Bulanık Mantık ve Görüntü İşleme ile Metal Döküm Ürünlerinin Otomatik Kalite Derecelendirmesi

Öz

Yüksek hacimli üretim süreçlerinde kalite kontrol, özellikle manuel denetimlerin hataya açık ve tutarsız olması nedeniyle önemli bir zorluktur. Bu çalışmada, kusur tespiti ve sınıflandırma süreçlerini iyileştirmek amacıyla görüntü işleme ve bulanık mantık tekniklerini entegre eden otomatik bir kalite değerlendirme sistemi önerilmiştir. Çalışmada, 512×512 piksel boyutlarında 1.300 adet disk biçimli döküm ürünü içeren bir veri seti kullanılmıştır. Görüntü işleme aşamasında Gauss filtreleme ve Canny kenar algılama teknikleriyle ürünlerin kusur boyutu, renk farkı ve şekil bozulması gibi özellikleri elde edilmiştir. Bu veriler, bulanık mantık tabanlı bir sistemle işlenerek ürünlere kalite puanı atanmış ve ürünler düşük (≤40), orta (41–70) ve yüksek (>70) kalite olarak sınıflandırılmıştır. Sonuçlara göre ürünlerin %84,8’i düşük kalite, sadece %3,6’sı ise yüksek kalite sınıfına girmiştir. Buna ek olarak, kalite puanlarına dayalı sıralama için Bulanık TOPSIS yöntemi uygulanarak, ürünlerin ideal çözüme yakınlığına göre önceliklendirilmesi sağlanmıştır. Bu hibrit yapı, kalite değerlendirmesinde tutarlılığı artırmakta ve karar destek sistemlerine entegrasyon imkânı sunmaktadır.

Anahtar Kelimeler

• Bulanık Mantık
• Görüntü İşleme
• Kusur Tespiti
• Bulanık TOPSIS
• Kalite Sıralaması
• Döküm Ürünleri
• Çok Kriterli Karar Verme

Integrated Fuzzy Logic and Image Processing for Automated Quality Grading in Metal Casting

Öz

Improving quality control in high-volume manufacturing remains a critical challenge, especially where manual inspections are error-prone and inconsistent. This study presents an automated quality assessment framework combining image processing and fuzzy logic techniques to enhance defect detection and classification. A dataset comprising 1,300 grayscale images of disk-shaped cast products (512×512 pixels) was analyzed. Gaussian filtering and Canny edge detection were applied to extract defect features such as size, color deviation, and shape distortion. These features were processed through a fuzzy inference system to assign quality scores, categorizing products into low (≤40), medium (41–70), and high quality (>70). Results revealed that 84.8% of products were low quality, while only 3.6% were rated high quality. Additionally, the Fuzzy TOPSIS method was implemented to rank products based on similarity to an ideal solution, offering a decision-support perspective beyond classification. This hybrid approach improves consistency, objectivity, and scalability in quality evaluation workflows.

Anahtar Kelimeler

• Fuzzy Logic
• Image Processing
• Defect Detection
• Fuzzy TOPSIS
• Quality Ranking
• Cast Products
• Multi-Criteria Decision Making

Kaynakça

1. [1] J. Mokyr, The Lever of Riches: Technological Creativity and Economic Progress, 1st Oxford Univ. Press paperback ed., Oxford: Oxford Univ. Press, 1992.
2. [2] K. Schwab, The Fourth Industrial Revolution, 1st U.S. ed., New York: Crown Business, 2016.
3. [3] L. A. Zadeh, "The concept of a linguistic variable and its application to approximate reasoning—I," Information Sciences, vol. 8, no. 3, pp. 199–249, 1975, doi: 10.1016/0020-0255(75)90036-5.
4. [4] T. J. Ross, Fuzzy Logic with Engineering Applications, 2nd ed., Hoboken, NJ: John Wiley, 2004.
5. [5] M. A. H. Ali and A. K. Lun, "A cascading fuzzy logic with image processing algorithm–based defect detection for automatic visual inspection of industrial cylindrical object’s surface," Int. J. Adv. Manuf. Technol., vol. 102, no. 1–4, pp. 81–94, May 2019, doi: 10.1007/s00170-018-3171-7.
6. [6] H. K. Mohajan, "The First Industrial Revolution: Creation of a New Global Human Era," The First Industrial Revolution, 2019.
7. [7] D. W. Jorgenson, Ed., The Economics of Productivity, Cheltenham: Elgar, 2009.
8. [8] J. De Vries, The Economic Future in Historical Perspective, British Academy, 2006.

