A comparative predictive maintenance application based on machine and deep learning

Yıl 2024, , 1037 - 1048, 30.11.2023

Ayşenur Hatipoğlu , Yiğit Güneri , Ersen Yılmaz

https://doi.org/10.17341/gazimmfd.1221105

Öz

In today's industry, technical equipment is evolving with an increasing complexity. More flexible maintenance strategies are of interest to provide the high reliability and sustainability of industrial equipment. Maintenance strategies are collected under three headings: preventive, corrective, and predictive maintenance. It has become imperative to monitor the data-driven industrial systems of today’s technology before potential failures occur. Predictive maintenance predicts these failures before they occur and takes the necessary action to prevent malfunctions from occurring. Predictive maintenance is a strategy which is based on both the prior and the real-time data to plan the maintenance. It is known that in industrial applications it improves overall performance, thus reducing the cost of maintenance. In this study a comparative predictive maintenance application which is based on machine and deep learning is realized. In the application classical machine learning methods and deep learning architectures are used. Logistic Regression, Naive Bayes Classifier, Decision Tree, Support Vector Machine, Random Forest, and K-Nearest Neighborhood are used as the classical machine learning methods while Long Short-Term Memory and Gated Recurrent Unit are used as the deep learning architectures. The performances of the methods are examined on the Predictive Maintenance dataset from UCI Machine Learning Repository and the results are presented comparatively in terms of metrics in detail.

Anahtar Kelimeler

Machine learning, deep learning, predictive maintenance, classification

Makine ve derin öğrenme temelli karşılaştırmalı bir öngörücü bakım uygulaması

Öz

Günümüz endüstrisinde teknik donanımlar artan bir karmaşıklıkla gelişmektedir. Endüstriyel donanımların yüksek güvenilirliğini ve sürdürülebilirliğini sağlamak için daha esnek bakım stratejileri ilgi çekmektedir. Bakım stratejileri; önleyici bakım, düzeltici bakım ve öngörücü bakım olmak üzere üç ana başlıkta toplanmaktadır. Günümüz teknolojisinin veri odaklı endüstriyel sistemlerini potansiyel arızalar oluşmadan önce takip etmek zorunlu hale gelmiştir. Öngörücü bakım bu arızaları oluşmadan önce tahmin eder ve oluşacak arızadan korunmak için zorunlu eylemlerin alınmasını sağlar. Öngörücü bakım, geçmiş ve gerçek zamanlı veriler üzerinde temellendirilmiş bir bakım planı stratejisidir. Endüstriyel uygulamalarda toplam başarımı iyileştirerek bakım maliyetlerini düşürdüğü bilinmektedir. Bu çalışmada, makine ve derin öğrenme temelli karşılaştırmalı bir öngörücü bakım uygulaması gerçekleştirilmiştir. Uygulamada klasik makine öğrenmesi yöntemleri ve derin öğrenme mimarileri kullanılmıştır. Klasik makine öğrenmesi yöntemi olarak Lojistik Regresyon, Naive Bayes Sınıflandırıcı, Karar Ağacı, Destek Vektör Makinesi, Rastgele Orman ve K-En Yakın Komşuluk; derin öğrenme mimarisi olarak ise Uzun Kısa Süreli Bellek ve Geçitli Tekrarlayan Birim kullanılmıştır. Yöntemlerin başarımları UCI Makine Öğrenmesi Ambarlarından alınan Öngörücü Bakım veri seti üzerinde incelenmiş ve sonuçlar karşılaştırmalı olarak ölçütler bazında detaylı bir biçimde sunulmuştur.

