ENDÜSTRİYEL EKİPMANLARDA YAPAY ZEKA DESTEKLİ ÖN KESTİRİMCİ BAKIM STRATEJİLERİNİN GELİŞTİRİLMESİ VE UYGULANMASI

Abstract

Endüstriyel üretim süreçlerinde makinelerin güvenilirliği ve kullanılabilirliği, üretim verimliliği açısından kritik öneme sahiptir. Geleneksel bakım yaklaşımları, arıza gerçekleştikten sonra veya belirli periyotlarla müdahaleyi esas alırken, bu yöntemler gereksiz bakım maliyetlerine ve plansız duruşlara neden olabilmektedir. Bu çalışmanın amacı, yapay zeka tabanlı ön kestirimci bakım yaklaşımı geliştirerek, ekipman arızalarının gerçekleşmeden önce tahmin edilmesini sağlamaktır. Araştırmada, CMX 1100 V model CNC freze tezgahından elde edilen açık kaynaklı sensör verileri kullanılmış; veriler Python ortamında işlenmiş ve XGBoost algoritması ile analiz edilmiştir. Model, işleme durumunu yüksek doğruluk oranı ile sınıflandırmış ve olasılık tabanlı bakım kararı verebilen bir karar destek sistemi olarak tasarlanmıştır. Elde edilen sonuçlar, yapay zeka destekli ön kestirimci bakımın üretim süreçlerinde bakım planlamasını optimize ederek maliyetleri azaltabileceğini ve üretim sürekliliğini artırabileceğini göstermektedir. Çalışma, makine öğrenimi tabanlı karar mekanizmalarını endüstriyel bakım stratejilerine entegre ederek Endüstri 4.0'ın dijital dönüşümüne katkıda bulunmaktadır. 

Keywords

• Ön Kestirimci Bakım
• Yapay Zeka
• CNC freze
• Makine Öğrenmesi
• Endüstri 4.0
• Sensör Verisi

Development and Implementation of Artificial Intelligence-Based Predictive Maintenance Strategies in Industrial Equipment

Abstract

Reliability and availability of industrial equipment are critical factors for production efficiency. Traditional maintenance strategies, which rely on periodic or post-failure interventions, often result in unnecessary maintenance costs and unplanned downtime. This study aims to develop an artificial intelligence–based predictive maintenance approach to anticipate equipment failures before they occur. Open-source sensor data from a CMX 1100 V CNC milling machine were processed using Python, and analyzed with the XGBoost algorithm. The developed model successfully classified machining conditions with high accuracy and was structured as a decision-support system capable of providing probability-based maintenance recommendations. Results indicate that AI-driven predictive maintenance can optimize maintenance planning, reduce operational costs, and enhance production continuity. The study contributes to the digital transformation of Industry 4.0 by integrating machine learning–based decision mechanisms into industrial maintenance strategies.

Keywords

• Predictive Maintenance
• Artificial Intelligence
• CNC Milling
• Machine Learning
• Industry 4.0
• Sensor Data

References

1. Akdeniz, E. ve Arslan, H. (2024). Experimental study on new tool holder design to reduce vibration in turning operations. Journal of Vibration Engineering ve Technologies, 12, 6341–6353. https://doi.org/10.1007/s42417-023-01255-2
2. Arrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbudo, A., ... ve Herrera, F. (2020). Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion, 58, 82–115. https://doi.org/10.48550/arXiv.1910.10045
3. Bannat, A., Bautze, T., Beetz, M., Blume, J., Diepold, K., Ertelt, C., Geiger, F., Gmeiner, T., Gyger, T., Knoll, A., Lau, C., Lenz, C., Ostgathe, M., Reinhart, G., Roesel, W., Ruehr, T., Schuboe, A., Shea, K., Stork genannt Wersborg, I., … ve Zaeh, M. F. (2011). Artificial cognition in production systems. IEEE Transactions on Automation Science and Engineering, 8(1), 148–174. https://doi.org/10.1109/TASE.2010.2053534
4. Bhattacharya, S., ve Chakraborty, S. (2021). Application of XGBoost algorithm as a predictive tool in a CNC turning process. Reports in Mechanical Engineering, 2(1), 190–201. https://www.rme-journal.org/index.php/asd/article/view/51
5. Breiman, L. (2001). Random forests. Machine Learning, 45, 5–32. https://doi.org/10.1023/A:1010933404324
6. Bukhsh, Z. A., Saeed, A., Stipanovic, I., ve Dorée, A. G. (2019). Predictive maintenance using tree-based classification techniques: A case of railway switches. Transportation Research Part C: Emerging Technologies, 101, 35–54. https://doi.org/10.1016/j.trc.2019.02.001
7. Carvalho, T. P., Soares, F. A., Vita, R., Francisco, R. D. P., Basto, J. P., ve Alcalá, S. G. S. (2019). A systematic literature review of machine learning methods applied to predictive maintenance. Computers ve Industrial Engineering, 137, 106024. https://doi.org/10.1016/j.cie.2019.106024
8. Christian, C. (2024). Predictive maintenance market report 2023–2030. https://iot-analytics.com/iot-2023-in-review/. (Son erişim tarihi: 25 Aralık 2025)