9. [9] J. Yong and A. Wilkinson, "The long and winding road: The evolution of quality management," Total Quality Management, vol. 13, no. 1, pp. 101–121, Jan. 2002, doi: 10.1080/09544120120098591.
10. [10] K. Canbay and G. Akman, "Investigating changes of total quality management principles in the context of Industry 4.0: Viewpoint from an emerging economy," Technol. Forecast. Soc. Change, vol. 189, p. 122358, Apr. 2023, doi: 10.1016/j.techfore.2023.122358.
11. [11] H.-C. Liu, R. Liu, X. Gu, and M. Yang, "From total quality management to Quality 4.0: A systematic literature review and future research agenda," Front. Eng. Manag., vol. 10, no. 2, pp. 191–205, Jun. 2023, doi: 10.1007/s42524-022-0243-z.
12. [12] M. J. Sánchez-Franco, A. Calvo-Mora, and R. Periáñez-Cristobal, "Clustering abstracts from the literature on Quality Management (1980–2020)," Total Quality Management & Business Excellence, vol. 34, no. 7–8, pp. 959–989, May 2023, doi: 10.1080/14783363.2022.2139674.
13. [13] Y. Wilhelm, U. Schreier, P. Reimann, B. Mitschang, and H. Ziekow, "Data Science Approaches to Quality Control in Manufacturing: A Review of Problems, Challenges and Architecture," in Service-Oriented Computing, vol. 1310, S. Dustdar, Ed., Commun. Comput. Inf. Sci., Cham: Springer, 2020, pp. 45–65, doi: 10.1007/978-3-030-64846-6_4.
14. [14] A. Bousdekis, K. Lepenioti, D. Apostolou, and G. Mentzas, "Data analytics in Quality 4.0: Literature review and future research directions," Int. J. Comput. Integr. Manuf., vol. 36, no. 5, pp. 678–701, May 2023, doi: 10.1080/0951192X.2022.2128219.
15. [15] A. Zonnenshain and R. S. Kenett, "Quality 4.0—the challenging future of quality engineering," Quality Engineering, vol. 32, no. 4, pp. 614–626, Oct. 2020, doi: 10.1080/08982112.2019.1706744.
16. [16] S. Sader, I. Husti, and M. Daroczi, "A review of Quality 4.0: Definitions, features, technologies, applications, and challenges," Total Quality Management & Business Excellence, vol. 33, no. 9–10, pp. 1164–1182, Jul. 2022, doi: 10.1080/14783363.2021.1944082.
17. [17] İ. Ertuğrul and M. Güneş, "Fuzzy Goal Programming and an Application of Production Process," in Analysis and Design of Intelligent Systems using Soft Computing Techniques, vol. 41, P. Melin et al., Eds., Adv. Soft Comput., Berlin: Springer, 2007, pp. 649–659, doi: 10.1007/978-3-540-72432-2_66.
18. [18] M. Nasiri and S. A. Darestani, "A literature review investigation on quality control charts based on fuzzy logic," Int. J. Productivity and Quality Management, vol. 18, no. 4, p. 474, 2016, doi: 10.1504/IJPQM.2016.077778.
19. [19] C. A. Escobar, M. E. McGovern, and R. Morales-Menendez, "Quality 4.0: A review of big data challenges in manufacturing," J. Intell. Manuf., vol. 32, no. 8, pp. 2319–2334, Dec. 2021, doi: 10.1007/s10845-021-01765-4.
20. [20] S. Pranav, "Defect Detection Dataset," Kaggle, 2023. [Online]. Available: https://www.kaggle.com/code/ssaipranav/defect-detection/input
21. [21] G. Bradski, "The OpenCV Library," Dr. Dobb's Journal, vol. 25, no. 11, pp. 120–125, 2000.
22. [22] J. Warner et al., JDWarner/scikit-fuzzy: Scikit-Fuzzy 0.5.0, Zenodo, Aug. 2024. doi: 10.5281/ZENODO.13372212.
23. [23] W. K. Pratt, Digital Image Processing (Third Edition): PIKS Inside, 3rd ed., New York: Wiley-Interscience, 2001.
24. [24] C. Lee, J. Ko, and T. Choe, "Two-way partitioning of a recursive gaussian filter in cuda", EURASIP Journal on Image and Video Processing, vol. 2014, no. 1, 2014. https://doi.org/10.1186/1687-5281-2014-33
25. [25] J. Canny, "A Computational Approach to Edge Detection," IEEE Trans. Pattern Anal. Mach. Intell., vol. PAMI-8, no. 6, pp. 679–698, Nov. 1986, doi: 10.1109/TPAMI.1986.4767851.
26. [26] R. C. Gonzalez and R. E. Woods, Digital Image Processing, 2nd ed., Upper Saddle River, NJ: Prentice-Hall, 2002.
27. [27] C. Hwang and K. Yoon, Multiple Attribute Decision Making: Methods and Applications—A State-of-the-Art Survey, Lecture Notes in Economics and Mathematical Systems, no. 186, Berlin: Springer, 1981, doi: 10.1007/978-3-642-48318-9.
28. [28] C.-T. Chen, "Extensions of the TOPSIS for group decision-making under fuzzy environment," Fuzzy Sets and Systems, vol. 114, no. 1, pp. 1–9, Aug. 2000, doi: 10.1016/S0165-0114(97)00377-1.