Çelik Levha Arıza Tespiti için Makine Öğrenimi Algoritmalarının Karşılaştırmalı Analizi

Metaller, modern zamanların en önemli yapı malzemelerinden biridir. Özellikle yassı metal sacın üretim ve işleme süreci oldukça hassastır. Üretim sürecinin kontrolü sadece ara ürünlerin değil, aynı zamanda son ürünlerinde kalitesini etkiler. Çelik levha yüzeylerinde oluşan hataların erken tespiti, endüstriyel üretimde önemli bir görevdir. Geleneksel olarak süreç kontrolü ve hata tespiti uzman kişiler tarafından manuel olarak yapılmaktadır. Ancak bu yöntem hem zaman hem de maliyet açısından uygun değildir. Sanayi devrimi IR 4.0 ile ürünlerde hata tespit problemlerini çözmek için makine öğrenimi (ML) teknikleri geliştirilmiştir. Bu çalışma, çelik yüzeyde üretim esnasında oluşabilecek altı farklı hata sınıfının tespiti için temel makine öğrenme yöntemleri geliştirmeye odaklanmıştır. Sınıflandırma problemi için beş standart ML modeli: LD, KNN, DT, SVM, RF ve bir derin öğrenme (DNN) modeli: tek boyutlu DNN geliştirilmiştir. Deneysel veri seti olarak UCI çelik plaka deformasyon veri seti kullanılmıştır. Yöntemlerin başarısını tespit etmek için beş performans kriteri: Doğruluk, Duyarlılık, Özgüllük, Kesinlik, F1 değeri kullanılmıştır. LD, KNN, DT, SVM, RF ve DNN sınıflandırma yöntemlerinin başarı oranları sırasıyla 90.136%, 91.780%, 93.013%, 93.287%, 95.479%, 96.986% olarak elde edilmiştir. Sonuçlar, makina öğrenmesi yaklaşımının çelik levha arıza teşhis problemindeki önemli etkisini gösterilmiştir.

Anahtar Kelimeler:

Çelik Levha Arızası, Arıza Tespiti, Makine Öğrenimi

Comparison Analysis of Machine Learning Algorithms for Steel Plate Fault Detection

Metals are one of the most important building materials of modern times. Especially the production and metalworking process of flat metal sheets is very sensitive. Control of the manufacturing process affects not only the intermediate products but also the quality of final products. Early detection of defects on steel plate surfaces is an important task in industrial production. Process control and mistake detection have traditionally been done manually by experts. However, this method is not proper in terms of both time and cost. With the industrial revolution IR 4.0, machine learning (ML) techniques have been developed to solve fault detection problems in products. This study focuses on developing basic machine learning methods for the detection of six different error classes that may occur during production on steel surfaces. Five standard ML models: LD, KNN, DT, SVM, RF, and deep learning (DNN) model: one-dimensional DNN was developed for the classification problem. The UCI steel plate deformation data set was used as the experimental data set. Five performance criteria: Accuracy, Sensitivity, Specificity, Precision, and F1 value were used to determine the success of the methods. The success rates of LD, KNN, DT, SVM, RF and DNN classification methods were 90.136%, 91.7880%, 93.013%, 93.287%, 95.479%, 96.986%, respectively. The results show the significant impact of the machine learning approach on the steel plate fault diagnosis problem.

Keywords:

