Toplam Ekipman Etkinliğine Etki Eden Faktörlerin Makine Öğrenim Yöntemleri ile Analizi

Year 2024, Volume: 58 Issue: 2, 171 - 184, 30.04.2024

Özgül Vupa Çilengiroğlu , İlke Genç

https://doi.org/10.51551/verimlilik.1266852

Abstract

Amaç: Üretim sektöründeki bir firmanın 2018-2019 yılı orjinal verilerinden türetilmiş sıralı ölçekteki Toplam Ekipman Etkinliği (TEE) puanı üzerinde etkili olan değişkenlerin makine öğrenim algoritmaları ile modellenmesi, yorumlanması ve model performanslarının karşılaştırılması çalışmanın temel amacıdır.
Yöntem: TEE puanının modellemesinde karar ağaçları (CART, CHAID), lojistik regresyon (LogR) ve yapay sinir ağları (YSA) kullanılmıştır. Kurulan modellerin performans değerleri “duyarlılık”, “seçicilik”, “kesinlik” ve “doğruluk” kriterlerine göre hesaplanmıştır. Modelleri yorumlarken karar ağaçları ve YSA sonuçları için yüzdelerden, LogR için odds oranından yararlanılmıştır.
Bulgular: Modellerde TEE puanı üzerinde “saat”, “üretim”, “tecrübe” ve “kayıp metre” değişkenleri incelenmiştir. Performans karşılaştırmasında en iyi sonuç veren algoritmanın sıralı LogR olduğu ve bu modele göre üretimin düşük ve çalışanlarının daha az tecrübeli olduğu firmalarda daha “düşük” TEE puanı elde edilirken, kayıp metresi daha az olan firmalarda daha “yüksek” TEE” puanı alma şanslarının olduğu saptanmıştır.
Özgünlük: Literatürde sürekli olarak modellenen TEE puanının kategorik hale getirilerek sınıflar arasındaki farklılığın belirlenmesiyle firmaların kendi konumlarını belirlemesi sağlanmıştır. Böylece firmalar kategorisini belirleyip seçilen modeldeki önemlilik sırasındaki faktörlerini değiştirerek bir üst kategoriye daha hızlı çıkabilecektir. Literatürde kategorik olanTEE puanını makine öğrenim algoritmaları ile çözümleyen modellerin olmaması bu çalışmanın özgünlüğü olarak belirlenmiştir.

Keywords

Toplam Ekipman Etkinliği, Karar Ağaçları, Sıralı Lojistik Regresyon, Yapay Sinir Ağları

Supporting Institution

yoktur

Project Number

yoktur

Analysis of the Factors Affecting the Total Equipment Efficiency with Machine Learning Methods

Abstract

Purpose: The main purpose of the study was determined as modeling, interpreting and comparing the model performances of the variables with machine learning algorithms. Based on the original data in 2018-2019 from a company operating in the manufacturing sector, variables that are effective on the Overall Equipment Effectiveness (OEE) score in the ordinal scale obtained by the simulation study are used.
Methodology: Decision trees (CART, CHAID), logistic regression (LogR) and artificial neural networks (ANN) were used in modeling the OEE score. The performance values of the established models were calculated according to the criteria of “sensitivity”, “specificity”, “precision” and “accuracy”. While interpreting the models, percentages were used for decision trees and ANN results, and odds ratio was used for LogR.
Findings: In the models, "hour", "production", "experience" and "lost meter" variables were examined on OEE score. By comparing the performance criteria, it was determined that the algorithm that gave the best results was ordinal LogR. It has been determined that those with low production and less experience have a “lower" OEE score, and those with less lost meters have a higher chance of getting a “higher" OEE score.
Originality: OEE, which is modeled as a continuous in the literature, was made categorical and the companies were able to determine their own positions by determining the difference between the classes. Thus, companies will be able to move up to the next category faster by determining their category and changing the variables in order of importance in the selected model. The lack of models in the literature that analyze categorical OEE with machine learning has been determined as the originality of this study.

