Magnetoresistance sensor-based rotor fault detection in induction motor using non-decimated wavelet and streaming data

Kavitha, S; Bhuvaneswari, N. S.; Senthilkumar, R.; Shanker, N. R.

doi:10.1080/00051144.2022.2052533

Cited by 5 publications

(4 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where c signifies the DVof the SF s a , and v the DVof the TF s t [16]. Moreover, the original signal rðtÞ is a DV to rðqÞ, of which q signifies the DV of t. Like this, two subbands (SBs) can be calculated.…”

Section: Methodology Of Wacpn 31 Discrete Wavelet Transformmentioning

confidence: 99%

“…Now, we deduct the definition of DWT from CWT. The equation (5) is discretized by substituting s a and s t with two discrete variables (DVs) c and v,

where c signifies the DV of the SF s a , and v the DV of the TF s t [ 16 ]. Moreover, the original signal r ( t ) is a DV to r ( q ), of which q signifies the DV of t. Like this, two subbands (SBs) can be calculated.…”

Section: Methodology Of Wacpnmentioning

confidence: 99%

See 1 more Smart Citation

WACPN: A Neural Network for Pneumonia Diagnosis

Wang¹,

Khan²,

Zhu³

et al. 2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

Community-acquired pneumonia (CAP) is considered a sort of pneumonia developed outside hospitals and clinics. To diagnose community-acquired pneumonia (CAP) more efficiently, we proposed a novel neural network model. We introduce the 2-dimensional wavelet entropy (2d-WE) layer and an adaptive chaotic particle swarm optimization (ACP) algorithm to train the feed-forward neural network. The ACP uses adaptive inertia weight factor (AIWF) and Rossler attractor (RA) to improve the performance of standard particle swarm optimization. The final combined model is named WE-layer ACP-based network (WACPN), which attains a sensitivity of 91.87 ± 1.37%, a specificity of 90.70 ± 1.19%, a precision of 91.01 ± 1.12%, an accuracy of 91.29 ± 1.09%, F1 score of 91.43 ± 1.09%, an MCC of 82.59 ± 2.19%, and an FMI of 91.44 ± 1.09%. The AUC of this WACPN model is 0.9577. We find that the maximum deposition level chosen as four can obtain the best result. Experiments demonstrate the effectiveness of both AIWF and RA. Finally, this proposed WACPN is efficient in diagnosing CAP and superior to six state-of-the-art models. Our model will be distributed to the cloud computing environment.

show abstract

Section: Methodology Of Wacpn 31 Discrete Wavelet Transformmentioning

confidence: 99%

“…Now, we deduct the definition of DWT from CWT. The equation (5) is discretized by substituting s a and s t with two discrete variables (DVs) c and v,

Section: Methodology Of Wacpnmentioning

confidence: 99%

WACPN: A Neural Network for Pneumonia Diagnosis

Wang¹,

Khan²,

Zhu³

et al. 2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

show abstract

“…Much research efforts have been contributed in decades to detect the damage feature from vibration measurements, and various signal denoising or analyzing techniques have been reported in which the single fault detection is greatly focused. These achievements mainly contain filtering methods such as wavelet transforms (WTs) (Kavitha et al, 2022), wavelet package transform (WPT) (Yan et al, 2014), spectral kurtosis (Fu et al, 2021), and flexible-frame wavelet transforms (Zhang et al, 2015, 2020; Cao et al, 2019); adaptive vibration signal decomposition methods such as empirical mode decomposition (EMD) (Zheng et al, 2022), local mean decomposition (LMD) (Chen et al, 2022), variable mode decomposition (VMD) (Fan et al, 2022), and ensemble empirical mode decomposition (EEMD) (Hsu and Huang, 2022); feature enhancement methods such as stochastic resonance (Lu et al, 2017) with nonlinear bistable oscillators (Cui et al, 2021), and sparse decomposition (Li et al, 2020; Wang et al, 2018); and intelligent classification methods such as machine learning (Mahami et al, 2022) and deep learning (Hou et al, 2022; Guo et al, 2018). Most of these methods have been applied for analyzing simulation and experimental vibration signals, and some of these aforementioned methods are reported suitable for incipient fault diagnosis (Jiang et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

