Araştırma Makalesi
BibTex RIS Kaynak Göster

Dalgacık Dönüşümü Tabanlı Özellikler Kullanarak Fırçasız DC Motor Seslerinin Makine Öğrenmesi Yöntemleri ile Analizi

Yıl 2025, Cilt: 4 Sayı: 2, 363 - 374, 26.06.2025
https://doi.org/10.62520/fujece.1632384

Öz

Fırçasız DA (BLDC) motorlar, yüksek verimlilikleri, güvenilirlikleri ve düşük bakım gereksinimleri nedeniyle çeşitli uygulamalarda yaygın olarak kullanılmaktadır. Bu motorlar, mekanik fırçaların bulunmaması nedeniyle daha az aşınma ve düşük bakım gereksinimi sağlar. Bu özellikleri, özellikle endüstriyel otomasyon, elektrikli araçlar, robotik sistemler gibi birçok alanda tercih edilmelerini sağlar. Makine öğrenimi (MÖ) ile BLDC motorlarının entegrasyonu, bu motorların verimliliğini, güvenilirliğini ve performansını önemli ölçüde artırabilir.
ML algoritmaları, motorun performans verilerini analiz ederek arızaların önceden tespit edilmesine yardımcı olabilir. Motorun normal çalışma koşullarından sapmalarını izleyen ML algoritmaları, arızalı durumları hızlı bir şekilde tanımlayabilir. Makine öğrenimi, motorun çalışma koşullarına bağlı olarak en verimli çalışma noktalarını öğrenebilir ve buna göre motorun hızını veya diğer parametrelerini dinamik olarak optimize edebilir. Bu çalışmada ses analizi ile BLDC motorlarındaki mekanik arızaların tespit edilmesini sağlayan bir yöntem önerilmektedir. Ses analizi ile normal ve arızalı motorların ses kayıtlarından Ayrık Dalgacık Dönüşümü (ADD) tabanlı özellikler çıkarılmış ve elde edilen özellikler makine öğrenimi yöntemleriyle sınıflandırılmıştır. Burada, ADD ile veri boyutu azaltılmıştır, istenmeyen ve önemsiz katsayılar baskılanmıştır. Elde edilen yeni verilerle aşırı uyumdan kaçınacak Bagging trees kullanılmıştır. Bagging, birden fazla karar ağacını birleştirerek her ağacın aşırı uyum sağlama eğilimini dengelemeye çalışır ve modelin genelleme kapasitesi artar. Ayrıca, her model bağımsız olarak eğitildiği için paralel hesaplamaya imkân sağlar. Elde edilen model ile %89.205 doğruluk, 0.821 kappa değeri elde edilmiştir.

Etik Beyan

Çalışma araştırma; yayın etiğine uygundur.

