An incipient fault diagnosis method based on Att-GCN for analogue circuits

Abstract

Incipient faults for analogue circuits in modern electronic systems are difficult to diagnose due to poor fault features. To address this issue, a method based on the attention weighted graph convolution network (Att-GCN) is proposed in this paper. The structural and data features of samples are jointly extracted to mine the effective characteristics from incipient faults. First, a wavelet packet energy transform and a probabilistic principal component analysis (ProbPCA) are employed to enhance the sample fault information. Then, the distance clustering method is deployed to construct the sample set into a non-European structure sample graph, where the structural features of fault samples are preserved. Second, an Att GCN, which combines the spatial-domain graph convolution network and improved self-attention mechanism, is constructed to extract the structural features and data features to obtain more effective fault information. Additionally, the multisample dropout method is introduced to reduce network overfitting in the training process. To assess the method's actual performance for fault diagnosis, experiments are carried out in the Sallen-Key bandpass filter circuit, the four-op-amp biquadratic filter circuit and the amplifier board circuit. The outcomes indicate that this method improves the incipient fault diagnosis accuracy for analogue circuits.

An Exploration into the Fault Diagnosis of Analog Circuits Using Enhanced Golden Eagle Optimized 1D-Convolutional Neural Network (CNN) with a Time-Frequency Domain Input and Attention Mechanism

“…To verify the effectiveness of the proposed ECWGEO-ATFCNN for solving analog circuit troubleshooting, this paper adopts the four-op-amp biquadratic filter circuit, a highly common and representative circuit in the field of analog circuit fault diagnosis [ 14 , 32 ], as shown in Figure 7 .…”

“…Simulations consider both hard and soft faults, and the proposed method achieves a computational time of 0.2 s and an accuracy rate of 97.4%, outperforming other techniques in various metrics. J. Yang et al [ 14 ] proposed an attention-weighted graph convolution network (Att-GCN) method for diagnosing incipient faults in analog circuits, which are challenging due to subtle fault features. The Att-GCN, combining spatial-domain graph convolution with an improved self-attention mechanism, extracts comprehensive fault features.…”

A dual-view network for fault diagnosis in rotating machinery using unbalanced data

“…The use of relationship information modeling can provide more robust additional information that integrates multiple factors, thus improving the performance of downstream tasks. There have been studies successfully applied to fault diagnosis [28,29]. Experimental results of fault diagnosis with balanced data show that relationship information modeling performs better than typical convolution in terms of feature extraction.…”

An effective method for fault diagnosis of rotating machinery under noisy environment

“…Gears and bearings are the core parts of connecting and transmitting energy in a rotating machinery system, and their working conditions are directly related to the normal operation and efficiency of mechanical equipment [1,2]. Some literature points out that the total machine failure rate caused by bearings and gears exceeds 60%.…”