A Comparative Analysis of Deep Learning Convolutional Neural Network Architectures for Fault Diagnosis of Broken Rotor Bars in Induction Motors DOI Creative Commons
Kevin Barrera, Jordi Burriel-Valencia, Ángel Sapena-Bañó

et al.

Sensors, Journal Year: 2023, Volume and Issue: 23(19), P. 8196 - 8196

Published: Sept. 30, 2023

Induction machines (IMs) play a critical role in various industrial processes but are susceptible to degenerative failures, such as broken rotor bars. Effective diagnostic techniques essential addressing these issues. In this study, we propose the utilization of convolutional neural networks (CNNs) for detection To accomplish this, generated dataset comprising current samples versus angular position using finite element method magnetics (FEMM) software squirrel-cage with 28 bars, including scenarios 0 6 bars at every possible relative position. The consists total 16,050 per motor. We evaluated performance six different CNN architectures, namely Inception V4, NasNETMobile, ResNET152, SeNET154, VGG16, and VGG19. Our automatic classification system demonstrated an impressive 99% accuracy detecting VGG19 performing exceptionally well. Specifically, exhibited high accuracy, precision, recall, F1-Score, values approaching 0.994 0.998. Notably, crucial activations its feature maps, particularly after domain-specific training, highlighting effectiveness fault detection. Comparing architectures assists selecting most suitable one application based on processing time, effectiveness, training losses. This research suggests that deep learning can detect induction comparable traditional methods by analyzing signals CNNs.

Language: Английский

Real-Time Artifacts Reduction during TMS-EEG Co-Registration: A Comprehensive Review on Technologies and Procedures DOI Creative Commons
Giuseppe Varone, Zain Hussain, Zakariya Sheikh

et al.

Sensors, Journal Year: 2021, Volume and Issue: 21(2), P. 637 - 637

Published: Jan. 18, 2021

Transcranial magnetic stimulation (TMS) excites neurons in the cortex, and neural activity can be simultaneously recorded using electroencephalography (EEG). However, TMS-evoked EEG potentials (TEPs) do not only reflect transcranial as they contaminated by artifacts. Over last two decades, significant developments amplifiers, TMS-compatible technology, customized hardware open source software have enabled researchers to develop approaches which substantially reduce TMS-induced In TMS-EEG experiments, various physiological external occurrences been identified attempts made minimize or remove them online techniques. Despite these advances, technological issues methodological constraints prevent straightforward recordings of early TEPs components. To best our knowledge, there is no review on both artifacts technologies literature to-date. Our survey aims provide an overview research studies this field over 40 years. We artifacts, their sources waveforms present state-of-the-art front-end characteristics. also propose a synchronization toolbox for laboratories. then subject preparation frameworks reduction maneuvers improving data acquisition conclude outlining challenges future directions field.

Language: Английский

Citations

31
EEG decoding method based on multi-feature information fusion for spinal cord injury DOI Creative Commons
Fangzhou Xu, Jincheng Li,

Gege Dong

et al.

Neural Networks, Journal Year: 2022, Volume and Issue: 156, P. 135 - 151

Published: Sept. 30, 2022

To develop an efficient brain-computer interface (BCI) system, electroencephalography (EEG) measures neuronal activities in different brain regions through electrodes. Many EEG-based motor imagery (MI) studies do not make full use of network topology. In this paper, a deep learning framework based on modified graph convolution neural (M-GCN) is proposed, which temporal-frequency processing performed the data S-transform (MST) to improve decoding performance original EEG signals types MI recognition. MST can be matched with spatial position relationship This method fusions multiple features temporal-frequency-spatial domain further recognition performance. By detecting function characteristics each specific rhythm, generated by imaginary movement effectively analyzed obtain subjects' intention. Finally, patients spinal cord injury (SCI) are used establish correlation matrix containing channel information, M-GCN employed decode relation features. The proposed has better than other existing methods. accuracy classifying and identifying tasks reach 87.456%. After 10-fold cross-validation, average rate 87.442%, verifies reliability stability algorithm. Furthermore, provides effective rehabilitation training for SCI partially restore function.

Language: Английский

Citations

22
Automatic Assessment of Motor Impairments in Autism Spectrum Disorders: A Systematic Review DOI
Thomas Gargot,

Dominique Archambault,

Mohamed Chétouani

et al.

Cognitive Computation, Journal Year: 2022, Volume and Issue: 14(2), P. 624 - 659

Published: Jan. 10, 2022

Language: Английский

Citations

20
Priming cross-session motor imagery classification with a universal deep domain adaptation framework DOI
Xin Zhang, Zhengqing Miao, Carlo Menon

et al.

Neurocomputing, Journal Year: 2023, Volume and Issue: 556, P. 126659 - 126659

Published: Aug. 16, 2023

Language: Английский

Citations

12
A Comparative Analysis of Deep Learning Convolutional Neural Network Architectures for Fault Diagnosis of Broken Rotor Bars in Induction Motors DOI Creative Commons
Kevin Barrera, Jordi Burriel-Valencia, Ángel Sapena-Bañó

et al.

Sensors, Journal Year: 2023, Volume and Issue: 23(19), P. 8196 - 8196

Published: Sept. 30, 2023

Induction machines (IMs) play a critical role in various industrial processes but are susceptible to degenerative failures, such as broken rotor bars. Effective diagnostic techniques essential addressing these issues. In this study, we propose the utilization of convolutional neural networks (CNNs) for detection To accomplish this, generated dataset comprising current samples versus angular position using finite element method magnetics (FEMM) software squirrel-cage with 28 bars, including scenarios 0 6 bars at every possible relative position. The consists total 16,050 per motor. We evaluated performance six different CNN architectures, namely Inception V4, NasNETMobile, ResNET152, SeNET154, VGG16, and VGG19. Our automatic classification system demonstrated an impressive 99% accuracy detecting VGG19 performing exceptionally well. Specifically, exhibited high accuracy, precision, recall, F1-Score, values approaching 0.994 0.998. Notably, crucial activations its feature maps, particularly after domain-specific training, highlighting effectiveness fault detection. Comparing architectures assists selecting most suitable one application based on processing time, effectiveness, training losses. This research suggests that deep learning can detect induction comparable traditional methods by analyzing signals CNNs.

Language: Английский

Citations

12