Compound faults diagnosis of rotating machinery via enhanced two-layer sliding correlated kurtosis

Zhang

Hou

Wang³

et al. 2023

Journal of Vibration and Control

View full text Add to dashboard Cite

Compound faults identification from vibration signals is still a challenge for rotating machinery because the multiple periodic impulsive fault signals may oscillate with the same frequency. In this research, a method termed enhanced two-layer sliding correlated kurtosis (TLSCK) is presented for isolating and identifying the compound defects from the monitored data containing strong background noise and compound faults. The method contains two main steps: the dual-tree complex wavelet package transform (DTCWPT) based correlated kurtogram is conducted on the raw monitored data as a frequency filtering step; further, the enhanced TLSCK method is conducted to diagnosis the compound defects from above filtered signals. The output signal of the enhanced TLSCK could locate the occurrence of interested fault impulses, while the unwanted vibration components and residual noise are well eliminated. Both numerically simulated and experimentally measured vibration data of damaged rolling bearings are analyzed via the presented method to test its performance, and the analysis results validate that the proposed method is effective in detecting compound faults of rotating machinery.

show abstract

“…Lee et al [8] proposed a rotor fault diagnosis model for induction motors based on local mean decomposition and wavelet packet decomposition, and feature selection based on multi-layer signal analysis and hybrid genetic binary chicken flock optimization, and the accuracy of the diagnostic model was limited due to the lack of learning depth. Kavitha et al [9] proposed a giant magnetoelectric blocking rotor method to diagnose the early faults of induction motor rotor rod from the external magnetic flux generated by the giant magnetoresistance. Zhao et al [10] proposed a fault diagnosis method of a multichannel motor rotor system based on multimanifold deep extreme learning algorithm to achieve fast fusion and intelligent diagnosis of multichannel data.…”

Section: Introductionmentioning

confidence: 99%

Rotor Fault Diagnosis Using Domain-Adversarial Neural Network with Time-Frequency Analysis

Liu

Wan

et al. 2022

Machines

View full text Add to dashboard Cite

Intelligent fault diagnosis of rotors always requires a large amount of labeled samples, but insufficient vibration signals can be obtained in operational rotor systems for detecting the fault modes. To solve this problem, a domain-adaptive transfer learning model based on a small number of samples is proposed. Time-domain vibration signals are collected by overlapping sampling and converted into time-frequency diagrams by using short-time Fourier transform (STFT) and characteristics in the time domain and frequency domain of vibration signals are reserved. The features of source domain and target domain are projected into the same feature space through a domain-adversarial neural network (DANN). This method is verified by a simulated gas generator rotor and experimental rig of rotor. Both the transfer in the identical machine (TIM) and transfer across different machines (TDM) are realized. The results show that this method has high diagnosis accuracy and good robustness for different types of faults. By training a large number of simulation samples and a small number of experimental samples in TDM, high fault diagnosis accuracy is achieved, avoiding collecting a large amount of experimental data as the source domain to train the fault diagnosis model. Then, the problem of insufficient rotor fault samples can be solved.

show abstract

Magnetoresistance sensor-based rotor fault detection in induction motor using non-decimated wavelet and streaming data

Cited by 5 publications

References 50 publications

WACPN: A Neural Network for Pneumonia Diagnosis

WACPN: A Neural Network for Pneumonia Diagnosis

Compound faults diagnosis of rotating machinery via enhanced two-layer sliding correlated kurtosis

Rotor Fault Diagnosis Using Domain-Adversarial Neural Network with Time-Frequency Analysis

Contact Info

Product

Resources

About