AI-Assisted CNC Process Planning Using Computer Vision

Prajakta Dadasaheb Veer; Subhankar Sharad Kulkarni; Raj Rupesh Kumar Bhosale; Rushiprasad Uttam Gorgile

doi:10.69968/ijisem.2026v5i2376-380

Authors

Prajakta Dadasaheb Veer Mechanical Engineering Kolhapur Institute of Technology’s College of Engineering (Autonomous) Kolhapur, prajaktaveer28@gmail.com
Subhankar Sharad Kulkarni Mechanical Engineering Kolhapur Institute of Technology’s College of Engineering (Autonomous) Kolhapur, shubhankar.jsp@gmail.com
Raj Rupesh Kumar Bhosale Mechanical Engineering Kolhapur Institute of Technology’s College of Engineering (Autonomous) Kolhapur rajbhosale9261@gmail.com
Rushiprasad Uttam Gorgile Mechanical Engineering Kolhapur Institute of Technology’s College of Engineering (Autonomous) Kolhapur rushiprasadgorgile@gmail.com

DOI:

https://doi.org/10.69968/ijisem.2026v5i2376-380

Keywords:

CNC machining, computer vision, automated process planning, machine learning Industry 4.0

Abstract

Computer Numerical Control (CNC) machining is now an essential component of the modern manufacturing process, contributing to the creation of accurate components in various manufacturing sectors such as automotive and consumer electronics. However, traditional CNC programming remains a skill-intensive activity. Engineers are forced to look through engineering drawings, select the appropriate cutting tools, calculate machining operations, and set tool-paths in CAM packages all of which require time and rely heavily on personal experience. The paper is describing an AI-based system that processes the planning of CNC processes directly on the part drawings bypassing human input. It is capable of extracting machining features on its own drawings with the help of computer vision and image processing. Machine learning then intervenes to determine the appropriate operations, recommend appropriate tools, and compile initial toolpaths. All one does is to input a part image with a handful of critical dimensions and the system does the rest. It was prototyped in Python, with OpenCV on the vision side, and Scikit-learn on the machine learning. Experiments on a synthetic dataset provided good results on both feature recognition and tool suggestion, demonstrating that the idea works in practice. This entire framework is aimed at reducing CNC programming time and decreasing reliance on expert knowledge which is exactly in line with Industry 4.0 objectives. The geometries with complexities are yet a bit of a challenge and actual testing in the real world is another step to be considered.

References

[1] Y. Altintas, Manufacturing Automation: Metal Cut-ting Mechanics, Machine Tool Vibrations, and CNC Design. Cambridge, U.K.: Cambridge University Press, 2012.

[2] M. P. Groover, Automation, Production Systems, and Computer-Integrated Manufacturing, 4th ed. Pear-son, 2020.

[3] S. Kalpakjian and S. Schmid, Manufacturing Engineering and Technology, 7th ed. Pearson, 2014.

[4] H. Kagermann, W. Wahlster, and J. Helbig, “Recommendations for implementing the strategic initiative INDUSTRIE 4.0,” German National Academy of Sci-ence and Engineering, 2013.

[5] J. Lee, B. Bagheri, and H. A. Kao, “A cyber-physical systems architecture for Industry 4.0-based manufacturing systems,” Manufacturing Letters, vol. 3, pp. 18–23, 2015.

[6] S. T. Newman, A. Nassehi, R. Imani-Asrai, and V. Dhokia, “Energy efficient process planning for CNC machining,” CIRP Journal of Manufacturing Science and Technology, vol. 5, no. 2, pp. 127–136, 2012.

[7] K. Cheng and D. Huo, Micro-Cutting: Fundamentals and Applications. Wiley, 2013.

[8] T. Moriwaki, “Multi-functional machine tool,” CIRP Annals, vol. 57, no. 2, pp. 736–749, 2008.

[9] R. Teti, K. Jemielniak, G. O’Donnell, and D. Dornfeld, “Advanced monitoring of machining operations,” CIRP Annals, vol. 59, no. 2, pp. 717–739, 2010.

[10] J. Sun, Y. Guo, and Z. Liang, “Machining feature recognition based on geometric reasoning,” Computer-Aided Design, vol. 43, no. 12, pp. 1680–1690, 2011.

[11] Y. C. Nee, S. K. Ong, and K. F. Chryssolouris, “Computer-aided process planning,” CIRP Annals, vol. 56, no. 2, pp. 739–770, 2007.

[12] L. Wang and R. X. Gao, “Intelligent machining systems,” Springer, 2018.

[13] B. Denkena and J. Schmidt, “Adaptive process planning in milling,” CIRP Annals, vol. 55, no. 1, pp. 77–80, 2006.

[14] D. Dornfeld, Green Manufacturing: Fundamentals and Applications. Springer, 2013.

[15] Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, 2016.

[16] Krizhevsky, I. Sutskever, and G. Hinton, “ImageNet classification with deep convolutional neu-ral networks,” Advances in Neural Information Processing Systems, 2012.

[17] Redmon et al., “You Only Look Once: Unified real-time object detection,” IEEE Conference on Com-puter Vision and Pattern Recognition, 2016.

[18] G. Bradski, “The OpenCV library,” Dr. Dobb’s Journal of Software Tools, 2000.

[19] Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.

[20] S. Smith and J. Tlusty, “Update on high-speed milling dynamics,” Journal of Engineering for Industry, vol. 112, pp. 142–149, 1990.

[21] C. Brecher, Machine Tool Structures. Springer, 2015.

[22] J. Gao, Y. Yao, V. Y. C. Yip, L. L. Yeung, and C.

[23] Chan, “A cyber-physical systems architecture for Industry 4.0-based manufacturing systems,” Robotics and Computer-Integrated Manufacturing, vol. 39, pp. 11–18, 2016.

[24] Xu, J. M. David, and S. H. Kim, “The fourth industrial revolution: Opportunities and challenges,” International Journal of Financial Research, vol. 9, no. 2, pp. 90–95, 2018.

[25] K. Fu, S. Feng, and J. Gao, “Machining feature recognition for process planning,” Journal of Manufacturing Systems, vol. 37, pp. 398–407, 2015.

[26] Y. Liu, X. Xu, and L. Wang, “Cloud manufacturing: Key technologies and applications,” Robotics and Computer-Integrated Manufacturing, vol. 45, pp. 28–37, 2017.

[27] S. Wang, J. Wan, D. Li, and C. Zhang, “Implementing smart factory of Industry 4.0,” International Journal of Distributed Sensor Networks, vol. 12, 2016.

[28] T. Chang, Expert Process Planning for Manufacturing. Addison-Wesley, 1990.

[29] P. Ferreira and R. Liu, “Tool path generation for CNC machining,” Journal of Manufacturing Science and Engineering, vol. 128, no. 2, pp. 337–345, 2006.

[30] J. Lee, H. Davari, J. Singh, and V. Pandhare, “Industrial AI applications in smart manufacturing,” Manufacturing Letters, vol. 18, pp. 20–23, 2018.

[31] Verl, L. Wang, and G. Seliger, “Sustainable manufacturing systems,” CIRP Annals, vol. 63, no. 2, pp. 585–608, 2014.