Keywords

Overall Equipment Effectiveness, Decision Trees, Ordinal Logistic Regression, Artificial Neural Networks

Project Number

yoktur

References

• Abdelbar, K.M., Bouami, D., Elfezazi, S. (2019). “New Approach towards Formulation of the Overall Equipment Effectiveness”, Journal of Quality in Maintenance Engineering, 25(1), 90-127. DOI: 10.1108/JQME-07-2017-0046
• Acar, Ö. ve Çakırkaya, M. (2018). “Bir Üretim Hattında Toplam Ekipman Etkinliğinin Ölçülmesi ve Geliştirilmesi Üzerine Bir Uygulama”, Gümüşhane Üniversitesi Sosyal Bilimler Enstitüsü Elektronik Dergisi, 9(24), 217-230.
• Acosta, C.P, Terán, H.C., Arteaga, O. ve Terán, M.B. (2020). “Machine Learning in Intelligent Manufacturing System for Optimization of Production Costs and Overall Effectiveness of Equipment in Fabrication Models”, Journal of Physics: Conference Series, 1432. DOI: 10.1088/1742-6596/1432/1/012085
• Akçacı, T. ve Özyurt, S. (2021). “Yalın Üretime Geçiş: İplik Sektöründe Bir Uygulama”, İşletme ve İktisat Çalışmaları Dergisi, 9(2), 85-103.
• Becker, J.M., Borst, J. ve Veen, A. (2015). “Improving the Overall Equipment Effectiveness in High-Mix-Low-Volume Manufacturing Environments”, CIRP Annals, 64(1), 419-422.
• Braglia, M., Frosolini, M. ve Zammori, F. (2009). “Overall Equipment Effectiveness of a Manufacturing Line (OEEML): An Integrated Approach to Assess Systems Performance”, Journal of Manufacturing Technology Management, 20(1), 8-29. DOI: 10.1108/17410380910925389
• Corrales, L.C., Lambán, M.P., Hernandez Korner, M.E., Royo, J. (2020). “Overall Equipment Effectiveness: Systematic Literature Review and Overview of Different Approaches”, Applied Science, 10, 6469. DOI: 10.3390/app10186469
• Costa, J. ve Cardoso, J. (2005). “Classification of Ordinal Data Using Neural Networks”, 16th European Conference on Machine Learning, Porto, Portugal, October 3-7, 2005 Proceedings, 690-697. ISBN-13 978-3-540-29243-2 Springer Berlin Heidelberg New York. DOI: 10.1007/11564096_70
• Çelik, H. (2019). “5S Uygulamalarının Ayar Süreleri ve Toplam Ekipman Etkinliğine Etkisi”, Yorum Yönetim Yöntem Uluslararası Yönetim Ekonomi ve Felsefe Dergisi, 7(2), 95-110.
• Çelik, H. (2020). “Ekipman Etkinliğine Farklı Bir Yaklaşım: Genel Operasyon Etkinliği”, Verimlilik Dergisi, 4, 25-40. DOI: 10.51551/verimlilik.560600
• Dobra, P ve Jósvai, J. (2022). “Predicting the impact of type changes on Overall Equipment Effectiveness (OEE) through machine learning”, 2022 IEEE 1st International Conference on Internet of Digital Reality, 23-24 June. DOI: 10.1109/IOD55468.2022.9986645
• Domingo, R. ve Aguado, S. (2015). “Overall Environmental Equipment Effectiveness as a Metric of a Lean and Green Manufacturing System”, Sustainability, 7, 9031–9047. DOI: 10.3390/su7079031
• Engelmann, B. Schmitt, S., Miller, E., Bräutigam, V. ve Schmitt, J. (2020). “Advances in Machine Learning Detecting Changeover Processes in Cyber Physical Production Systems”, J. of Manufacturing and Materials Processing, 4(108). DOI: 10.3390/jmmp4040108
• Ersöz, F. ve Çınar, Y. (2021). “Veri Madenciliği ve Makine Öğrenimi Yaklaşımlarının Karşılaştırılması: Tekstil Sektöründe bir Uygulama”, Avrupa Bilim ve Teknoloji Dergisi, 29, 397-414. DOI: 10.31590/ejosat.1035124
