基于多尺度卷积神经网络和注意力机制的模拟电路早期故障诊断方法OACSTPCD

The nonlinearity and tolerance of analog circuits always lead to the aliasing phenomenon among different fault modes,which increases the difficulty of fault diagnosis,especially in scenarios with incipient faults.An incipient fault diagnosis method for analog cir-cuits is proposed.Multi-scale convolutional neural network with feature attention mechanism(MS-FACNN)is developed,which can ob-tain complementary and rich diagnosis information from multi-scale components extracted by wavelet transform and identify the fault modes.Then,the efficient channel attention(ECA)module is employed to emphasize the feature regions associated with fault diagnosis and suppress the irrelevant feature regions,which can improve the representation ability of important fault features.The experimental re-sults show that the proposed method is very effective in feature extraction for fault diagnosis,and has superior classification performance for incipient faults compared with other excellent models recently proposed.