Comprehensive analysis of large language model capabilities in face milling operations domain with virtual twin verification

Abstract

This paper presents a comprehensive analysis of large language models (LLMs) capabilities in the machine tool domain, specifically focusing on face milling operations. The research evaluates how different prompt techniques (zero-shot, few-shot, and tree-of-thought) affect LLMs' ability to perform tasks traditionally requiring human domain expertise, such as interpreting G-code, recommending appropriate cutting tools, and calculating machining parameters. Performance is evaluated by comparing LLM outputs to industry-standard CAM software and digital twin simulations to verify practical applicability. The findings indicate that current LLM technology shows promise for transforming and optimizing complex engineering tasks in manufacturing but still requires additional operator input and customized approaches to achieve complete operational accuracy. This work contributes to understanding how generative Artificial Intelligence (AI) can be leveraged to optimize, generalize, and standardize machining procedures in industrial applications.

Keywords

• Machining
• Face Milling
• Artificial Intelligence
• Large Language Models
• Generative AI

Yüzey frezeleme işlemleri alanında büyük dil modellerinin yeteneklerinin sanal ikiz doğrulama yöntemiyle kapsamlı analizi

Abstract

Bu makale, büyük dil modellerinin (LLM'lerin) takım tezgahı alanındaki yeteneklerine dair kapsamlı bir analiz sunmaktadır ve özellikle alın frezeleme operasyonlarına odaklanmaktadır. Araştırma, farklı istem tekniklerinin (sıfır-atışlı, az-atışlı ve düşünce ağacı) LLM'lerin geleneksel olarak insan alan uzmanlığı gerektiren görevleri yerine getirme yeteneğini nasıl etkilediğini değerlendirmektedir; bu görevler arasında G-kodunu yorumlama, uygun kesici takımlar önerme ve işleme parametrelerini hesaplama yer almaktadır. Performans, LLM çıktılarının endüstri standardı CAM yazılımı ve dijital ikiz simülasyonları ile karşılaştırılarak pratik uygulanabilirliğin doğrulanması yoluyla değerlendirilmektedir. Bulgular, mevcut LLM teknolojisinin imalatta karmaşık mühendislik görevlerini dönüştürme ve optimize etme konusunda umut vaat ettiğini ancak tam operasyonel doğruluğa ulaşmak için hala ek operatör girdisi ve özelleştirilmiş yaklaşımlar gerektirdiğini göstermektedir. Bu çalışma, üretken Yapay Zekanın (AI) endüstriyel uygulamalarda işleme prosedürlerini optimize etmek, genelleştirmek ve standartlaştırmak için nasıl kullanılabileceğinin anlaşılmasına katkıda bulunmaktadır.

Keywords

• İşleme
• Alın Frezeleme
• Yapay Zeka
• Büyük Dil Modelleri
• Üretken Yapay Zeka

References

1. [1] Parashar, B. S. N., & Mittal, R. (2013). Elements of manufacturing processes. PHI Learning Pvt. Ltd. [Cro
2. [2] Yusup, N., Zain, A. M., & Hashim, S. Z. M. (2012). Evolutionary techniques in optimizing machining parameters: Review and recent applications (2007–2011). Expert Systems with Applications, 39, 9909–9927. [CroosRef]
3. [3] Davis, J. R. (Ed.). (1989). ASM handbook, volume 16: Machining. ASM International.
4. [4] Soori, M., Arezoo, B., & Dastres, R. (2023). Machine learning and artificial intelligence in CNC machine tools, a review. Sustainable Manufacturing and Service Economics, 2, Article 100014. [CroosRef]
5. [5] Pimenov, D. Y., Bustillo, A., Wojciechowski, S., Sharma, V. S., Gupta, M. K., & Kuntoğlu, M. (2023). Artificial intelligence systems for tool condition monitoring in machining: Analysis and critical review. Journal of Intelligent Manufacturing, 34, 2079–2121. [CroosRef]
6. [6] Navaneethan, G., Palanisamy, S., Jayaraman, P. P., Kang, Y.B., Stephens, G., Papageourgiou, A., & Navarro-Devia, J. (2024). A review of automated cutting tool selection methods. The International Journal of Advanced Manufacturing Technology, 133, 1063–1092. [CroosRef]
7. [7] Oberg, E., Jones, F. D., Horton, H. L., Ryffel, H. H., & McCauley, C. J. (2020). Machinery's handbook (31st ed.). Industrial Press.
8. [8] Li, Y., Zhao, H., Jiang, H., Pan, Y., Liu, Z., Wu, Z., Shu, P., Tian, J., Lyu, Y., Blenk, P., Pence, J., Rupram, J., Banu, E., Liu, N, Song, W., Zhai, X., Song, K., Zhu, D., Li, B., Wang, X., & Liu, T. (2024). Large language models for manufacturing arXiv. Preprint. doi: 10.48550/arXiv.2410.21418

