Vibration Signal-Based Fault Diagnosis of Rotary Machinery Through Convolutional Neural Network and Transfer Learning Method

Artificial Intelligence (AI) is revolutionizing proactive repair systems by enabling real-time identification of bearing faults in industrial machinery. However, traditional fault detection methods often struggle in dynamic environments due to their dependence on specific training conditions. To add...

Full description

Saved in:
Bibliographic Details
Main Authors: Chirag Mongia, Shankar Sehgal
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Vibration
Subjects:
Online Access:https://www.mdpi.com/2571-631X/8/2/27
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849418074430636032
author Chirag Mongia
Shankar Sehgal
author_facet Chirag Mongia
Shankar Sehgal
author_sort Chirag Mongia
collection DOAJ
description Artificial Intelligence (AI) is revolutionizing proactive repair systems by enabling real-time identification of bearing faults in industrial machinery. However, traditional fault detection methods often struggle in dynamic environments due to their dependence on specific training conditions. To address this limitation, a transfer learning (TL)-based methodology has been developed for bearing fault detection, so that the model trained under some specific training conditions can perform accurately under significantly different real-time working conditions, thereby significantly improving diagnostic efficiency while reducing training time. Initially, a deep learning approach utilizing convolutional neural networks (CNNs) has been employed to diagnose faults based on vibration data. After achieving high classification performance at source domain conditions, the performance of the model is re-evaluated by applying it to the Case Western Reserve University (CWRU) dataset as the target domain through the TL method. short-time Fourier transform is employed for signal preprocessing, enhancing feature extraction and model performance. The proposed methodology has been validated across various CWRU dataset configurations under different operating conditions and environments. The proposed approach achieved a 99.7% classification accuracy in the target domain, demonstrating effective adaptability and robustness under domain shifts. The results demonstrate how TL-enhanced CNNs can be used as a scalable and efficient way to diagnose bearing faults in industrial environments.
format Article
id doaj-art-cdbc239ea43f41028f468a091abbd735
institution Kabale University
issn 2571-631X
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Vibration
spelling doaj-art-cdbc239ea43f41028f468a091abbd7352025-08-20T03:32:32ZengMDPI AGVibration2571-631X2025-05-01822710.3390/vibration8020027Vibration Signal-Based Fault Diagnosis of Rotary Machinery Through Convolutional Neural Network and Transfer Learning MethodChirag Mongia0Shankar Sehgal1Mechanical Engineering, UIET, Panjab University, Chandigarh 160014, IndiaMechanical Engineering, UIET, Panjab University, Chandigarh 160014, IndiaArtificial Intelligence (AI) is revolutionizing proactive repair systems by enabling real-time identification of bearing faults in industrial machinery. However, traditional fault detection methods often struggle in dynamic environments due to their dependence on specific training conditions. To address this limitation, a transfer learning (TL)-based methodology has been developed for bearing fault detection, so that the model trained under some specific training conditions can perform accurately under significantly different real-time working conditions, thereby significantly improving diagnostic efficiency while reducing training time. Initially, a deep learning approach utilizing convolutional neural networks (CNNs) has been employed to diagnose faults based on vibration data. After achieving high classification performance at source domain conditions, the performance of the model is re-evaluated by applying it to the Case Western Reserve University (CWRU) dataset as the target domain through the TL method. short-time Fourier transform is employed for signal preprocessing, enhancing feature extraction and model performance. The proposed methodology has been validated across various CWRU dataset configurations under different operating conditions and environments. The proposed approach achieved a 99.7% classification accuracy in the target domain, demonstrating effective adaptability and robustness under domain shifts. The results demonstrate how TL-enhanced CNNs can be used as a scalable and efficient way to diagnose bearing faults in industrial environments.https://www.mdpi.com/2571-631X/8/2/27convolutional neural networks (CNNs)fault diagnosisrotary machineryshort-time Fourier transform (STFT)transfer learningvibration signal analysis
spellingShingle Chirag Mongia
Shankar Sehgal
Vibration Signal-Based Fault Diagnosis of Rotary Machinery Through Convolutional Neural Network and Transfer Learning Method
Vibration
convolutional neural networks (CNNs)
fault diagnosis
rotary machinery
short-time Fourier transform (STFT)
transfer learning
vibration signal analysis
title Vibration Signal-Based Fault Diagnosis of Rotary Machinery Through Convolutional Neural Network and Transfer Learning Method
title_full Vibration Signal-Based Fault Diagnosis of Rotary Machinery Through Convolutional Neural Network and Transfer Learning Method
title_fullStr Vibration Signal-Based Fault Diagnosis of Rotary Machinery Through Convolutional Neural Network and Transfer Learning Method
title_full_unstemmed Vibration Signal-Based Fault Diagnosis of Rotary Machinery Through Convolutional Neural Network and Transfer Learning Method
title_short Vibration Signal-Based Fault Diagnosis of Rotary Machinery Through Convolutional Neural Network and Transfer Learning Method
title_sort vibration signal based fault diagnosis of rotary machinery through convolutional neural network and transfer learning method
topic convolutional neural networks (CNNs)
fault diagnosis
rotary machinery
short-time Fourier transform (STFT)
transfer learning
vibration signal analysis
url https://www.mdpi.com/2571-631X/8/2/27
work_keys_str_mv AT chiragmongia vibrationsignalbasedfaultdiagnosisofrotarymachinerythroughconvolutionalneuralnetworkandtransferlearningmethod
AT shankarsehgal vibrationsignalbasedfaultdiagnosisofrotarymachinerythroughconvolutionalneuralnetworkandtransferlearningmethod