Research Article
BibTex RIS Cite

AI-Driven Optimization of a 2.45 Ghz Microwave Drying System for Raw Corn: Enhancing Efficiency and Uniformity via Hybrid CNN-RNN Control

Year 2026, Volume: 9 Issue: 1, 11 - 12
https://doi.org/10.34248/bsengineering.1766754

Abstract

Bu çalışma, çok değişkenli ve doğrusal olmayan bir süreç olan çiğ mısırın mikrodalga ile kurutulmasını modellemek ve optimize etmek için Makine Öğrenimi (ML) ve Derin Öğrenme (DL) yaklaşımlarını entegre bir metodolojiye entegre etmektedir. Sürecin elektromanyetik davranışı ilk olarak CST Studio Suite yazılımı kullanılarak simüle edildi; çoklu mikrodalga kaynağının tek bir kaynağa kıyasla daha homojen ve etkili ısıtma sağladığı bulundu. Deney aşamasında, çeşitli giriş güçleri (200-500 W) ve geometrik konfigürasyonlar altında toplanan veriler kullanılarak Lojistik Regresyon ve SVR gibi klasik ML modelleri ile ANN, 1D CNN ve LSTM/GRU gibi DL modelleri eğitildi. Sonuçlar, CNN-RNN modelinin nem içeriği dinamikleri için en yüksek tahmin doğruluğunu sağladığını gösterdi. Deneysel verilerin sistematik AI odaklı analizi ile optimal kurutma konfigürasyonu 500 W mikrodalga gücü, 8,1 cm dalga kılavuzu mesafesi ve 26 cm dikey yerleştirme olarak belirlendi. Bu koşullar altında, 100 gram çiğ mısır 5 dakika içinde minimum kalite kaybıyla 40 grama kadar kurutuldu. ANN modeli, bu süreçte 0,978 R², 0,041 RMSE ve 0,033 MAE gibi etkileyici performans ölçütleri sergiledi. Bu sonuçlar, fiziksel simülasyon ve yapay zeka entegrasyonunun, mikrodalga kurutma gibi karmaşık endüstriyel süreçlerin verimliliğini ve kontrolünü iyileştirmek için güçlü bir karar destek sistemi oluşturma potansiyelini göstermektedir.

Project Number

124E825

References

  • Ak, M. U., Bilgin, G., Kaya, D., Kaya, A., & Bilgin, S. (2024). Vibration-based measurement system for breast tissue. Mühendislik Bilimleri ve Tasarım Dergisi, 12(2), 319–327.
  • Akdag, İ. (2021). Estimation of scattering parameters of U-slotted rectangular RFID patch antenna with machine learning models. Journal of Artificial Intelligence and Data Science, 1(1), 63–70.

AI-Driven Optimization of a 2.45 Ghz Microwave Drying System for Raw Corn: Enhancing Efficiency and Uniformity via Hybrid CNN-RNN Control

Year 2026, Volume: 9 Issue: 1, 11 - 12
https://doi.org/10.34248/bsengineering.1766754

Abstract

This study integrates Machine Learning (ML) and Deep Learning (DL) approaches into an integrated methodology to model and optimize the microwave drying of raw corn, which is a multi-variable and non-linear process. The electromagnetic behavior of the process was first simulated using CST Studio Suite software; it was found that a multi-microwave source provides more homogeneous and effective heating compared to a single source. In the experimental phase, classical ML models such as Logistic Regression and SVR, and DL models such as ANN, 1D CNN, and LSTM/GRU were trained using data collected under various input powers (200-500 W) and geometric configurations. The results demonstrated that the CNN-RNN model achieved the highest predictive accuracy for moisture content dynamics. Through systematic AI-driven analysis of experimental data, the optimal drying configuration was identified as 500 W microwave power, 8.1 cm waveguide distance, and 26 cm vertical placement. Under these conditions, 100 grams of raw corn was dehydrated to 40 grams in 5 minutes with minimal quality degradation. The ANN model demonstrated impressive performance metrics in this process, including 0.978 R², 0.041 RMSE, and 0.033 MAE. These results demonstrate the potential of physical simulation and artificial intelligence integration to create a powerful decision support system for improving the efficiency and control of complex industrial processes such as microwave drying.

