Optimalisasi Set Point RPM Fan ID pada Industri Semen Menggunakan Algoritma XGBoost Regressor Berbasis Parameter Operasional dan Komposisi Kimia
DOI:
https://doi.org/10.26740/jte.v15n3.p185-194Keywords:
industri semen, Induced Draft Fan, RPM, XGBoost Regressor, machine learning, Google Looker StudioAbstract
Industri semen merupakan salah satu sektor industri berenergi tinggi yang membutuhkan pengelolaan operasi efisien untuk menjaga efisiensi energi dan stabilitas proses pembakaran pada kiln. Salah satu peralatan vital dalam sistem kiln adalah Induced Draft (ID) Fan yang berfungsi mengatur tekanan negatif dan aliran gas buang selama proses pembakaran. Penentuan setpoint kecepatan putar (RPM) ID Fan yang masih dilakukan secara manual berdasarkan pengalaman operator sering kali sulit menyesuaikan fluktuasi kondisi operasional dan karakteristik bahan baku. Penelitian ini bertujuan untuk mengoptimalkan penentuan setpoint RPM ID Fan menggunakan algoritma XGBoost Regressor berbasis 20 parameter operasional kiln. Dataset historis sebanyak 2.143 observasi diproses melalui alur prapemrosesan data, seleksi variabel, serta pembagian data training dan testing dengan rasio 80:20. Kinerja model dievaluasi menggunakan Mean Absolute Error (MAE), Root Mean Square Error (RMSE), dan Koefisien Determinasi (). Hasil penelitian menunjukkan bahwa model XGBoost Regressor dengan konfigurasi estimators 100 dan learning rate 0,1 menghasilkan performa terbaik dengan nilai sebesar 96,86%, MAE sebesar 0,7068 RPM, dan RMSE sebesar 0,9546 RPM, mengungguli Regresi Linear Dasar ( = 96,34%) serta menawarkan stabilitas regularisasi yang lebih baik dibanding Random Forest Regressor ( = 97,39%). Hasil prediksi diintegrasikan ke dalam dashboard interaktif Google Looker Studio untuk memberikan visualisasi real-time yang mendukung pengambilan keputusan berbasis data (data-driven decision-making) bagi Control Room Operator (CRO) guna meningkatkan efisiensi energi listrik dan stabilitas operasi kiln.
Kata kunci: industri semen, Induced Draft Fan, RPM, XGBoost Regressor, machine learning, Google Looker Studio.
Downloads
References
Aghdasinia, H., Hosseini, S. S., & Hamedi, J. (2020). Improvement of a cement rotary kiln performance using artificial neural network. Journal of Ambient Intelligence and Humanized Computing, 12, 7765 - 7776. https://doi.org/10.1007/s12652-020-02501-1
Allassak, N., Trichni, S., & Omary, F. (2025). Hybrid ARIMAX–LSTM Modeling for Enhanced Vibration Prediction in Rotating Machinery: Application to a Cement Mill Fan. Engineering, Technology & Applied Science Research. https://doi.org/10.48084/etasr.11845
Benchekroun, M. T., Zaki, S., Aboussaleh, M., Belrhiti, H., & Diassana, F. (2024). Development of a kiln petcoke mill predictive model based on a multi-regression XGBoost algorithm. The International Journal of Advanced Manufacturing Technology, 1-14. https://doi.org/10.1007/s00170-023-12689-z
Benchekroun, M. T., Zaki, S., & Aboussaleh, M. (2023). Kiln predictive modelization for performance optimization. The International Journal of Advanced Manufacturing Technology, 127, 1333 - 1339. https://doi.org/10.1007/s00170-023-11563-2
Bolbot, I., & Slovikovskyi, O. (2025). Intelligent Optimization Of Gas Burner Operating Modes For Cement Drying Units. Lighting Engineering & Power Engineering. https://doi.org/10.33042/2079-424x.2025.64.1.02
Cao, G., Zhang, Q., Lu, Z., & Liu, Z. (2023). Optimization Study of Setting Reference Values based on Combined Cement Grinding System. 2023 China Automation Congress (CAC), 2202-2207. https://doi.org/10.1109/cac59555.2023.10450494
Chelgani, S. C., Fatahi, R., Pournazari, A., & Nasiri, H. (2025). Modeling energy consumption indexes of an industrial cement ball mill for sustainable production. Scientific Reports, 15. https://doi.org/10.1038/s41598-025-03232-z
Demir, F., Özer, S., Demir, U., Körükçü, K., Oduncu, H., & Ekin, M. Ş. (2025). Design Optimization and Field Validation of Industrial Fans with CFD for Cement Production: Performance, Energy Savings, and Environmental Benefits. Sustainability. https://doi.org/10.3390/su172210279
Fatahi, R., Nasiri, H., Homafar, A., Khosravi, R., Siavoshi, H., & Chelgani, C. S. (2022). Modeling operational cement rotary kiln variables with explainable artificial intelligence methods – a “conscious lab” development. Particulate Science and Technology, 41, 715 - 724. https://doi.org/10.1080/02726351.2022.2135470
Fatahi, R., Nasiri, H., Dadfar, E., & Chelgani, C. S. (2022). Modeling of energy consumption factors for an industrial cement vertical roller mill by SHAP-XGBoost: a "conscious lab" approach. Scientific Reports, 12. https://doi.org/10.1038/s41598-022-11429-9
Machalek, D., & Powell, K. M. (2019). Model predictive control of a rotary kiln for fast electric demand response. Minerals Engineering, 144, 106021. https://doi.org/10.1016/j.mineng.2019.106021
Okoji, A., Anozie, A., Omoleye, J., Taiwo, A., & Babatunde, D. (2023). Evaluation of adaptive neuro-fuzzy inference system-genetic algorithm in the prediction and optimization of NOx emission in cement precalcining kiln. Environmental Science and Pollution Research, 30, 54835-54845. https://doi.org/10.1007/s11356-023-26282-0
Okoji, A., Anozie, A., Omoleye, J., Taiwo, A., & Osuolale, F. (2021). Energetic assessment of a precalcining rotary kiln in a cement plant using process simulator and neural networks. Alexandria Engineering Journal. https://doi.org/10.1016/j.aej.2021.10.010
Okoji, A., Anozie, A., & Omoleye, J. (2022). Evaluating the thermodynamic efficiency of the cement grate clinker cooler process using artificial neural networks and ANFIS. Ain Shams Engineering Journal. https://doi.org/10.1016/j.asej.2022.101704
Shin, D., Lee, J., Son, J., Yun, Y., Song, Y.-A., & Song, J. (2024). Intelligent Combustion Control in Waste-to-Energy Facilities: Enhancing Efficiency and Reducing Emissions Using AI and IoT. Energies. https://doi.org/10.3390/en17184634
Siame, M. C., Zvarivadza, T., Edjeou, W., Simate, I. N., & Lusambo, E. (2024). Integrating Process Re-Engineering Models in Cement Production to Improve Energy Efficiency. Applied Sciences. https://doi.org/10.3390/app14198850
Usman, M., Ahmad, I., Kano, M., Ahmad, F., Ahsan, M., & Sikander, U. (2025). Machine Learning-Based Optimization of Thermodynamic Performance of Combustion Processes in a Cement Manufacturing Plant. ACS Engineering Au. https://doi.org/10.1021/acsengineeringau.5c00050
Downloads
Published
How to Cite
Issue
Section
Abstract views: 17
,
PDF Downloads: 9
