ÜRETİM SÜREÇLERİNDE KUSUR ORANLARININ SINIFLANDIRILMASI: YENİLİKÇİ KAREKOD DÖNÜŞÜMÜ İLE DERİN ÖĞRENME TABANLI BİR YAKLAŞIM

Year 2025, Volume: 26 Issue: 1, 245 - 276, 27.03.2025

Yunus Emre Gür , Mesut Toğaçar , Bilal Solak , Cem Ayden

https://doi.org/10.53443/anadoluibfd.1514908

Abstract

Bu çalışma, üretim süreçlerindeki kusur oranlarının doğru sınıflandırılması ve kalite kontrol süreçlerinin optimize edilmesi için yenilikçi bir yöntem sunmaktadır. Çalışmada, sayısal veriler iki boyutlu QR kod görüntülerine dönüştürülerek AlexNet modeli ile analiz edilmiştir. Bu yöntem, derin öğrenme modellerinin güçlü desen tanıma yeteneklerinden yararlanarak kusur oranlarını yüksek doğrulukla sınıflandırmayı amaçlamaktadır. Veri seti, düşük ve yüksek kusur oranları olarak etiketlenmiş ve %80 eğitim, %20 test olarak bölünmüştür. Karar Ağacı, Gradient Boosting, K-En Yakın Komşu, Lojistik Regresyon, Saf Bayes, Rastgele Orman ve Destek Vektör Makinesi gibi çeşitli makine öğrenmesi modelleri ile karşılaştırılmıştır. Sonuçlar, AlexNet modelinin kusur oranlarını %100 doğrulukla sınıflandırdığını göstermektedir. Bu bulgular, derin öğrenme algoritmalarının üretim süreçlerindeki kalite kontrol ve kusur tespiti için son derece etkili olabileceğini vurgulamaktadır. Ayrıca, çalışmanın kısıtlılıkları ve gelecekteki araştırmalar için öneriler sunulmuştur. Bu yenilikçi metodoloji, diğer endüstriyel süreçlerde ve farklı veri setlerinde de geniş bir kullanım potansiyeline sahip olup, üretim verimliliğinin artırılmasına katkı sağlayacaktır.

Keywords

Kusur Oranı Sınıflandırma, Makine Öğrenmesi, Derin Öğrenme, Karekod Dönüşümü, AlexNet

Ethical Statement

Çalışma için etik kurul iznine ihtiyaç duyulmamıştır.

CLASSIFICATION OF DEFECT RATES IN PRODUCTION PROCESSES: AN APPROACH BASED ON DEEP LEARNING WITH INNOVATIVE QR CODE CONVERSION

Abstract

This study presents an innovative method for accurately classifying defect rates in manufacturing processes and optimizing quality control processes. In the study, numerical data are transformed into two-dimensional QR code images and analyzed with the AlexNet model. This method aims to classify defect rates with high accuracy by utilizing the powerful pattern recognition capabilities of deep learning models. The dataset was labeled as low and high defect rates and divided into 80% training and 20% testing. It is compared with various machine learning models such as Decision Tree, Gradient Boosting, K-Nearest Neighbor, Logistic Regression, Naive Bayes, Random Forest and Support Vector Machine. The results show that the AlexNet model classifies defect rates with 100% accuracy. These findings emphasize that deep learning algorithms can be highly effective for quality control and defect detection in manufacturing processes. Furthermore, limitations of the study and suggestions for future research are presented. This innovative methodology has the potential to be widely used in other industrial processes and different data sets, contributing to the improvement of production efficiency.

