Model Prediksi Pembentukan Blast Furnace Slag Berbasis Regresi Linear Berganda pada Industri Baja
DOI:
https://doi.org/10.29313/bcsies.v6i2.24045Keywords:
Blast furnace Slag, Predictive modeling, Regresi Linear Berganda, Industri Baja, Komposisi Kimia SlagAbstract
Abstract. Blast furnace generates slag as a major by-product in the steel industry, affecting operational efficiency, flux consumption, energy requirements, and waste management. Variations in slag chemical composition contribute to fluctuations in slag formation, requiring a data-driven predictive approach to support process control. This study aims to develop a blast furnace slag formation prediction model using multiple linear regression based on key chemical composition parameters, including CaO, SiO₂, Fe, and Al₂O₃. The research data were obtained from blast furnace process observations during April 2026, consisting of 17 operational datasets. The analysis involved regression model development, significance testing, coefficient of determination evaluation, and comparison between actual and Predicted slag values. The results indicate that the developed regression model achieved an R² value of 0.9244, an adjusted R² value of 0.8969, and a Significance F value of 4.1296 × 10⁻⁶. The model successfully explains most variations in slag formation and demonstrates high agreement between actual and Predicted values. Multiple linear regression provides a potential predictive modeling approach for improving blast furnace operation control and supporting sustainable steel industry development.
Abstrak. Blast furnace menghasilkan slag sebagai produk samping utama dalam industri baja yang berpengaruh terhadap efisiensi operasi, konsumsi flux, kebutuhan energi, dan pengelolaan limbah. Variasi komposisi kimia slag menyebabkan perubahan jumlah slag yang terbentuk sehingga diperlukan pendekatan prediktif berbasis data untuk mendukung pengendalian proses. Penelitian ini bertujuan mengembangkan model prediksi pembentukan blast furnace slag menggunakan regresi linear berganda berdasarkan parameter komposisi kimia CaO, SiO₂, Fe, dan Al₂O₃. Data penelitian diperoleh dari pengamatan proses blast furnace selama April 2026 dengan 17 data pengamatan. Analisis dilakukan melalui pembentukan model regresi, pengujian signifikansi, evaluasi koefisien determinasi, serta perbandingan nilai aktual dan prediksi. Hasil penelitian menunjukkan model regresi menghasilkan nilai R² sebesar 0,9244, adjusted R² sebesar 0,8969, dan Significance F sebesar 4,1296 × 10⁻⁶. Model mampu menjelaskan sebagian besar variasi pembentukan slag serta menunjukkan kedekatan tinggi antara nilai aktual dan prediksi. Pendekatan regresi linear berganda berpotensi diterapkan sebagai predictive modeling untuk mendukung optimasi operasi blast furnace dan pengembangan industri baja berkelanjutan.
References
Affan, H., Fehr, L., Al-Massri, G., Alassaad, F., Yaghi, A., & Ghanem, H. (2026). Valorization of Minimally Processed Blast furnace Slag in Industrial Mortars: Early-Age Performance and Embodied Carbon Reduction. Recycling, 11(7). https://doi.org/https://doi.org/10.3390/recycling11070122
Analia, X. V., & Aviasti. (2021). Perbaikan Kinerja Rantai Pasok Halal Berdasarkan Pengukuran dengan Model Supply Chain Operation Reference (SCOR). Jurnal Riset Teknik Industri, 1(2), 103–109. https://doi.org/10.29313/jrti.v1i2.395