• Eroğlu, D.Y. (2019). “Systematization, Implementation and Analysis of the Overall Throughput Effectiveness Calculation for the Finishing Processes After Weaving”. Tekstil ve Konfeksiyon, 29(2), 121-132.
• García-Arca, J., Prado-Prado J.C. ve Fernández-González, A.J. (2018). Integrating KPIs for Improving Efficiency in Road Transport. International Journal of Physical Distribution & Logistics Management, 48(9), 931-951. DOI: 10.1108/IJPDLM-05-2017-0199
• Garza-Reyes, J.A., Eldridge, S., Barber, K.D. ve Soriano Meier, H. (2010). “Overall Equipment Effectiveness (OEE) and Process Capability (PC) Measures: A Relationship Analysis”, International Journal of Quality and Reliability Management, 27(1), 48-62. DOI: 10.1108/02656711011009308
• Ghafoorpoor Yazdi, P., Azizi, A., Hashemipour, M. (2018). “An Empirical Investigation of the Relationship between Overall Equipment Efficiency (OEE) and Manufacturing Sustainability in Industry 4.0 with Time Study Approach”, Sustainability, 10, 3031. DOI: 10.3390/su10093031
• Görener, A. (2012). “Toplam Verimli Bakım ve Ekipman Etkinliği: Bir İmalat İşletmesinde Uygulama”, Electronic Journal of Vocational Colleges, 2(1), 15-20.
• Grossfeld, B. (2020). “Deep Learning vs Machine Learning”. Zendesk Blog. January, 2023. https://www.zendesk.com/blog/machine-learning-and-deep-learning/ (Erişim Tarihi: 12.03.2024).
• Hassani, I., Mazgualdi, C. ve Masrour, T. (2019). “Artificial Intelligence and Machine Learning to Predict and Improve Efficiency in Manufacturing Industry”, arXiv: 1901.02256, 2019.
• Him, L.C., Poh, Y.Y. ve Pheng, L.W. (2020). “Improvement of Overall Equipment Effectiveness from Predictive Maintenance”, International Conference on Digital Transformation and Applications (ICDXA).
• Kıyak Öztürk, E., Birant, K.U. ve Birant, D. (2019). “An Ordinal Classification Approach for Software Bug Prediction”. Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi. 21(62), 533-544. DOI: 10.21205/deufmd.2019216218
• Muchiri, P. ve Pintelon, L. (2008). “Performance Measurement Using Overall Equipment Effectiveness (OEE): Literature Review and Practical Application Discussion”, International Journal of Production Research, 46(13), 3517-3535. DOI:10.1080/00207540601142645
• Muñoz-Villamizar, A., Santos, J., Montoya-Torres, J., Jaca, C. (2018). ”Using OEE to Evaluate the Effectiveness of Urban Freight Transportation Systems: A Case Study. International Journal of Production Economics, 197, 232–242. DOI: 10.1016/j.ijpe.2018.01.011
• Nakajima, S. (1988). “Introduction to TPM: Total Productive Maintenance”. 11th Ed. New York, USA, Productivity Press.
• Nayak, D.M., Kumar, V.M.M., Naidu, G.S. ve Sharkar, V. (2013). “Evaluation of OEE in a Continuous Process Industry on an Insulation Line in a Cable Manufacturing Unit”, International Journal of Innovative Research in Science, Engineering and Technology, 2(5), 1629-1634.
• Özkan, N.F., Ada, E.C. ve Genlik, S. (2019). “Toplam Ekipman Etkinliğinin İyileştirilmesinde Triz Kullanımı: Bir Uygulama”, Verimlilik Dergisi, 2, 169-184.
