基于时频卷积神经网络的供水管道漏损识别

赖凌轩,柳景青,周一粟,李秀娟

Identification of leakage in water supply pipelines based on time-frequency convolutional neural network

Lingxuan LAI,Jingqing LIU,Yisu ZHOU,Xiujuan LI

表 3 基于短时傅里叶变换和卷积神经网络的供水管道漏损识别模型参数

Tab.3 Parameters of water supply pipeline leakage identification model based on short-time Fourier transform and convolutional neural network

层名 层参数 输出 Conv1 Kernel size=(3, 3), stride=(1, 1), padding=(1, 1) [32, 513, 17] Pool1 Kernel size=(2, 2), stride=(1, 1) [32, 256, 8] Conv2 Kernel size=(3, 3), stride=(1, 1), padding=(1, 1) [64, 256, 8] Pool2 Kernel size=(2, 2), stride=(1, 1) [64, 128, 4] FC1 — [128] Dropout Dropout=0.3 [128] FC2 — [5]