This study proposes a system for generating efficient tool paths for complex shape machining using a standard triangulated language (STL)-format CAD model as input. As the STL format represents the surface of a three-dimensional shape as a collection of triangular meshes, it is a generic data format independent of CAD software, ensuring compatibility between different systems. The proposed system introduces a new tool-path generation algorithm to overcome the limitations of conventional scanning and achieve the high-precision and efficient machining of complex shapes. To accommodate complex geometries, including overhangs, this study incorporates 5-axis indexing machining, enabling multidirectional machining. Furthermore, the system performs shape simulation simultaneously with tool-path generation, enabling the identification of material removal regions and the elimination of unnecessary tool paths, thereby reducing machining time. A major challenge in this approach is the increased computational cost owing to the large number of iterative calculations required. To address this, this study utilizes parallel computation with a graphics processing unit to accelerate tool-path generation and air-cut detection, significantly reducing analysis time. Finally, this study conducted a case study to validate the effectiveness of the proposed system. Using an STL-format CAD model of a product shape, this study generated a numerical control program with the proposed system and performed actual machining. The results of the case study confirmed that the target CAD model could be machined without any issues.

1. [1] H. Ueno, “Intelligent technology for machine tools, flexible automation,” General Special Issue, Vol.61, No.3, pp. 107-112, 2017 (in Japanese). https://doi.org/10.11509/isciesci.61.3_107
2. [2] L. Wang, M. Holm, and G. Adamson, “Embedding a process plan in function blocks for adaptive machining,” CIRP Annals, Vol.59, Issue 1, pp. 433-436, 2010. https://doi.org/10.1016/j.cirp.2010.03.144
3. [3] Y. Woo, E, Wang, Y. S. Kim, and H. M. Rho, “A hybrid feature recognizer for machining process planning systems,” CIRP Annals, Vol.54, Issue 1, pp. 397-400, 2005. https://doi.org/10.1016/S0007-8506(07)60131-0
4. [4] X. Zhang, J. Wang, K. Yamazaki, and M. Mori, “A surface based approach to recognition of geometric features for quality freeform surface machining,” Computer-Aided Design, Vol.36, Issue 8, pp. 735-744, 2004. https://doi.org/10.1016/j.cad.2003.09.002
5. [5] J. Wang, Z. Wang, W. Zhu, and Y. Ji, “Recognition of freeform surface machining features,” J. of Computing and Information Science in Engineering, Vol.10, Issue 4, Article No.041006, 2010. https://doi.org/10.1115/1.3527075
6. [6] S. Lim, C. Yeo, F. He, J. Lee, and D. Mun, “Machining feature recognition using descriptors with range constraints for mechanical 3D models,” Int. J. of Precision Engineering and Manufacturing, Vol.24, pp. 1865-1888, 2023. https://doi.org/10.1007/s12541-023-00836-1
7. [7] E. Morinaga, T. Hara, H. Joko, H. Wakamatsu, and E. Arai, “Improvement of computational efficiency in flexible computer-aided process planning,” Int. J. Automation Technol., Vol.8, No.3, pp. 396-405, 2014. https://doi.org/10.20965/ijat.2014.p0396
8. [8] K. Dwijayanti and H. Aoyama, “Basic study on process planning for turning-milling center based on machining feature recognition,” J. of Advanced Mechanical Design, Systems and Manufacturing, Vol.8, No.4, Article No.14-00095, 2014. https://doi.org/10.1299/jamdsm.2014jamdsm0058
9. [9] Y. Shinoki, M. M. Isnaini, R. Sato, and K. Shirase, “Machining operation planning system which utilize past machining operation data to generate new NC program,” Trans. of the Japan Society of Mechanical Engineers, Vol.81, No.832, Article No.15-00280, 2015 (in Japanese). https://doi.org/10.1299/transjsme.15-00280