Kaynakça

  • T. G. Wilson and P. H. Trickey, “D.C. Machine. With Solid State Commutation,” AIEE Paper, no. CP62-1372, Oct. 7, 1962.
  • Y. Xu, H. B. Pan, S. Z. He, and L. Li, “Monolithic H-bridge brushless DC vibration motor driver with a highly sensitive Hall sensor in 0.18 μm complementary metal-oxides semiconductor technology,” IET Circuits, Devices & Systems, vol. 7, no. 4, pp. 204–210, 2013.
  • Y. Yaşa, “An Efficient Brushless DC Motor Design for Unmanned Aerial Vehicles,” Eur. J. Sci. Technol., vol. 35, pp. 288–294, 2022.
  • B. Kaynak and A. Y. Arabul, "Sizing, Design and Analysis of Fixed Wing Unmanned Aerial Vehicle’s Wing," in 6th Int. Mardin Artuklu Sci. Res. Conf., Mardin, Türkiye, pp. 74–81, Jun. 25–27, 2021.
  • M. R. Minaz, “Fırçasız DC Motorunun Eksen Kaçıklığı ve Kırık Mıknatıs Arızalarının Tespitinin Bilgisayar Benzetimi ile Yapılması,” BEU J. Sci., vol. 9, no. 2, pp. 846–861, 2020.
  • F. Cira, M. Arkan, and B. Gümüş, “Detection of stator winding inter-turn short circuit faults in permanent magnet synchronous motors and automatic classification of fault severity via a pattern recognition system,” J. Electr. Eng. Technol., vol. 11, no. 2, pp. 416–424, 2016.
  • F. Cira, “Sürekli Mıknatıslı Senkron Motorun Stator Kısa Devre Arızasının Tespiti ve Arıza Şiddetinin Otomatik Olarak Belirlenmesi,” Ph.D. dissertation, İnönü Univ., Inst. Sci., Malatya, 2017.
  • Ö. Alaca, R. Selbaş, and M. Türkkalesi, “Fırçasız Motor Sürücülerin Enerji Verimliliği,” Int. J. Sustain. Eng. Technol., vol. 6, no. 1, pp. 1–9, 2022.
  • B. Er, B. Demirsoya, and A. Fenercioğlu, “Analysis of the Effect of Switching Frequency on Acoustic Noise in External Rotor Brushless DC Motors,” Balkan J. Electr. Comput. Eng., vol. 12, no. 1, 2024.
  • R. Kavin et al., “Fault Detection and Monitoring of BLDC Motor Using ANN,” in Proc. 2023 Int. Conf. Netw. Commun. (ICNWC), Chennai, India, pp. 1–5, 2023.
  • W. Abed, S. Sharma, and R. Sutton, “Fault diagnosis of brushless DC motor for an aircraft actuator using a neural wavelet network,” IET Conf. Proc., pp. 05–05, 2013.
  • W. Abed et al., “A Robust Bearing Fault Detection and Diagnosis Technique for Brushless DC Motors Under Non-stationary Operating Conditions,” J. Control Autom. Electr. Syst., vol. 26, pp. 241–254, 2015.
  • K. Kudelina et al., “Bearing Fault Analysis of BLDC Motor for Electric Scooter Application,” Designs, vol. 4, no. 4, Art. no. 42, 2020.
  • M. Khan et al., “Securing Electric Vehicle Performance: Machine Learning-Driven Fault Detection and Classification,” IEEE Access, vol. 12, pp. 71566–71584, 2024.
  • K. Sarman, T. Madhu, and M. Prasad, “Fault Diagnosis in the Brushless Direct Current Drive Using Hybrid Machine Learning Models,” ECTI Trans. Electr. Eng., Electron. Commun., 2022.
  • F. C. Veras et al., "Eccentricity Failure Detection of Brushless DC Motors From Sound Signals Based on Density of Maxima," IEEE Access, vol. 7, pp. 150318–150326, 2019.
  • R. Prieto, D. Montenegro, and C. Rengifo, “Machine hearing for predictive maintenance of BLDC motors,” J. Qual. Maint. Eng., 2024.
  • R. Sree, S. Jayanthy, and E. Vigneshwaran, “Estimation of Remaining Useful Life (RUL) of BLDC Motor using Machine Learning Approaches,” in Proc. 2022 7th Int. Conf. Commun. Electron. Syst. (ICCES), pp. 286–291, 2022.
  • P. Estacio and R. Stiward, “Brushless DC Motor sound dataset for PdM,” Mendeley Data, vol. 1, 2023.
  • S. Santoso, E. J. Powers, W. M. Grady, and P. Hofman, “Power Quality assessment via wavelet transform analysis,” IEEE Energy Oper. Energy Convers. Manag., vol. 52, no. 4, pp. 1959–1967, 1996.
  • M. Uyar, S. Yıldırım, and M. T. Gençoğlu, “Güç Kalitesindeki Bozulma Türlerinin Sınıflandırılması için bir örüntü tanıma yaklaşımı,” Gazi Univ. J. Sci. Eng., vol. 26, no. 1, pp. 14–56, 2011.
  • M. A. S. K. and M. A. K. Rahman, “Development and Implementation of a Novel Fault Diagnostic and Protection Technique for IPM Motor Drives,” IEEE Trans. Ind. Electron., vol. 56, no. 1, pp. 85–92, 2009.
  • S. Bayhan and D. Yılmaz, “Güç Sistemlerinde meydana gelen dalga şekli bozukluklarının dalgacık dönüşümü yardımıyla tespiti,” Technol. Appl. Sci., vol. 4, no. 2, pp. 151–162, 2009.
  • I. Daubechies, “The wavelet transform time frequency localization and signal analysis,” IEEE Trans. Inf. Theory, vol. 36, no. 5, pp. 961–1005, 1990.
  • J. Lever, M. Krzywinski, and N. Altman, “Points of Significance: Logistic regression,” Nat. Methods, vol. 13, pp. 541–542, 2016.
  • M. Schonlau and R. Zou, “The random forest algorithm for statistical learning,” Stata J., vol. 20, no. 29, Art. no. 3, 2020.
  • R. Hu, X. Zhu, Y. Zhu, and J. Gan, “Robust SVM with adaptive graph learning,” World Wide Web, vol. 23, pp. 1945–1968, 2019.
  • G. Singh, Y. Pal, and A. Dahiya, “Classification of Power Quality Disturbances using Linear Discriminant Analysis,” Appl. Soft Comput., vol. 138, Art. no. 110181, 2023.
  • G. Ngo, R. Beard, and R. Chandra, “Evolutionary bagging for ensemble learning,” Neurocomputing, vol. 510, pp. 1–14, 2022.
  • O. Yıldız, O. Irsoy, and E. Alpaydın, “Bagging Soft Decision Trees,” pp. 25–36, 2016.

