Araştırma Makalesi
BibTex RIS Kaynak Göster

Contactless Detection of Electrical Machine Bearing Faults: A Radar-Based Solution

Yıl 2025, Cilt: 8 Sayı: 5, 1328 - 1338, 15.09.2025
https://doi.org/10.34248/bsengineering.1673237

Öz

Bearing failures represent the most prevalent fault type in electrical machines, potentially leading to catastrophic consequences if not detected early. Conventional detection methods primarily rely on thermal, acoustic, and vibration sensors. Traditional vibration-based techniques have gained widespread adoption due to their stable and straightforward signal-processing capabilities. However, these approaches require direct motor mounting, introducing economic, temporal, and safety inefficiencies. This study presents the first investigation of contactless radar-based detection of bearing faults according to the authors' knowledge. The research employs the absolute value of complex signals derived from quadrature signals recorded by a 24 GHz radar transceiver as the vibration signal. Various defects like corrosion, improper oil levels, and scratches were deliberately introduced to the inner race, outer race, and balls of bearings, establishing 16 distinct fault classes. Classification performance was evaluated using both time-domain statistical features and frequency-domain PSD features. Multiple machine learning algorithms were applied to both approaches, consistently achieving accuracy rates exceeding 98%. This study validates the potential of radar-based systems for bearing fault diagnosis and introduces a novel paradigm for contactless bearing fault detection comprising radar signal data from 880 experiments. The results demonstrate that radar technology offers a promising alternative to traditional contact-requiring methods, enabling efficient and reliable bearing fault classification through non-invasive vibration detection.

Etik Beyan

Ethics committee approval was not required for this study because of there was no study on animals or humans.

Destekleyen Kurum

-none

Teşekkür

The authors gratefully acknowledge the ART company for their valuable contribution in supplying the bearing components and for their technical expertise in assembling the artificially aged bearing specimens essential for this research.