10. [10] I. Nishida and K. Shirase, “Automatic determination of cutting conditions for NC program generation by reusing machining case data based on geometric properties of removal volume,” J. of Advanced Mechanical Design, Systems, and Manufacturing, Vol.12, No.4, Article No.18-00237, 2018. https://doi.org/10.1299/jamdsm.2018jamdsm0093
11. [11] W.-L. Chu, M.-J. Xie, Q.-W. Chang, and H.-T. Yau, “Research on the recognition of machining conditions based on sound and vibration signals of a CNC milling machine,” IEEE Sensors J., Vol.22, Issue 7, pp. 6364-6377, 2022. https://doi.org/10.1109/jsen.2022.3150751
12. [12] F. Hojati, B. Azarhoushang, A. Daneshi, and R. H. Khiabani, “Prediction of machining condition using time series imaging and deep learning in slot milling of titanium alloy,” J. of Manufacturing and Materials Processing, Vol.6, Issue 6, Article No.145, 2022. https://doi.org/10.3390/jmmp6060145
13. [13] B. Bhandari and G. Park, “Non-contact surface roughness evaluation of milling surface using CNN-deep learning models,” Int. J. of Computer Integrated Manufacturing, Vol.37, Issue 4, pp. 423-437, 2021. https://doi.org/10.1080/0951192X.2022.2126012
14. [14] K. V. Rao, “Assessment of tool condition and surface quality using hybrid deep neural network: CNN-LSTM-based segmentation and statistical analysis,” J. of Tribology, Vol.147, Issue 8, Article No.084201, 2024. https://doi.org/10.1115/1.4067496
15. [15] K. Nakamoto, K. Shirase, H. Wakamatsu, A. Tsumaya, and E. Arai, “Development of digital copy milling system to realize nc programless machining: 3rd report, machining strategy for in-process adaptation of cutting conditions,” Trans. of the Japan Society of Mechanical Engineers Series C, Vol.69, No.677, pp. 270-277, 2003 (in Japanese). https://doi.org/10.1299/kikaic.69.270
16. [16] K. Shirase and K. Nakamoto, “Simulation technologies for the development of an autonomous and intelligent machine tool,” Int. J. Automation Technol., Vol.7, No.1, pp. 6-15, 2013. https://doi.org/10.20965/ijat.2013.p0006
17. [17] K. Shirase, T. Kondo, M. Okamoto, H. Wakamatsu, and E. Arai, “Development of virtual copy milling system to realize NC programless machining: Real time tool path generation for autonomous NC machine tool,” Trans. of the Japan Society of Mechanical Engineers Series C, Vol.66, No.644, pp. 1368-1373, 2000 (in Japanese). https://doi.org/10.1299/kikaic.66.1368
18. [18] D. Hamada, K. Nakamoto, T. Ishida, and Y. Takeuchi, “Development of CAPP system for multi-tasking machine tool,” Trans. of the Japan Society of Mechanical Engineers Series C, Vol.78, No.791, pp. 2698-2709, 2012 (in Japanese). https://doi.org/10.1299/kikaic.78.2698
19. [19] T. Kishinami, “Data exchange and data sharing,” J. of the Japan Society of Precision Engineering, Vol.75, No.1, pp. 48-49, 2009 (in Japanese). https://doi.org/10.2493/jjspe.75.48
20. [20] Y. Watanabe and K. Nakamoto, “Proposal of a machining features recognition method for 5-axis index milling on multi-tasking machine tools,” J. of Advanced Mechanical Design, Systems, and Manufacturing, Vol.14, No.7, Article No.20-00347, 2020. https://doi.org/10.1299/jamdsm.2020jamdsm0108
21. [21] T. Nomura, E. Yamada, H. Nakatsuji, and I. Nishida, “Automated NC program generation for hole drilling and swarf machining by 5-axis indexing machining,” J. of Advanced Mechanical Design, Systems, and Manufacturing, Vol.18, No.4, Article No.23-00499, 2024. https://doi.org/10.1299/jamdsm.2024jamdsm0039
22. [22] I. Nishida and K. Shirase, “Automated process planning system for end-milling operation by CAD model in STL format,” Int. J. of Automation Technol., Vol.15, No.2, pp. 149-157, 2021. https://doi.org/10.20965/ijat.2021.p0149