Adaptive Transfer Learning Based on a Two-Stream Densely Connected Residual Shrinkage Network for Transformer Fault Diagnosis over Vibration Signals

Abstract

Vibration signal analysis is an efficient online transformer fault diagnosis method for improving the stability and safety of power systems. Operation in harsh interference environments and the lack of fault samples are the most challenging aspects of transformer fault diagnosis. High-precision performance is difficult to achieve when using conventional fault diagnosis methods. Thus, this study proposes a transformer fault diagnosis method based on the adaptive transfer learning of a two-stream densely connected residual shrinkage network over vibration signals. First, novel time-frequency analysis methods (i.e., Synchrosqueezed Wavelet Transform and Synchrosqueezed Generalized S-transform) are proposed to convert vibration signals into different images, effectively expanding the samples and extracting effective features of signals. Second, a Two-stream Densely Connected Residual Shrinkage (TSDen2NetRS) network is presented to achieve a high accuracy fault diagnosis under different working conditions. Furthermore, the Residual Shrinkage layer (RS layer) is applied as a nonlinear transformation layer to the deep learning framework to remove unimportant features and enhance anti-interference performance. Lastly, an adaptive transfer learning algorithm that can automatically select the source data set by using the domain measurement method is proposed. This algorithm accelerates the training of the deep learning network and improves accuracy when the number of samples is small. Vibration experiments of transformers are conducted under different operating conditions, and their results show the effectiveness and robustness of the proposed method.

A self-adaptive DRSN-GPReLU for bearing fault diagnosis under variable working conditions

“…The DRSN employs a fundamental Resnet structure and perfectly combines the attention mechanism with the signal processing knowledge of the wavelet denoising. The DRSN has become one of the best deep learning architectures in the field of fault diagnosis [20][21][22][23]. For instance, Liu et al [21] combined a transfer learning method with the DRSN under harsh interference environments.…”

“…The DRSN has become one of the best deep learning architectures in the field of fault diagnosis [20][21][22][23]. For instance, Liu et al [21] combined a transfer learning method with the DRSN under harsh interference environments. Zhang et al [22] modified the shrinkage function of the DRSN to significantly improve the fault diagnosis accuracy of the original DRSN under strong background noise.…”

Rolling Bearing Fault Diagnosis Based on SVD-GST Combined with Vision Transformer

“…The principle of GST is based on the ideas of short-time Fourier transform (STFT) and continuous wavelet transform (CWT). Its core concept is to perform local spectral analysis of the signal at different time points [25]. The specific principles are as follows:…”

Power transformer fault diagnosis using dynamic multiscale graph modeling and M2SGCN network based on statistical fusion

“…Deep neural networks have shown greater effectiveness compared to traditional algorithms such as multilayer perceptron and support vector machine. Diverse deep learning techniques, such as CNNs [16,17], Res2Net [18,19], RNN [20], Transformer, Swin Transformer and so on, have been widely employed in fault diagnosis research.…”