9. Çakır, Mustafa & Güvenç, Mehmet Ali & Mistikoglu, Selcuk. (2019). IoT based Condition Monitoring System Design for Investigation of Non-Oil Ball Bearing in terms of Vibration, Temperature, Acoustic Emission, Current and Revolution Parameters.
10. Çakır, M., Guvenc, M. A., & Mistikoglu, S. (2021). The experimental application of popular machine learning algorithms on predictive maintenance and the design of IIoT based condition monitoring system. Computers & Industrial Engineering, 151, 106948. https://doi.org/10.1016/j.cie.2020.106948
11. Çakır, Mustafa. (2026). Prediction of fatigue crack growth rate, maximum strain energy release rate, and total energy dissipation in adhesive bonds: a machine learning approach and interactive R-Shiny panel development. PeerJ Computer Science. 12. e3450. 10.7717/peerj-cs.3450.
12. Dündar, D. R., Sarıçiçek, İ., Çınar, E., ve Yazıcı, A. (2021). Kestirimci bakımda makine öğrenmesi: Literatür araştırması. Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi, 29(2), 256–276. https://doi.org/10.31796/ogummf.873963
13. Farooq, U., Ademola, M., ve Shaalan, A. (2024). Comparative analysis of machine learning models for predictive maintenance of ball bearing systems. Electronics, 13(2), 438. https://doi.org/10.3390/electronics13020438
14. Freund, Y., ve Schapire, R. E. (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 55(1), 119–139. https://doi.org/10.1006/jcss.1997.1504
15. He, Y., Han, X., Gu, C., ve Chen, Z. (2018). Cost-oriented predictive maintenance based on mission reliability state for cyber manufacturing systems. Advances in Mechanical Engineering, 10(1). https://doi.org/10.1177/1687814017751467
16. Hector, I., ve Panjanathan, R. (2024). Predictive maintenance in Industry 4.0: A survey of planning models and machine learning techniques. PeerJ Computer Science, 10, e2016. https://doi.org/10.7717/peerj-cs.2016
17. https://www.deloitte.com/us/en/services/consulting/services/predictive-maintenance-and-the-smart-factory.html, Erişim tarihi: 25 Aralık 2025, Konu: Varlık Optimizasyonu: Ön Kestirimci Bakım.
18. https://www.ibm.com/think/topics/explainable-ai, Erişim tarihi: 25 Aralık 2025, Konu: Açıklanabilir Yapay Zeka Nedir?
19. https://tr.dmgmori.com/ueruenler/makineler/freze/dikey-freze/cmx-v/cmx-1100-v, Erişim tarihi: 25 Aralık 2025, Konu: CMX 1100 V - Dikey Frezeleme
20. https://aws.amazon.com/what-is/olap/, Erişim tarihi: 25 Aralık 2025, Konu: OLAP Nedir?
21. Jain, A. (2025). Understanding the 1D convolutional layer in deep learning. https://medium.com/@abhishekjainindore24/understanding-the-1d-convolutional-layer-in-deep-learning-7a4cb994c981. (Son erişim tarihi: 25 Aralık 2025)
22. Kanawaday, A., ve Sane, A. (2017). Machine learning for predictive maintenance of industrial machines using IoT sensor data. In 2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS). (pp. 87–90). https://doi.org/10.1109/ICSESS.2017.8342870
23. Kasap, M., Çinar, E., Yazici, A., ve Özkan, K. (2021). An experimental evaluation of intelligent fault detection and classification for induction motors utilizing machine learning approaches. Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi, 29(2), 126-136. https://doi.org/10.31796/ogummf.853090
24. Kavlakoglu, E. (2021). Random forest – a commonly used algorithm for both classification and regression problems. https://www.ibm.com/think/topics/random-forest. (Son erişim tarihi: 25 Aralık 2025)
25. Lundberg, S. M., ve Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30. https://doi.org/10.48550/arXiv.1705.07874
26. Mahamad, A. K., Saon, S., ve Hiyama, T. (2010). Predicting remaining useful life of rotating machinery based artificial neural network. Computers ve Mathematics with Applications, 60(4), 1078–1087. https://doi.org/10.1016/j.camwa.2010.03.065
27. Mobley, R. K. (2002). An Introduction to Predictive Maintenance (2nd ed.). Butterworth-Heinemann. https://doi.org/10.1016/B978-0-7506-7531-4.X5000-3
