Investigation on the Use of 2D-DOST on Time–Frequency Representations of Stray Flux Signals for Induction Motor Fault Classification Using a Lightweight CNN Model

Díaz-Saldaña, Geovanni; Morales-Velazquez, Luis; Biot-Monterde, Vicente; Antonino-Daviu, José Alfonso

doi:10.3390/machines13111001

Open AccessArticle

Investigation on the Use of 2D-DOST on Time–Frequency Representations of Stray Flux Signals for Induction Motor Fault Classification Using a Lightweight CNN Model

by

Geovanni Díaz-Saldaña

^1,2

,

Luis Morales-Velazquez

¹,

Vicente Biot-Monterde

²

and

José Alfonso Antonino-Daviu

^2,*

¹

Cuerpo Académico Mecatrónica, Facultad de Ingeniería, Universidad Autónoma de Querétaro, Campus San Juan del Río, Av. Río Moctezuma 249, San Juan del Río 76807, Querétaro, Mexico

²

Instituto Tecnológico de la Energía (ITE), Universitat Politècnica de València (UPV), Camino de Vera S/N, 46022 Valencia, Spain

^*

Author to whom correspondence should be addressed.

Machines 2025, 13(11), 1001; https://doi.org/10.3390/machines13111001

Submission received: 24 September 2025 / Revised: 29 October 2025 / Accepted: 29 October 2025 / Published: 31 October 2025

(This article belongs to the Section Electrical Machines and Drives)

Download

Browse Figures

Versions Notes

Abstract

Condition monitoring and fault detection in induction motors (IMs) are priorities in the industrial environment to secure safe conditions for the processes and production. Convolutional Neural Networks (CNNs) are gaining interest in these tasks as they allow automatic extraction of features from the inputs, sometimes Time–Frequency Distributions (TFDs) obtained with various transforms, directly into large models for data classification. This work presents a proposal for the application of a widely used texture analysis tool in the medical field, the 2D Discrete Orthonormal Stockwell Transform (2D-DOST), to improve the accuracy of a lightweight CNN when using different TFDs and comparing the results to the use of the TFDs in RGB and grayscale. The results show that the use of the 2D-DOST improves the classification accuracy in a two to five percent range for all motor conditions under study, while having minimal variations to the training times when compared to RGB or grayscale images, opening the possibility for the use of image processing tools on TFDs to improve automatic feature extraction while using small CNN models.

Keywords: induction motor; fault detection; CNN; 2D-DOST; STFT; CWT; FSST; ST-MUSIC

Share and Cite

MDPI and ACS Style

Díaz-Saldaña, G.; Morales-Velazquez, L.; Biot-Monterde, V.; Antonino-Daviu, J.A. Investigation on the Use of 2D-DOST on Time–Frequency Representations of Stray Flux Signals for Induction Motor Fault Classification Using a Lightweight CNN Model. Machines 2025, 13, 1001. https://doi.org/10.3390/machines13111001

AMA Style

Díaz-Saldaña G, Morales-Velazquez L, Biot-Monterde V, Antonino-Daviu JA. Investigation on the Use of 2D-DOST on Time–Frequency Representations of Stray Flux Signals for Induction Motor Fault Classification Using a Lightweight CNN Model. Machines. 2025; 13(11):1001. https://doi.org/10.3390/machines13111001

Chicago/Turabian Style

Díaz-Saldaña, Geovanni, Luis Morales-Velazquez, Vicente Biot-Monterde, and José Alfonso Antonino-Daviu. 2025. "Investigation on the Use of 2D-DOST on Time–Frequency Representations of Stray Flux Signals for Induction Motor Fault Classification Using a Lightweight CNN Model" Machines 13, no. 11: 1001. https://doi.org/10.3390/machines13111001

APA Style

Díaz-Saldaña, G., Morales-Velazquez, L., Biot-Monterde, V., & Antonino-Daviu, J. A. (2025). Investigation on the Use of 2D-DOST on Time–Frequency Representations of Stray Flux Signals for Induction Motor Fault Classification Using a Lightweight CNN Model. Machines, 13(11), 1001. https://doi.org/10.3390/machines13111001

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Investigation on the Use of 2D-DOST on Time–Frequency Representations of Stray Flux Signals for Induction Motor Fault Classification Using a Lightweight CNN Model

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI