Kırık Rotor Çubuğu Sayısının Ampirik Mod Ayrışımı ve Makine Öğrenmesi Yaklaşımları İle Belirlenmesi

Öz

Endüstriyel sürücü sistemlerinde verimlilikleri, sağlamlıkları, güç ve boyut çeşitlilikleri nedeniyle asenkron motorlar sıklıkla kullanılmaktadırlar. Asenkron motorlarda meydana gelen kırık rotor çubuğu arızaları, sistemin verimliliğini doğrudan etkilediğinden arıza teşhisi gittikçe önem kazanmaktadır. Kırık rotor çubuğu arızalarının teşhisi için hem stator akım sinyali hem de motor titreşim sinyali kullanılmaktadır. Son zamanlarda bu konuda yapılan çalışmalarda bazı sinyal işlemle teknikleri ile birlikte makine öğrenmesi yöntemleri kullanılmaktadır. Bu çalışmada, ampirik mod ayrışımı (AMA) ve makine öğrenmesi yöntemleri kullanılarak kırık rotor çubuğu sayısının sınıflandırılması gerçekleştirilmiştir. İlk olarak arızalı motor veri setinden alınan bir faz akımı ve motor titreşim sinyali filtrelenip zarflanmıştır. İkinci adımda bu sinyaller AMA yöntemiyle 5 adet içsel mod fonksiyonuna (İMF) ayrıştırılıp spektral entropi ve anlık frekans öznitelikleri elde edilmiştir. Üçüncü adımda bu öznitelikler uç uca eklenip yeni öznitelik vektörü oluşturulmuştur. Dördüncü adımda, öznitelik vektörleri destek vektör makinesi (DVM), k en yakın komşu (KEK) ve karar ağacı (KA) makine öğrenmesi yöntemleriyle sınıflandırılmıştır. Başarı parametresi olarak sınıflandırma doğruluğu kullanılmış ve en yüksek başarı %93,9 ile DVM sınıflandırma yönteminden elde edilmiştir. Çalışmanın sonunda literatürde aynı veri seti için yapılan çalışmalar ile performans karşılaştırılması yapılmış ve bunların sonucunda kırık rotor çubuğu sayısının sınıflandırılmasının AMA ve DVM ile yapılabileceği görülmüştür.

Anahtar Kelimeler

• Ampirik mod ayrışımı
• Asenkron motor
• Kırık rotor çubuğu
• Makine öğrenmesi

Determination of The Number of Broken Rotor Bars by Empirical Mode Decomposition and Machine Learning Approaches

Öz

Induction motors are frequently used in the industrial drive systems due to their efficiency, robustness, power and size diversity. Diagnosis is becoming increasingly important as broken rotor bar failures in induction motors directly affect the efficiency of the system. Both the stator current signal and the motor vibration signal are used to diagnose broken rotor bar faults. In recent studies on this subject, machine-learning methods are used together with some signal processing techniques. In this study, determination of the number of broken rotor bars was performed using empirical mode decomposition (EMD) and machine learning methods. Firstly, a phase current and vibration signal taken from the faulty motor data set are filtered and enveloped. In the second step, these signals were decomposed into five intrinsic mode functions (IMF) using by the EMD method, and their spectral entropy and instantaneous frequency features were obtained. In the third step, these features are added end-to-end and a new feature vector is created. In the last step, feature vectors are classified by support vector machine (SVM), k nearest neighbor (KNN) and decision tree (DT) machine learning methods. Classification accuracy was used as the success parameter and the highest success in classification was obtained with SVM, with a classification accuracy of 93.9%. Final of the study, performance comparisons were made with the studies conducted for the same data set in the literature. As a result, it has been seen that the classification of the number of broken rotor bars can be done successfully with EMD and SVM.

Anahtar Kelimeler

• Broken rotor bar
• Induction motor
• Empirical mode decomposition
• Instantaneous frequency
• Machine learning

Kaynakça

1. Garcia M, Antonino-Daviu J. Efficiency assessment of induction motors operating under different fault conditions. Proceedings of the IEEE International Conference on Industrial Technology, 2018-Şubat, 1837–42.
2. Halder S, Bhat S, Zychma D, Sowa P. Broken Rotor Bar Fault Diagnosis Techniques Based on Motor Current Signature Analysis for Induction Motor—A Review. Energies, 2022, 15, 1–20.
3. Mohammed A, Melecio JI, Djurovic S. Stator winding fault thermal signature monitoring and analysis by in Situ FBG sensors. IEEE Transactions on Industrial Electronics, 2019, 66, 8082–92.
4. Shao S, Yan R, Lu Y, Wang P, Gao RX. DCNN-Based multi-signal induction motor fault diagnosis. IEEE Transactions on Instrumentation and Measurement, IEEE. 2020, 69, 2658–69.
5. Sbaa S, Bessous N, Pusca R, Romary R. A comparative study dedicated to rotor failure detection in induction motors using MCSA, DWT, and EMD techniques. 2020 International Conference on Electrical Engineering, ICEE 2020,.
6. Ágoston K. Fault Detection of the Electrical Motors Based on Vibration Analysis. Procedia Technology, 2015, 19, 547–53.
7. Fourati A, Feki N, Bourdon A, Rémond D, Chaari F, Haddar M. Electrical modeling for faults detection based on motor current signal analysis and angular approach. Applied Condition Monitoring, 2016, p. 15–25.
8. Reddy MSP, Reddy DM, Devendiran S, Mathew AT. Bearing Fault Diagnosis Using Empirical Mode Decomposition, Entropy Based Features and Data Mining Techniques. Materials Today: Proceedings, Elsevier Ltd. 2018, 5, 11460–75.

