IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v17y2024i2p368-d1317456.html
   My bibliography  Save this article

Classifying the Percentage of Broken Magnets in Permanent Magnet Synchronous Motors Using Combined Short-Time Fourier Transform and a Pre-Trained Convolutional Neural Network

Author

Listed:
  • Amin Ghafouri Matanagh

    (Department of Electrical Engineering, Istanbul Technical University, Istanbul 34469, Türkiye)

  • Salih Baris Ozturk

    (Department of Electrical Engineering, Istanbul Technical University, Istanbul 34469, Türkiye)

  • Taner Goktas

    (Department of Electrical and Electronics Engineering, Dokuz Eylul University, Izmir 35160, Türkiye)

  • Omar Hegazy

    (MOBI Research Group, ETEC Department, Vrije Universiteit Brussel (VUB), 1050 Brussels, Belgium
    MOBI Core-Lab, Flanders Make, 3001 Heverlee, Belgium)

Abstract

In critical applications of electrical machines, ensuring validity and safety is paramount to prevent system failures with potentially hazardous consequences. The integration of machine learning (ML) technologies plays a crucial role in monitoring system performance and averting failures. Among various motor types, permanent magnet synchronous motors (PMSMs) are widely favored for their versatile speed range, enhanced power density, and ease of control, finding applications in both industrial settings and electric vehicles. This study focuses on the detection and classification of the percentage of broken magnets in PMSMs using a pre-trained AlexNet convolutional neural network (CNN) model. The dataset was generated by combining finite element methods (FEMs) and short-time Fourier transform (STFT) applied to stator phase currents, which exhibited significant variations due to diverse broken magnet structures. Leveraging transfer learning, the pre-trained AlexNet model underwent adjustments, including the elimination and rearrangement of the final three layers and the introduction of new layers tailored for electrical machine applications. The resulting pre-trained CNN model achieved a remarkable performance, boasting a 99.94% training accuracy and 0.0004% training loss in the simulation dataset, utilizing a PMSM with 4% magnet damage for experimental validation. The model’s effectiveness was further affirmed by an impressive 99.95% area under the receiver operating characteristic (ROC) curve in the experimental dataset. These results underscore the efficacy and robustness of the proposed pre-trained CNN method in detecting and classifying the percentage of broken magnets, even with a limited dataset.

