Tri-axial vibration based collective feature analysis for decent fault classification of VFD fed induction motor

Panigrahy, Parth Sarathi; Chattopadhyay, Paramita

doi:10.1016/j.measurement.2020.108460

Cited by 11 publications

(10 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Conversely, the order of wavelet function decides the filter size. For db N wavelet, the each filter length embedded in DWT-IDWT architecture, becomes 2N [5,7,3,33,34]. It is observed from the investigation that 97%~99% of similarity index is maintained for db 10 wavelet for all cases as depicted in Fig.…”

Section: Feature Extraction and Wavelet Transformmentioning

confidence: 84%

“…The proposed deep learning based algorithm has been validated with real time data accrued through Machinery Fault Simulator (MFS) [7] as shown in Fig. 2.…”

Section: Data Acquisition Using Machinery Fault Simulatormentioning

confidence: 99%

“…A feature [32] describes a distinctive signature, a recognizable dimension, and a valuable constituent obtained from a sector of pattern. Feature engineering is based on collection statistical information where Variance, Mean, Root Mean Square (RMS), Standard Deviation etc are considered as valuable features extensively which used to represent important properties, associated with a signal [7]. From the reviewed works it has been observed that using DWT-IDWT, various features can be utilized to efficiently classify different patterns or motor faults as the energy content of different sub bands gets changed with an occurrence of a specific fault [7].…”

Section: Feature Extraction and Wavelet Transformmentioning

confidence: 99%

“…Conventionally labor intensive handcrafted feature engineering techniques, consisting of feature extraction and feature selection modules, are carried out to provide effective features to train the learning algorithms. Majority of the researcher have exploited the vibration signals [2,6,7] because these signatures are fault informative and produce relatively good quality feature space, making the classification task easier.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Signal Processing and Machine Learning Techniques Based Hybrid Approaches for Decent Fault Classification of Induction Motor

PANIGRAHY,

CHATTOPADHYAY

2024

Preprint

Self Cite

View full text Add to dashboard Cite

Learning of better feature representation instinctively by Convolutional Neural Networks (CNN) has inspired to address the unsolved issues in the stator current based multi-class fault diagnosis of induction motor drives. Current envelope of stator current acquired using the Hilbert transform is proven to be the effective pre-processing method to handle the complex data pattern of motor current and reveal the masked defect information. The self-synthesized quality features through deep convolution layers outperforms and reaches an unmatched accuracy level compared to the counterpart-feature engineering scheme. The method of feature engineering is also developed with DHT-DWT based feature extraction process with novel idea of suitable mother wavelet selection scheme. The most notable achievement of this research work is to address the unique advantages of hybridization of signal processing technique and CNN model where the enrichment in feature quality is acquired due to unveiling the buried fault information close to dominating supply frequency. The proposed method is reliable in analyzing multi-class motor fault detection having a good generalization approach. The compact design of hybrid CNN-envelope approach dealt with very low resolution stator current sampled at 1.28 kHz, has reduced the computation intricacies to a great extent and projected it as the right aspirant for real-time applications.

show abstract

Section: Feature Extraction and Wavelet Transformmentioning

confidence: 84%

“…The proposed deep learning based algorithm has been validated with real time data accrued through Machinery Fault Simulator (MFS) [7] as shown in Fig. 2.…”

Section: Data Acquisition Using Machinery Fault Simulatormentioning

confidence: 99%

Section: Feature Extraction and Wavelet Transformmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Signal Processing and Machine Learning Techniques Based Hybrid Approaches for Decent Fault Classification of Induction Motor

PANIGRAHY,

CHATTOPADHYAY

2024

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…It also includes triaxial vibration data of three phase induction motor in healthy condition. The acquired data can be used for evaluation of new methods proposed for bearing fault detection and identification such as methods presented in the research [1] , [2] , [3] , [4] . The collected datasets are stored in comma separated values (CSV) files.…”

Section: Data Descriptionmentioning

confidence: 99%

Triaxial bearing vibration dataset of induction motor under varying load conditions

et al. 2022

View full text Add to dashboard Cite

Patterns Based on Clarke and Park Transforms of Wavelet Coefficients for Classification of Electrical Machine Faults

Vitor

Scalassara

Goedtel

et al. 2022

J Control Autom Electr Syst

View full text Add to dashboard Cite

Tri-axial vibration based collective feature analysis for decent fault classification of VFD fed induction motor

Cited by 11 publications

References 27 publications

Signal Processing and Machine Learning Techniques Based Hybrid Approaches for Decent Fault Classification of Induction Motor

Signal Processing and Machine Learning Techniques Based Hybrid Approaches for Decent Fault Classification of Induction Motor

Triaxial bearing vibration dataset of induction motor under varying load conditions

Patterns Based on Clarke and Park Transforms of Wavelet Coefficients for Classification of Electrical Machine Faults

Contact Info

Product

Resources

About