Anahtar Kelimeler

Makine öğrenmesi, derin öğrenme, öngörücü bakım, sınıflandırma

Kaynakça

• 1. Dangut M. D., Skaf Z., Jennions I.K., An integrated machine learning model for aircraft components rare failure prognostics with log-based dataset, ISA Transactions, 113, 127-139, 2021.
• 2. Mobley R. K., An introduction to predictive maintenance, Second Edition, Elsevier Science, USA, 2002.
• 3. De Faria H., Costa J. G. S., Olivas J. L. M., A review of monitoring methods for predictive maintenance of electric power transformers based on dissolved gas analysis, Renew. Sustain. Energy Rev., 46, 201–209, 2015.
• 4. Yu T., Zhu C., Chang Q., Wang J., Imperfect corrective maintenance scheduling for energy efficient manufacturing systems through online task allocation method, Journal of Manufacturing Systems, 53, 282-290, 2019.
• 5. Wang Y., Deng C., Wu J., Wang Y., Xiong Y., A corrective maintenance scheme for engineering equipment, Engineering Failure Analysis, 36, 269–283, 2014.
• 6. Ran Y., Zhou X., Lin P., Wen Y., Deng R., A Survey of Predictive Maintenance: Systems, Purposes and Approache, ArXiv, 1-36, 2019.
• 7. Sharma D. K., Brahmachari S., Singhal K., Gupta D, Data driven predictive maintenance applications for industrial systems with temporal convolutional networks, Computers & Industrial Engineering, 169, 2022.
• 8. Garcia M. C., Sanz-Bobi M. A., del Pico J., SIMAP: Intelligent System for Predictive Maintenance. Application to the health condition monitoring of a windturbine gearbox, Comput. Ind., 57 (6), 552–568, 2006.
• 9. Hashemian H. M., Bean W. C., State-of-the-art predictive maintenance techniques, IEEE Trans. Instrum. Meas., 60 (10), 3480–3492, 2011.
• 10. Liao L., Köttig F., Review of hybrid prognostics approaches for remaining useful life prediction of engineered systems, and an application to battery life prediction, IEEE Transactions on Reliability, 63, 191-207, 2014.
• 11. Türe B. A., Akbulut A., Zaim A.H., Techniques for apply predictive maintenance and remaining useful life: A systematic mapping study, BSEU Journal of Science, 8, 497-511, 2021.
• 12. Hermawan A. P., Kim D. S., Lee J. M., Predictive maintenance of aircraft engine using deep learning technique, 2020 International Conference on Information and Communication Technology Convergence (ICTC), Jeju Island - Korea, 1296-1298, 21-23 Ekim, 2020.
• 13. Louridas, P., Ebert, C., Machine learning, IEEE Software, 33 (5), 110–115, 2016.
• 14. Jones, P. J., Catt M., Davies M. J., Edwardson C. L., Mirkes E. M., Khunti K., Yates T., Rowlands A. V, Review Feature selection for unsupervised machine learning of accelerometer data physical activity clusters – A systematic review, 90, 120-128, 2021.
• 15. Ouadah A., Zemmouchi-Ghomari Salhi L., N., Selecting an appropriate supervised machine learning algorithm for predictive maintenance, The International Journal of Advanced Manufacturing Technology, 4277-4301, 2022.
• 16. Mueller A. C., Guido S., Introduction to Machine Learning with Python, O’Reilly Media, United States of America, 2016.
• 17. Güemes- Peña D., Nozal C. L., Sánchez R. M., Maudes J., Emerging topics in mining software repositories: Machine learning in software repositories and datasets, Progress in Artificial Intelligence, 7 (5), 237-247, 2018.
• 18. Raschka S., Python Machine Learning, Packt Publishing, Birmingham, UK, 2016.
• 19. Rovira M., Engvall K., Duwig C., Identifying key features in reactive flows: A tutorial on combining dimensionality reduction, unsupervised clustering, and feature correlation, Chemical Engineering Journal, 438, 1-15, 2022.
• 20. Ahfock D., McLachlan G.J., Semi-supervised learning of classifiers from a statistical perspective: A brief review, Econometrics and Statistics, 1-25, 2022.
• 21. VanderPlas J., Python Data Science Handbook Essential Tools for Working with Data, O’Reilly Media, United States of America, 2017.
• 22. B. Yoshua, Goodfellow I. J., Courville A., Deep Learning, MIT Press, 2016.
• 23. Sutton R. S., Barto A. G., Reinforcement Learning, An Introduction second edition, The MIT Press Cambridge, Massachusetts London, England, 2018.
