Machine Learning-Based Surrogate Modeling and Genetic Algorithm Optimization of Industrial Spray Drying Operations

Abstract

Industrial spray drying is a complex nonlinear process characterized by strong interactions among thermal, mechanical, environmental, and temporal variables, making accurate prediction and operational optimization challenging. This study proposes a hybrid machine learning–evolutionary optimization framework for predictive modeling and intelligent operational optimization in industrial spray drying systems. The framework integrates Random Forest Regression (RFR) for nonlinear process prediction with a Genetic Algorithm (GA) for adaptive exploration of optimal operating conditions under industrial constraints. The RFR model achieved strong predictive performance, with a coefficient of determination of R² = 0.9144 and stable generalization performance (cross-validation R² = 0.8427 ± 0.2027), demonstrating robustness under dynamic industrial variability. Feature importance analysis revealed gas flow and temporal dynamics as the dominant process drivers, enhancing interpretability and supporting operational decision-making. The GA-based optimization identified operating configurations that improved process efficiency by approximately 5.91% compared to baseline conditions while maintaining operational feasibility. The results demonstrate that integrating ensemble learning with evolutionary optimization provides both high predictive accuracy and actionable optimization capability for complex industrial systems. Furthermore, the proposed surrogate-assisted framework reduces computational dependency on physical experimentation by enabling rapid evaluation of candidate operating conditions through data-driven intelligence. The study contributes a deployable data-driven optimization architecture for intelligent and energy-efficient manufacturing operations within Industry 4.0 environments.

Keywords

• Machine Learning
• Random Forest Regression
• Genetic Algorithm
• Surrogate-Assisted Optimization
• Intelligent Manufacturing
• Industry 4.0

Makine Öğrenmesi ve Akıllı Süreç Modelleme Kullanılarak Endüstriyel Sprey Kurutma İşlemlerinin Vekil Destekli Evrimsel Optimizasyonu

Abstract

Endüstriyel sprey kurutma, termal, mekanik, çevresel ve zamansal değişkenler arasındaki güçlü etkileşimlerle karakterize edilen karmaşık doğrusal olmayan bir süreçtir ve bu durum doğru tahmin ile operasyonel optimizasyonu zorlaştırmaktadır. Bu çalışma, endüstriyel sprey kurutma sistemlerinde tahmine dayalı modelleme ve akıllı operasyonel optimizasyon için hibrit bir makine öğrenmesi–evrimsel optimizasyon çerçevesi önermektedir. Önerilen çerçeve, doğrusal olmayan süreç tahmini için Rastgele Orman Regresyonu (RFR) ve endüstriyel kısıtlar altında optimum çalışma koşullarının uyarlanabilir şekilde araştırılması için Genetik Algoritmayı (GA) entegre etmektedir. RFR modeli, R² = 0,9144 belirleme katsayısı ve kararlı genelleştirme performansı (çapraz doğrulama R² = 0,8427 ± 0,2027) ile güçlü tahmin başarısı göstermiştir. Özellik önem analizi, gaz akışı ve zamansal dinamiklerin temel süreç belirleyicileri olduğunu ortaya koyarak yorumlanabilirliği ve operasyonel karar desteğini artırmıştır. GA tabanlı optimizasyon, operasyonel uygulanabilirliği korurken temel çalışma koşullarına kıyasla yaklaşık %5,91 süreç verimliliği artışı sağlayan optimum parametre yapılandırmalarını belirlemiştir. Sonuçlar, topluluk öğrenmesi ve evrimsel optimizasyonun entegrasyonunun karmaşık endüstriyel sistemlerde hem yüksek tahmin doğruluğu hem de uygulanabilir optimizasyon yeteneği sağladığını göstermektedir. Ayrıca önerilen vekil destekli çerçeve, veri odaklı zeka yoluyla aday çalışma koşullarının hızlı değerlendirilmesini sağlayarak fiziksel deneylere olan hesaplama bağımlılığını azaltmaktadır. Bu çalışma, Endüstri 4.0 ortamlarında akıllı ve enerji verimli üretim operasyonları için uygulanabilir veri odaklı bir optimizasyon mimarisi sunmaktadır.

