مهندسی مکانیک مدرس

مهندسی مکانیک مدرس

توسعه یک سیستم نیمه هوشمند برای اندازه‌گیری خودکار پروفیل دوبعدی قطعات مبتنی بر بینایی ماشین و الگوریتم تشخیص لبه

نوع مقاله : مقاله پژوهشی

نویسندگان
آرین حسینی
سعید خدایگان
حسین سروش
دانشگاه صنعتی شریف، تهران
10.48311/mme.2025.96913.0
چکیده
مسئله اندازه‌گیری ابعادی خودکار قطعات به دلیل نیاز به دستگاه‌های دقیق و پرهزینه، چالشی مهم در صنعت محسوب می‌شود. همچنین تخصص بالای اپراتور برای کار با این دستگاه‌ها ضروری است. در این پژوهش، یک روش خودکار نیمه‌هوشمند مبتنی بر بینایی ماشین با هدف کاهش زمان اندازه‌گیری و خطای انسانی برای اندازه‌گیری پروفیل قطعات توسعه یافته است. بدین منظور، دستگاه اندازه‌گیری تصویری دستی به یک دستگاه خودکار تبدیل شده است. الگوریتم ارائه شده شامل دو مرحله است. در ابتدا به کمک دوربین جانبی، قطعات روی میز بدون دخالت دست شناسایی و موقعیت‌یابی شده‌اند. سپس، مسیر حرکتی و تصویربرداری جزئی ایجاد شده تا اندازه‌گیری تصویری قطعات انجام شده و ابرنقاط دوبعدی به دست آید. داده‌های به ‌دست‌آمده از این مرحله برای انجام تحلیل‌های ابعادی استفاده شده است. علاوه بر این، به منظور بهبود کاربرپسندی و رفع محدودیت‌های نرم‌افزار اصلی دستگاه، یک رابط گرافیکی مبتنی بر ویندوز نیز توسعه یافته است. در پایان، برای صحت‌سنجی روش ارائه شده، اندازه‌گیری پروفیل دو بعدی گیج‌های استاندارد طولی، زاویه‌ای و رزوه، و همچنین یک نمونه چرخ‌زنجیر استاندارد ANSI 40A26  در شرایط کاری واقعی انجام شد. سیستم توسعه‌یافته دقت اندازه‌گیری متوسط در محدوده ۱۰ میکرومتر را به‌دست آورد و میانگین اختلاف ۱۵ میکرومتر نسبت به اندازه‌گیری CMM داشت. با این حال، سیستم فعلی محدود به اندازه‌گیری پروفیل‌های دوبعدی قطعات است. نتایج حاصل دقت روش ارائه شده را تأیید نمود و کارایی آن را به‌عنوان یک راهکار مقرون‌به‌صرفه برای بازرسی ابعادی خودکار نشان می‌دهد
کلیدواژه‌ها
اندازه‌گیری خودکار
بینایی ماشین
اندازه‌گیری تصویری
پروفیل دو بعدی

موضوعات

عنوان مقاله English

Development of a Semi-Intelligent System for Automatic Measurement of Two-Dimensional Profiles of Parts Based on Machine Vision and edge detection algorithm

نویسندگان English

Arian Hosseini
Saeed Khodaygan
Hossein Soroush
Sharif University of Technology
چکیده English

Dimensional metrology ensures that manufactured components meet precise dimensions, shapes, and geometric features. Automatic measurement of mechanical profiles faces challenges such as high costs and the need for skilled operators. In this study, a semi-intelligent automated measurement method based on machine vision was developed to reduce measurement time and minimize human error. Accordingly, a manual vision measurement system was retrofitted and automated. A two-stage algorithm was designed for this purpose. In the first stage, a side-mounted camera automatically detected and localized parts placed on the worktable without manual intervention. In the second step, a measurement path was generated to enable image measurement of the part profile. Next, the collected data from the previous step was reconstructed into a two-dimensional point cloud for dimensional analysis. A Windows-based graphical user interface (GUI) was developed to enhance the system’s usability and overcome the limitations of the original device software. Standard gauges for length, angle, and thread dimensions were used to obtain the 2D profile and check the accuracy of the presented system. Furthermore, profile dimensional measurement of a standard ANSI 40A26 sprocket was carried out to explore the efficiency of the presented algorithm in actual working conditions. The developed system achieved an average measurement accuracy within 10 µm, with an average deviation of 15 µm compared to CMM-based measurements. However, the current system is limited to two-dimensional profile measurements of components. The results confirmed the system’s measurement precision and demonstrated its potential as a cost-effective solution for dimensional inspection

