Novel Preprocessing of Multimodal Condition Monitoring Data for Classifying Induction Motor Faults Using Deep Learning Methods

Hejazi, Shahd; Packianather, Michael; Liu, Ying

doi:10.1109/isssc56467.2022.10051321

Cited by 6 publications

(8 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method, tested on CWRU and MFPT datasets, demonstrated superior diagnostic accuracy and stability. Another approach, proposed in [17], applied a multimodal image fusion preprocessing approach for Induction Motor (IM) fault classification using thermal images, which enhanced fault classification accuracy trained using ResNet-18 and SqueezeNet. The field of induction motor fault classification remains an active area of research, focusing on optimal feature extraction and selection techniques and leveraging various machine learning methods.…”

Section: State-of-the-art and Research Gapsmentioning

confidence: 99%

“…Consequently, efforts have been focused on developing reliable and costeffective methods for diagnosing faults in induction motors. Early detection of potential failures is crucial to proactively prevent significant damage to machinery [12][13][14][15][16][17]. Despite the recognised importance of feature extraction and selection in intelligent diagnosis systems, there is a noticeable gap in the literature, particularly concerning evaluating load impact [18][19][20].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Customised Load Adaptive Framework for Induction Motor Fault Classification Utilising MFPT Bearing Dataset

Hejazi,

Packianather,

Liu

2024

Machines

Self Cite

View full text Add to dashboard Cite

This research presents a novel Customised Load Adaptive Framework (CLAF) for fault classification in Induction Motors (IMs), utilising the Machinery Fault Prevention Technology (MFPT) bearing dataset. CLAF represents a pioneering approach that extends traditional fault classification methodologies by accounting for load variations and dataset customisation. Through a meticulous two-phase process, it unveils load-dependent fault subclasses that have not been readily identified in traditional approaches. Additionally, new classes are created to accommodate the dataset’s unique characteristics. Phase 1 involves exploring load-dependent patterns in time and frequency domain features using one-way Analysis of Variance (ANOVA) ranking and validation via bagged tree classifiers. In Phase 2, CLAF is applied to identify mild, moderate, and severe load-dependent fault subclasses through optimal Continuous Wavelet Transform (CWT) selection through Wavelet Singular Entropy (WSE) and CWT energy analysis. The results are compelling, with a 96.3% classification accuracy achieved when employing a Wide Neural Network to classify proposed load-dependent fault subclasses. This underscores the practical value of CLAF in enhancing fault diagnosis in IMs and its future potential in advancing IM condition monitoring.

show abstract

Section: State-of-the-art and Research Gapsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Novel Customised Load Adaptive Framework for Induction Motor Fault Classification Utilising MFPT Bearing Dataset

Hejazi,

Packianather,

Liu

2024

Machines

Self Cite

View full text Add to dashboard Cite

show abstract

“…This method, tested on CWRU and MFPT datasets, demonstrated superior diagnostic accuracy and stability. Other approaches proposed in [17], such as multimodal preprocessing using image fusion, enhance fault classification accuracy for ResNet-18 and SqueezeNet in induction motors. The field of induction motor fault classification remains an active area of research, focusing on optimal feature extraction and selection techniques and leveraging various machine learning methods.…”

Section: State-of-the-art and Research Gapsmentioning

confidence: 99%

“…Consequently, there has been a focused effort to develop reliable and cost-effective methods for diagnosing faults in IM. The early detection of possible failures is paramount, as it can proactively prevent substantial damage to the machinery [12][13][14][15][16][17]. Despite the recognised significance of feature extraction and selection within intelligent diagnosis systems, assessing load impact has not received proportional attention in the literature [18,19].…”

Section: State-of-the-art and Research Gapsmentioning

confidence: 99%

“…Consequently, efforts have been focused on developing reliable and cost-effective methods for diagnosing faults in induction motors. Early detection of potential failures is crucial to proactively prevent significant damage to machinery [12][13][14][15][16][17]. Despite the recognized importance of feature extraction and selection in intelligent diagnosis systems, there is a noticeable gap in the literature, particularly concerning evaluating load impact [18][19][20].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Customised Load Adaptive Framework for Induction Motor Fault Classification Utilizing MFPT Bearing Dataset

Hejazi,

Packianather,

Liu

2023

Preprint

View full text Add to dashboard Cite

This research presents a novel Customised Load Adaptive Framework (CLAF) for fault classifica-tion in Induction Motors (IMs), utilizing the Machinery Fault Prevention Technology (MFPT) Bearing Dataset. CLAF represents a pioneering approach that extends traditional fault classification methodologies by accounting for load variations and dataset customization. Through a meticulous two-phase process, it unveils load-dependent fault subclasses that have not been readily identified in traditional approaches. Additionally, new classes are created to accommodate the dataset's unique characteristics. Phase 1 involves the exploration of load-dependent patterns in time and frequency domain features using one-way Analysis of Variance (ANOVA) ranking and validation via bagged tree classifiers. In Phase 2, CLAF is applied to identify mild, moderate, and severe load-dependent fault subclasses through optimal Continuous Wavelet Transform (CWT) selection through Wavelet Singular Entropy (WSE) and CWT energy analysis. The results are compelling, with a 96.3% classification accuracy achieved when employing a wide neural network to classify proposed load-dependent fault subclasses. This underscores the practical value of CLAF in en-hancing fault diagnosis in IMs and its future potential in advancing IM condition monitoring.

show abstract

Ensemble-based multimodal medical imaging fusion for tumor segmentation

Karthik,

Hamatta,

Patthi

et al. 2024

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

Novel Preprocessing of Multimodal Condition Monitoring Data for Classifying Induction Motor Faults Using Deep Learning Methods

Cited by 6 publications

References 25 publications

A Novel Customised Load Adaptive Framework for Induction Motor Fault Classification Utilising MFPT Bearing Dataset

A Novel Customised Load Adaptive Framework for Induction Motor Fault Classification Utilising MFPT Bearing Dataset

A Novel Customised Load Adaptive Framework for Induction Motor Fault Classification Utilizing MFPT Bearing Dataset

Ensemble-based multimodal medical imaging fusion for tumor segmentation

Contact Info

Product

Resources

About