Investigation of Transfer Learning Method for Motor Fault Detection

Industry 4.0 is propelling modern industries forward due to its reliability, stability, and performance. Electric motors (EMs) are utilized in multiple industries for their efficiency, precise speed and torque control, and robustness. Detecting faults in motors at an early stage is crucial to ensure...

Full description

Saved in:
Bibliographic Details
Main Authors: Prashant Kumar, Saurabh Singh, Doug Young Song
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Machines
Subjects:
Online Access:https://www.mdpi.com/2075-1702/13/4/329
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849714934732029952
author Prashant Kumar
Saurabh Singh
Doug Young Song
author_facet Prashant Kumar
Saurabh Singh
Doug Young Song
author_sort Prashant Kumar
collection DOAJ
description Industry 4.0 is propelling modern industries forward due to its reliability, stability, and performance. Electric motors (EMs) are utilized in multiple industries for their efficiency, precise speed and torque control, and robustness. Detecting faults in motors at an early stage is crucial to ensure maximum productivity. Recently, DL has been implemented as a data-driven approach for detecting faults in motors. However, due to the limited availability of labeled fault data, the performance of the DL model is constrained. This issue is addressed by leveraging transfer learning (TL), which uses knowledge from a larger source domain to improve performance in a smaller target domain. In this paper, a multiple fault detection (FD) model for EMs is proposed by combining the ideas of deep convolutional neural networks (CNNs) and TL. A one-dimensional signal-to-image conversion technique is suggested for converting the vibration signal to images, and an Inception-ResNet-v2-inspired FD model is proposed for detecting bearing faults in the motor. The proposed method achieved a mean accuracy of more than 99%.
format Article
id doaj-art-bea403ae07dd4e968cfb3ac636ff9fa6
institution DOAJ
issn 2075-1702
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Machines
spelling doaj-art-bea403ae07dd4e968cfb3ac636ff9fa62025-08-20T03:13:32ZengMDPI AGMachines2075-17022025-04-0113432910.3390/machines13040329Investigation of Transfer Learning Method for Motor Fault DetectionPrashant Kumar0Saurabh Singh1Doug Young Song2Department of AI and Big Data, Woosong University, Daejeon 34606, Republic of KoreaDepartment of AI and Big Data, Woosong University, Daejeon 34606, Republic of KoreaDepartment of AI and Big Data, Woosong University, Daejeon 34606, Republic of KoreaIndustry 4.0 is propelling modern industries forward due to its reliability, stability, and performance. Electric motors (EMs) are utilized in multiple industries for their efficiency, precise speed and torque control, and robustness. Detecting faults in motors at an early stage is crucial to ensure maximum productivity. Recently, DL has been implemented as a data-driven approach for detecting faults in motors. However, due to the limited availability of labeled fault data, the performance of the DL model is constrained. This issue is addressed by leveraging transfer learning (TL), which uses knowledge from a larger source domain to improve performance in a smaller target domain. In this paper, a multiple fault detection (FD) model for EMs is proposed by combining the ideas of deep convolutional neural networks (CNNs) and TL. A one-dimensional signal-to-image conversion technique is suggested for converting the vibration signal to images, and an Inception-ResNet-v2-inspired FD model is proposed for detecting bearing faults in the motor. The proposed method achieved a mean accuracy of more than 99%.https://www.mdpi.com/2075-1702/13/4/329transfer learning (TL)convolutional neural network (CNN)bearing faultselectric motor
spellingShingle Prashant Kumar
Saurabh Singh
Doug Young Song
Investigation of Transfer Learning Method for Motor Fault Detection
Machines
transfer learning (TL)
convolutional neural network (CNN)
bearing faults
electric motor
title Investigation of Transfer Learning Method for Motor Fault Detection
title_full Investigation of Transfer Learning Method for Motor Fault Detection
title_fullStr Investigation of Transfer Learning Method for Motor Fault Detection
title_full_unstemmed Investigation of Transfer Learning Method for Motor Fault Detection
title_short Investigation of Transfer Learning Method for Motor Fault Detection
title_sort investigation of transfer learning method for motor fault detection
topic transfer learning (TL)
convolutional neural network (CNN)
bearing faults
electric motor
url https://www.mdpi.com/2075-1702/13/4/329
work_keys_str_mv AT prashantkumar investigationoftransferlearningmethodformotorfaultdetection
AT saurabhsingh investigationoftransferlearningmethodformotorfaultdetection
AT dougyoungsong investigationoftransferlearningmethodformotorfaultdetection