Analysis of Brushless DC Motor Sounds with Machine Learning Methods Using Wavelet Transform Based Features

Yıl 2025, Cilt: 4 Sayı: 2, 363 - 374, 26.06.2025
https://doi.org/10.62520/fujece.1632384

Öz

Brushless DC (BLDC) motors are widely used in various applications due to their high efficiency, reliability and low maintenance requirements. The absence of mechanical brushes reduces wear and minimizes maintenance. These features make them preferred in many areas, especially industrial automation, electric vehicles, and robotic systems. Integration of a BLDC motors with machine learning (ML) can significantly increase the efficiency, reliability and performance of these motors. ML algorithms can help detect faults in advance by analyzing the performance data of the motor. ML algorithms, which monitor deviations from the normal operating conditions of the motor, can quickly identify faulty situations. ML can learn the most efficient operating points depending on the operating conditions of the motor and dynamically optimize the speed or other parameters of the motor accordingly. In this study, a method is proposed that enables the detection of mechanical faults in a BLDC motors with sound analysis. With sound analysis, Discrete Wavelet Transform (DWT) based features were extracted from the sound recordings of normal and faulty motors and the obtained features were classified with machine learning methods. Here, the data size is reduced with DWT, unwanted and unimportant coefficients are suppressed. Bagging trees are used to avoid overfitting with extracted statistical features. Bagging tries to balance the overfitting tendency of each tree by combining multiple decision trees and the generalization capacity of the model increases. In addition, since each model is trained independently, it allows parallel calculation. With the obtained model, 89.205% accuracy and 0.821 kappa value were obtained.

Etik Beyan

The study is complied with research and publication ethics.

