摘要(英) |
This study developed an automated optical defect detection system aimed at inspecting the surface of cast metal objects, specifically focusing on golf club heads made from cast metal as the research subject. Initially, a light source configuration was designed, comprising a primary light source and a passive auxiliary lighting structure. The study utilized a directional light source to illuminate the target object for image capture, identifying the optimal imaging conditions to achieve the best image quality. Vision Assistant was employed as the primary tool for image processing, incorporating morphological operations, Laplacian filtering, binary segmentation, particle filtering, and defect analysis techniques to handle large volumes of image data.Additionally, LabVIEW was used to develop a virtual instrument (VI) to create a fast and detailed real-time inspection interface, providing precise defect information for foundries. On the hardware side, the study constructed a complete imaging system and a light pattern measurement device. The imaging system consisted of nine CMOS sensors arranged to capture different regions and was equipped with a golf club head clamping and positioning platform, along with a Python-developed positioning verification program to simplify operation and ensure positioning accuracy. To meet the requirements for lighting conditions, the system meticulously measured and recorded the light pattern, scattering, illumination angle, and intensity to ensure the consistency of lighting conditions during subsequent inspections.When inspecting micro-defects with an area as small as 0.022mm2, the system achieved a zero omission rate, maintaining a detection success rate of over 90% without any undetected defects. To meet the practical needs of foundries, the system integrated various functional modules, including defect count analysis, defect distribution analysis, and large defect detection, along with a classification system to facilitate subsequent defect handling or manual review. The entire inspection process takes approximately five seconds, requiring no adjustments to angles or light sources, significantly reducing the risk of human error during operation. This system effectively reduces the cost of optical defect detection while maintaining high convenience and functionality, providing an efficient AOI inspection solution for traditional foundries. |
參考文獻 |
[1] 「全球高爾夫裝備市場規模預測」,檢自:
https://uanalyze.com.tw/articles/418064965
[2] 「一文了解半導體檢測-AOI自動光學檢測」,檢自:https://uanalyze.com.tw/articles/851395328
[3] 「高爾夫鐵桿頭選鍛造與鑄造CASTING有什麼差別呢?高爾夫知識系列~鐵桿桿頭的工法(中)篇:鑄造的原理,鐵桿鑄造流程解析。」檢自: https://goodshot.org/casting/
[4]鄭日威(2022)。一種應用於鑄造金屬表面瑕疵的自動光學檢測技術探討(碩士論文)。國立中央大學,桃園市。
[5] Melali, P., Boutorabi, S. M. A., & Divandari, M. (2023). The effect of casting revert-virgin alloy with different portions on the microstructure and mechanical properties of 1.4930 heat-resistant stainless-steel alloy in investment casting process. International Journal of Metalcasting, 18, 2119–2132. https://doi.org/10.1007/s40962-023-01144-0
[6] Melali, P., Boutorabi, S. M. A., & Divandari, M. (2023). Applications of investment casting as a manufacturing process for injection mold tooling. International Journal of Metalcasting, 18, 2119–2132. https://doi.org/10.1007/s40962-023-01144-0
[7] Sahoo, S. K., & Goswami, S. S. (2023). Investigating the causes and remedies for porosity defects in the casting process: A review. BOHR International Journal of Engineering, 2023(2), 15–29. https://doi.org/10.54646/bije.2023.13
[8] Galan, U., Ahuett-Garza, H., Orta, P., & Kurfess, T. (2019). Shadow identification and height estimation of defects by direct processing of grayscale images. The International Journal of Advanced Manufacturing Technology, 101(1-4), 317–328. https://doi.org/10.1007/s00170-018-2933-6
[9]Mansano, M., Pavesi, L., Oliveira, L. S., Britto Jr., A., & Koerich, A. (2011). Inspection of metallic surfaces using Local Binary Patterns. Proceedings of the IEEE International Conference on Industrial Informatics, 2227–2231.
[10]Lin, J., Wen, K., Liu, Y., & Zhang, X. (2021). Recognition and classification of surface defects of aluminum castings based on machine vision. 2021 International Conference on Machine Learning and Intelligent Systems Engineering (MUSE), 10–15.
