轴承故障诊断经典模型pytorch复现(一)——WDCNN

论文地址：《A New Deep Learning Model for Fault Diagnosis with Good Anti-Noise and Domain Adaptation Ability on Raw Vibration Signals》—张伟

我们要复现的论文是轴承故障诊断里比较经典的一个模型WDCNN，最近在看的很多论文都把WDCNN作为比较模型，但是只找到过tensorflow版本的源码且只有原始的WDCNN没有改进的WDCNN-AdaBN版本，而我自己又是用的pytorch，因此就打算自己复现一下。话不多说直接上代码。

WDCNN：

#!/usr/bin/Python
# -*- coding:utf-8 -*-
import torch
from torch import nn
import warnings
# ----------------------------inputsize >=28-------------------------------------------------------------------------
class WDCNN(nn.Module):
    def __init__(self, in_channel=1, out_channel=10):
        super(WDCNN, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv1d(in_channel, 16, kernel_size=64,stride=16,padding=24),  
            nn.BatchNorm1d(16),
            nn.ReLU(inplace=True),
            nn.MaxPool1d(kernel_size=2,stride=2)
            )
        self.layer2 = nn.Sequential(
            nn.Conv1d(16, 32, kernel_size=3,padding=1), 
            nn.BatchNorm1d(32),
            nn.ReLU(inplace=True),
            nn.MaxPool1d(kernel_size=2, stride=2))  
        self.layer3 = nn.Sequential(
            nn.Conv1d(32, 64, kernel_size=3,padding=1),  
            nn.BatchNorm1d(64),
            nn.ReLU(inplace=True),
            nn.MaxPool1d(kernel_size=2, stride=2)
        )  # 32, 12,12     (24-2) /2 +1
        self.layer4 = nn.Sequential(
            nn.Conv1d(64, 64, kernel_size=3,padding=1),  
            nn.BatchNorm1d(64),
            nn.ReLU(inplace=True),
            nn.MaxPool1d(kernel_size=2, stride=2)
        )  # 32, 12,12     (24-2) /2 +1
        self.layer5 = nn.Sequential(
            nn.Conv1d(64, 64, kernel_size=3),  
            nn.BatchNorm1d(64),
            nn.ReLU(inplace=True),
            nn.MaxPool1d(kernel_size=2, stride=2)
            # nn.AdaptiveMaxPool1d(4)
        )  # 32, 12,12     (24-2) /2 +1
        self.fc=nn.Sequential(
            nn.Linear(192, 100),
            nn.ReLU(inplace=True),
            nn.Linear(100, out_channel)
        )
    def forward(self, x):
        # print(x.shape)
        x = self.layer1(x) #[16 64]
        # print(x.shape)
        x = self.layer2(x)  #[32 124]
        # print(x.shape)
        x = self.layer3(x)#[64 61]
        # print(x.shape)
        x = self.layer4(x)#[64 29]
        # print(x.shape)
        x = self.layer5(x)#[64 13]
        # print(x.shape)
        x = x.view(x.size(0), -1)
        x = self.fc(x)
        return x

WDCNN在CWRU数据集上的表现,效果相当的好嘛。