9. Faiz J, Ghorbanian V, Ebrahimi BM. EMD-Based analysis of industrial induction motors with broken rotor bars for identification of operating point at different supply modes. IEEE Transactions on Industrial Informatics, IEEE. 2014, 10, 957–66.
10. Valles-Novo R, De Jesus Rangel-Magdaleno J, Ramirez-Cortes JM, Peregrina-Barreto H, Morales-Caporal R. Empirical mode decomposition analysis for broken-bar detection on squirrel cage induction motors. IEEE Transactions on Instrumentation and Measurement, IEEE. 2015, 64, 1118–28.
11. Huang NE, Shen, Z, Long SR, Wu MC, Snin HH, Zheng Q. The empirical mode decomposition and the Hubert spectrum for nonlinear and non-stationary time series analysis. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 1998, 454, 903–95.
12. Deniz E, Sobahi N, Omar N, Sengur A, Acharya UR. Automated robust human emotion classification system using hybrid EEG features with ICBrainDB dataset. Health Information Science and Systems, 2022, 10.
13. Demir F, Sengur A, Ari A, Siddique K, Alswaitti M. Feature Mapping and Deep Long Short Term Memory Network-Based Efficient Approach for Parkinson’s Disease Diagnosis. IEEE Access, IEEE. 2021, 9, 149456–64.
14. Aslan M, Akbulut Y, Şengür A, İnce MC. Skeleton based efficient fall detection. Journal of the Faculty of Engineering and Architecture of Gazi University, 2017, 32, 1025–34.
15. Ucar, F., Alcin, O.F., Dandil, B. and Ata, F. Machine learning based power quality event classification using wavelet - Entropy and basic statistical features. 2016 21st International Conference on Methods and Models in Automation and Robotics, MMAR 2016, 414–9.
16. Dişli, F., Gedikpınar, M. ve Şengür, A. Deep Transfer Learning-Based Broken Rotor Fault Diagnosis For Induction Motors Asenkron Motor Kırık Rotor Çubuğu Arızasının Derin Transfer Öğrenme Tabanlı Teşhisi. Turkish Journal of Science & Technology, 2023, 18, 275–90.
17. Şengür, D. Investigation of the relationships of the students ’ academic level and gender with Covid-19 based anxiety and protective behaviors : A data mining approach. Turkish Journal of Science & Technology, 2020, 15, 93–9.
18. Samantaray SR, Kamwa I, Joos G. Decision tree based fault detection and classification in distance relaying. Engineering Intelligent Systems, 2011, 19, 139–47.
19. Kilincer IF, Ertam F, Sengur A. Machine learning methods for cyber security intrusion detection: Datasets and comparative study. Computer Networks, Elsevier B.V. 2021, 188, 107840.
20. Şengür D, Turhan M. Prediction Of The Action Identification Levels Of Teachers Based On Organizational Commitment And Job Satisfaction By Using K-Nearest Neighbors Method. Fırat University Turkish Journal of Science and Technology, 2018, 13, 61–8.
21. Aline ET, Rogério AF, Marcelo S, Narco ARM. Experimental database for detecting and diagnosing rotor broken bar in a three-phase induction motor, IEEE Dataport 2020. https://doi.org/https://dx.doi.org/10.21227/fmnm-bn95
22. Chauhan DS, Dubey J. Envelope Spectrum Analysis for Rolling Element Bearing Faults Diagnosis by Using Kurtogram and Spectral Kurtosis for Band Selection. International Journal of Scientific Research and Engineering Development, 2021, 4, 794–801.
23. Amazon Machine Learning: Developer Guide. https://docs.aws.amazon.com/machine-learning/latest/dg/multiclass-model-insights.html
24. Powers, D.M.W. Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation, 2020.
25. Gonzalez-Ramirez A, Lopez J, ToreesRoman D, Yanez-Vargas I. Analysis Analysis of multi-class classification performance metrics for remote sensing imagery imbalanced datasets. Journal of Quantitative and Statistical Analysis, 2021, 8, 11–7.
26. Matworks. https://www.mathworks.com/help/predmaint/ug/broken-rotor-fault-detection-in-ac-induction-motors-using-vibration-and-electrical-signals.html.
27. Misra S, Kumar S, Sayyad S, Bongale A, Jadhav P, Kotecha K. Fault Detection in Induction Motor Using Time Domain and Spectral Imaging-Based Transfer Learning Approach on Vibration Data. Sensors, 2022, 22, 1–17.