Suggested Citation

  • Amin Ghafouri Matanagh & Salih Baris Ozturk & Taner Goktas & Omar Hegazy, 2024. "Classifying the Percentage of Broken Magnets in Permanent Magnet Synchronous Motors Using Combined Short-Time Fourier Transform and a Pre-Trained Convolutional Neural Network," Energies, MDPI, vol. 17(2), pages 1-17, January.
    • Handle: RePEc:gam:jeners:v:17:y:2024:i:2:p:368-:d:1317456
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/17/2/368/pdf
    Download Restriction: no
    File URL: https://www.mdpi.com/1996-1073/17/2/368/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Paul Waide & Conrad U. Brunner, 2011. "Energy-Efficiency Policy Opportunities for Electric Motor-Driven Systems," IEA Energy Papers 2011/7, OECD Publishing.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Bortoni, Edson C. & Magalhães, Leonardo P. & Nogueira, Luiz A.H. & Bajay, Sérgio V. & Cassula, Agnelo M., 2020. "An assessment of energy efficient motors application by scenarios evaluation," Energy Policy, Elsevier, vol. 140(C).
    2. Sauer, Ildo L. & Tatizawa, Hédio & Salotti, Francisco A.M. & Mercedes, Sonia S., 2015. "A comparative assessment of Brazilian electric motors performance with minimum efficiency standards," Renewable and Sustainable Energy Reviews, Elsevier, vol. 41(C), pages 308-318.
    3. Fernández Oro, J.M. & Barrio Perotti, R. & Galdo Vega, M. & González, J., 2023. "Effect of the radial gap size on the deterministic flow in a centrifugal pump due to impeller-tongue interactions," Energy, Elsevier, vol. 278(PA).
    4. de Almeida, Anibal T. & Fong, Joao & Falkner, Hugh & Bertoldi, Paolo, 2017. "Policy options to promote energy efficient electric motors and drives in the EU," Renewable and Sustainable Energy Reviews, Elsevier, vol. 74(C), pages 1275-1286.
    5. Zi-Qiang Zhu & Dawei Liang, 2022. "Perspective of Thermal Analysis and Management for Permanent Magnet Machines, with Particular Reference to Hotspot Temperatures," Energies, MDPI, vol. 15(21), pages 1-51, November.
    6. Anibal T. de Almeida & Fernando J. T. E. Ferreira & João Fong, 2023. "Perspectives on Electric Motor Market Transformation for a Net Zero Carbon Economy," Energies, MDPI, vol. 16(3), pages 1-16, January.
    7. Christoph Sejkora & Lisa Kühberger & Fabian Radner & Alexander Trattner & Thomas Kienberger, 2020. "Exergy as Criteria for Efficient Energy Systems—A Spatially Resolved Comparison of the Current Exergy Consumption, the Current Useful Exergy Demand and Renewable Exergy Potential," Energies, MDPI, vol. 13(4), pages 1-51, February.
    8. Taylor, Josh A. & Dhople, Sairaj V. & Callaway, Duncan S., 2016. "Power systems without fuel," Renewable and Sustainable Energy Reviews, Elsevier, vol. 57(C), pages 1322-1336.
    9. Oğuz Mısır & Mehmet Akar, 2022. "Efficiency and Core Loss Map Estimation with Machine Learning Based Multivariate Polynomial Regression Model," Mathematics, MDPI, vol. 10(19), pages 1-18, October.
    10. F. Knobloch & J. -F. Mercure, 2016. "The behavioural aspect of green technology investments: a general positive model in the context of heterogeneous agents," Papers 1603.06888, arXiv.org.
    11. Paramonova, Svetlana & Nehler, Therese & Thollander, Patrik, 2021. "Technological change or process innovation – An empirical study of implemented energy efficiency measures from a Swedish industrial voluntary agreements program," Energy Policy, Elsevier, vol. 156(C).
    12. Paramonova, Svetlana & Thollander, Patrik & Ottosson, Mikael, 2015. "Quantifying the extended energy efficiency gap-evidence from Swedish electricity-intensive industries," Renewable and Sustainable Energy Reviews, Elsevier, vol. 51(C), pages 472-483.
    13. Gang Lei & Jianguo Zhu & Youguang Guo & Chengcheng Liu & Bo Ma, 2017. "A Review of Design Optimization Methods for Electrical Machines," Energies, MDPI, vol. 10(12), pages 1-31, November.
    14. Hosain, Md Lokman & Bel Fdhila, Rebei & Rönnberg, Kristian, 2017. "Taylor-Couette flow and transient heat transfer inside the annulus air-gap of rotating electrical machines," Applied Energy, Elsevier, vol. 207(C), pages 624-633.
    15. Schulze, Rita & Buchert, Matthias, 2016. "Estimates of global REE recycling potentials from NdFeB magnet material," Resources, Conservation & Recycling, Elsevier, vol. 113(C), pages 12-27.
    16. Guo, Jingquan & Ma, Xinqiang & Ahmadpour, Ali, 2021. "Electrical–mechanical evaluation of the multi–cascaded induction motors under different conditions," Energy, Elsevier, vol. 229(C).
    17. Danilo Ferreira de Souza & Francisco Antônio Marino Salotti & Ildo Luís Sauer & Hédio Tatizawa & Aníbal Traça de Almeida & Arnaldo Gakiya Kanashiro, 2022. "A Performance Evaluation of Three-Phase Induction Electric Motors between 1945 and 2020," Energies, MDPI, vol. 15(6), pages 1-31, March.
    18. Julio R. Gómez & Enrique C. Quispe & Rosaura del Pilar Castrillón & Percy R. Viego, 2020. "Identification of Technoeconomic Opportunities with the Use of Premium Efficiency Motors as Alternative for Developing Countries," Energies, MDPI, vol. 13(20), pages 1-16, October.
    19. Zuberi, M. Jibran S. & Bless, Frédéric & Chambers, Jonathan & Arpagaus, Cordin & Bertsch, Stefan S. & Patel, Martin K., 2018. "Excess heat recovery: An invisible energy resource for the Swiss industry sector," Applied Energy, Elsevier, vol. 228(C), pages 390-408.
    20. Zuberi, M. Jibran S. & Tijdink, Anton & Patel, Martin K., 2017. "Techno-economic analysis of energy efficiency improvement in electric motor driven systems in Swiss industry," Applied Energy, Elsevier, vol. 205(C), pages 85-104.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jeners:v:17:y:2024:i:2:p:368-:d:1317456. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.