A Deep Learning Method for Bearing Fault Diagnosis Based on Time-Frequency Image

Wang, Yunlong; Mo, Zhenling; Zhang, Heng; Miao, Qiang

doi:10.1109/access.2019.2907131

Cited by 170 publications

(127 citation statements)

References 45 publications

Supporting

Mentioning

126

Contrasting

Unclassified

Order By: Relevance

“…As shown in Table 2, transforming measured data such as waveforms into pictures through certain data visualization techniques and inputting them to CNN for diagnosis is a commonly used method in the current researches of diagnostic methods [42]. DGA fault data contains rich information on transformer fault states.…”

Section: Cnn-based Transformer Dga Diagnostic Methodsmentioning

confidence: 99%

A Deep Parallel Diagnostic Method for Transformer Dissolved Gas Analysis

Duan

2020

Applied Sciences

View full text Add to dashboard Cite

With the development of Industry 4.0, as a pivotal part of the power system, large-capacity power transformers are requiring fault diagnostic methods with higher intelligence, accuracy and anti-interference ability. Considering the powerful capability for extracting non-linear features and the sensitivity differences to features of deep learning methods, this paper proposes a deep parallel diagnostic method for transformer dissolved gas analysis (DGA). In view of the insufficient and imbalanced dataset of transformers, adaptive synthetic oversampling (ADASYN) was implemented to augment the fault dataset. Then, the newly constructed dataset was normalized and input into the LSTM-based diagnostic framework. Then, the dataset was converted into images as the input of the CNN-based diagnostic framework. At the same time, the problem of still insufficient data was compensated by the introduction of transfer learning technology. Finally, the diagnostic models were trained and tested respectively, and the Dempster-Shafer (DS) evidence theory was introduced to fuse the diagnostic confidence matrices of the two models to achieve deep parallel diagnosis. The results of the proposed deep parallel diagnostic method show that without complex feature extraction, the diagnostic accuracy rate could reach 96.9%. Even when the dataset was superimposed with 3% random noises, the rate only decreased by 0.62%.Appl. Sci. 2020, 10, 1329 2 of 18 their shortcomings in learning ability, processing efficiency, and feature extraction ability. For example, the learning ability of the fuzzy methods are not satisfying [7,8]. Neural networks (NN) tend to fall into local optimal solutions [9,10]. The K-nearest neighbor (KNN) method is inefficient in high-dimensional space [11]. The support vector machine (SVM) is essentially a two-classifier, which makes it more troublesome to deal with multi-classification problems [12,13]. There are also some relevant diagnosis studies on combining traditional ratio methods and intelligent methods, which are combinations of previous researches, and have achieved certain effects [14][15][16]. However, the features extracted by the ratio methods are still limited. And the anti-interference ability of the combined models need further testing. In recent years, due to the strong ability of deep learning to extract complex non-linear features, some papers have tried to introduce it into the field of transformer fault diagnosis. And the fault diagnostic accuracy of deep learning methods has been significantly improved compared to traditional machine learning diagnostic models'. The authors in [17] proposed a DBN-based fault diagnostic method that used the uncoded ratio of DGA data as the model input. Compared with the traditional methods', the accuracy was significantly improved. The authors in [18] introduced a method for identifying and locating winding faults based on CNN and transformer impulse tests. And the results showed that the method was effective. The authors in [19] studied the internal fault diagnosis of...

show abstract

Section: Cnn-based Transformer Dga Diagnostic Methodsmentioning

confidence: 99%

A Deep Parallel Diagnostic Method for Transformer Dissolved Gas Analysis

Duan

2020

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…However, for raw fault signals, it is often difficult to extract enough useful signal features for fault classification, especially under varied working conditions. Thus, the method of transforming vibration signal to time-frequency graphs (TFGs) has been proposed, which using short-time Fourier transform(STFT) and TFGs can reflect the characteristic information of bearings [17]- [19]. Zhu et al [20] used the capsule network (ICN) to analyze the TFGs which effectively improved the fault classification accuracy.…”

