An interpretable hybrid framework combining convolution latent vectors with transformer based attention mechanism for rolling element fault detection and classification

Failure of industrial assets can cause financial, operational and safety hazards across different industries. Monitoring their condition is crucial for successful and smooth operations. The colossal volume of sensory data generated and acquired throughout industrial operations supports real-time con...

Full description

Saved in:
Bibliographic Details
Main Authors: Ali Saeed, M. Usman Akram, Muazzam Khattak, M. Belal Khan
Format: Article
Language:English
Published: Elsevier 2024-11-01
Series:Heliyon
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2405844024150244
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846167151534145536
author Ali Saeed
M. Usman Akram
Muazzam Khattak
M. Belal Khan
author_facet Ali Saeed
M. Usman Akram
Muazzam Khattak
M. Belal Khan
author_sort Ali Saeed
collection DOAJ
description Failure of industrial assets can cause financial, operational and safety hazards across different industries. Monitoring their condition is crucial for successful and smooth operations. The colossal volume of sensory data generated and acquired throughout industrial operations supports real-time condition monitoring of these assets. Leveraging digital technologies to analyze acquired data creates an ideal environment for applying advanced data-driven machine learning techniques, such as convolutional neural networks (CNNs) and vision transformer (ViT) to detect faults and classify, enabling accurate prediction and timely maintenance of industrial assets. In this paper, we present a novel hybrid framework based on the local feature extraction ability of CNN with comprehensive understanding of transformer within a global context. The proposed method leverages the complex weight-sharing properties of CNNs and ability of transformers to understand the larger context of spatial relationships in large-scale patterns, making it applicable to datasets of varying sizes. Preprocessing methods such as data augmentation are used to train the model on the Case Western Reserve University (CWRU) dataset in order to increase generalization through computational efficiency. An average fault classification accuracy of 99.62% is accomplished over all three fault classes with an average time-to-fault detection of 38.4 ms. MFPT fault dataset is used to further validate the method with an accuracy of 99.17% for outer race and 99.26% for inner race. Moreover, the proposed framework can be modified to accommodate alternative convolutional models.
format Article
id doaj-art-e49bc6db36c54b54824bf98184fb2a41
institution Kabale University
issn 2405-8440
language English
publishDate 2024-11-01
publisher Elsevier
record_format Article
series Heliyon
spelling doaj-art-e49bc6db36c54b54824bf98184fb2a412024-11-15T06:12:30ZengElsevierHeliyon2405-84402024-11-011021e38993An interpretable hybrid framework combining convolution latent vectors with transformer based attention mechanism for rolling element fault detection and classificationAli Saeed0M. Usman Akram1Muazzam Khattak2M. Belal Khan3Quaid-i-Azam University, Islamabad, 45320, Pakistan; Corresponding authors.National University of Sciences & Technology, Islamabad, 44000, PakistanQuaid-i-Azam University, Islamabad, 45320, PakistanOtto-von-Guericke University, Magdeburg, 39106, Germany; Corresponding authors.Failure of industrial assets can cause financial, operational and safety hazards across different industries. Monitoring their condition is crucial for successful and smooth operations. The colossal volume of sensory data generated and acquired throughout industrial operations supports real-time condition monitoring of these assets. Leveraging digital technologies to analyze acquired data creates an ideal environment for applying advanced data-driven machine learning techniques, such as convolutional neural networks (CNNs) and vision transformer (ViT) to detect faults and classify, enabling accurate prediction and timely maintenance of industrial assets. In this paper, we present a novel hybrid framework based on the local feature extraction ability of CNN with comprehensive understanding of transformer within a global context. The proposed method leverages the complex weight-sharing properties of CNNs and ability of transformers to understand the larger context of spatial relationships in large-scale patterns, making it applicable to datasets of varying sizes. Preprocessing methods such as data augmentation are used to train the model on the Case Western Reserve University (CWRU) dataset in order to increase generalization through computational efficiency. An average fault classification accuracy of 99.62% is accomplished over all three fault classes with an average time-to-fault detection of 38.4 ms. MFPT fault dataset is used to further validate the method with an accuracy of 99.17% for outer race and 99.26% for inner race. Moreover, the proposed framework can be modified to accommodate alternative convolutional models.http://www.sciencedirect.com/science/article/pii/S2405844024150244Intelligent fault diagnosisDeep learningCNN and transformerFault classificationHybrid models
spellingShingle Ali Saeed
M. Usman Akram
Muazzam Khattak
M. Belal Khan
An interpretable hybrid framework combining convolution latent vectors with transformer based attention mechanism for rolling element fault detection and classification
Heliyon
Intelligent fault diagnosis
Deep learning
CNN and transformer
Fault classification
Hybrid models
title An interpretable hybrid framework combining convolution latent vectors with transformer based attention mechanism for rolling element fault detection and classification
title_full An interpretable hybrid framework combining convolution latent vectors with transformer based attention mechanism for rolling element fault detection and classification
title_fullStr An interpretable hybrid framework combining convolution latent vectors with transformer based attention mechanism for rolling element fault detection and classification
title_full_unstemmed An interpretable hybrid framework combining convolution latent vectors with transformer based attention mechanism for rolling element fault detection and classification
title_short An interpretable hybrid framework combining convolution latent vectors with transformer based attention mechanism for rolling element fault detection and classification
title_sort interpretable hybrid framework combining convolution latent vectors with transformer based attention mechanism for rolling element fault detection and classification
topic Intelligent fault diagnosis
Deep learning
CNN and transformer
Fault classification
Hybrid models
url http://www.sciencedirect.com/science/article/pii/S2405844024150244
work_keys_str_mv AT alisaeed aninterpretablehybridframeworkcombiningconvolutionlatentvectorswithtransformerbasedattentionmechanismforrollingelementfaultdetectionandclassification
AT musmanakram aninterpretablehybridframeworkcombiningconvolutionlatentvectorswithtransformerbasedattentionmechanismforrollingelementfaultdetectionandclassification
AT muazzamkhattak aninterpretablehybridframeworkcombiningconvolutionlatentvectorswithtransformerbasedattentionmechanismforrollingelementfaultdetectionandclassification
AT mbelalkhan aninterpretablehybridframeworkcombiningconvolutionlatentvectorswithtransformerbasedattentionmechanismforrollingelementfaultdetectionandclassification
AT alisaeed interpretablehybridframeworkcombiningconvolutionlatentvectorswithtransformerbasedattentionmechanismforrollingelementfaultdetectionandclassification
AT musmanakram interpretablehybridframeworkcombiningconvolutionlatentvectorswithtransformerbasedattentionmechanismforrollingelementfaultdetectionandclassification
AT muazzamkhattak interpretablehybridframeworkcombiningconvolutionlatentvectorswithtransformerbasedattentionmechanismforrollingelementfaultdetectionandclassification
AT mbelalkhan interpretablehybridframeworkcombiningconvolutionlatentvectorswithtransformerbasedattentionmechanismforrollingelementfaultdetectionandclassification