• 24. James G., Witten D., Hastie Tibshirani T., R., An Introduction to Statistical Learning with Applications in R, Springer, 2021.
• 25. Zhang S., Zhang S., Wang B., Habetler T.G., Deep Learning Algorithms for Bearing Fault Diagnostics – A Comprehensive Review, IEEE Access, 8, 29857-29881, 2020.
• 26. Bruce P., Bruce A., Gedeck P., Practical Statistics for Data Scientists 50+ Essential Concepts Using R and Python, O’Reilly Media, United States of America, 2020.
• 27. S.Raschka, V.Mirjalili, Python Machine Learning, Packt Publishing, 2018.
• 28. Cortes, C., Vapnik, V., Support vector networks. Machine Learning, 20, 273–297, 1995.
• 29. Gökdemir A., Çalhan A., Deep learning and machine learning based anomaly detection in internet of things environments, Journal of the Faculty of Engineering and Architecture of Gazi University 37 (4), 1945-1956, 2022.
• 30. Ross S.M., Introduction to Probability Models, Introduction to Probability Theory, Elsevier, 2014.
• 31. Sherstinsky A., Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network, Physica D: Nonlinear Phenomena, 404 (8), 132306, 2020.
• 32. Hochreiter S., Schmidhuber J., Long Short-Term Memory, Neural Computation, 9 (8), 1735-1780, 1997.
• 33. Akın M., Sağıroğlu Ş., Short term traffic speed prediction with RNN method for roads characterized by density-based clustering method, Journal of the Faculty of Engineering and Architecture of Gazi University 37 (2), 581-593, 2022.
• 34. Dangut M.D., Skaf Z., Jennions I.K. Rescaled-LSTM for predicting aircraft component replacement under imbalanced dataset constraint, 2020 Advances in Science and Engineering Technology International Conferences (ASET), Dubai-United Arab Emirates, 1-9, 02-04 Şubat, 2020.
• 35. Kong Z., Cui Y., Xia Z., Lv H., Convolution and long short-term memory hybrid deep neural networks for remaining useful life prognostics, Appl. Sci., 9 (19), 2019.
• 36. Dey R., Salem F.M., Gate-Variants of Gated Recurrent Unit (GRU) Neural Networks, 2017 IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS), Boston, Massachusetts-USA, 1597-1600, 6-9 Ağustos, 2017.
• 37. Czum J. M., Dive Into Deep Learning, J. Am. Coll. Radiol., 17 (5), 637–638, 2020.
• 38. Hagmeyer S., Mauthe F., Zeiler P., Creation of publicly available data sets for prognostics and diagnostics addressing data scenarios relevant to industrial applications, International Journal of Prognostics and Health Management, 12 (2), 2153-2648, 2021.
• 39. Matzka S., Explainable artifical intelligence for predictive maintenance applications, 2020 Third International Conference on Artificial Intelligence for Industries (AI41), Irvine, CA-USA, 69-74, 21-23 Eylül, 2020.
• 40. Katkar R., Buktar R., Big data and predictive analytics in manufacturing enterprises for enhanced decision making, Journal of Emerging Technologies and Innovative Research (JETIR), 8 (9), 374-384, 2021.
• 41. Chawla N. V., Bowyer K. W., Hall L. O., Kegelmeyer W. P., SMOTE: Synthetic Minority Over-sampling Technique, Journal of Artificial Intelligence Research, 16, 321–357, 2002.
• 42. Elreedy D., Atiya A. F., A Comprehensive Analysis of Synthetic Minority Oversampling Technique (SMOTE) for handling class imbalance, Information Sciences, 505 (2019), 32-64, 2019.
• 43. Yilmaz E., Fetal State Assessment from Cardiotocogram Data Using Artificial Neural Networks, J. Med. Biol. Eng., 36, 820–832, 2016.
• 44. Kohavi, R., & Provost, F. (1998). Glossary of terms. Machine Learning, 30 (2–3), 271–274.
• 45. Ghasemkhani, B., Aktas, O., Birant D., Balanced K-Star: An Explainable Machine Learning Method for Internet-of-Things-Enabled Predictive Maintenance in Manufacturing, Machines, 11 (3), 322, 2023.
• 46. Iantovics L. Bl & Enăchescu C., Method for Data Quality Assessment of Synthetic Industrial Data, Sensors 2022, 22, 1608, 2022.
• 47. Harichandran A., Raphael B., Mukherjee A., Equipment activity recognition and early fault detection in automated construction through a hybrid machine learning framework, Computer‐Aided Civil and Infrastructure Engineering, 1-16, 2022.
• 48. Souza, P.V.C.; Lughofer, E. EFNC-Exp: An evolving fuzzy neural classifier integrating expert rules and uncertainty. Fuzzy Sets Syst., in press, 2022.