Bernárdez, J. M., Boo, J., Diaz, J. I., & Medina, R. (2025). Interdepartmental Optimization in Steel Manufacturing: An Artificial Intelligence Approach for Enhancing Decision-Making and Quality Control. Applied System Innovation, 8(3). https://doi.org/https://doi.org/10.3390/asi8030063
Biswas, S., Grundlingh, N., Boardman, J., White, J., & Le, L. (2025). A Target Permutation Test for Statistical Significance of Feature Importance in Differentiable Models. Electronics, 14(3), 571. https://doi.org/10.3390/electronics14030571
Calix, R. A., Ugarte, O., Okosun, T., & Wang, H. (2023). Machine learning-Based Regression Models for Ironmaking Blast furnace Automation. Dynamics, 3(4), 636–655. https://doi.org/10.3390/dynamics3040034
Chen, H., Ou, Z., Lin, H., Wu, J., & He, M. (2026). Effect of Chemical Composition of Granulated Blast furnace Slag on Its Cementitious Properties. Buildings, 16(11), 2073. https://doi.org/10.3390/buildings16112073
Čuchor, T., Koleda, P., Šustek, J., Štefančin, L., Kminiak, R., Koleda, P., & Vyhnáliková, Z. (2026). Evaluation of Regression Models for Predicting Cutting Forces Based on Spindle Speed, Feed Speed and Milling Strategy During MDF Board Milling. Machines, 14(4), 359. https://doi.org/10.3390/machines14040359
Dzięcioł, J., & Radziemska, M. (2022). Blast furnace Slag, Post-Industrial Waste or Valuable Building Materials with Remediation Potensial? Minerals, 12(4). https://doi.org/https://doi.org/10.3390/min12040478
Ehteram, M., & Banadkooki, F. B. (2023). A Developed Multiple Linear Regression (MLR) Model for Monthly Groundwater Level Prediction. Water, 15(22), 3940. https://doi.org/10.3390/w15223940
Guo, Y., Zhang, Y., Chen, F., Wang, S., Yang, L., Xie, Y., & Xia, X. (2025). Optimizing High-Al2O3 Limonite Pellet Performance: The Critical Role of Basicity in Consolidation and Reduction. Metals, 15(7), 801. https://doi.org/10.3390/met15070801
Ilham Ramadhani Hasibuan, Rakhmat Ceha, & Luthfi Nurwandi. (2023). Penerapan Model Supply Chain 4.0 Scorecard di MIKHA Coffee Shop Bandung. Jurnal Riset Teknik Industri, 113–120. https://doi.org/10.29313/jrti.v3i2.2851
Jafar, R., Awad, A., Hatem, I., Jafar, K., Awad, E., & Shahrour, I. (2023). Multiple Linear Regression and Machine learning for Predicting the Drinking Water Quality Index in Al-Seine Lake. Smart Cities, 6(5), 2807–2827. https://doi.org/10.3390/smartcities6050126
Jovanović, B., Shabanaj, K., & Ševrović, M. (2023). Conceptual Model for Determining the Statistical Significance of Predictive Indicators for Bus Transit Demand Forecasting. Sustainability, 15(1), 749. https://doi.org/10.3390/su15010749
Lin, S.-J., Liu, C.-C., Tsai, D. M. T., Shih, Y.-H., Lin, C.-L., & Hsu, Y.-C. (2024). Prediction Models Using Decision Tree and Logistic Regression Method for Predicting Hospital Revisits in Peritoneal Dialysis Patients. Diagnostics, 14(6), 620. https://doi.org/10.3390/diagnostics14060620
Lin, Y., Yi, Y., Fang, M., Ma, W., & Liu, W. (2023). Prediction Model for SiO2 Activity in the CaO-Al2O3-SiO2-MgO Quaternary Slag System. Minerals, 13(4), 509. https://doi.org/10.3390/min13040509
Liu, R., Gao, Z.-Y., Li, H.-Y., Liu, X.-J., & Lv, Q. (2024). Research on Blast furnace Ingredient Optimization Based on Improved Grey Wolf Optimization Algorithm . Metals, 14(7). https://doi.org/https://doi.org/10.3390/met14070798
