Localization of the Work Coordinate System Using Computer Vision and Geometric Transformations on Three-Axis CNC Milling Machines

Manuel Meraz Mendez; Jorge Duarte Loera; Claudia Lerma Hernández

doi:10.4108/airo.9898

Authors

Manuel Meraz Mendez Universidad Tecnológica de Chihuahua https://orcid.org/0000-0001-8254-9571
Jorge Duarte Loera Universidad Tecnológica de Chihuahua https://orcid.org/0000-0002-6721-1406
Claudia Lerma Hernández Polytechnic University of Chihuahua https://orcid.org/0000-0003-3232-0431

DOI:

https://doi.org/10.4108/airo.9898

Keywords:

milling, work coordinate system, repeatability, computer vision, geometric trasnformations, optimization

Abstract

This paper presents a novel methodology for the location of the workpiece coordinate system origin (WCS) on three-axis computer numerical control (CNC) milling machines. The proposed approach uses computer vision techniques to detect geometric features on the workpiece and calculates zero-point coordinates through pixel-based adjustment and coordinate transformation matrices. The method includes a calibration process to align the camera system with the machine’s coordinate reference frames and compensates for displacement between the vision sensor and the tool center point. Experimental validation was carried out on a HAAS VF1 CNC milling machine, comparing the proposed method with traditional probing techniques. The results demonstrate improved repeatability and accuracy in the location of the WCS, with deviations maintained within acceptable industrial tolerances. This approach facilitates faster setup times and improves process automation in intelligent manufacturing environments.

Downloads

Download data is not yet available.

Author Biographies

Manuel Meraz Mendez, Universidad Tecnológica de Chihuahua

Manuel Meraz-Méndez is Mexican by birth and earned a Ph.D. in Technology from the Universidad Autónoma de Ciudad Juárez with a CONAHCYT scholarship. He obtained a Master’s degree in Quality and Productivity from Universidad Tecmilenio in 2008, and a Master’s degree in Higher Education from the Universidad Autónoma de Chihuahua in 2009. He is a full-time professor at the Universidad Tecnológica de Chihuahua with 23 years of service, and at the Instituto Tecnológico de Chihuahua (TECNM) with 12 years of service. He is a member of the Industrial Development Academic Body of the Industrial Maintenance Engineering program and holds the Perfil PRODEP.

His areas of interest include computer numerical control (CNC) machining, computer-aided design (CAD), automation, and robotics, with applications in artificial intelligence and computer vision technologies.

Areas of Interest:
Product design and development, creative thinking in design, design engineering, prototyping, CAD modeling, sketching, 3D printing, invention, reverse engineering, CNC machining, manufacturing systems, industrial training, big data, artificial intelligence, product development, rapid prototyping, automation, robotics, computer-aided engineering, machine learning, production engineering, product management, product engineering, CNC programming, manufacturing processes, mechanics, machining processes, and additive manufacturing.

Jorge Duarte Loera, Universidad Tecnológica de Chihuahua

Institutional Role & Academic Profile
Dr. Jorge Duarte Loera is a member of the Predictive Maintenance Systems academic team, within the field of Engineering and Technology at utch.edu.mx. He also serves as a professor, teaching technical courses such as Analog Electronics and Digital Electronics in the Industrial Maintenance program, where he is listed as “Jorge Duarte Loera” at mantenimiento.utch.edu.mx.

Contribution Highlights
Although a detailed public biography with his academic background, publications, or professional experience is not available, his teaching responsibilities and participation in the academic body indicate strong involvement in technical education and applied engineering—particularly in predictive maintenance and electronics.

Claudia Lerma Hernández, Polytechnic University of Chihuahua

Institutional Role & Academic Profile
Claudia Lerma Hernández is a full-time professor at the Universidad Politécnica de Chihuahua (UPCH), where she is recognized for her commitment to students—as one of the most highly evaluated tutors in the Administration and Business Management program.

She has also contributed to the Labor Administration academic community through active participation in international events. For instance, she co-organized the IV Congreso Internacional de Recursos Humanos, collaborating virtually with universities from Costa Rica and Colombia. In addition, she delivered the presentation “System of Information Applied to Human Talent Management in a Local Company in Chihuahua,” alongside other UPCH faculty

Furthermore, Claudia Lerma Hernández represented UPCH at the Simposio de Sostenibilidad y Programación Global en América Latina held in Costa Rica. There, she presented a talk titled "Experience of Internationalized Classrooms Through the Collaborative Online International Learning (COIL Methodology)," sharing her insights on international education strategies

Contribution Highlights
Claudia Lerma Hernández is valued both by her students and institutional leadership. As a consistently top-rated tutor, she demonstrates exceptional dedication to academic guidance. Her involvement in international academic forums—both organizing and presenting—highlights her active role in fostering global and innovative learning environments, particularly within human resource management and collaborative online education.

References

[1] de Araujo, P.R.M. and Lins, R.G. (2021) Cloud-based approach for automatic cnc workpiece origin localization based on image analysis. Robotics and Computer-Integrated Manufacturing 68: 102090. URL https://doi.org/10.1016/j.rcim.2020.102090.