Project Number

124E825

References

  • Ak, M. U., Bilgin, G., Kaya, D., Kaya, A., & Bilgin, S. (2024). Vibration-based measurement system for breast tissue. Mühendislik Bilimleri ve Tasarım Dergisi, 12(2), 319–327.
  • Akdag, İ. (2021). Estimation of scattering parameters of U-slotted rectangular RFID patch antenna with machine learning models. Journal of Artificial Intelligence and Data Science, 1(1), 63–70.
There are 2 citations in total.

Details

Primary Language English
Subjects Engineering Electromagnetics
Journal Section Research Article
Authors

Caner Murat 0000-0001-9251-9149

Project Number 124E825
Early Pub Date December 3, 2025
Publication Date December 3, 2025
Submission Date August 16, 2025
Acceptance Date November 17, 2025
Published in Issue Year 2026 Volume: 9 Issue: 1

Cite

APA Murat, C. (2025). AI-Driven Optimization of a 2.45 Ghz Microwave Drying System for Raw Corn: Enhancing Efficiency and Uniformity via Hybrid CNN-RNN Control. Black Sea Journal of Engineering and Science, 9(1), 11-12. https://doi.org/10.34248/bsengineering.1766754
AMA Murat C. AI-Driven Optimization of a 2.45 Ghz Microwave Drying System for Raw Corn: Enhancing Efficiency and Uniformity via Hybrid CNN-RNN Control. BSJ Eng. Sci. December 2025;9(1):11-12. doi:10.34248/bsengineering.1766754
Chicago Murat, Caner. “AI-Driven Optimization of a 2.45 Ghz Microwave Drying System for Raw Corn: Enhancing Efficiency and Uniformity via Hybrid CNN-RNN Control”. Black Sea Journal of Engineering and Science 9, no. 1 (December 2025): 11-12. https://doi.org/10.34248/bsengineering.1766754.
EndNote Murat C (December 1, 2025) AI-Driven Optimization of a 2.45 Ghz Microwave Drying System for Raw Corn: Enhancing Efficiency and Uniformity via Hybrid CNN-RNN Control. Black Sea Journal of Engineering and Science 9 1 11–12.
IEEE C. Murat, “AI-Driven Optimization of a 2.45 Ghz Microwave Drying System for Raw Corn: Enhancing Efficiency and Uniformity via Hybrid CNN-RNN Control”, BSJ Eng. Sci., vol. 9, no. 1, pp. 11–12, 2025, doi: 10.34248/bsengineering.1766754.
ISNAD Murat, Caner. “AI-Driven Optimization of a 2.45 Ghz Microwave Drying System for Raw Corn: Enhancing Efficiency and Uniformity via Hybrid CNN-RNN Control”. Black Sea Journal of Engineering and Science 9/1 (December2025), 11-12. https://doi.org/10.34248/bsengineering.1766754.
JAMA Murat C. AI-Driven Optimization of a 2.45 Ghz Microwave Drying System for Raw Corn: Enhancing Efficiency and Uniformity via Hybrid CNN-RNN Control. BSJ Eng. Sci. 2025;9:11–12.
MLA Murat, Caner. “AI-Driven Optimization of a 2.45 Ghz Microwave Drying System for Raw Corn: Enhancing Efficiency and Uniformity via Hybrid CNN-RNN Control”. Black Sea Journal of Engineering and Science, vol. 9, no. 1, 2025, pp. 11-12, doi:10.34248/bsengineering.1766754.
Vancouver Murat C. AI-Driven Optimization of a 2.45 Ghz Microwave Drying System for Raw Corn: Enhancing Efficiency and Uniformity via Hybrid CNN-RNN Control. BSJ Eng. Sci. 2025;9(1):11-2.

                            24890