafar, A., & Nasiri, H. (2024). CatBoost-SHAP for modeling industrial operational flotation variables–A “conscious lab” approach. Minerals Engineering, 213, 108754.
[10] Chelgani, S. C., Nasiri, H., & Tohry, A. (2021). Modeling of particle sizes for industrial HPGR products by a unique explainable AI tool-A “Conscious Lab” development. Advanced Powder Technology, 32(11), 4141-4148.
[11] Chelgani, S. C., Nasiri, H., Tohry, A., & Heidari, H. R. (2023). Modeling industrial hydrocyclone operational variables by SHAP-CatBoost-A “conscious lab” approach. Powder technology, 420, 118416.
[12] Fahrland, T., & Zysk, K. (2013). Cements ground in the vertical roller mill fulfil the quality requirements of the market. Cement International, 11(2), 64-69.
[13] Fatahi, R., Abdollahi, H., Noaparast, M., & Hadizadeh, M. (2025). Modeling the working pressure of a cement vertical roller mill using SHAP-XGBoost: A “conscious lab of grinding principle” approach. Powder technology, 120923.
[14] Fatahi, R., Khosravi, R., Siavoshi, H., Yazdani, S., Hadavandi, E., & Chehreh Chelgani, S. (2021). Ventilation prediction for an industrial cement raw ball mill by bnn—a “conscious lab” approach. Materials, 14(12), 3220.
[15] Fatahi, R., Nasiri, H., Dadfar, E., & Chehreh Chelgani, S. (2022). Modeling of energy consumption factors for an industrial cement vertical roller mill by SHAP-XGBoost: a" conscious lab" approach. Scientific Reports, 12(1), 7543.
[16] Fatahi, R., Nasiri, H., Homafar, A., Khosravi, R., Siavoshi, H., & Chehreh Chelgani, S. (2023). Modeling operational cement rotary kiln variables with explainable artificial intelligence methods–a “conscious lab” development. Particulate Science and Technology, 41(5), 715-724.
[17] Fatahi, R., Pournazari, A., & Shah, M. P. (2022). A cement Vertical Roller Mill modeling based on the number of breakages. Advanced Powder Technology, 33(10), 103750.
[18] Fedoryshyn, R., Nykolyn, H., Zagraj, V., & Pistun, Y. (2012). The improved system for automation and optimization of solid material grinding by means of ball mills. Annals of DAAAM for 2012 & Proceedings of the 23rd International DAAAM Symposium,
[19] Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine. Annals of statistics, 1189-1232.
[20] Fujimoto, S. (1993). Reducing specific power usage in cement plants. World Cement;(United Kingdom), 24(7).
[21] Gong, H., Sun, Y., Shu, X., & Huang, B. (2018). Use of random forests regression for predicting IRI of asphalt pavements. Construction and Building Materials, 189, 890-897.
[22] Harder, J. (2010). Grinding trends in the cement industry. ZKG INTERNATIONAL, 63(4), 46-+.
[23] Hu, H., Li, Y., Lu, Y., Li, Y., Song, G., & Wang, X. (2024). Numerical Study of Flow Field and Particle Motion Characteristics on Raw Coal Vertical Roller Mill Circuits. Minerals Engineering, 218, 108997.
[24] Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T.-Y. (2017). Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30.
[25] Li, B., Chen, G., Si, Y., Zhou, X., Li, P., Li, P., & Fadiji, T. (2022). GNSS/INS integration based on machine learning LightGBM model for vehicle navigation. Applied sciences, 12(11), 5565.
[26] Lin, X.-F., & Zhang, M.-Q. (2016). Modelling of the vertical raw cement mill grinding process based on the echo state network. 2016 12th World Congress on Intelligent Control and Automation (WCICA),
[27] Little, W. (2021). Performance of the vertical roller mill in a mineral processing application when coupled with internal and external classifiers.
[28] Liu, C., Chen, Z., Zhang, W., Yang, C., Mao, Y., Yu, Y., & Xie, Q. (2020). Effects of blade parameters on the flow field and classification performance of the vertical roller mill via numerical investigations. Mathematical Problems in Engineering, 2020(1), 3290694.
[29] Liu, H., Xiao, Q., Jin, Y., Mu, Y., Meng, J., Zhang, T., Jia, H., & Teodorescu, R. (2022). Improved LightGBM-based framework for electric vehicle lithium-ion battery remaining useful life prediction using multi health indicators. Symmetry, 14(8), 1584.
[30] Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in neural information processing systems, 30.
[31] Mangalathu, S., Shin, H., Choi, E., & Jeon, J.-S. (2021). Explainable machine learning models for punching shear strength estimation of flat slabs without transverse reinforcement. Journal of Building Engineering, 39, 102300.
[32] Mao, H., Deng, X., Jiang, H., Shi, L., Li, H., Tuo, L., Shi, D., & Guo, F. (2021). Driving safety assessment for ride-hailing drivers. Accident Analysis & Prevention, 149, 105574.
[33] Matin, S., Hower, J. C., Farahzadi, L., & Chelgani, S. C. (2016). Explaining relationships among various coal analyses with coal grindability index by Random Forest. International Journal of Mineral Processing, 155, 140-146.
[34] Meng, Q., Wang, Y., Xu, F., & Shi, X. (2015). Control strategy of cement mill based on bang-bang and fuzzy PID self-tuning. 2015 IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER),
[35] Ouallouche, F., Lazri, M., & Ameur, S. (2018). Improvement of rainfall estimation from MSG data using Random Forests classification and regression. Atmospheric Research, 211, 62-72.
[36] Pareek, P., & Sankhla, V. S. (2021). Increase productivity of vertical roller mill using seven QC tools. IOP Conference Series: Materials Science and Engineering,
[37] Sahasrabudhe, R., Sistu, P., Sardar, G., & Gopinath, R. (2006). Control and optimization in cement plants. IEEE Control Systems Magazine, 26(6), 56-63.
[38] Schaefer, H. (2001). Loesche vertical roller mills for the comminution of ores and minerals. Minerals Engineering, 14(10), 1155-1160.
[39] Stanišić, D., Jorgovanović, N., Popov, N., & Čongradac, V. (2015). Soft sensor for real-time cement fineness estimation. ISA transactions, 55, 250-259.
[40] Wager, S., & Athey, S. (2018). Estimation and inference of heterogeneous treatment effects using random forests. Journal of the American Statistical Association, 113(523), 1228-1242.
[41] Worrell, E., Martin, N., & Price, L. (2000). Potentials for energy efficiency improvement in the US cement industry. Energy, 25(12), 1189-1214.
[42] Xu, B., & Sun, Y. (2020). On fault feature extraction and diagnosis of vertical mill. Engineering Research Express, 2(4), 045006.
[43] Yan-yan, N., Guang, Z., Ming-zhe, Y., & Zhuo, W. (2011). Design of intelligent control system for Vertical Roller Mill. 2011 2nd International Conference on Intelligent Control and Information Processing,
[44] Zhu, M., Ji, Y., Zhang, Z., & Sun, Y. (2020). A data-driven decision-making framework for online control of vertical roller mill. Computers & Industrial Engineering, 143, 106441.
International Journal of Mining and Geo-Engineering
Volume 59, Issue 2
June 2025
Pages 129-135

Files

Share

How to cite

Statistics