Ti6AI7Nb Alaşımının Mikro Frezelenmesinde Kesme Kuvvetinin Öngörülmesi için Yenilikçi Hibrit Derin Sinir Ağı Modeli

Öz

Titanyum alaşımları, yüksek mukavemet-ağırlık oranları, korozyon dirençleri ve biyouyumlulukları sayesinde havacılıktan savunmaya, biyomedikalden uzay teknolojilerine kadar pek çok kritik alanda vazgeçilmez malzemeler haline gelmiştir. Ancak bu alaşımlar, düşük ısıl iletkenlik ve yüksek kimyasal reaktivite gibi özellikleri nedeniyle işlenmesi güç malzemeler olarak bilinmektedir. Bu durum, özellikle, kesme kuvveti, takım ömrünü, boyutsal hassasiyeti ve iş parçası bütünlüğünü doğrudan etkileyen temel bir parametre olmasından dolayı kesme kuvvetinin doğru tahmin edilmesini hem teknik açıdan zorlaştırmakta hem de süreç güvenilirliği açısından zorunlu kılmaktadır. Bu çalışmada, Ti6AI7Nb alaşımının mikro frezelenmesi sürecinde kesme kuvvetinin yüksek doğrulukla tahmin edilmesine yönelik yeni bir hibrit derin sinir ağı modeli önerilmektedir. Önerilen modelde, evrişimli sinir ağı katmanı ile veriden anlamlı yerel özellikler otomatik olarak çıkarılırken, bu katmana paralel olarak konumlandırılan tam bağlantılı katmanlarda karmaşık ilişkileri ve küresel bilgileri çıkarmak üzere entegre edilmiştir. Önerilen model ve güncel yöntemlerin eğitimi ve testi için kısıtlı olan gerçek deneysel veriler, veri artırma tekniğiyle çoğaltılarak sentetik veriler üretilmiştir. Gerçekleştirilen kapsamlı analizlerde, önerilen paralel hibrit derin öğrenme modelinin kesme kuvveti tahmininde %97.13 R² skoru ile geleneksel makine öğrenmesi yöntemlerinden daha yüksek performans sergilediği ortaya koyulmuştur.

Anahtar Kelimeler

• Titanyum alaşımı
• mikro frezeleme
• kesme kuvveti
• yapay sinir ağı
• Ti6AI7Nb

Teşekkür

Bu çalışma, TÜBİTAK tarafından 223M358 numaralı proje kapsamında desteklenmiştir. Desteklerinden dolayı TÜBİTAK'a teşekkür ederiz.

An Innovative Hybrid Deep Neural Network Model for Predicting Cutting Force in the Micro-Milling of Ti6AI7Nb Alloy

Öz

Titanium alloys have become indispensable materials in many critical fields, ranging from aerospace and defense to biomedical applications and space technologies, owing to their high strength-to-weight ratio, corrosion resistance, and biocompatibility. However, these alloys are widely recognized as difficult-to-machine materials due to their inherently low thermal conductivity and high chemical reactivity. This characteristic makes the accurate prediction of cutting forces both technically challenging and practically essential, as cutting force is a fundamental parameter that directly influences tool life, dimensional accuracy, and workpiece integrity. In this study, a new parallel hybrid deep learning model is proposed for high-accuracy cutting force prediction in the micro-milling of Ti6Al7Nb alloy. In the proposed model, a convolutional neural network branch automatically extracts meaningful local features from the data, while a fully connected branch, positioned in parallel, is integrated to capture complex relationships and global information simultaneously. To address the scarcity of real experimental data required for training and testing the proposed model alongside state-of-the-art methods, a data augmentation technique was applied to generate statistically consistent synthetic samples. The comprehensive analyses conducted in this study demonstrate that the proposed parallel hybrid deep learning model achieves an R² score of 97.13% in cutting force prediction, outperforming conventional machine learning methods by a significant margin.

Anahtar Kelimeler

• Titanium alloy
• micro-milling
• cutting force
• artificial neural network
• Ti6AI7Nb.