Keywords

Defect Rate Classification, Machine Learning, Deep Learning, QR Code Conversion, AlexNet

References

• Abdallah, M., Joung, B. G., Lee, W. J., Mousoulis, C., Raghunathan, N., Shakouri, A., & Bagchi, S. (2023). Anomaly detection and inter-sensor transfer learning on smart manufacturing datasets. Sensors, 23(1). doi: 10.3390/s23010486
• Ademujimi, T. T., Brundage, M. P., & Prabhu, V. V. (2017). A review of current machine learning techniques used in manufacturing diagnosis. In M. F. Zaeh (Ed.), Advances in Production Management Systems. The Path to Intelligent, Collaborative and Sustainable Manufacturing: IFIP WG 5.7 International Conference, APMS 2017, Hamburg, Germany, September 3-7, 2017, Proceedings, Part I (pp. 407-415). Springer International Publishing. doi: 10.1007/978-3-319-66923-6_48
• Belnoue, J. P., Nixon-Pearson, O. J., Thompson, A. J., Ivanov, D., Potter, K. D., & Hallett, S. R. (2018). Consolidation-driven defect generation in thick composite parts. Journal of Manufacturing Science and Engineering, 140(7). doi: 10.1115/1.4039555
• Blondheim, D. Jr. (2022). Improving manufacturing applications of machine learning by understanding defect classification and the critical error threshold. International Journal of Metalcasting, 16(2), 502-520. doi: 10.1007/s40962-021-00637-0
• Borkovskaya, V., & Passmore, D. (2018). Application of failure mode and effects analysis in ecology in Russia. MATEC Web of Conferences, 193, 05026. doi: 10.1051/matecconf/201819305026
• Breitenbach, J., Eckert, I., Mahal, V., Baumgartl, H., & Buettner, R. (2022). Automated defect detection of screws in the manufacturing industry using convolutional neural networks. Proceedings of the Annual Hawaii International Conference on System Sciences. doi: 10.24251/hicss.2022.151
• Bullejos, M., Cabezas, D., Martín-Martín, M., & Alcalá, F. (2022). A k-nearest neighbors algorithm in Python for visualizing the 3D stratigraphic architecture of the Llobregat River Delta in NE Spain. Journal of Marine Science and Engineering, 10(7). doi: 10.3390/jmse10070986
• Burt, J. R., Torosdagli, N., Khosravan, N., RaviPrakash, H., Mortazi, A., Tissavirasingham, F., & Bağcı, U. (2018). Deep learning beyond cats and dogs: Recent advances in diagnosing breast cancer with deep neural networks. The British Journal of Radiology. doi: 10.1259/bjr.20170545
• Cao, Y., & Chun-hai, Z. (2012). Algorithm with weighted attributes for unresolved exception in decision tree induction algorithm. 2012 Second International Conference on Business Computing and Global Informatization. doi: 10.1109/bcgin.2012.140
• Chen, Y., Peng, X., Kong, L., Dong, G., Remani, A., & Leach, R. (2021). Defect inspection technologies for additive manufacturing. International Journal of Extreme Manufacturing, 3(2). doi: 10.1088/2631-7990/abe0d0
• Chien, C. F., Hung, W. T., & Liao, E. T. Y. (2022). Redefining monitoring rules for intelligent fault detection and classification via CNN transfer learning for smart manufacturing. IEEE Transactions on Semiconductor Manufacturing, 35(2), 158-165. doi: 10.1109/TSM.2022.3164904
• Demetgul, M. (2013). Fault diagnosis on production systems with support vector machine and decision trees algorithms. The International Journal of Advanced Manufacturing Technology, 67, 2183-2194. doi: 10.1007/s00170-012-4639-5
• Dudyrev, E., & Kuznetsov, S. O. (2021). Decision concept lattice vs. decision trees and random forests. In Formal Concept Analysis: 16th International Conference, ICFCA 2021, Strasbourg, France, June 29–July 2, 2021, Proceedings 16 (pp. 252-260). Springer International Publishing. doi: 10.48550/arxiv.2106.00387
• Escobar, C. A., & Morales-Menendez, R. (2018). Machine learning techniques for quality control in high conformance manufacturing environment. Advances in Mechanical Engineering, 10(2), 1687814018755519. doi: 10.1177/1687814018755519