Kaynakça

  • T. G. Wilson and P. H. Trickey, “D.C. Machine. With Solid State Commutation,” AIEE Paper, no. CP62-1372, Oct. 7, 1962.
  • Y. Xu, H. B. Pan, S. Z. He, and L. Li, “Monolithic H-bridge brushless DC vibration motor driver with a highly sensitive Hall sensor in 0.18 μm complementary metal-oxides semiconductor technology,” IET Circuits, Devices & Systems, vol. 7, no. 4, pp. 204–210, 2013.
  • Y. Yaşa, “An Efficient Brushless DC Motor Design for Unmanned Aerial Vehicles,” Eur. J. Sci. Technol., vol. 35, pp. 288–294, 2022.
  • B. Kaynak and A. Y. Arabul, "Sizing, Design and Analysis of Fixed Wing Unmanned Aerial Vehicle’s Wing," in 6th Int. Mardin Artuklu Sci. Res. Conf., Mardin, Türkiye, pp. 74–81, Jun. 25–27, 2021.
  • M. R. Minaz, “Fırçasız DC Motorunun Eksen Kaçıklığı ve Kırık Mıknatıs Arızalarının Tespitinin Bilgisayar Benzetimi ile Yapılması,” BEU J. Sci., vol. 9, no. 2, pp. 846–861, 2020.
  • F. Cira, M. Arkan, and B. Gümüş, “Detection of stator winding inter-turn short circuit faults in permanent magnet synchronous motors and automatic classification of fault severity via a pattern recognition system,” J. Electr. Eng. Technol., vol. 11, no. 2, pp. 416–424, 2016.
  • F. Cira, “Sürekli Mıknatıslı Senkron Motorun Stator Kısa Devre Arızasının Tespiti ve Arıza Şiddetinin Otomatik Olarak Belirlenmesi,” Ph.D. dissertation, İnönü Univ., Inst. Sci., Malatya, 2017.
  • Ö. Alaca, R. Selbaş, and M. Türkkalesi, “Fırçasız Motor Sürücülerin Enerji Verimliliği,” Int. J. Sustain. Eng. Technol., vol. 6, no. 1, pp. 1–9, 2022.
  • B. Er, B. Demirsoya, and A. Fenercioğlu, “Analysis of the Effect of Switching Frequency on Acoustic Noise in External Rotor Brushless DC Motors,” Balkan J. Electr. Comput. Eng., vol. 12, no. 1, 2024.
  • R. Kavin et al., “Fault Detection and Monitoring of BLDC Motor Using ANN,” in Proc. 2023 Int. Conf. Netw. Commun. (ICNWC), Chennai, India, pp. 1–5, 2023.
  • W. Abed, S. Sharma, and R. Sutton, “Fault diagnosis of brushless DC motor for an aircraft actuator using a neural wavelet network,” IET Conf. Proc., pp. 05–05, 2013.
  • W. Abed et al., “A Robust Bearing Fault Detection and Diagnosis Technique for Brushless DC Motors Under Non-stationary Operating Conditions,” J. Control Autom. Electr. Syst., vol. 26, pp. 241–254, 2015.
  • K. Kudelina et al., “Bearing Fault Analysis of BLDC Motor for Electric Scooter Application,” Designs, vol. 4, no. 4, Art. no. 42, 2020.
  • M. Khan et al., “Securing Electric Vehicle Performance: Machine Learning-Driven Fault Detection and Classification,” IEEE Access, vol. 12, pp. 71566–71584, 2024.
  • K. Sarman, T. Madhu, and M. Prasad, “Fault Diagnosis in the Brushless Direct Current Drive Using Hybrid Machine Learning Models,” ECTI Trans. Electr. Eng., Electron. Commun., 2022.
  • F. C. Veras et al., "Eccentricity Failure Detection of Brushless DC Motors From Sound Signals Based on Density of Maxima," IEEE Access, vol. 7, pp. 150318–150326, 2019.
  • R. Prieto, D. Montenegro, and C. Rengifo, “Machine hearing for predictive maintenance of BLDC motors,” J. Qual. Maint. Eng., 2024.
  • R. Sree, S. Jayanthy, and E. Vigneshwaran, “Estimation of Remaining Useful Life (RUL) of BLDC Motor using Machine Learning Approaches,” in Proc. 2022 7th Int. Conf. Commun. Electron. Syst. (ICCES), pp. 286–291, 2022.
  • P. Estacio and R. Stiward, “Brushless DC Motor sound dataset for PdM,” Mendeley Data, vol. 1, 2023.
  • S. Santoso, E. J. Powers, W. M. Grady, and P. Hofman, “Power Quality assessment via wavelet transform analysis,” IEEE Energy Oper. Energy Convers. Manag., vol. 52, no. 4, pp. 1959–1967, 1996.
  • M. Uyar, S. Yıldırım, and M. T. Gençoğlu, “Güç Kalitesindeki Bozulma Türlerinin Sınıflandırılması için bir örüntü tanıma yaklaşımı,” Gazi Univ. J. Sci. Eng., vol. 26, no. 1, pp. 14–56, 2011.
  • M. A. S. K. and M. A. K. Rahman, “Development and Implementation of a Novel Fault Diagnostic and Protection Technique for IPM Motor Drives,” IEEE Trans. Ind. Electron., vol. 56, no. 1, pp. 85–92, 2009.
  • S. Bayhan and D. Yılmaz, “Güç Sistemlerinde meydana gelen dalga şekli bozukluklarının dalgacık dönüşümü yardımıyla tespiti,” Technol. Appl. Sci., vol. 4, no. 2, pp. 151–162, 2009.
  • I. Daubechies, “The wavelet transform time frequency localization and signal analysis,” IEEE Trans. Inf. Theory, vol. 36, no. 5, pp. 961–1005, 1990.
  • J. Lever, M. Krzywinski, and N. Altman, “Points of Significance: Logistic regression,” Nat. Methods, vol. 13, pp. 541–542, 2016.
  • M. Schonlau and R. Zou, “The random forest algorithm for statistical learning,” Stata J., vol. 20, no. 29, Art. no. 3, 2020.
  • R. Hu, X. Zhu, Y. Zhu, and J. Gan, “Robust SVM with adaptive graph learning,” World Wide Web, vol. 23, pp. 1945–1968, 2019.
  • G. Singh, Y. Pal, and A. Dahiya, “Classification of Power Quality Disturbances using Linear Discriminant Analysis,” Appl. Soft Comput., vol. 138, Art. no. 110181, 2023.
  • G. Ngo, R. Beard, and R. Chandra, “Evolutionary bagging for ensemble learning,” Neurocomputing, vol. 510, pp. 1–14, 2022.
  • O. Yıldız, O. Irsoy, and E. Alpaydın, “Bagging Soft Decision Trees,” pp. 25–36, 2016.
Toplam 30 adet kaynakça vardır.