Kaynakça

  • Acar YE, Cetinkal SB. 2025. SU RF Sensing Lab. Bearing Fault Diagnosis Dataset. Kaggle. https://www.kaggle.com/datasets/yunusemreacar1/su-rf-sensing-lab-bearing-fault-diagnosis-dataset (accesed date, March 15, 2025).
  • Acar YE. 2024. Radar-enabled non-contact speed estimation for rotating electrical machinery. Measurement, 235: 114989.
  • Acar YE, Saritas I, Yaldiz E. 2021. An S-band zero-IF SFCW through-the-wall radar for range, respiration rate, and DOA estimation. Measurement, 186: 110221.
  • Akar M, Hekim M, Orhan U. 2015. Mechanical fault detection in permanent magnet synchronous motors using equal width discretization-based probability distribution and a neural network model. Turk J Electr Eng Comput Sci, 23: 813–823.
  • Gu C, Huang TY, Li C, Lin J. 2017. Microwave and millimeter-wave radars for vital sign monitoring. In: Amin MG, editor. Radar for Indoor Monitoring. CRC Press, Florida, USA, pp: 199–226.
  • Brito LC, Susto GA, Brito JN, Duarte MA. 2022. An explainable artificial intelligence approach for unsupervised fault detection and diagnosis in rotating machinery. Mech Syst Signal Process, 163: 108105.
  • Ercire M, Ünsal A. 2024. Asenkron motor eş zamanlı çoklu arızalarının titreşim sinyalleri ile çok etiketli sınıflandırılması. Duzce Univ J Sci Technol, 12: 1296–1314.
  • Ertarğın M, Yıldırım Ö, Orhan A. 2023. Motor yataklarında meydana gelen arızaları tespit etmek için yeni bir tek boyutlu konvolüsyonel sinir ağı modeli. Firat Univ J Eng Sci, 35: 669–678.
  • Glowacz A, Sulowicz M, Zielonka J, Li Z, Glowacz W, Kumar A. 2025. Acoustic fault diagnosis of three-phase induction motors using smartphone and deep learning. Expert Syst Appl, 262: 125633.
  • Kao IH, Wang WJ, Lai YH, Perng JW. 2018. Analysis of permanent magnet synchronous motor fault diagnosis based on learning. IEEE Trans Instrum Meas, 68: 310–324.
  • Karabacak YE, Özmen NG. 2022. Rulmanlarda titreşim verilerinden durum izleme ve arıza teşhisi için derin öğrenme yönteminin uygulanması. Konya J Eng Sci, 10: 346–365.
  • Kilic ME, Acar YE. 2024. Performance evaluation of the time-frequency transformation methods on electrical machinery fault detection. Bitlis Eren Univ J Sci, 13: 1147–1157.
  • Liu W, Chen W, Zhang Z. 2020. A novel fault diagnosis approach for rolling bearing based on high-order synchrosqueezing transform and detrended fluctuation analysis. IEEE Access, 8: 12533–12541.
  • Lopez-Perez D, Antonino-Daviu J. 2017. Application of infrared thermography to failure detection in industrial induction motors: Case stories. IEEE Trans Ind Appl, 53: 1901–1908.
  • Mehta A, Goyal D, Choudhary A, Pabla B, Belghith S. 2021. Machine learning-based fault diagnosis of self-aligning bearings for rotating machinery using infrared thermography. Math Probl Eng, 2021: 9947300.
  • Mueller PN, Woelfl L, Can S. 2023. Bridging the gap between AI and the industry—a study on bearing fault detection in PMSM-driven systems using CNN and inverter measurement. Eng Appl Artif Intell, 126: 106834.
  • Nayana B, Geethanjali P. 2017. Analysis of statistical time-domain features effectiveness in identification of bearing faults from vibration signal. IEEE Sens J, 17: 5618–5625.
  • Pacheco-Cherrez J, Fortoul-Diaz JA, Cortes Santacruz F, Aloso Valerdi LM, Ibarra Zarate DI. 2022. Bearing fault detection with vibration and acoustic signals: Comparison among different machine learning classification methods. Eng Fail Anal, 139: 106515.
  • Qiao M, Yan S, Tang X, Xu C. 2020. Deep convolutional and LSTM recurrent neural networks for rolling bearing fault diagnosis under strong noises and variable loads. IEEE Access, 8: 66257–66269.
  • Sabir R, Rosato D, Hartmann S, Gühmann C. 2019. LSTM based bearing fault diagnosis of electrical machines using motor current signal. In: Proceedings of 18th IEEE International Conference on Machine Learning and Applications, December 16–19, Boca Raton, USA, pp: 613–618.
  • Seflek I, Acar YE, Yaldiz E. 2020. Small motion detection and non-contact vital signs monitoring with continuous wave Doppler radars. Elektron Elektrotech, 26: 54–60.
  • Smith WA, Randall RB. 2015. Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study. Mech Syst Signal Process, 64: 100–131.
  • Zhang S, Zhang S, Wang B, Habetler TG. 2020. Deep learning algorithms for bearing fault diagnostics—A comprehensive review. IEEE Access, 8: 29857–29881.
  • Zhang Y, Xing K, Bai R, Sun D, Meng Z. 2020. An enhanced convolutional neural network for bearing fault diagnosis based on time–frequency image. Measurement, 157: 107667.
  • Zhu Z, Lei Y, Qi G, Chai Y, Mazur N, An Y, Huang X. 2023. A review of the application of deep learning in intelligent fault diagnosis of rotating machinery. Measurement, 206: 112346.

Contactless Detection of Electrical Machine Bearing Faults: A Radar-Based Solution

Yıl 2025, Cilt: 8 Sayı: 5, 1328 - 1338, 15.09.2025
https://doi.org/10.34248/bsengineering.1673237

Öz

Bearing failures represent the most prevalent fault type in electrical machines, potentially leading to catastrophic consequences if not detected early. Conventional detection methods primarily rely on thermal, acoustic, and vibration sensors. Traditional vibration-based techniques have gained widespread adoption due to their stable and straightforward signal-processing capabilities. However, these approaches require direct motor mounting, introducing economic, temporal, and safety inefficiencies. This study presents the first investigation of contactless radar-based detection of bearing faults according to the authors' knowledge. The research employs the absolute value of complex signals derived from quadrature signals recorded by a 24 GHz radar transceiver as the vibration signal. Various defects like corrosion, improper oil levels, and scratches were deliberately introduced to the inner race, outer race, and balls of bearings, establishing 16 distinct fault classes. Classification performance was evaluated using both time-domain statistical features and frequency-domain PSD features. Multiple machine learning algorithms were applied to both approaches, consistently achieving accuracy rates exceeding 98%. This study validates the potential of radar-based systems for bearing fault diagnosis and introduces a novel paradigm for contactless bearing fault detection comprising radar signal data from 880 experiments. The results demonstrate that radar technology offers a promising alternative to traditional contact-requiring methods, enabling efficient and reliable bearing fault classification through non-invasive vibration detection.

