Intelligent Fault Diagnosis and Forecast of Time-Varying Bearing Based on Deep Learning VMD-DenseNet

Lin, Shih-Lin

doi:10.3390/s21227467

Cited by 27 publications

(11 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rotating machinery using bearings is one of the most important components of a wide range of mechanical setups from small motors to turbines, compressors and heavy ground and air vehicles [1,2]. Different faults arise during the mechanical and industrial process, generating vibration and Acoustic Emission (AE) signals [3,4]. These signals have different characteristics due to the nature of faults, the complexity of the underlying industrial setup and the correlation between different mechanical components [5,6].…”

Section: Introductionmentioning

confidence: 99%

A New Statistical Features Based Approach for Bearing Fault Diagnosis Using Vibration Signals

Altaf

Akram

Khan

et al. 2022

Sensors

View full text Add to dashboard Cite

In condition based maintenance, different signal processing techniques are used to sense the faults through the vibration and acoustic emission signals, received from the machinery. These signal processing approaches mostly utilise time, frequency, and time-frequency domain analysis. The features obtained are later integrated with the different machine learning techniques to classify the faults into different categories. In this work, different statistical features of vibration signals in time and frequency domains are studied for the detection and localisation of faults in the roller bearings. These are later classified into healthy, outer race fault, inner race fault, and ball fault classes. The statistical features including skewness, kurtosis, average and root mean square values of time domain vibration signals are considered. These features are extracted from the second derivative of the time domain vibration signals and power spectral density of vibration signals. The vibration signal is also converted to the frequency domain and the same features are extracted. All three feature sets are concatenated, creating the time, frequency and spectral power domain feature vectors. These feature vectors are finally fed into the K- nearest neighbour, support vector machine and kernel linear discriminant analysis for the detection and classification of bearing faults. With the proposed method, the reduction percentage of more than 95% percent is achieved, which not only reduces the computational burden but also the classification time. Simulation results show that the signals are classified to achieve an average accuracy of 99.13% using KLDA and 96.64% using KNN classifiers. The results are also compared with the empirical mode decomposition (EMD) features and Fourier transform features without extracting any statistical information, which are two of the most widely used approaches in the literature. To gain a certain level of confidence in the classification results, a detailed statistical analysis is also provided.

show abstract

Section: Introductionmentioning

confidence: 99%

A New Statistical Features Based Approach for Bearing Fault Diagnosis Using Vibration Signals

Altaf

Akram

Khan

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…The VMD-DenseNet intelligent time-varying bearing fault diagnosis method is used to analyse the Hilbert spectrum through VMD, convert vibration signals into images, and then use DenseNet to extract features from each image block to give full play to the advantages of deep learning to obtain accurate results. The experimental results show that this method can accurately identify four common bearing faults [40]. In the comparative experiment, data set A is used to compare the accuracy and training time of the proposed method, ResNet-34 and VMD-DenseNet.…”

Section: Comparison With Related Methodsmentioning

confidence: 99%

Fault diagnosis of rolling bearing under time-varying speed conditions based on EfficientNetv2

Qu¹,

Yang²,

Shen³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

Rolling bearing is a widely used component in engineering. Fault diagnosis of rolling bearing is the key issue to ensure the normal operation of equipment. At present, the research on fault diagnosis of rolling bearing mainly focuses on the analysis of vibration data under constant working conditions. Nevertheless, when dealing with practical engineering problems, the operation of equipment is frequent in the case of variable speed. To analyze the vibration data in the case of frequency conversion and accurately extract the fault characteristic frequency is a challenge especially when the fault characteristics are weak. In addition, the traditional vibration characteristic analysis requires professional technicians to supervise the operation of the equipment, which requires certain professional ability of the staff. Based on the above two problems, this paper proposes a rolling bearing fault diagnosis model under time-varying working conditions based on EfficientNetv2 network. This method uses short-time Fourier transform to convert one-dimensional vibration signal into two-dimensional image signal, and uses the advantages of image recognition network to realize the fault diagnosis under time-varying speed conditions. After training the network based on transfer learning, the experimental data verify that the accuracy of the results reach 99.9 ± 0.1% even though in the case of weak fault characteristics, and there is no need for professional technicians to supervise and diagnose after model training, which is conducive to practical application.

show abstract

“…Therefore, we will have five groups of data, each group has 12 data sets from three trials. The sampling frequency is 200 000 Hz, and the sampling duration is 10 s [32]. The structural parameters of bearings are listed in table 3, and dataset numbering is listed in table 4.…”

Section: Case Studymentioning

confidence: 99%

Parallel adversarial feature learning and enhancement of feature discriminability for fault diagnosis of a planetary gearbox under time-varying speed conditions

Zhao¹,

Zhang²

2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

The intelligent fault diagnosis of a planetary gearbox under variable speed is still a challenging topic. Due to the similar spectrum structure, overlapping features occur and result in decreasing diagnosis accuracy. Autoencoder-based methods can extract features adaptively but few studies proposed approaches to enhance the discriminability of features from different classes under variable speeds. Besides, the adverse variability of encoder weights may result in an adverse effect on the decoder. Adversarially learned inference (ALI) trains the encoder and decoder independently, but it is time-consuming to reach Nash equilibrium. To address the issues, a parallel adversarial learning inference model (PALI) is proposed, which aims at validating the parallel training of encoder and decoder and enhancing the discriminability of features. Specifically, time-frequency analysis is utilized to reveal the time-varying characteristics of raw signals and obtain time-frequency images as input for the encoder. Then, an explicit multi-dimensional uniform distribution is used for the merit of a simple probability density function to construct visualized and well-classified samples as input for the decoder. After that, a parallel adversarial game is explored to train the encoder and decoder simultaneously and independently, which will reduce computing interference and make the extracted features similar to the well-classified samples and reconstruct the raw signals. Finally, a Softmax classifier is trained and tested by the features. This method and its generability are validated via a planetary gearbox data set and a public bearing data under variable speed. The results indicate that the proposed parallel adversarial game is valid for training encoder and decoder independently, and PALI works as well as adversarial autoencoder (AAE) and outperforms ALI, variational autoencoder (VAE) in obtaining well-clustered features over different training data. Compared to Wigner-Ville distribution (WVD) and continuous wavelet transform (CWT), PALI based on short-time Fourier transformation (STFT) works better over different training data.

show abstract

Intelligent Fault Diagnosis and Forecast of Time-Varying Bearing Based on Deep Learning VMD-DenseNet

Cited by 27 publications

References 32 publications

A New Statistical Features Based Approach for Bearing Fault Diagnosis Using Vibration Signals

A New Statistical Features Based Approach for Bearing Fault Diagnosis Using Vibration Signals

Fault diagnosis of rolling bearing under time-varying speed conditions based on EfficientNetv2

Parallel adversarial feature learning and enhancement of feature discriminability for fault diagnosis of a planetary gearbox under time-varying speed conditions

Contact Info

Product

Resources

About