• Essid, O., Laga, H., & Samir, C. (2018). Automatic detection and classification of manufacturing defects in metal boxes using deep neural networks. PLOS ONE, 13(11), e0203192. doi: 10.1371/journal.pone.0203192
• Gemert, J., Snoek, C., Veenman, C., & Smeulders, A. (2006). The influence of cross-validation on video classification performance. Proceedings of the ACM International Conference on Multimedia. doi: 10.1145/1180639.1180786
• Goel, E., & Abhilasha, E. (2017). Random forest: A review. International Journal of Advanced Research in Computer Science and Software Engineering, 7(1), 251-257. doi: 10.23956/ijarcsse/v7i1/01113
• Herzog, T., Brandt, M., Trinchi, A., Sola, A., & Molotnikov, A. (2024). Process monitoring and machine learning for defect detection in laser-based metal additive manufacturing. Journal of Intelligent Manufacturing, 35(4), 1407-1437. doi: 10.1007/s10845-023-02119-y
• Hidayaturrohman, Q. A., Clarke, H. G., Taflan, G. Y., & Sancaktar, I. (2023). A comparative study of machine learning approaches to heart disease prediction: An empirical analysis. Preprint version. doi: 10.21203/rs.3.rs-3098962/v1
• Karthikeyan, T., & Thangaraju, P. (2013). Analysis of classification algorithms applied to hepatitis patients. International Journal of Computer Applications, 62(15), 25-30. doi: 10.5120/10157-5032
• Kharoua, R. E. (2024). Predicting manufacturing defects dataset. Kaggle. https://www.kaggle.com/datasets/rabieelkharoua/predicting-manufacturing-defects-dataset adresinden erişildi.
• Kim, A., Oh, K., Jung, J. Y., & Kim, B. (2018). Imbalanced classification of manufacturing quality conditions using cost-sensitive decision tree ensembles. International Journal of Computer Integrated Manufacturing, 31(8), 701-717. doi: 10.1080/0951192X.2017.1407447
• Kotsiopoulos, T., Sarigiannidis, P., Ioannidis, D., & Tzovaras, D. (2021). Machine learning and deep learning in smart manufacturing: The smart grid paradigm. Computer Science Review, 40. doi: 10.1016/j.cosrev.2020.100341
• Lee, K. B., Cheon, S., & Kim, C. O. (2017). A convolutional neural network for fault classification and diagnosis in semiconductor manufacturing processes. IEEE Transactions on Semiconductor Manufacturing, 30(2), 135-142. doi: 10.1109/TSM.2017.2676245
• Liu, J., Cui, J., & Chen, C. (2023). Online efficient secure logistic regression based on function secret sharing. Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. doi: 10.1145/3583780.3614998
• Lv, M., Zhou, G., He, M., Chen, A., Zhang, W., & Hu, Y. (2020). Maize leaf disease identification based on feature enhancement and DMS-robust AlexNet. IEEE Access, 8, 57952-57966. doi: 10.1109/access.2020.2982443
• Mai, J., Chen, Z., Yi, C., & Ding, Z. (2021). Human activity recognition of exoskeleton robot with supervised learning techniques. Preprint version. doi: 10.21203/rs.3.rs-1161576/v1
• Natekin, A., & Knoll, A. (2013). Gradient boosting machines: A tutorial. Frontiers in Neurorobotics, 7. doi: 10.3389/fnbot.2013.00021
• Nuhu, A. A., Zeeshan, Q., Safaei, B., & Shahzad, M. A. (2023). Machine learning-based techniques for fault diagnosis in the semiconductor manufacturing process: A comparative study. The Journal of Supercomputing, 79(2), 2031-2081. doi: 10.1007/s11227-022-04730-x
• Oktaria, A. S., Prakasa, E., & Suhartono, E. (2019). Wood species identification using convolutional neural network (CNN) architectures on macroscopic images. Journal of Information Technology and Computer Science, 4(3), 274-283. doi: 10.25126/jitecs.201943155
• Olorunlambe, K. A., Hua, Z., Shepherd, D. E. T., & Dearn, K. D. (2021). Towards a diagnostic tool for diagnosing joint pathologies: Supervised learning of acoustic emission signals. Sensors, 21(23), 8091. doi: 10.3390/s21238091