López-Rodríguez, J., Jiménez-Lugos, C., Flores-Favela, M., Hernández-Ramírez, A., Cruz-Ramírez, A., Martínez-Morales, C., Pérez-Labra, M., & Romero-Serrano, A. (2026). Softening and Melting Behavior of Lead Blast furnace Slags. Metals, 16(1). https://doi.org/https://doi.org/10.3390/met16010104
Lorincz, J., Kusačić, M., Čusto, E., & Blažević, Z. (2025). A Comprehensive Multiple Linear Regression Modeling and Analysis of LoRa User Device Energy Consumption. Journal of Sensor and Actuator Networks, 15(1), 5. https://doi.org/10.3390/jsan15010005
Metlenkin, D. A., Kiselev, N. V., Platov, Y. T., Khaidarov, B. B., Khaidarov, T. B., Kolesnikov, E. A., Kuznetsov, D. V., Gorokhovsky, A. V., Offor, P. O., & Burmistrov, I. N. (2022). Identification of the Elemental Composition of Granulated Blast furnace Slag by FTIR-Spectroscopy and Chemometrics. Processes, 10(11), 2166. https://doi.org/10.3390/pr10112166
Mutombo, N. M.-A., & Numbi, B. P. (2022). Development of a Linear Regression Model Based on the Most Influential Predictors for a Research Office Cooling Load. Energies, 15(14), 5097. https://doi.org/10.3390/en15145097
Rauf, R. I., Alrasheedi, M. A., Sadiq, R., & Aldawsari, A. M. A. (2024). Evaluating Predictive Accuracy of Regression Models with First-Order Autoregressive Disturbances: A Comparative Approach Using Artificial Neural Networks and Classical Estimators. Mathematics, 12(24), 3966. https://doi.org/10.3390/math12243966
Rosdiana, H., Ashari, Y., & Fauzi Isniarno, N. (n.d.). Pengaruh Intensitas Curah Hujan terhadap Kegiatan Pemompaan pada Sump Berdasarkan Water Balance di PT XYZ. Jurnal Sangkuriang Bandung. Retrieved https://journal.sbpublisher.com/index.php/minetech
Rossi, E., Pecorini, I., & Iannelli, R. (2022). Multilinear Regression Model for Biogas Production Prediction from Dry Anaerobic Digestion of OFMSW. Sustainability, 14(8), 4393. https://doi.org/10.3390/su14084393
Sarici, T., Geckil, T., Ok, B., & Aksoy, H. S. (2025). An Investigation of the Usability of Alkali-Activated Blast furnace Slag-Additive Construction Demolition Waste as Filling Material. Materials, 18(2). https://doi.org/https://doi.org/10.3390/ma18020398
Sun, Y., Zhang, Z., Wu, C., & Liu, Z. (2025). Effect of CaO/SiO2 and MgO/Al2O3 on the Metallurgical Properties of Low Boron-Bearing High-Alumina Slag. Inorganics, 13(11), 346. https://doi.org/10.3390/inorganics13110346
Tian, H., Tang, J., & Wang, T. (2024). Furnace Temperature Model Predictive Control Based on Particle Swarm Rolling Optimization for Municipal Solid Waste Incineration. Sustainability, 16(17), 7670. https://doi.org/10.3390/su16177670
Wang, Z., Zheng, H., Zhang, Y., & Ge, L. (2024). Optimization of High-Alumina Blast furnace Slag Based on Exergy Analysis. Metals, 14(4), 465. https://doi.org/10.3390/met14040465
Yang, J.-A., & Lee, Y. (2025). Performance Improvement of a Multiple Linear Regression-Based Storm Surge Height Prediction Model Using Data Resampling Techniques. Journal of Marine Science and Engineering, 13(11), 2173. https://doi.org/10.3390/jmse13112173
Zhang, Q., Xing, H., Yang, A., Li, J., & Han, Y. (2025). A Comprehensive Review of Slag-Coating Mechanisms in Blast-Furnace Staves: Furnace Profile Optimazation and Material-Structure Design . Materials, 18(16). https://doi.org/https://doi.org/10.3390/ma18163727
Zhang, S., Jiang, D., Wang, Z., Wang, F., Zhang, J., Zong, Y., & Zeng, S. (2023). Predictive modeling of the Hot metal Sulfur Content in a Blast furnace Based on Machine learning. Metals, 13(2). https://doi.org/https://doi.org/10.3390/met13020288
