Fault Diagnosis of Electric Motors by a Novel Convolutional-based Neural Network and STFT

Mohammad-Alikhani, Arta; Pradhan, Subarni; Dhale, Sumedh; Nahid-Mobarakeh, Babak

doi:10.1109/peds57185.2023.10246634

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2023

2024

Publication Types

Select...

Other2

Article1

Relationship

Self Cite0

Independent3

Authors

Journals

Cited by 3 publications

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Operation and Maintenance Services in an Intelligent Railway Control System Architecture

Atanasov,

Pencheva,

Trifonov

2024

2024 International Conference on Control, Automation and Diagnosis (ICCAD)

View full text Add to dashboard Cite

Operation and Maintenance Services in an Intelligent Railway Control System Architecture

Atanasov,

Pencheva,

Trifonov

2024

2024 International Conference on Control, Automation and Diagnosis (ICCAD)

View full text Add to dashboard Cite

Dynamic Load Emulation for Evaluating EVs Machines Based on Sliding Mode Control

Adib,

Vahedi

2023

2023 3rd International Conference on Electrical Machines and Drives (ICEMD)

View full text Add to dashboard Cite

Improved Fault Detection Using Shifting Window Data Augmentation of Induction Motor Current Signals

Wright,

Fajri,

et al. 2024

Energies

View full text Add to dashboard Cite

Deep learning models have demonstrated potential in Condition-Based Monitoring (CBM) for rotating machinery, such as induction motors (IMs). However, their performance is significantly influenced by the size of the training dataset and the way signals are presented to the model. When trained on segmented signals over a fixed period, the model’s accuracy can decline when tested on signals that differ from the training interval or are randomly sampled. Conversely, models utilizing data augmentation techniques exhibit better generalization to unseen conditions. This paper highlights the bias introduced by traditional training methods towards specific periodic waveform sampling and proposes a new method to augment phase current signals during training using a shifting window technique. This approach is considered as a practical approach for motor current augmentation and is shown to enhance classification accuracy and improved generalization when compared to existing techniques.

show abstract

Fault Diagnosis of Electric Motors by a Novel Convolutional-based Neural Network and STFT

Cited by 3 publications

References 18 publications

Operation and Maintenance Services in an Intelligent Railway Control System Architecture

Operation and Maintenance Services in an Intelligent Railway Control System Architecture

Dynamic Load Emulation for Evaluating EVs Machines Based on Sliding Mode Control

Improved Fault Detection Using Shifting Window Data Augmentation of Induction Motor Current Signals

Contact Info

Product

Resources

About