Kaynakça

1. Q. Jiang and J. Song, “A Review on Cutting Force and Thermal Modeling, Toolpath Planning, and Vibration Suppression for Advanced Manufacturing,” Machines, vol. 14, no. 1, p. 60, Jan. 2026, doi: 10.3390/machines14010060.
2. R. Kaur, R. Kumar, and H. Aggarwal, “Systematic Review of Artificial Intelligence, Machine Learning, and Deep Learning in Machining Operations: Advancements, Challenges, and Future Directions,” Archives of Computational Methods in Engineering, vol. 32, no. 8, pp. 4983–5036, Dec. 2025, doi: 10.1007/s11831-025-10290-z.
3. K. Chen, W. Zhao, and X. Zhang, “Real-time milling force monitoring based on a parallel deep learning model with dual-channel vibration fusion,” The International Journal of Advanced Manufacturing Technology, vol. 126, no. 5–6, pp. 2545–2565, May 2023, doi: 10.1007/s00170-023-11233-3.
4. M. Pasandidehpoor, A. R. Nogueira, J. Mendes-Moreira, and R. Sousa, “Survey on machine learning applied to CNC milling processes,” Adv. Manuf., vol. 13, no. 4, pp. 847–885, Dec. 2025, doi: 10.1007/s40436-025-00564-x.
5. O. I. Elly and M. Takács, “Leveraging ensemble regressors and a metaheuristic algorithm for efficiency improvement of the micromilling process through force prediction and parameter optimization,” The International Journal of Advanced Manufacturing Technology, vol. 142, no. 9–10, pp. 4705–4726, Feb. 2026, doi: 10.1007/s00170-025-17156-5.
6. Z. A. Cevik, K. Ozsoy, A. Ercetin, and G. Sariisik, “Machine Learning-Driven Optimization of Machining Parameters Optimization for Cutting Forces and Surface Roughness in Micro-Milling of AlSi10Mg Produced by Powder Bed Fusion Additive Manufacturing,” Applied Sciences, vol. 15, no. 12, p. 6553, Jun. 2025, doi: 10.3390/app15126553.
7. V. Kumar, V. Dubey, and A. Kumar Sharma, “Comparative analysis of different machine learning algorithms in prediction of cutting force using hybrid nanofluid enriched cutting fluid in turning operation,” Mater. Today Proc., May 2023, doi: 10.1016/j.matpr.2023.05.216.
8. J. Xie, P. Hu, J. Chen, W. Han, and R. Wang, “Deep learning-based instantaneous cutting force modeling of three-axis CNC milling,” Int. J. Mech. Sci., vol. 246, p. 108153, May 2023, doi: 10.1016/j.ijmecsci.2023.108153.