Steel Plate Defect, Fault Detection, Machine Learning,

PDF

___

[1] S.M. Halawani, "A study of decision tree ensembles and feature selection for steel plates faults detection", International Journal of Technical Research and Applications, vol. 2, no. 4, pp. 127–131, 2014.
[2] K. Rajan, "Materials informatics". Materials Today, vol. 8, no.10, pp. 38–45, 2005. https://doi.org/10.1016/S1369-7021(05)71123-8
[3] A. Kelly, K.M. Knowles, "Crystallography and crystal defects: second edition", John Wiley & Sons, Ltd., ISBN:9780470750155, 2012. https://doi.org/10.1002/9781119961468
[4] A. Abdullahi, N.A. Samsudin, M.R. Ibrahim, M.S. Aripin, S.K.A. Khalid, Z.A. Othman, "Towards IR4.0 implementation in e-manufacturing: Artificial intelligence application in steel plate fault detection", Indonesian Journal of Electrical Engineering and Computer Science, vol.20, no.1, pp. 430–436, 2020. https://doi.org/10.11591/ijeecs.v20.i1.pp430-436
[5] T. Nkonyana, Y. Sun, B. Twala, E. Dogo, "Performance evaluation of data mining techniques in steel manufacturing industry", Procedia Manufacturing, vol. 35, pp. 623–628, 2019. https://doi.org/10.1016/j.promfg.2019.06.004
[6] S. Nasiri, M.R. Khosravani, K. Weinberg, "Fracture mechanics and mechanical fault detection by artificial intelligence methods: A review", Engineering Failure Analysis, vol. 81, pp. 270–293, 2017. https://doi.org/10.1016/j.engfailanal.2017.07.011
[7] Z. Wang, W. Yang, H. Zhang, Y. Zheng, "SPA-based modified local reachability density ratio wSVDD for nonlinear multimode process monitoring", Complexity, vol. 2021, pp.1–15, https://doi.org/10.1155/2021/5517062
[8] A. Schumacher, T. Nemeth, W. Sihn, "Roadmapping towards industrial digitalization based on an Industry 4.0 maturity model for manufacturing enterprises". Procedia CIRP, vol. 79, pp. 409–414, 2019, https://doi.org/10.1016/j.procir.2019.02.110
[9] W.S. Alaloul, M.S. Liew, N.A.W.A. Zawawi, I.B. Kennedy, "Industrial revolution 4.0 in the construction industry: Challenges and opportunities for stakeholders", Ain Shams Engineering Journal, vol. 11, no.1, pp. 225–230, 2020, https://doi.org/10.1016/j.asej.2019.08.010
[10] J. Han, M. Kamber, J. Pei, "Data mining: Data mining concepts and techniques", Morgan Kaufmann Publishers is an imprint of Elsevier,225 Wyman Street, Waltham, MA 02451, USA, 2014.
[11] M. Perzyk, A. Kochanski, J. Kozlowski, A. Soroczynski, R. Biernacki, "Comparison of data mining tools for significance analysis of process parameters in applications to process fault diagnosis", Information Sciences, vol. 259, pp. 380–392 ,2014. https://doi.org/10.1016/j.ins.2013.10.019
[12] Z. Zhao, J. Yang, W. Lu, X. Wang, "Application of local outlier factor method and back-propagation neural network for steel plates fault diagnosis". The 27th Chinese Control and Decision Conference (2015 CCDC), pp. 2416–2421, 2015. https://doi.org/10.1109/CCDC.2015.7162326
[13] A. Kharal, "Explainable artificial intelligence based fault diagnosis and insight harvesting for steel plates manufacturing", 2020, https://doi.org/10.48550/arXiv.2008.04448.
[14] Y. Tian, M. Fu, F. Wu, "Steel plates fault diagnosis on the basis of support vector machines", Neurocomputing, vol. 151, pp. 296–303 (2015). https://doi.org/10.1016/j.neucom.2014.09.036
[15] S. Jain, C. Azad, J. Vijay Kumar, "Steel faults diagnosis using predictive", International Journal of Computer Engineering and Applications, vol. 4, no. 3, pp. 69–78, 2014.
[16] J. Chen, "The Application of tree-based ML algorithm in steel plates faults identification", Journal of Applied and Physical Sciences, vol. 4, no.2, pp. 47–54, 2018. https://doi.org/10.20474/japs-4.2.1
[17] J.S. Chou, T.T.P. Pham, C.C. Ho, "Article metaheuristic optimized multi-level classification learning system for engineering management", Appl. Sci., vol. 11, no.12, pp. 5533-5556, 2021. https://doi.org/10.3390/app11125533
[18] M. Gamal, A. Donkol, A. Shaban, F. Costantino, G. Di, R. Patriarca, "Anomalies detection in smart manufacturing using machine learning and deep learning algorithms", Proceedings of the International Conference on Industrial Engineering and Operations Management, Rome, Italy, August 2-5, 2021, pp. 1611–1622.
[19] Semeion Centro Ricerche, "Semeion: research center of sciences of communication", Via Sersale 117, 00128, Rome, Italy, 2021, www.semeion.it.
[20] J.M. Johnson, T.M. Khoshgoftaar, "Survey on deep learning with class imbalance", Johnson and Khoshgoftaar J Big Data, vol. 6, no.27, 2019. https://doi.org/10.1186/s40537-019-0192-5
[21] A. Alan, M. Karabatak, "Sınıflandırma İlişkisinde Performansa Etki Eden Faktörlerin Değerlendirilmesi", Fırat Üniversitesi Mühendislik Bilim. Derg., vol. 32, no.2, pp. 531–540, 2020. https://doi.org/10.35234/fumbd.738007
[22] M. Pal, G.M. Foody, "Feature selection for classification of hyperspectral data by SVM", EEE Transactions on Geoscience and Remote Sensing, vol. 48, no.5, pp. 2297–2307, 2010. https://doi.org/10.1109/TGRS.2009.2039484
[23] O. Yaman, T. Tuncer, B. Tasar, "DES-Pat: A novel DES pattern-based propeller recognition method using underwater acoustical sounds", Applied Acoustics, vol. 175, pp. 107859, 2021. https://doi.org/10.1016/j.apacoust.2020.107859
[24] Ş.Y. Yiğiter, S.S. Sarı, T. Karabulut, E.E. Başakın, "Kira sertifikasi fiyat değerlerinin makine öğrenmesi metodu ile tahmini", International Journal of Islamic Economics and Finance Studies, vol. 4, no.3, pp. 74–82, 2018. https://doi.org/10.25272/ijisef.412760
[25] J. Bjorck, C. Gomes, B. Selman, KQ Weinberger, "Understanding batch normalization", Adv Neural Inf Process Syst, vol. 2018, pp. 7694–7705, 2018.