Fault Recognition of Analog Circuits Based on Ultra-Lightweight Subspace Attention Module

Abstract

In order to improve the classification accuracy of analog circuit failure modes, this paper proposes an ultra-lightweight subspace attention module (ULSAM) classification method, which combines lightweight (reducing parameters) with attention mechanism to improve convolutional neural networks (CNN) feature extraction and classification performance. This article uses depthwise separable (DWS) convolution, by decomposing the standard convolution into depthwise convolution (feature extraction) and pointwise convolution (feature aggregation). Meanwhile, the attention mechanism is applied, only one 1×1 filter is used after depthwise convolution, which can compute efficient interaction of cross-channel information, and uses the linear relationship between feature maps to avoid the use of multi-layer perceptron (MLP). The application of the failure modes of analog circuits shows that the proposed ULSAM method can realize the pattern classification of analog circuit faults more quickly and accurately.