[11] Zhang, Q., Feng, W., Wan, L., Tian, F.-P., Wang, X., & Tan, P. (2020). Active lighting recurrence by parallel lighting analogy for fine-grained change detection. arXiv. https://doi.org/10.48550/arXiv.2002.09663
[12] Hecht, E. (2016). Optics (5th ed.). Pearson. ISBN: 978-1292096933.
[13] Haralick, R. M., Sternberg, S. R., & Zhuang, X. (1987). Image analysis using mathematical morphology. IEEE Transactions on Pattern Analysis and Machine Intelligence, 9(4), 532–550. https://doi.org/10.1109/TPAMI.1987.4767941
[14] Anuradha, M. (1992). Advances in digital image processing. IETE Journal of Education, 33(3), 197–208. https://doi.org/10.1080/09747338.1992.11436379
[15] 陳建宏(2006)。用於適應環境光亮度的影像處理方法(碩士論文)。國立台灣科技大學,台北市。
[16] 王偉仁(2018),自動化光學檢測於梭織物瑕疵辨識分類與應用(碩士論文)。國立台灣科技大學,台北市。
[17] Gatos, B., Pratikakis, I., & Perantonis, S. J. (2006). Adaptive degraded document image binarization. Pattern Recognition, 39(3), 317–327. https://doi.org/10.1016/j.patcog.2005.09.010
[18] Otsu, N. (1979). A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics, 9(1), 62–66. https://doi.org/10.1109/TSMC.1979.4310076
[19]施其安(2020)。應用機器視覺與深度學習於鋼珠表面之瑕疵檢測(碩士論文)。國立臺北科技大學,台北市。
[20] akura Membership Services Limited. (2020年12月23日). 各種高爾夫球杆的介紹。Sakura Membership Services Limited. 節自 https://www.sakura-membership.com/archives/58048
[21]Dawang Casting. (n.d.). 金屬鑄造缺陷的成因與解決方法。Dawang Metals. 取自 https://dawangmetals.com/zh-TW/resources/metal-casting-defects/
[22]蔡介峰(2006)。常見人工光源測試研究(研究報告編號:095301070000G2030)。內政部建築研究所。
[23]Gonzalez, R. C., & Woods, R. E. (2018). Digital Image Processing (4th ed.). Pearson.
[24] Mardiris, V., & Chatzis, V. (2016). A Configurable Design for Morphological Erosion and Dilation Operations in Image Processing Using Quantum-dot Cellular Automata. Journal of Engineering Science and Technology Review, 9(1), 25-30.
[25]Nellutla, A., Chittajallu, G. S. G., & Feroz, S. (2020). Leaf disease detection using LabVIEW IMAQ vision. International Journal of Recent Technology and Engineering (IJRTE), 9(3), September 2020.
[26]Sonka, M., Hlavac, V., & Boyle, R. (2014). Image processing, analysis, and machine vision (4th ed.). Cengage Learning.
[27]許志豪(2009)。影像二值化演算處理器之軟/硬整合設計與實現(碩士論文)。國立臺灣科技大學,臺北市。檢自:https://etheses.lib.ntust.edu.tw/detail/0b52c07ce4a117adc997b844967e9a01/
[28]Wikipedia contributors. (n.d.). Pinhole camera: Selection of pinhole size. Wikipedia. Retrieved December 21, 2024, from https://en.wikipedia.org/wiki/Pinhole_camera#Selection_of_pinhole_size
[29] 劉彥錚(2013),應用多重特徵於提升材質辨識的準確性,國立交通大學電控工程系碩士學位論文。
[30] 曾炫皓(2013),空間變異之適應性參數的gamma校正運用於高曝光與低曝光影像之研究 ,國立勤益科技大學資訊工程系碩士學位論文。
[31]黃繼震(編著),村日富(審稿)(2001)。微電腦控制能力本位訓練教材:操作LabVIEW語言(編號:PEN-MCC0906)。行政院勞工委員會職業訓練局。
[32]Lunetto, V., Basile, D., Razza, V., & Russo Spena, P. (2024). Active and Passive Filling Stir Repairing of AISI 304 Alloy. Metals, 14(911). https://doi.org/10.3390/met14080911
[33] MetaLine. (n.d.). Casting Porosities and Pinholes. Retrieved October 7, 2024,
https://metaline.com/en/applications/general-manufacturing/casting-porosities-pinholes.html |