Etik Beyan

Ethics committee approval was not required for this study because of there was no study on animals or humans.

Teşekkür

The authors gratefully acknowledge the ART company for their valuable contribution in supplying the bearing components and for their technical expertise in assembling the artificially aged bearing specimens essential for this research.

Kaynakça

  • Acar YE, Cetinkal SB. 2025. SU RF Sensing Lab. Bearing Fault Diagnosis Dataset. Kaggle. https://www.kaggle.com/datasets/yunusemreacar1/su-rf-sensing-lab-bearing-fault-diagnosis-dataset (accesed date, March 15, 2025).
  • Acar YE. 2024. Radar-enabled non-contact speed estimation for rotating electrical machinery. Measurement, 235: 114989.
  • Acar YE, Saritas I, Yaldiz E. 2021. An S-band zero-IF SFCW through-the-wall radar for range, respiration rate, and DOA estimation. Measurement, 186: 110221.
  • Akar M, Hekim M, Orhan U. 2015. Mechanical fault detection in permanent magnet synchronous motors using equal width discretization-based probability distribution and a neural network model. Turk J Electr Eng Comput Sci, 23: 813–823.
  • Gu C, Huang TY, Li C, Lin J. 2017. Microwave and millimeter-wave radars for vital sign monitoring. In: Amin MG, editor. Radar for Indoor Monitoring. CRC Press, Florida, USA, pp: 199–226.
  • Brito LC, Susto GA, Brito JN, Duarte MA. 2022. An explainable artificial intelligence approach for unsupervised fault detection and diagnosis in rotating machinery. Mech Syst Signal Process, 163: 108105.
  • Ercire M, Ünsal A. 2024. Asenkron motor eş zamanlı çoklu arızalarının titreşim sinyalleri ile çok etiketli sınıflandırılması. Duzce Univ J Sci Technol, 12: 1296–1314.
  • Ertarğın M, Yıldırım Ö, Orhan A. 2023. Motor yataklarında meydana gelen arızaları tespit etmek için yeni bir tek boyutlu konvolüsyonel sinir ağı modeli. Firat Univ J Eng Sci, 35: 669–678.
  • Glowacz A, Sulowicz M, Zielonka J, Li Z, Glowacz W, Kumar A. 2025. Acoustic fault diagnosis of three-phase induction motors using smartphone and deep learning. Expert Syst Appl, 262: 125633.
  • Kao IH, Wang WJ, Lai YH, Perng JW. 2018. Analysis of permanent magnet synchronous motor fault diagnosis based on learning. IEEE Trans Instrum Meas, 68: 310–324.
  • Karabacak YE, Özmen NG. 2022. Rulmanlarda titreşim verilerinden durum izleme ve arıza teşhisi için derin öğrenme yönteminin uygulanması. Konya J Eng Sci, 10: 346–365.
  • Kilic ME, Acar YE. 2024. Performance evaluation of the time-frequency transformation methods on electrical machinery fault detection. Bitlis Eren Univ J Sci, 13: 1147–1157.
  • Liu W, Chen W, Zhang Z. 2020. A novel fault diagnosis approach for rolling bearing based on high-order synchrosqueezing transform and detrended fluctuation analysis. IEEE Access, 8: 12533–12541.
  • Lopez-Perez D, Antonino-Daviu J. 2017. Application of infrared thermography to failure detection in industrial induction motors: Case stories. IEEE Trans Ind Appl, 53: 1901–1908.
  • Mehta A, Goyal D, Choudhary A, Pabla B, Belghith S. 2021. Machine learning-based fault diagnosis of self-aligning bearings for rotating machinery using infrared thermography. Math Probl Eng, 2021: 9947300.
  • Mueller PN, Woelfl L, Can S. 2023. Bridging the gap between AI and the industry—a study on bearing fault detection in PMSM-driven systems using CNN and inverter measurement. Eng Appl Artif Intell, 126: 106834.
  • Nayana B, Geethanjali P. 2017. Analysis of statistical time-domain features effectiveness in identification of bearing faults from vibration signal. IEEE Sens J, 17: 5618–5625.
  • Pacheco-Cherrez J, Fortoul-Diaz JA, Cortes Santacruz F, Aloso Valerdi LM, Ibarra Zarate DI. 2022. Bearing fault detection with vibration and acoustic signals: Comparison among different machine learning classification methods. Eng Fail Anal, 139: 106515.
  • Qiao M, Yan S, Tang X, Xu C. 2020. Deep convolutional and LSTM recurrent neural networks for rolling bearing fault diagnosis under strong noises and variable loads. IEEE Access, 8: 66257–66269.
  • Sabir R, Rosato D, Hartmann S, Gühmann C. 2019. LSTM based bearing fault diagnosis of electrical machines using motor current signal. In: Proceedings of 18th IEEE International Conference on Machine Learning and Applications, December 16–19, Boca Raton, USA, pp: 613–618.
  • Seflek I, Acar YE, Yaldiz E. 2020. Small motion detection and non-contact vital signs monitoring with continuous wave Doppler radars. Elektron Elektrotech, 26: 54–60.
  • Smith WA, Randall RB. 2015. Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study. Mech Syst Signal Process, 64: 100–131.
  • Zhang S, Zhang S, Wang B, Habetler TG. 2020. Deep learning algorithms for bearing fault diagnostics—A comprehensive review. IEEE Access, 8: 29857–29881.
  • Zhang Y, Xing K, Bai R, Sun D, Meng Z. 2020. An enhanced convolutional neural network for bearing fault diagnosis based on time–frequency image. Measurement, 157: 107667.
  • Zhu Z, Lei Y, Qi G, Chai Y, Mazur N, An Y, Huang X. 2023. A review of the application of deep learning in intelligent fault diagnosis of rotating machinery. Measurement, 206: 112346.
Toplam 25 adet kaynakça vardır.

Ayrıntılar

Birincil Dil İngilizce
Konular Elektrik Makineleri ve Sürücüler, Mühendislik Elektromanyetiği, Sinyal İşleme
Bölüm Research Articles
Yazarlar

Yunus Emre Acar 0000-0002-6809-9006

Salih Bilal Çetinkal 0000-0001-6212-7670

Erken Görünüm Tarihi 9 Temmuz 2025
Yayımlanma Tarihi 15 Eylül 2025
Gönderilme Tarihi 10 Nisan 2025
Kabul Tarihi 17 Haziran 2025
Yayımlandığı Sayı Yıl 2025 Cilt: 8 Sayı: 5

Kaynak Göster

APA Acar, Y. E., & Çetinkal, S. B. (2025). Contactless Detection of Electrical Machine Bearing Faults: A Radar-Based Solution. Black Sea Journal of Engineering and Science, 8(5), 1328-1338. https://doi.org/10.34248/bsengineering.1673237
AMA Acar YE, Çetinkal SB. Contactless Detection of Electrical Machine Bearing Faults: A Radar-Based Solution. BSJ Eng. Sci. Eylül 2025;8(5):1328-1338. doi:10.34248/bsengineering.1673237
Chicago Acar, Yunus Emre, ve Salih Bilal Çetinkal. “Contactless Detection of Electrical Machine Bearing Faults: A Radar-Based Solution”. Black Sea Journal of Engineering and Science 8, sy. 5 (Eylül 2025): 1328-38. https://doi.org/10.34248/bsengineering.1673237.
EndNote Acar YE, Çetinkal SB (01 Eylül 2025) Contactless Detection of Electrical Machine Bearing Faults: A Radar-Based Solution. Black Sea Journal of Engineering and Science 8 5 1328–1338.
IEEE Y. E. Acar ve S. B. Çetinkal, “Contactless Detection of Electrical Machine Bearing Faults: A Radar-Based Solution”, BSJ Eng. Sci., c. 8, sy. 5, ss. 1328–1338, 2025, doi: 10.34248/bsengineering.1673237.
ISNAD Acar, Yunus Emre - Çetinkal, Salih Bilal. “Contactless Detection of Electrical Machine Bearing Faults: A Radar-Based Solution”. Black Sea Journal of Engineering and Science 8/5 (Eylül2025), 1328-1338. https://doi.org/10.34248/bsengineering.1673237.
JAMA Acar YE, Çetinkal SB. Contactless Detection of Electrical Machine Bearing Faults: A Radar-Based Solution. BSJ Eng. Sci. 2025;8:1328–1338.
MLA Acar, Yunus Emre ve Salih Bilal Çetinkal. “Contactless Detection of Electrical Machine Bearing Faults: A Radar-Based Solution”. Black Sea Journal of Engineering and Science, c. 8, sy. 5, 2025, ss. 1328-3, doi:10.34248/bsengineering.1673237.
Vancouver Acar YE, Çetinkal SB. Contactless Detection of Electrical Machine Bearing Faults: A Radar-Based Solution. BSJ Eng. Sci. 2025;8(5):1328-3.

                           24890