Balanced Adaptation Regularization Based Transfer Learning for Unsupervised Cross-Domain Fault Diagnosis

Hu, Qin; Si, Xiaosheng; Qin, Aisong; Lv, Yunrong; Liu, Mei

doi:10.1109/jsen.2022.3174396

Cited by 47 publications

(28 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The fundamental concept of few-shot learning is to enable models to acquire prior knowledge, allowing them to achieve their target tasks with a limited number of samples in a new task set. This approach bears a strong resemblance to transfer learning [21,22] and meta-learning [23,24]. Consequently, there is a proposition to apply transfer learning and metalearning to the field of bearing fault diagnosis.…”

Section: Introductionmentioning

confidence: 99%

Transfer learning rolling bearing fault diagnosis model based on deep feature decomposition and class-level alignment

Dong,

Jiang,

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Research on transfer learning in rolling bearing fault diagnosis can help overcome challenges such as different data distributions and limited fault samples. However, most existing methods still struggle to address the zero-shot cross-domain problem within the same equipment and the few-shot cross-machine problem. In response to these challenges, this paper introduces a transfer learning rolling bearing fault diagnosis model based on deep feature decomposition and class-level alignment (FDCATL). The model consists of two stages. In the first stage, the original vibration signals undergo continuous wavelet transform to obtain time-frequency diagram. Subsequently, a convolutional neural network extracts features from the diagram. The obtained deep features are decomposed into four types: uncertain features, domain-shared features, domain-specific features and category features. Multiple loss functions are then employed to remove extraneous features beyond the category features. In the second stage, category features are further extracted, and Convolutional Block Attention Module (CBAM) is introduced to further reduce the potential interference of unexcluded irrelevant information within the category features with classification results. Simultaneously applying a class-level alignment strategy effectively alleviates inter-domain class distribution discrepancies. Experimental validation was conducted on three distinct datasets, revealing a significant improvement in the classification performance of the proposed method over alternative methods. Furthermore, the model demonstrated robustness and noise resistance.

show abstract

Section: Introductionmentioning

confidence: 99%

Transfer learning rolling bearing fault diagnosis model based on deep feature decomposition and class-level alignment

Dong,

Jiang,

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Reducing the impact of ifferent distributions is of great help in improving the practical application ability of diagnostic algorithms. Given this, Hu et al used multi-scale sample entropy to improve the discriminability of fault features and then used a transfer learning algorithm to realize cross-domain fault diagnosis, which solved the negative impact of the inconsistent distribution of training set and test set on diagnosis accuracy [32]. Lei et al used VMD and mixed domain feature extraction methods to obtain diversified features of vibration signals and selected the most representative feature information of faults through the importance of features [33].…”

Section: Introductionmentioning

confidence: 99%

Bearing fault diagnosis based on inverted Mel-scale frequency cepstral coefficients and deformable convolution networks

Zhao¹,

baofu²,

yuhang³

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

In the online test of bearing fault diagnosis algorithm based on data-driven, it is difficult to guarantee that the training and testing data come from the same time series distribution. Inconsistent distribution will lead to a decline in diagnostic performance. In addition, the convolutional neural network is limited by the fixed shape of its convolution kernel, which makes it difficult to fully extract the spatial constraint features between fault data. To solve the above problems, this paper proposes a bearing fault diagnosis method based on inverted Mel-scale frequency cepstrum coefficients and deformable convolution networks. The core of traditional Mel-scale frequency cepstrum coefficients is to construct a non-uniformly distributed frequency domain filter bank. It is characterized by the dense distribution of low-frequency regions and the sparse distribution of high-frequency regions. Considering that the features that can well characterize the fault information are concentrated in the high-frequency part, we reconstruct the traditional Mel-scale frequency cepstrum coefficients filter bank and propose a feature extraction method of inverted Mel-scale frequency cepstrum coefficients. This method can obtain the frequency domain characteristics of bearing vibration signals, highlight the fault information contained in the high-frequency region, and reduce the influence of time series distribution inconsistency between training samples and testing samples on the diagnosis accuracy. In order to further improve the spatial discrimination between different fault categories, the deformable convolution networks model is introduced to extract the spatial distribution information of fault features and improve the accuracy of fault diagnosis. Finally, two public datasets and an experimental platform data verify that the method can achieve high-precision fault diagnosis, and inverted Mel-scale Frequency cepstrum coefficients are effective in solving the problem of inconsistent distribution.

show abstract

“…12 Advances in control theory and integrated circuits lead to complex FD and FTC based on complex models. [13][14][15][16] Yan et al 17 used T-S fuzzy model to extend the linear modeling and FTC into HFV. Pourbabaee et al 18 designed the fault detection and diagnosis (FDD) method for the sensor fault in aero-engine based on Kalman filter.…”

Section: Introductionmentioning

confidence: 99%

Adaptive diagnosis and non-fragile predictive control for HFV engine with non-Gaussian uncertain output

Cheng

Gong

2023

Proceedings of the Institution of Mechanical Engineers, Part G:

View full text Add to dashboard Cite

This study presents an adaptive fault estimation and model predictive fault-tolerant control (FTC) for the hypersonic vehicle engine with non-Gaussian uncertain output jet plume. The non-Gaussian probability density function (PDF) describing the plume velocity in a stochastic system is approximated by Type II fuzzy radial basis functions. In the fault observer, the novel prey adaptive estimation method is designed for the valve faults with different amplitudes. Ultimately, this fuzzy-prey fusion adaptive observer shields perturbation and accurately estimates complex faults including incipient and intermittent faults. A predictive tolerant controller compensates for all the faults effects and non-fragile compensation factors of FTC eliminate the perturbation interference, thence the output PDF matches with the expected value. Finally, the more refined internal structure of plume output distribution replaces the local and rough valve position variables, helping this study realizes the hypersonic vehicle engine integrated refine control. Simulation result verifies the effectiveness of the proposed approaches and the superiority compared with the existing method.

show abstract

Balanced Adaptation Regularization Based Transfer Learning for Unsupervised Cross-Domain Fault Diagnosis

Cited by 47 publications

References 36 publications

Transfer learning rolling bearing fault diagnosis model based on deep feature decomposition and class-level alignment

Transfer learning rolling bearing fault diagnosis model based on deep feature decomposition and class-level alignment

Bearing fault diagnosis based on inverted Mel-scale frequency cepstral coefficients and deformable convolution networks

Adaptive diagnosis and non-fragile predictive control for HFV engine with non-Gaussian uncertain output

Contact Info

Product

Resources

About