[2] Chen, Y., Gunraj, H., Zeng, E.Z., Meyer, R., Gilles, M. and Wong, A. (2023) Mmrnet: Improving reliability for multimodal object detection and segmentation for bin picking via multimodal redundancy. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW): 68–77. URL https://doi.org/10.1109/CVPRW59228.2023.00012.

[3] Ruijiao Yin, J.Y. (2019) Research on robot control technology based on vision localization. Journal on Artificial Intelligence 1(1): 37–44. URL http://www.techscience.com/jai/v1n1/29010.

[4] Xiong, Z., Chu, Y., Liu, G. and Li, Z. (2001) Workpiece localization and computer aided setup system. In Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180), 2: 1141–1146 vol.2. URL https://doi.org/10.1109/IROS.2001.976322.

[5] Zhu, W., Qin, Z., Wang, P. and Qiao, H. (2013) Model-based work-piece localization with salient feature selection. In 2013 IEEE International Conference on Robotics and Biomimetics (ROBIO): 493–497. URL https://doi.org/10.1109/ROBIO.2013.6739508.

[6] Li, Z., Sato, R., Shirase, K. and Sakamoto, S. (2021) Study on the influence of geometric errors in rotary axes on cubic-machining test considering the workpiece coordinate system. Precision Engineering 71: 36–46. URL https://doi.org/10.1016/j.precisioneng.2021.02.011.

[7] Torres-Medina, Y. (2020) El análisis del error humano en la manufactura: un elemento clave para mejorar la calidad de la producción. Revista UIS Ingenierías 19(4): 53–62. URL https://doi.org/10.18273/revuin.v19n4-2020005.

[8] Soori, M., Arezoo, B. and Habibi, M. (2013) Dimensional and geometrical errors of three-axis cnc milling machines in a virtual machining system. Computer-Aided Design 45(11): 1306–1313. URL https://doi.org/10.1016/j.cad.2013.06.002.

[9] Grisales-Grisales, N., Durango-Idárraga, S., Álvarez-Vargas, C.A. and Flórez-Hurtado, R.D. (2020) Calibración cinemática de una ruteadora cnc usando un modelo cuasi-estático de error y fotogrametría monocular. Revista UIS Ingenierías 19(3): 15–30. URL https: //doi.org/10.18273/revuin.v19n3-2020002.

[10] Báez, Y.A., Rodríguez, M.A., De la Vega, E.J. and Tlapa, D.A. (2013) Factores que influyen en el error humano de los trabajadores en líneas de montaje manual. Información tecnológica 24(6): 67–78. URL https://doi.org/10.4067/S0718-07642013000600010.

[11] Popov, K., Dimov, S., Ivanov, A., Pham, D.T. and Gandarias, E. (2010) New tool-workpiece setting up technology for micro-milling. The International Journal of Advanced Manufacturing Technology 47(1): 21–27. URL https://doi.org/10.1007/s00170-009-2055-2.

[12] XuYi, Ma, L. and Li, Z. (2008) A geometric algorithm for symmetric workpiece localization. In 2008 7th World Congress on Intelligent Control and Automation: 6065–6069. URL https://doi.org/10.1109/WCICA.2008.4592864.

[13] Setti, A., Bosetti, P. and Ragni, M. (2016) Artoolaugmented reality platform for machining setup and maintenance. In Proceedings of SAI Intelligent Systems Conference (Springer): 457–475. URL https://doi.org/10.1007/978-3-319-56994-9_33.

[14] Gu, J., Agapiou, J.S. and Kurgin, S. (2015) Cnc machine tool work offset error compensation method. Journal of Manufacturing Systems 37: 576–585. URL https://doi. org/10.1016/j.jmsy.2015.04.001.

[15] Xu, H.H. and Dai, C. (2014) Research on precision detection and error compensation technology for 3-axis cnc milling machine. Applied Mechanics and Materials 455: 505–510. URL https://doi.org/10.4028/www.scientific.net/AMM.455.505.

[16] Zhang, J. (2018) Research on cnc lathe programming and improving machining accuracy. In IOP Conference Series: Materials Science and Engineering (IOP Publishing), 452: 042050. URL https://doi.org/10.1088/1757-899X/452/4/042050.

[17] Martinova, L., Obukhov, A. and Sokolov, S. (2020) Practical aspects of ensuring accuracy of machining on cnc machine tools within framework of “smart manufacturing”. In 2020 International Russian Automation Conference (RusAutoCon) (IEEE): 898–902. URL https://doi.org/10.1109/RusAutoCon49822.2020.9208079.

[18] Salas-Arias, K.M., Madriz-Quirós, C.E., Sánchez-Brenes, O., Sánchez-Brenes, M. and Hernández-Granados, J.B. (2018) Factores que influyen en errores humanos en procesos de manufactura moderna. Revista Tecnología en Marcha 31(1): 22–34. URL https://doi.org/10.18845/tm.v31i1.3494.