9. [9] Makatura, L., Foshey, M., Wang, B., Hähnlein, F., Ma, P., Deng, B., Tjandrasuwita, M., Spielberg, A., Owens, C. E., Chen, P. Y., Zhao, A., Zhu, A., Norton, W. J., Gu, E., Jacob, J., Li, Y., Schulz, A., & Matusik, W. (2024). Large language models for design and manufacturing. MIT GenAI. https://mit-genai.pubpub.org/pub/nmypmnhs Accessed Jun 03, 2026.
10. [CroosRef]
11. [10] Ni, M., Wang, T., Leng, J., Chen, C., & Chen, L. (2025). A large language model-based manufacturing process planning approach under industry 5.0. International Journal of Production Research, 120. [CroosRef] [11] Shahin, M., Hosseinzadeh, A., & Chen, F. F. (2025). Generative artificial intelligence in manufacturing: Applications, case studies, and future directions for next-generation intelligent production systems. The International Journal of Advanced Manufacturing Technology, 141(3-4), 11591265. [CroosRef]
12. [12] Mata, O., Ponce, P., Perez, C., & Ramirez, M. (2026). Digital twin designs with generative AI: Crafting a comprehensive framework for manufacturing systems. Journal of Intelligent Manufacturing, 37, 10491072. [CroosRef]
13. [13] Jignasu, A., Marshall, K., Ganapathysubramanian, B., Balu, A., Hegde, C., & Krishnamurthy, A. (2023). Towards foundational AI models for additive manufacturing: Language models for G-code debugging, manipulation, and comprehension. arXiv. Preprint. doi: 10.48550/arXiv.2309.02465 [CroosRef]
14. [14] Šket, K., Potočnik, D., Brezočnik, M., & Ficko, M. (2025). Large language models for G-code generation in CNC machining: A comparison of ChatGPT-3.5 and ChatGPT-4o. Advances in Production Engineering & Management, 20(2), 224–238. [CroosRef]
15. [15] Abdelaal, M., Lokadjaja, S., & Engert, G. (2025). GLLM: Self-corrective G-code generation using large language models with user feedback. arXiv. Preprint. doi: 10.48550/arXiv.2501.17584 [16] Kanimozhi, S., & Sriker, Y. S. (2024). Explorative deployment of fine-tuned large language model for on-site computerized numeric control machine operator assistance. 2024 IEEE Silchar Subsection Conference (SILCON). IEEE. [17] Jeon, J., Sim, Y., Lee, H., Han, C., Yun, D., & Kim, E. (2026). CNC-talks: Conversational machine monitoring via large language model and real-time data retrieval augmented generation. Journal of Manufacturing Systems, 85, 678688. [CroosRef]
16. [18] Stathatos, E., Benardos, P., & Vosniakos, G. C. (2026). Large language models for high-level computer-aided process planning in a distributed manufacturing paradigm. Robotics and Computer-Integrated Manufacturing, 100, 103233. [CroosRef]
17. [19] Smid, P. (2003). CNC programming handbook: A comprehensive guide to practical CNC programming. Industrial Press. [20] Stephenson, D. A., & Agapiou, J. S. (2016). Metal cutting theory and practice (3rd ed.). CRC Press. [CroosRef]
18. [21] Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, A., Schulman, J., Hilton, J., Kelton, F., Miller, K., Simens, M., Askell, A., Welinder, P., Christiano, P., Leike, J., & Lowe, R. (2022). Training language models to follow instructions with human feedback. arXiv. Preprint. doi: 10.48550/arXiv.2203.02155
19. [22] Wei, J., Bosma, M., Zhao, V. Y., Guu, K., Yu, A. W., Lester, B., Du, N., Dai, A. M., & Le, Q. V. (2021). Finetuned language models are zero-shot learners. arXiv. Preprint. doi: 10.48550/arXiv.2109.01652
20. [23] Min S, Lyu X, Holtzman A, Artetxe M, Lewis M, Hajishirzi H, & Zettlemoyer, L. Rethinking the role of demonstrations: What makes in-context learning work? arXiv. Preprint. doi: 10.48550/arXiv.2202.12837
21. [24] Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., & Zhou, D. (2022). Chain-of-thought prompting elicits reasoning in large language models arXiv. Preprint. doi: 10.48550/arXiv.2201.11903
22. [25] Siemens Digital Industries Software. (n.d.). NX CAM software: NX for manufacturing. Siemens Digital Industries Software. https://www.siemens.com/en-us/products/nx-manufacturing/cam-software Accessed on Jun 03, 2026.
23. [26] Siemens AG. (n.d.). Run MyVirtual Machine. Retrieved 2024, from Siemens AG. https://www.dex.siemens.com/industrialsoftware/machine-tool-software/create-myvirtual-machine-operate Accessed on Jun 03, 2026.
24. [27] Anthropic. (2025, February 24). Claude 3.5 Sonnet. https://www.anthropic.com/news/claude-3-7-sonnet Accessed on Jun 03, 2026
25. [28] DeepSeek. (2025, January 20). DeepSeek-R1. https://api-docs.deepseek.com/news/news250120 Accessed on Jun 03, 2026
26. [29] OpenAI. (2025, February 27). GPT 4.5. https://openai.com/index/introducing-gpt-4-5 Accessed on Jun 03, 2026
27. [30] Campean, E., & Pop, G. (2026). CNC milling optimization via intelligent algorithms: An AI-based methodology. Machines, 14(1), 89. [CroosRef]
28. [31] Aghaei, S., & Ansari, F. (2026). Foundation language models through the lens of manufacturing. Production & Manufacturing Research, 14(1), 2632468. [CroosRef]
29. [32] Darshan, S., Desai, K. A., & Bhattacharyya, A. (2025). Physics-informed experimental design for neural network-based cutting force model in end milling of carbon fiber reinforced polymer composites. Journal of Manufacturing Processes, 42, 440452. [CroosRef]
30. [33] Zhang, Q., Zhang, Q., Zhao, Y., Liu, Y., Wang, Z., & Ma, Y. (2025). Inverse solution of process parameters in gear grinding using hierarchical Bayesian physics informed neural network (HBPINN). Scientific Reports, 15, 18005. [CroosRef]