Pytorch完整的1DCNN代码 故障诊断

以下是一个基于PyTorch的1D卷积神经网络（1DCNN）的完整代码，用于故障诊断：

import torch
import torch.nn as nn
import torch.optim as optim
import numpy as np

class Net(nn.Module):
    def __init__(self, num_classes=10):
        super(Net, self).__init__()
        self.conv1 = nn.Conv1d(in_channels=1, out_channels=64, kernel_size=3, stride=1, padding=1)
        self.maxpool1 = nn.MaxPool1d(kernel_size=2, stride=2)
        self.conv2 = nn.Conv1d(in_channels=64, out_channels=128, kernel_size=3, stride=1, padding=1)
        self.maxpool2 = nn.MaxPool1d(kernel_size=2, stride=2)
        self.conv3 = nn.Conv1d(in_channels=128, out_channels=256, kernel_size=3, stride=1, padding=1)
        self.maxpool3 = nn.MaxPool1d(kernel_size=2, stride=2)
        self.conv4 = nn.Conv1d(in_channels=256, out_channels=512, kernel_size=3, stride=1, padding=1)
        self.maxpool4 = nn.MaxPool1d(kernel_size=2, stride=2)
        self.fc1 = nn.Linear(in_features=512*7, out_features=1024)
        self.fc2 = nn.Linear(in_features=1024, out_features=num_classes)

    def forward(self, x):
        x = self.conv1(x)
        x = nn.functional.relu(x)
        x = self.maxpool1(x)
        x = self.conv2(x)
        x = nn.functional.relu(x)
        x = self.maxpool2(x)
        x = self.conv3(x)
        x = nn.functional.relu(x)
        x = self.maxpool3(x)
        x = self.conv4(x)
        x = nn.functional.relu(x)
        x = self.maxpool4(x)
        x = x.view(-1, 512*7)
        x = self.fc1(x)
        x = nn.functional.relu(x)
        x = self.fc2(x)
        return x

# 训练集
train_data = np.random.randn(1000, 1, 100)
train_label = np.random.randint(0, 10, size=(1000,))

# 测试集
test_data = np.random.randn(100, 1, 100)
test_label = np.random.randint(0, 10, size=(100,))

# 超参数
batch_size = 100
num_epochs = 10
learning_rate = 0.001

# 数据处理
train_data = torch.FloatTensor(train_data)
train_label = torch.LongTensor(train_label)
test_data = torch.FloatTensor(test_data)
test_label = torch.LongTensor(test_label)

# 模型初始化
model = Net(num_classes=10)

# 损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=learning_rate)

# 训练
for epoch in range(num_epochs):
    for i in range(0, len(train_data), batch_size):
        inputs = train_data[i:i+batch_size]
        labels = train_label[i:i+batch_size]
        # 前向传播
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        # 反向传播和优化
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
    print('Epoch [{}/{}], Loss: {:.4f}'.format(epoch+1, num_epochs, loss.item()))

# 测试
with torch.no_grad():
    correct = 0
    total = 0
    for i in range(0, len(test_data), batch_size):
        inputs = test_data[i:i+batch_size]
        labels = test_label[i:i+batch_size]
        outputs = model(inputs)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()
    print('Test Accuracy: {:.2f}%'.format(100 * correct / total))

这个代码中，我们定义了一个四层1D卷积神经网络，用于对故障诊断数据进行分类。我们使用了PyTorch内置的交叉熵损失函数和Adam优化器进行训练，并且在测试时输出了模型的准确率。