• Paprocka, I., Kempa, W.M., Kalinowski, K., Grabowik, C. (2015). “Estimation of Overall Equipment Effectiveness Using Simulation Programme”, IOP Conference Series: Materials Science and Engineering, 95 (1), 1-6.
• Patel, C. ve Deshpande, V. (2016). “A Review on Improvement in Overall Equipment Effectiveness.” International Journal for Research in Applied Science & Engineering Technology, 4, 642-650.
• Piccarreta, R. (2008). “Classification Trees for Ordinal Variables”, Computational Statistics, 23, 407-427. DOI: 10.1007/s00180-007-0077-5
• Reyes, J.A.G. (2015). “From Measuring Overall Equipment Effectiveness (OEE) to Overall Resource Effectiveness (ORE)”, Journal of Quality in Maintenance Engineering, 21(4),506-527. DOI: 10.1108/JQME-03-2014-0014
• Purba, H.H., Wijayanto, E. ve Aristiara, N. (2018). “Analysis of Overall Equipment Effectiveness (OEE) with Total Productive Maintenance Method on Jig Cutting : A Case Study in Manufacturing Industry”, Journal of Scientific and Engineering Research, 5(7), 397-406.
• Reddy, R.V.K. ve Babu, U.R. (2018). “A Review on Classification Techniques in Machine Learning”, International Journal of Advance Research in Science and Engineering, 7(30), 40-47.
• Samoili, S., López Cobo, M., Gómez, E., De Prato, G., Martínez-Plumed, F. ve Delipetrev B. (2020). “Defining Artificial Intelligence. Towards an Operational Definition and Taxonomy of Artificial Intelligence”. Luxembourg Publications Office of the European Union. ISBN 978+92-76-17045-7. DOI: 10.2760/382730
• Sarı, B.E., (2019). “Measuring The Performances of the Machines Via Preference Selection Index (PSI) Method and Comparing Them with Values of Overall Equipment Efficiency (OEE)”, İzmir İktisat Dergisi, 34(4), 573-581.
• Singh, R.K., Clements, E.J. ve Sonwaney, V. (2018). “Measurement of Overall Equipment Effectiveness to Improve Operational Efficiency”, Int. J. Process Management and Benchmarking, 8(2), 246-261.
• Şapcı, B. ve Taşlı Pektaş, Ş. (2021). “Makine Öğrenmesi Aracılığı ile Kullanıcı Deneyimi Bilgilerinin Erken Mimari Tasarım Süreçleriyle Bütünleştirilmesi”, Journal of Computational Design, 2(1), 67-94.
• Tsarouhas, P.H. (2013). “Evaluation Of Overall Equipment Effectiveness in The Beverage Industry: A Case Study”, International Journal of Production Research, 51(2), 515-253. DOI: 10.1080/00207543.2011.653014
• Udomraksasakul, C. ve Udomraksasakul, C. (2018). “Increase Improvement of Overall Equipment Effectiveness of Plastic Molding Machine”, International Journal of Mechanical Engineering and Technology, 9(10), 1107-1113.
• Wudhikarn, R. (2016). “Implementation of the Overall Equipment Cost Loss (OECL) Methodology for Comparison with Overall Equipment Effectiveness (OEE)”, Journal of Quality in Maintenance Engineering, 22(1), 81-93.
• Yaşin, M., Daş, G. (2017). “KOBİ’lerde Ekipman Etkinliğinin İyileştirilmesinde TEE Tabanlı Yeni Bir Yaklaşım: Bir Ahşap Işleme Kuruluşunda Uygulama”, Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, 32(1), 45-52.
• Yılmaz, Ü. Ve Kuvat, Ö. (2023). “Investigating the Effect of Feature Selection Methods on the Success of Overall Equipment Effectiveness Prediction”, Uludağ University Journal of the Faculty of Engineering, 28(2). DOI: 10.17482/uumfd.1296479