Keywords

• Makine Öğrenmesi
• Rastgele Orman Regresyonu
• Genetik Algoritma
• Vekil Destekli Optimizasyon
• Akıllı Üretim
• Endüstri 4.0

References

1. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
2. Cerqueira, V., Torgo, L., & Mozetič, I. (2020). Evaluating time series forecasting models: An empirical study on performance estimation methods. Machine Learning, 109(11), 1997–2028. https://doi.org/10.1007/s10994-020-05910-7
3. Deb, K., Pratap, A., Agarwal, S., & Meyarivan, T. (2002). A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation, 6(2), 182–197. https://doi.org/10.1109/4235.996017
4. Doshi-Velez, F., & Kim, B. (2017). Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608.
5. Farinola, L. A. (2026). A framework for implementing Industry 4.0 technologies in smart manufacturing environments. Kocaeli Journal of Science and Engineering. Accepted for publication.
6. Farinola, L. A., & Bazarkhan, D. (2025). Optimization of Complex Spray Drying Operations in Manufacturing Using Machine Learning: Evaluating Techniques for Energy Efficiency and Product Quality Enhancement. Open Journal of Applied Sciences, 15(9), 2662-2691. https://www.scirp.org/journal/paperinformation?paperid=145657
7. Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical learning: Data mining, inference, and prediction (2nd ed.). Springer.
8. Holland, J. H. (1975). Adaptation in natural and artificial systems. University of Michigan Press. Jordan, M. I., & Mitchell, T. M. (2015). Machine learning: Trends, perspectives, and prospects. Science, 349(6245), 255–260. https://doi.org/10.1126/science.aaa8415

9. Kagermann, H., Wahlster, W., & Helbig, J. (2013). Recommendations for implementing the strategic initiative INDUSTRIE 4.0: Securing the future of German manufacturing industry. Forschungsunion/acatech. The official acatech record confirms the 2013 final report.
10. Lee, J., Bagheri, B., & Kao, H.-A. (2015). A cyber-physical systems architecture for Industry 4.0-based manufacturing systems. Manufacturing Letters, 3, 18–23. https://doi.org/10.1016/j.mfglet.2014.12.001
11. Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30, 4765–4774.
12. Pham, D. T., & Afify, A. A. (2005). Machine learning in automated manufacturing. Journal of Intelligent Manufacturing, 16(3), 307–314. https://doi.org/10.1007/s10845-005-7026-3
13. Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). “Why should I trust you?” Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1135–1144). ACM. https://doi.org/10.1145/2939672.2939778
14. Vogel-Heuser, B., Fay, A., Schaefer, I., & Tichy, M. (2018). Evolution of software in automated production systems: Challenges and research directions. Journal of Systems and Software, 143, 1–16. https://doi.org/10.1016/j.jss.2018.05.011
15. Wahab, W., Alshamsi, R., Alharsousi, B., Alnuaimi, M., Alhammadi, Z., & Al-Zaitone, B. (2025). Recent Developments in Pharmaceutical Spray Drying: Modeling, Process Optimization, and Emerging Trends with Machine Learning. Pharmaceutics, 17(12), 1605. https://doi.org/10.3390/pharmaceutics17121605
16. Wuest, T., Weimer, D., Irgens, C., & Thoben, K.-D. (2019). Machine learning in manufacturing: Advantages, challenges, and applications. Production & Manufacturing Research, 7(1), 1–23. https://doi.org/10.1080/21693277.2018.1522620
17. Yin, S., Li, X., Gao, H., & Kaynak, O. (2015). Data-based techniques focused on modern industry: An overview. IEEE Transactions on Industrial Electronics, 62(1), 657–667. https://doi.org/10.1109/TIE.2014.2308133