Endüstriyel Robot Arızalarının Tahmin Edilmesinde Özellik Seçiminin Sınıflandırma Algoritmalarının Performansına Etkisi

Öz

Endüstriyel robotlar üretim verimliliğini, üretkenliği ve hassasiyeti artırır. Ancak arızalar üretim hatlarını kesintiye uğratarak kayıplara ve önemli sistem etkilerine yol açabilir. Bu çalışmada, UR3 CobotOps veri seti kullanılarak robot arızaları tahmin edilmektedir. Özellik seçiminin, iki hedefi (protective stops, and grip losses) tahmin etmede çeşitli sınıflandırma algoritmalarının performansı üzerindeki etkisini araştırıyor. Başlangıçta öznitelik seçimi yapılmayan sınıflandırıcıların temel performansı değerlendirilmiştir. Daha sonra ilk 10 özniteliğin seçilmesi ve sınıflandırıcı performansının yeniden değerlendirilmesi için iki farklı öznitelik seçme yöntemi (özyinelemeli öznitelik eleme ve Ki-Kare) uygulanmıştır. Beş farklı sınıflandırıcının (lojistik regresyon, karar ağacı, rastgele orman, destek vektör makinesi, ve k-en yakın komşu) test edildiği bu çalışmada öznitelik seçimi sonrasında sınıflandırma aşamasında karar ağacı ve rastgele orman ile yüksek sınıflandırma başarıları elde edilmiştir. Bu makale, farklı öznitelik seçme tekniklerini ve bunların sınıflandırma doğruluğu üzerindeki etkilerini belirleyerek makine öğrenimi alanına katkıda bulunarak sınıflandırıcıların farklı uygulamalarına ilişkin değerli bilgiler sağlar. Yapılan deneyler, rastgele orman algoritmasının endüstriyel robot arızalarını 0,99'a varan bir doğrulukla tahmin edebildiğini göstermektedir. Feature selection için Ki-Kare kullanıldığında da bu başarıya erişilmiştir. Bu araştırma sayesinde feature selection kullanılarak daha kısa sürede bu tahminin gerçekleştirilebileceği görülür.

Anahtar Kelimeler

• Kestirimci Bakım
• Operasyonel Verimlilik
• Öznitelik Seçimi
• Makine Öğrenmesi

Impact of Feature Selection on the Performance of Classification Algorithms in Predicting Industrial Robot Failures

Öz

Industrial robots enhance manufacturing efficiency, productivity, and precision. However, failures can disrupt production lines, leading to losses and significant system impact. In this study, robot failures are predicted using the UR3 CobotOps dataset and the impact of feature selection on the performance of various classification algorithms in predicting two targets (protective stops, and grip losses) is explored. Initially, the baseline performance of classifiers without feature selection has been evaluated. Then, two different feature selection methods (recursive feature elimination and chi-square) are applied to select the top 10 features and reassess the classifier’s performance. High classification success rates are obtained with Decision Tree and Random Forest after feature selection in this study, which tests five different classifiers (Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, and k-Nearest Neighbors) in the classification stage. This paper provides valuable insights into the different applications of classifiers, contributing to the field of machine learning by identifying different feature selection techniques and their impacts on classification accuracy. According to the experimental tests, an accuracy rate of about 99% has been obtained when Random Forest is used. This success has been also achieved when Chi-Square is used for feature selection. This paper shows that this prediction can be achieved in a shorter time using feature selection.

Anahtar Kelimeler

• Predictive Maintenance
• Operational Efficiency
• Feature Selection
• Machine Learning