Ayrıntılar

Birincil Dil İngilizce
Konular Devreler ve Sistemler
Bölüm Araştırma Makalesi
Yazarlar

Bilal Tekin 0000-0002-5166-1082

Turgay Kaya 0000-0002-7732-6194

Yayımlanma Tarihi 26 Haziran 2025
Gönderilme Tarihi 3 Şubat 2025
Kabul Tarihi 6 Nisan 2025
Yayımlandığı Sayı Yıl 2025 Cilt: 4 Sayı: 2

Kaynak Göster

APA Tekin, B., & Kaya, T. (2025). Analysis of Brushless DC Motor Sounds with Machine Learning Methods Using Wavelet Transform Based Features. Firat University Journal of Experimental and Computational Engineering, 4(2), 363-374. https://doi.org/10.62520/fujece.1632384
AMA Tekin B, Kaya T. Analysis of Brushless DC Motor Sounds with Machine Learning Methods Using Wavelet Transform Based Features. FUJECE. Haziran 2025;4(2):363-374. doi:10.62520/fujece.1632384
Chicago Tekin, Bilal, ve Turgay Kaya. “Analysis of Brushless DC Motor Sounds With Machine Learning Methods Using Wavelet Transform Based Features”. Firat University Journal of Experimental and Computational Engineering 4, sy. 2 (Haziran 2025): 363-74. https://doi.org/10.62520/fujece.1632384.
EndNote Tekin B, Kaya T (01 Haziran 2025) Analysis of Brushless DC Motor Sounds with Machine Learning Methods Using Wavelet Transform Based Features. Firat University Journal of Experimental and Computational Engineering 4 2 363–374.
IEEE B. Tekin ve T. Kaya, “Analysis of Brushless DC Motor Sounds with Machine Learning Methods Using Wavelet Transform Based Features”, FUJECE, c. 4, sy. 2, ss. 363–374, 2025, doi: 10.62520/fujece.1632384.
ISNAD Tekin, Bilal - Kaya, Turgay. “Analysis of Brushless DC Motor Sounds With Machine Learning Methods Using Wavelet Transform Based Features”. Firat University Journal of Experimental and Computational Engineering 4/2 (Haziran 2025), 363-374. https://doi.org/10.62520/fujece.1632384.
JAMA Tekin B, Kaya T. Analysis of Brushless DC Motor Sounds with Machine Learning Methods Using Wavelet Transform Based Features. FUJECE. 2025;4:363–374.
MLA Tekin, Bilal ve Turgay Kaya. “Analysis of Brushless DC Motor Sounds With Machine Learning Methods Using Wavelet Transform Based Features”. Firat University Journal of Experimental and Computational Engineering, c. 4, sy. 2, 2025, ss. 363-74, doi:10.62520/fujece.1632384.
Vancouver Tekin B, Kaya T. Analysis of Brushless DC Motor Sounds with Machine Learning Methods Using Wavelet Transform Based Features. FUJECE. 2025;4(2):363-74.