[19] Torres Diaz, C.A. (2019) Matrices y sistemas de ecuaciones lineales. Repositorio Institucional URL https://repositorioslatinoamericanos.uchile.cl/handle/2250/653643.

[20] Barrientos, A., Álvarez, M., Hernández, J.D.,Del Cerro, J. and Rossi, C. (2012) Modelado de Cadenas Cinemáticas mediante Matrices de Desplazamiento. Una alternativa al método de Denavit-Hartenberg (Science Direct), 9, 371–382. URL https://doi.org/10.1016/j.riai.2012.09.004.

[21] Diprasetya, M.R. and Schwung, A. (2022) Homogeneous transformation matrix based neural network for model based reinforcement learning on robot manipulator. In 2022 IEEE International Conference on Industrial Technology (ICIT) (IEEE): 1–6. URL https://doi.org/10.1109/ICIT48603.2022.10002834.

[22] Villamarín, D. (2015) Estado del arte, herramientas y aplicaciones para transformaciones geométricas 3d. In Congreso de Ciencia y Tecnología ESPE, 10: 226–231. URL https://www.researchgate.net/publication/290964976_Estado_del_Arte_Herramientas_y_Aplicaciones_para_Transformaciones_geometricas_3D.

[23] Barrientos, A. et al. (2017) Fundamentos de robótica (Arquitectura e Ingeniería), 2, 211–382. URL https://www.academia.edu/40692152/Fundamentos_de_Rob%C3%B3tica_A_Barrientos_L_Pe%C3%B1in_C_Balaguer_R_Aracil_2ed.

[24] Maldavsky, D. (1977) Teoría de las representaciones: sistemas y matrices, transformaciones y estilos. In Teoría de las representaciones: sistemas y matrices, transformaciones y estilos (Portal Regional BVS), 267–267. URL https://sibi.upn.mx/cgi-bin/koha/opac-detail.pl?biblionumber=96663.

[25] Meraz-Méndez, M., Muñoz-López, L.E., Reynoso-Jardón, E.L. and Corral-Ramírez, G. (2024) Camera calibration procedure for extracting form deviation features in machined parts through computer vision algorithms. Journal of Mechanical Engineering 8(21): 1–e30821111.

[26] Jiao, J., Huang, C., Liu, H. and Zhang, G. (2018) A chinese chessboard calibration method in chessplaying robot by machine vision sensing. In Journal of Physics: Conference Series (IOP Publishing), 1026: 012023. URL https://doi.org/10.1088/1742-6596/1026/1/012023.

[27] Mejia, J.B. and Varona, R.L. (2014) Calibración de cámara termográfica fluke ti-32. Scientia et technica 19(1): 59–66.

[28] Zhang, Z. (2000) A flexible new technique for camera calibration. IEEE Transactions on pattern analysis and machine intelligence 22(11): 1330–1334. URL https://doi.org/10.1109/34.888718.

[29] Yang, C. and Yu, Q. (2019) Multiscale fourier descriptor based on triangular features for shape retrieval. Signal Processing: Image Communication 71: 110–119. URL https://doi.org/10.1016/j.image.2018.11.004.

[30] Bipm, I., IFCC, I. and IUPAC, I. (1995) Oiml 2008 evaluation of measurement data—guide to the expression of uncertainty in measurement. Joint Committee for Guides in Metrology, Bureau International des Poids et Mesures, JCGM 100.

[31] International Organization for Standardization (2008), ISO/IEC Guide 98-3:2008 Uncertainty of measurement - Part 3: Guide to the expression of uncertainty in measurement (GUM:1995). Published (Edition 1, 2008). This standard was last reviewed and confirmed in 2023. Therefore this version remains current.

[32] Srinivasan, H., Harrysson, O. and Wysk, R. (2015) Automatic part localization in a cnc machine coordinate system by means of 3d scans. International Journal of Advanced Manufacturing Technology 81: 1127–1138. doi:10.1007/s00170-015-7178-z, URL https://doi.org/10.1007/s00170-015-7178-z.

[33] Wallace, J. (2010) Ten methods for calculating the uncertainty of measurement. Science & Justice 50(4): 182–186. doi: https://doi.org/10.1016/j.scijus.2010.06.003, URL

https://www.sciencedirect.com/science/article/pii/S1355030610000705.

[34] Khusainov, R., Ziangirova, E. and Davletshina, G. (2020) Estimation of precision parameters of milling machines. In IOP Conference Series: Materials Science and Engineering, 915: 012031. URL https://doi.org/10.1088/1757-899X/915/1/012031.

[35] Singh, K.D. and Singh, P.D. (2023) Machine learning in robotics with fog/cloud computing and iot. EAI Endorsed Transactions on AI and Robotics 2. URL https://doi.org/10.4108/airo.3621.

[36] Zangana, H., Mustafa, R. and Omar, A. (2024) A hybrid approach for robust object detection: Integrating template matching and faster r-cnn. EAI Endorsed Transactions on AI and Robotics 3. doi:10.4108/airo.6858,URL https://publications.eai.eu/index.php/airo/article/view/6858.