کلیدواژه‌ها English

Automatic Measurement
Machine Vision
Image Measurement
2D Profile
H. Soroush, S. Khodaygan, and J. Hemati Nik, "Tolerance allocation of mechanical assemblies including thermal deformation: A machine learning–based method," Journal of Thermal Stresses, vol. 48, no. 1, pp. 64-81, 2025,
               doi: 10.1080/01495739.2024.2444308.
[3]           W. Harmatys, A. Gąska, P. Gąska, M. Gruza, and J. A. Sładek, "Assessment of background illumination influence on accuracy of measurements performed on optical coordinate measuring machine equipped with video probe," Sensors, vol. 21, no. 7, p. 2509, 2021, doi: 10.3390/s21072509.
[4]           R. Koteras, M. Wieczorowski, and P. Znaniecki, "Acceptance and reverification of CMM in industrial conditions," Advances in Science and Technology. Research Journal, vol. 12, no. 1, 2018, doi:10.12913/22998624/80987.
[5]           A. Abdolahi, H. Soroush, and S. Khodaygan, "Process capability analysis of additive manufacturing process: a machine learning− based predictive model," Rapid Prototyping Journal, 2025, doi:10.1108/RPJ-08-2024-0349.
[6]           R. C. Gonzalez, Digital image processing. Pearson education india, 2009.
[7]           J. Canny, "A computational approach to edge detection," IEEE Transactions on pattern analysis and machine intelligence, no. 6, pp. 679-698, 1986,  doi:10.1109/TPAMI.1986.4767851.
[8]           Y. Luo and R. Duraiswami, "Canny edge detection on NVIDIA CUDA," in 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2008: IEEE, pp. 1-8, doi:10.1109/CVPRW.2008.4563088.
[9]           P. Agrawal, S. Shriwastava, and S. Limaye, "MATLAB implementation of image segmentation algorithms," in 2010 3rd International Conference on Computer Science and Information Technology, 2010, vol. 3: IEEE, pp. 427-431,  doi:10.1109/ICCSIT.2010.5564131.
[10]         G. Bradski and A. Kaehler, Learning OpenCV: Computer vision with the OpenCV library. " O'Reilly Media, Inc.", 2008.
[11]         S. Suzuki, "Topological structural analysis of digitized binary images by border following," Computer vision, graphics, and image processing, vol. 30, no. 1, pp. 32-46, 1985, doi:10.1016/0734-189X(85)90016-7.
[12]         H. Soroush, A. Nourani, and G. Farrahi, "A Machine learning model to predict fracture of solder joints considering geometrical and environmental factors," Theoretical and Applied Fracture Mechanics, p. 104865, 2025, doi: 10.1016/j.tafmec.2025.104865.
[13]         A. Golmohammadi, H. Soroush, and S. Khodaygan, "A Machine learning-based model to predict residual stress in aluminum shell formed by shot peening," International Journal of Solids and Structures, vol. 313, p. 113250, 2025, doi:10.1016/j.ijsolstr.2025.113250.
[14]         H. Soroush and A. Nourani, "Application of data mining techniques for assessment of fracture load and energy in double cantilever beam solder joints," Journal of Design Against Fatigue, vol. 1, no. 3, 2023, doi:10.62676/9v4azj82.
[15]         V. Karathanassi, C. Iossifidis, and D. Rokos, "Application of machine vision techniques in the quality control of pharmaceutical solutions," Computers in industry, vol. 32, no. 2, pp. 169-179, 1996, doi:10.1016/S0166-3615(96)00063-2.
[16]         M. Bahaghighat, M. Mirfattahi, L. Akbari, and M. Babaie, "Designing quality control system based on vision inspection in pharmaceutical product lines," in 2018 international conference on computing, mathematics and engineering technologies (iCoMET), 2018: IEEE, pp. 1-4, doi:10.1109/ICOMET.2018.8346360.
[17]         S. Anand and L. Priya, A guide for machine vision in quality control. Chapman and Hall/CRC, 2019.
[18]         A. A. J. Campbell, "Machine vision for in-process inspection on an automated peptide manufacturing platform," Massachusetts Institute of Technology, 2020.