Kaynakça

1. Alobaidy, M.A.A., Abdul-Jabbar, J.M., Al-khayyt, S.Z. 2020. Faults diagnosis in robot systems: A review. Al-Rafidain Engineering Journal (AREJ), Vol.25(2), pp.164–175.
2. Koca, O., Kaymakci, O.T., Mercimek, M. 2020. Advanced predictive maintenance with machine learning failure estimation in industrial packaging robots. In: 2020 International Conference on Development and Application Systems (DAS), pp.1–6.
3. Susto, G.A., Beghi, A., De Luca, C. 2012. A predictive maintenance system for epitaxy processes based on filtering and prediction techniques. Transactions on Semiconductor Manufacturing, Vol.25(4), pp.638–649.
4. Paolanti, M., Romeo, L., Felicetti, A., Mancini, A., Frontoni, E., Loncarski, J. 2018. Machine learning approach for predictive maintenance in industry 4.0. In: 2018 14th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA), pp.1–6.
5. Strauß, P., Schmitz, M., Wöstmann, R., Deuse, J. 2018. Enabling of predictive maintenance in the brownfield through low-cost sensors, an IIoT-architecture and machine learning. In: 2018 IEEE International Conference on Big Data (Big Data), pp.1474–1483.
6. Ayvaz, S., Alpay, K. 2021. Predictive maintenance system for production lines in manufacturing: A machine learning approach using IoT data in real-time. Expert Systems with Applications, Vol.173, p.114598.
7. Diryag, A., Mitić, M., Miljković, Z. 2014. Neural networks for prediction of robot failures. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, Vol.228(8), pp.1444–1458.
8. Pinto, R., Cerquitelli, T. 2019. Robot fault detection and remaining life estimation for predictive maintenance. Procedia Computer Science, Vol.151, pp.709–716.

9. Morettini, S. 2021. Machine learning in predictive maintenance of industrial robots. Master’s Thesis, KTH Royal Institute of Technology, School of Electrical Engineering and Computer Science.
10. Paolanti, M., Romeo, L., Felicetti, A., Mancini, A., Frontoni, E., Loncarski, J. 2018. Machine learning approach for predictive maintenance in industry 4.0. 14th IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications (MESA), pp.1–6.
11. Susto, G.A., Schirru, A., Pampuri, S., McLoone, S., Beghi, A. 2014. Machine learning for predictive maintenance: A multiple classifier approach. IEEE Transactions on Industrial Informatics, Vol.11(3), pp.812–820.
12. Tyrovolas, M., Aliev, K., Antonelli, D., Stylios, C. 2024. UR3 CobotOps, UCI Machine Learning Repository. DOI: 10.24432/C5J891.
13. Tyrovolas, M., Stylios, C., Aliev, K., Antonelli, D. 2024. Leveraging information flow-based fuzzy cognitive maps for interpretable fault diagnosis in industrial robotics. In: Doctoral Conference on Computing, Electrical and Industrial Systems, pp.98–110. Cham: Springer Nature Switzerland.
14. Zamri, N., Pairan, M.A., Azman, W.N.A.W., Abas, S.S., Abdullah, L., Naim, S., Gao, M. 2022. A comparison of unsupervised and supervised machine learning algorithms to predict water pollutions. Procedia Computer Science, Vol.204, pp.172–179.
15. Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P. 2002. SMOTE: synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, Vol.16, pp.321–357.
16. Yan, K., Zhang, D. 2015. Feature selection and analysis on correlated gas sensor data with recursive feature elimination. Sensors and Actuators B: Chemical, Vol.212, pp.353–363.
17. McHugh, M.L. 2013. The chi-square test of independence. Biochemia Medica, Vol.23(2), pp.143–149.
18. Cox, D.R. 1958. The regression analysis of binary sequences. Journal of the Royal Statistical Society Series B: Statistical Methodology, Vol.20(2), pp.215–232.
19. Morgan, J.N., Sonquist, J.A. 1963. Problems in the analysis of survey data, and a proposal. Journal of the American Statistical Association, Vol.58(302), pp.415–434.
20. Breiman, L. 2001. Random forests. Machine Learning, Vol.45, pp.5–32.
21. Cortes, C., Vapnik, V. 1995. Support-vector networks. Machine Learning, Vol.20, pp.273–297.
22. Cover, T., Hart, P. 1967. Nearest neighbor pattern classification. IEEE Transactions on Information Theory, Vol.13(1), pp.21–27.
23. Zhang, Z. 2016. Introduction to machine learning: k-nearest neighbors. Annals of Translational Medicine, Vol.4(11).