9. A. N. Balasubramanian, N. Yadav, and A. Tiwari, “Analysis of cutting forces in helical ball end milling process using machine learning,” Mater. Today Proc., vol. 46, pp. 9275–9280, 2021, doi: 10.1016/j.matpr.2020.02.098.
10. H. Klippel et al., “Cutting Force Prediction of Ti6Al4V using a Machine Learning Model of SPH Orthogonal Cutting Process Simulations,” Journal of Machine Engineering, vol. 22, no. 1, pp. 111–123, Mar. 2022, doi: 10.36897/jme/147201.
11. P. Sahoo, T. Pratap, and K. Patra, “A hybrid modelling approach towards prediction of cutting forces in micro end milling of Ti-6Al-4V titanium alloy,” Int. J. Mech. Sci., vol. 150, pp. 495–509, Jan. 2019, doi: 10.1016/j.ijmecsci.2018.10.032.
12. T. Jagadesh and G. L. Samuel, “Mechanistic and Finite Element Model for Prediction of Cutting Forces During Micro-Turning of Titanium Alloy,” Machining Science and Technology, vol. 19, no. 4, pp. 593–629, Oct. 2015, doi: 10.1080/10910344.2015.1085318.
13. M. Rehan, M. Sana, M. U. Farooq, W. S. Yip, and S. To, “Analysing surface quality evolution and cutting forces in micro-milling of Ti6Al4V using experimental and machine learning approaches,” The International Journal of Advanced Manufacturing Technology, vol. 142, no. 5–6, pp. 2971–2989, Jan. 2026, doi: 10.1007/s00170-025-17201-3.
14. T. R. Babu and G. L. Samuel, “Intelligent prediction of machine tool performance in micro turning using textured inserts,” Manufacturing Technology Today (MTT), vol. 22, no. 4, pp. 66–73, Apr. 2023, doi: 10.58368/MTT.22.4.2023.66-73.
15. Y. Feng et al., “Force prediction in ultrasonic vibration-assisted milling,” Machining Science and Technology, vol. 25, no. 2, pp. 307–330, Mar. 2021, doi: 10.1080/10910344.2020.1815048.
16. G. C. Verma and P. M. Pandey, “Machining forces in ultrasonic-vibration assisted end milling,” Ultrasonics, vol. 94, pp. 350–363, Apr. 2019, doi: 10.1016/j.ultras.2018.07.004.
17. X. Chen, J. Tang, W. Shao, B. Hu, and J. Ye, “An Analytical and Experimental Study on Cutting Characteristics and Transient Cutting Force Modeling in Feed Directional Ultrasonic Vibration-Assisted Cutting of High Strength Alloys,” Materials, vol. 15, no. 20, p. 7388, Oct. 2022, doi: 10.3390/ma15207388.
18. R. H. Namlu, C. Turhan, B. L. Sadigh, and S. E. Kılıç, “Cutting force prediction in ultrasonic-assisted milling of Ti–6Al–4V with different machining conditions using artificial neural network,” Artificial Intelligence for Engineering Design, Analysis and Manufacturing, vol. 35, no. 1, pp. 37–48, Feb. 2021, doi: 10.1017/S0890060420000360.
19. R. Agarwal, V. Gupta, J. Singh, and V. Jain, “Prediction of surface roughness and cutting force induced during rotary ultrasonic bone drilling via statistical and machine learning algorithms,” Proc. Inst. Mech. Eng. C J. Mech. Eng. Sci., vol. 236, no. 23, pp. 11123–11135, Dec. 2022, doi: 10.1177/09544062221110407.
20. H. Gürbüz and Y. E. Gönülaçar, “Farklı Kesme Parametreleri ve MQL Debilerinde Elde Edilen Deneysel Değerlerin S/N Oranları ve YSA ile Analizi,” Politeknik Dergisi, vol. 24, no. 3, pp. 1093–1107, Sep. 2021, doi: 10.2339/politeknik.833833.
21. A. Kosarac, C. Mladjenovic, M. Zeljkovic, S. Tabakovic, and M. Knezev, “Neural-Network-Based Approaches for Optimization of Machining Parameters Using Small Dataset,” Materials, vol. 15, no. 3, p. 700, Jan. 2022, doi: 10.3390/ma15030700.
22. A. Mahmat, G. Dogan, B. Ergen, and N. Tosun, “Modeling and analysis of WEDM with a new deep neural network,” Proc. Inst. Mech. Eng. C J. Mech. Eng. Sci., vol. 239, no. 12, pp. 4581–4592, Jun. 2025, doi: 10.1177/09544062251324111.
23. G. Doğan, H. Uyanık, and B. Ergen, “A new lightweight convolutional neural network model for detecting drivable road regions,” Inf. Sci. (N. Y)., vol. 717, Nov. 2025, doi: 10.1016/j.ins.2025.122305.
24. M. A. Ilani and Y. M. Banad, “EDMNet: unveiling the power of machine learning in regression modeling of powder mixed-EDM,” International Journal of Advanced Manufacturing Technology, vol. 135, no. 5–6, pp. 2555–2570, Nov. 2024, doi: 10.1007/s00170-024-14686-2.
25. J. Yuan, K. Wang, T. Yu, and M. Fang, “Reliable multi-objective optimization of high-speed WEDM process based on Gaussian process regression,” Int. J. Mach. Tools Manuf., vol. 48, no. 1, pp. 47–60, Jan. 2008, doi: 10.1016/j.ijmachtools.2007.07.011.