Bearing Fault Diagnosis of a PWM Inverter Fed-Induction Motor Using an Improved Short Time Fourier Transform

Khodja, Mohammed-El-Amine; Aimer, Ameur Fethi; Boudinar, Ahmed Hamida; Benouzza, Noureddine; Bendiabdellah, Azeddine

doi:10.1007/s42835-019-00096-y

Cited by 51 publications

(23 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since rolling-element bearings are constituted by an inner race, an outer race, a cage and balls, the singlepoint fault includes four types: cage fault, outer race fault, inner race fault and ball bearing fault, as shown in Figure 2 (Hamadache et al, 2015). Their corresponding characteristic fault frequencies are given by Equations (1-4) separately, where N ball is the number of balls in one bearing, D ball and D cage are the diameters of ball and cage respectively, θ is the contact angle, f r is the shaft speed, and f s is the sample frequency (Aimer et al, 2019;Eren, 2017).…”

Section: Bearing Fault Typesmentioning

confidence: 99%

“…Equations (1-4) enable us to know in advance the frequency bands where the fault signature is likely to appear. Therefore, it can reduce the length of the spectrum and consequently the computation time (Aimer et al, 2019;Boudinar et al, 2016) to process the data on these predictable fault frequencies band instead of those on all the spectra.…”

Section: Bearing Fault Typesmentioning

confidence: 99%

See 1 more Smart Citation

A self-Adaptive CNN with PSO for bearing fault diagnosis

Chen

Jiang

Guo

et al. 2020

Systems Science & Control Engineering

View full text Add to dashboard Cite

Section: Bearing Fault Typesmentioning

confidence: 99%

Section: Bearing Fault Typesmentioning

confidence: 99%

A self-Adaptive CNN with PSO for bearing fault diagnosis

Chen

Jiang

Guo

et al. 2020

Systems Science & Control Engineering

View full text Add to dashboard Cite

“…A conventional data-driven method usually consists of three stages, including handcrafted feature design, feature extraction/selection, and model training. Normally, handcrafted feature design is based on the signal processing methods such as Fourier transform (FT), short-time Fourier transform (STFT), wavelet transform (WT), wavelet package transform (WPT), Hilbert-Huang transform (HHT), and empirical mode decomposition (EMD) [8][9][10]. After a set of features are appropriately designed, they can be fed into some shallow machine learning algorithms such as EMD + SVM [10], HHT + SVM [11], DWT + KNN [12], WPT + KNN [13], and WT + Naive Bayes (NB) [14].…”

Section: Introductionmentioning

confidence: 99%

An Efficient CNN with Tunable Input-Size for Bearing Fault Diagnosis

Chen¹,

Jiang²,

Guo³

et al. 2021

IJCIS

View full text Add to dashboard Cite

Deep learning can automatically learn the complex features of input data and is recognized as an effective method for bearing fault diagnosis. Convolution neuron network (CNN) has been successfully used in image classification, and images of vibration signal or time-frequency information from short-time Fourier transform (STFT), wavelet transform (WT), and empirical mode decomposition (EMD) can be fed into CNN to achieve promising results. However, the CNN structure is complex and not efficient enough for different datasets. Furthermore, it is less efficient to process the input data by WT and EMD than by STFT. In this work, the low bound for input size of 2D data is analyzed by considering the relationship between the characteristic vibration frequencies and the window size of STFT to guide the determination of the minimum input size. Then a general adaptive CNN structure for different datasets is designed. According to the experimental results for four datasets, the proposed method is universal and the parameter settings can be guided by the low bound of input size. Surprisingly, all classification accuracies for the four datasets can achieve 100% in ten times of independent run without redesigning the CNN structure.

show abstract

“…Recently, some methods have been proposed to extract weak fault characteristics. Short-time Fourier transform (STFT) method (Khodja, Aimer, Boudinar, Benouzza, & Bendiabdellah, 2019;Li, Zhang, Qin, & Sun, 2018) is limited by the window function and has no universality. Wavelet transform method (Guo & Xiao, 2017; CONTACT Jie Ma mjbeijing@163.com Ma, Zhang, Fan, & Wang, 2019;Xu, Tian, Zhang, & Ma, 2019) needs to select an appropriate wavelet base for the fault diagnosis of rolling bearing, and the parameters are pre-set by prior knowledge, where the quality of the parameter selection often has a great impact on the results.…”

Section: Introductionmentioning

confidence: 99%

Weak fault diagnosis of rolling bearing based on FRFT and DBN

2020

Systems Science & Control Engineering

View full text Add to dashboard Cite

When diagnosing the weak fault of rolling bearing, the fault characteristic is difficult to be extracted because the fault signal has a small amplitude and is susceptible to noise. Aiming at this problem, a fault diagnosis method is proposed based on fractional Fourier transform (FRFT) and deep belief networks (DBN). The original fault signal is first transformed into the fractional domain, and the signal is filtered in this domain to extract the fault features. The characteristic signal is then input to the DBN, and the whole network is optimized to finally realized fault diagnosis by using the pre-training and the reverse propagation algorithm. The simulation results show that the method can effectively detect the weak fault of rolling bearing.

show abstract

Bearing Fault Diagnosis of a PWM Inverter Fed-Induction Motor Using an Improved Short Time Fourier Transform

Cited by 51 publications

References 24 publications

A self-Adaptive CNN with PSO for bearing fault diagnosis

A self-Adaptive CNN with PSO for bearing fault diagnosis

An Efficient CNN with Tunable Input-Size for Bearing Fault Diagnosis

Weak fault diagnosis of rolling bearing based on FRFT and DBN

Contact Info

Product

Resources

About