[19]         Q. Lu, Q. Fu, L. Luo, Q. Yuan, W. Hua, and Y. Yunguang, "Measurement method of LCD surface deformation for smartphone based on optical vision sensing system," Optik, vol. 172, pp. 1079-1088, 2018, doi:10.1016/j.ijleo.2018.07.122.
[20]         V. Chauhan and B. Surgenor, "Fault detection and classification in automated assembly machines using machine vision," The International Journal of Advanced Manufacturing Technology, vol. 90, pp. 2491-2512, 2017,  doi:10.1007/s00170-016-9581-5.
[21]         J. Molleda et al., "A profile measurement system for rail quality assessment during manufacturing," IEEE Transactions on Industry Applications, vol. 52, no. 3, pp. 2684-2692, 2016, doi:10.1109/TIA.2016.2524459.
[22]         Á. F. Millara, J. Molleda, R. Usamentiaga, and D. F. García, "Profile measurement of rails in a rolling mill: implementing and evaluating autonomic computing capabilities," IEEE Transactions on Industry Applications, vol. 55, no. 5, pp. 5466-5475, 2019, doi:10.1109/TIA.2019.2919487.
[23]         Á. F. Millara, J. Molleda, R. Usamentiaga, and D. F. García, "Calibrating a profile measurement system for dimensional inspection in rail rolling mills," Machine Vision and Applications, vol. 32, pp. 1-16, 2021, doi: 10.1007/s00138-020-01147-5.
[24]         J. Derganc, B. Likar, and F. Pernuš, "A machine vision system for measuring the eccentricity of bearings," Computers in industry, vol. 50, no. 1, pp. 103-111, 2003, doi: 10.1016/S0166-3615(02)00141-0.
[25]         R. Xiang, W. He, X. Zhang, D. Wang, and Y. Shan, "Size measurement based on a two-camera machine vision system for the bayonets of automobile brake pads," Measurement, vol. 122, pp. 106-116, 2018,  doi.: 10.1016/j.measurement.2018.03.017.
[26]         E. Gadelmawla, "Computer vision algorithms for measurement and inspection of spur gears," Measurement, vol. 44, no. 9, pp. 1669-1678, 2011, doi: /10.1016/j.measurement.2011.06.023.
[27]         D. K. Moru and D. Borro, "A machine vision algorithm for quality control inspection of gears," The International Journal of Advanced Manufacturing Technology, vol. 106, no. 1, pp. 105-123, 2020, doi:10.1007/s00170-019-04426-2.
[28]         J.-H. Ye and Q.-C. Hsu, "Automatic optical apparatus for inspecting bearing assembly defects," Sensors and Materials, vol. 30, no. 11, pp. 2637-2652, 2018, doi:10.18494/SAM.2018.2113.
[29]         G. Peng, Z. Zhang, and W. Li, "Computer vision algorithm for measurement and inspection of O-rings," Measurement, vol. 94, pp. 828-836, 2016, doi:10.1016/j.measurement.2016.09.012.
[30]         J. Rejc et al., "The mechanical assembly dimensional measurements with the automated visual inspection system," Expert Systems with Applications, vol. 38, no. 8, pp. 10665-10675, 2011, doi:10.1016/j.eswa.2011.02.133.
[31]         X. Wang, J. Liu, S. Liu, P. Jin, T. Wu, and Z. Wang, "Accurate radius measurement of multi-bend tubes based on stereo vision," Measurement, vol. 117, pp. 326-338, 2018, doi:10.1016/j.measurement.2017.12.009.
[32]         E. Gadelmawla, "Computer vision algorithms for measurement and inspection of external screw threads," Measurement, vol. 100, pp. 36-49, 2017, doi:10.1016/j.measurement.2016.12.034.
[33]         N.-V. Ngo, Q.-C. Hsu, W.-L. Hsiao, and C.-J. Yang, "Development of a simple three-dimensional machine-vision measurement system for in-process mechanical parts," Advances in Mechanical Engineering, vol. 9, no. 10, p. 1687814017717183, 2017, doi:10.1177/1687814017717183.
[34]         Q. Tan, Y. Kou, J. Miao, S. Liu, and B. Chai, "A model of diameter measurement based on the machine vision," Symmetry, vol. 13, no. 2, p. 187, 2021, doi:10.3390/sym13020187.
مهندسی مکانیک مدرس
دوره 25، شماره 10
مهر 1404
صفحه 635-651