Section: Introductionmentioning

confidence: 99%

A Novel Method of Bearing Fault Diagnosis in Time-Frequency Graphs Using InceptionResnet and Deformable Convolution Networks

Yang

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Bearing fault diagnosis has attracted increasing attention due to its importance in the health status of rotating machinery. The data-driven models based on deep learning (DL) have become more and more intelligent in the field of fault diagnosis, and among them convolutional neural network (CNN) has been widely used in recent researches. However, traditional CNN is not easy to capture right fault features due to their fixed geometric structures, especially under complex working conditions in fault diagnosis. To address these challenges, we propose a novel model by combining InceptionResnetV2 with Deformable Convolution Networks, named DeIN. We replace the basic form of convolution with deformable convolution in specific layers, and a main classifier and an auxiliary classifier are designed to output the classification result of our proposed model, to adapt to the non-rigid characters and larger receptive field in time-frequency graph (TFG). Experimentally, the one-dimensional signals are transformed into TFGs and as input of the proposed model, and this aims to find useful features during the training process. To verify the generalization ability of the proposed model, we apply a set of cross-over tests based on two popular datasets, and our model achieved 99.87% and 94.52% highest-precision fault classification results comparing with other state-of-the-art CNN models.

show abstract

“…However, rolling bearings usually serve under adverse working conditions, which is prone to occur various categories of failure. At the same time, the failure often directly influences the operational condition of the whole mechanical system [1][2][3][4][5]. Therefore, condition monitoring and fault diagnosis techniques of rolling bearings in the early stage are very critical to guarantee reliability and safety.…”

Section: Introductionmentioning

confidence: 99%

An Improved Empirical Mode Decomposition Based on Adaptive Weighted Rational Quartic Spline for Rolling Bearing Fault Diagnosis

Shen

et al. 2020

IEEE Access

View full text Add to dashboard Cite

As a powerful time-frequency signal analysis technique, empirical mode decomposition (EMD) has been commonly applied in fault diagnosis. However, the cubic spline-curve often causes outstanding over and undershoot problem, which significantly limits the performance of conventional EMD. To address this problem, an improved EMD (I-EMD) based on adaptive weighted rational quartic spline is proposed. Firstly, the original cubic spline interpolation in conventional EMD is replaced with the weighted rational quartic spline interpolation (WRQSI) which has two adjustable shape control parameters. Secondly, a novel parameter selection criterion termed envelope characteristic frequency ratio (ECFR) is designed to guide the construction of the optimal local envelope. And simulation analysis proved that ECFR is not only sensitive to the characteristic information but also robust to the weak noise and sudden impulses. Subsequently, the optimal shape control parameter can be searched by grasshopper optimization algorithm (GOA) using the maximum ECFR as the objective function. Then the sensitive modes selected via weighted Kurtosis index are employed for further Hilbert envelope spectrum analysis. Finally, two case studies on rolling bearing fault diagnosis are constructed to verify the rationality and effectiveness of the I-EMD method. The results show that I-EMD method can evidently solve the over and undershoot problem and restrain the mode mixing phenomenon. Moreover, I-EMD also performs better fault feature extraction ability under the same conditions compared with EMD, VMD and CEEMDAN. So it is expected that I-EMD will serve as a potential improvement for signal processing, fault feature extraction and fault diagnosis.

show abstract

A Deep Learning Method for Bearing Fault Diagnosis Based on Time-Frequency Image

Cited by 170 publications

References 45 publications

A Deep Parallel Diagnostic Method for Transformer Dissolved Gas Analysis

A Deep Parallel Diagnostic Method for Transformer Dissolved Gas Analysis

A Novel Method of Bearing Fault Diagnosis in Time-Frequency Graphs Using InceptionResnet and Deformable Convolution Networks

An Improved Empirical Mode Decomposition Based on Adaptive Weighted Rational Quartic Spline for Rolling Bearing Fault Diagnosis

Contact Info

Product

Resources

About