• Papageorgiou, Κ., Theodosiou, T., Rapti, A., Papageorgiou, E. I., Dimitriou, N., Tzovaras, D., & Margetis, G. (2022). A systematic review on machine learning methods for root cause analysis towards zero-defect manufacturing. Frontiers in Manufacturing Technology, 2. doi: 10.3389/fmtec.2022.972712
• Papernot, N. (2018). Deep k-nearest neighbors: Towards confident, interpretable and robust deep learning. Preprint version. doi: 10.48550/arxiv.1803.04765
• Rafdi, A., Mawengkang, H., & Efendi, S. (2021). Sentiment analysis using Naïve Bayes algorithm with feature selection particle swarm optimization (PSO) and genetic algorithm. International Journal of Advances in Data and Information Systems, 2(2). doi: 10.25008/ijadis.v2i2.1224
• Rizal, R. A., Purba, N. O., Siregar, L. A., Sinaga, K. P., & Azizah, N. (2020). Analysis of tuberculosis (TB) on X-ray images using SURF feature extraction and the k-nearest neighbor (KNN) classification method. Journal of Applied Information and Communication Technologies, 5(2). doi: 10.32497/jaict.v5i2.1979
• Ruiz, L., Torres, M., Gómez, A., Díaz, S., González, J. M., & Cavas, F. (2020). Detection and classification of aircraft fixation elements during manufacturing processes using a convolutional neural network. Applied Sciences, 10(19). doi: 10.3390/app10196856
• Safavian, S., & Landgrebe, D. A. (1991). A survey of decision tree classifier methodology. IEEE Transactions on Systems, Man, and Cybernetics, 21(3), 660-674. doi: 10.1109/21.97458
• Singh, S. A., & Desai, K. A. (2023). Automated surface defect detection framework using machine vision and convolutional neural networks. Journal of Intelligent Manufacturing, 34(4), 1995-2011. doi: 10.1007/s10845-021-01878-w
• Singh, S. A., Kumar, A. S., & Desai, K. A. (2023). Comparative assessment of common pre-trained CNNs for vision-based surface defect detection of machined components. Expert Systems with Applications, 218. doi: 10.1016/j.eswa.2023.119623
• Tran, H., Friendship, R., & Poljak, Z. (2023). Classification of group A rotavirus VP7 and VP4 genotypes using random forest. Frontiers in Genetics, 14. doi: 10.3389/fgene.2023.1029185
• Wakayama, R., Murata, R., Kimura, A., Yamashita, T., Yamauchi, Y., & Fujiyoshi, H. (2015). Distributed forests for MapReduce-based machine learning. 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR). doi: 10.1109/acpr.2015.7486509
• Wang, L., Wang, X., & Li, X. (2007). Inference and learning in hybrid probabilistic network. Frontiers of Computer Science in China, 1(4), 429-435. doi: 10.1007/s11704-007-0041-0
• Wang, R., & Chen, N. (2020). Defect pattern recognition on wafers using convolutional neural networks. Quality and Reliability Engineering International, 36(4), 1245-1257. doi: 10.1002/qre.2627
• Wang, W., Li, T., & Tu, Z. (2019). Multiple fingerprints-based indoor localization via GBDT: Subspace and RSSI. IEEE Access, 7, 80519-80529. doi: 10.1109/access.2019.2922995
• Wen, L., Wang, W., & Huo, W. (2020). RegBoost: A gradient boosted multivariate regression algorithm. International Journal of Crowd Science, 4(1), 60-72. doi: 10.1108/ijcs-10-2019-0029
• Wermelinger, J. (2023). Opportunities and challenges of supervised machine learning for the classification of motor evoked potentials according to muscles. BMC Medical Informatics and Decision Making, 23(1). doi: 10.1186/s12911-023-02276-3
• Xue-jun, S., & Yang, G. (2006). Linear programming approach for the inverse problem of support vector machines. Proceedings of the 2006 International Conference on Machine Learning and Cybernetics. doi: 10.1109/icmlc.2006.258544
• Yang, J., Li, S., Wang, Z., Dong, H., Wang, J., & Tang, S. (2020). Using deep learning to detect defects in manufacturing: A comprehensive survey and current challenges. Materials, 13(24). doi: 10.3390/ma13245755
• Yoshida, K., Iwasawa, T., Sano, N., Tanaka, M., & Suzuki, T. (2017). Construction of defect detection system for image data using machine learning and image processing. Total Quality Science, 3(2), 46-58. doi: 10.17929/tqs.3.46