28. Muratlar, E. R. (2020). XGBoost nasıl çalışır? https://www.veribilimiokulu.com/xgboost-nasil-calisir/ (Son erişim tarihi: 25 Aralık 2025)
29. Oral, O., & Çakır, M. (2017). Nesnelerin İnterneti Kavrami ve Örnek Bir Prototipin Oluşturulması. Mehmet Akif Ersoy Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 8(Özel (Special) 1), 172-177. https://izlik.org/JA69AP68RC
30. Pan, S. J., ve Yang, Q. (2010). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345-1359. https://doi.org/10.1109/TKDE.2009.191
31. Randall, R. B. (2011). Vibration-based condition monitoring: Industrial, automotive and aerospace applications. John Wiley ve Sons. https://doi.org/10.1002/9780470977668
32. Ribeiro, M. T., Singh, S., ve Guestrin, C. (2016). "Why should I trust you?": Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. (pp. 1135–1144). https://doi.org/10.1145/2939672.2939778
33. Rojek, I., Kacprzyk, Z., ve Dostatni, E. (2023). Application of artificial neural networks for predictive maintenance in manufacturing systems. Applied Sciences, 13(9), 4971. https://doi.org/10.3390/app13094971
34. Rousopoulou, T., Georgoulas, G., Lalos, A. S., Kostopoulos, A., ve Moustakidis, S. (2020). A cognitive approach for predictive maintenance in industrial systems using sensor data analytics. Frontiers in Artificial Intelligence, 3, 578152. https://doi.org/10.3389/frai.2020.578152
35. Şirin, E. (2017). Ensemble yöntemler (topluluk öğrenmesi): Basit teorik anlatım ve Python uygulama. https://www.veribilimiokulu.com/ensemble-yontemler-topluluk-ogrenmesi-basit-teorik-anlatim-ve-python-uygulama/ (Son erişim tarihi: 25 Aralık 2025)
36. Schapire, R. E., ve Freund, Y. (2012). Boosting: Foundations and algorithms. MIT Press. https://doi.org/10.7551/mitpress/8291.001.0001
37. Schmidt, B., ve Wang, L. (2016). Cloud-based predictive maintenance system for machine tool linear axes. IFAC-PapersOnLine, 49(31), 100–105. https://doi.org/10.1016/j.promfg.2018.10.022
38. Stetco, A., Dinmohammadi, F., Zhao, X., Robu, V., Flynn, D., Barnes, M., Keane, J., ve Nenadic, G. (2019). Machine learning methods for wind turbine condition monitoring: A review. Renewable Energy, 133, 620–635. https://doi.org/10.1016/j.renene.2018.10.047
39. Sullivan, G. P., Pugh, R., Melendez, A. P., ve Hunt, W. D. (2010). Operations ve maintenance best practices: A guide to achieving operational efficiency (Release 3.0) (Report No. PNNL-19634). Pacific Northwest National Laboratory. https://doi.org/10.2172/1034595
40. Tahan, M., Tsoutsanis, E., Muhammad, M., ve Karim, Z. A. (2017). Performance-based health monitoring, diagnostics and prognostics for condition-based maintenance of gas turbines: A review. Applied Energy, 198, 122–144. https://doi.org/10.1016/j.apenergy.2017.04.048
41. Tian, Z. (2012). An artificial neural network method for remaining useful life prediction of equipment subject to condition monitoring. Journal of Intelligent Manufacturing, 23, 227–237. https://doi.org/10.1007/s10845-009-0356-9
42. Tuyet-Doan, V.-N., Choi, M., ve Park, G. (2025). XGBoost Method-based gearbox fault diagnosis using time-domain signal under road vehicle characteristics. Electronics, 14(23), 4736. https://doi.org/10.3390/electronics14234736
43. Yan, R., Gao, R. X., ve Chen, X. (2014). Wavelets for fault diagnosis of rotary machines: A review with applications. Signal Processing, 96, 1-15. https://doi.org/10.1016/j.sigpro.2013.04.015
44. Zaeh, M. F., Beetz, M., Shea, K., Reinhart, G., Bender, K., Lau, C., Ostgathe, M., Vogl, W., Wiesbeck, M., Engelhard, M., Ertelt, C., Rühr, T., Friedrich, M., ve Herle, S. (2009). The Cognitive Factory. In Changeable and reconfigurable manufacturing systems. (pp. 355–371). https://doi.org/10.1007/978-1-84882-067-8_20
45. Zhao, R., Yan, R., Chen, Z., Mao, K., Wang, P., ve Gao, R. X. (2019). Deep learning and its applications to machine health monitoring. Mechanical Systems and Signal Processing, 115, 213–237. https://doi.org/10.1016/j.ymssp.2018.05.050