inception10滚动轴承故障诊断数据集代码

以下是使用TensorFlow和Keras实现的Inception10模型来进行滚动轴承故障诊断的代码。

首先，我们需要加载数据集。可以在此处下载数据集：https://data.mendeley.com/datasets/bxk2sdx3wy/1

import numpy as np
import os

# 加载数据集
def load_dataset():
    dataset_path = "data/"
    train_X = np.load(os.path.join(dataset_path, "train_X.npy"))
    train_y = np.load(os.path.join(dataset_path, "train_y.npy"))
    test_X = np.load(os.path.join(dataset_path, "test_X.npy"))
    test_y = np.load(os.path.join(dataset_path, "test_y.npy"))
    return train_X, train_y, test_X, test_y

接下来，我们需要构建Inception10模型。在这里，我们使用了Inception模块，这是Google在2014年提出的一种卷积神经网络结构。

from tensorflow.keras import layers, models

# 构建Inception模块
def inception_module(inputs, filters):
    path1 = layers.Conv2D(filters=filters[0], kernel_size=1, activation="relu")(inputs)

    path2 = layers.Conv2D(filters=filters[1], kernel_size=1, activation="relu")(inputs)
    path2 = layers.Conv2D(filters=filters[2], kernel_size=3, padding="same", activation="relu")(path2)

    path3 = layers.Conv2D(filters=filters[3], kernel_size=1, activation="relu")(inputs)
    path3 = layers.Conv2D(filters=filters[4], kernel_size=5, padding="same", activation="relu")(path3)

    path4 = layers.MaxPooling2D(pool_size=3, strides=1, padding="same")(inputs)
    path4 = layers.Conv2D(filters=filters[5], kernel_size=1, activation="relu")(path4)

    return layers.concatenate([path1, path2, path3, path4])

# 构建Inception10模型
def build_inception10(input_shape, num_classes):
    inputs = layers.Input(shape=input_shape)

    x = layers.Conv2D(filters=64, kernel_size=7, strides=2, padding="same", activation="relu")(inputs)
    x = layers.MaxPooling2D(pool_size=3, strides=2, padding="same")(x)

    x = layers.Conv2D(filters=64, kernel_size=1, activation="relu")(x)
    x = layers.Conv2D(filters=192, kernel_size=3, padding="same", activation="relu")(x)
    x = layers.MaxPooling2D(pool_size=3, strides=2, padding="same")(x)

    x = inception_module(x, filters=[64, 96, 128, 16, 32, 32])
    x = inception_module(x, filters=[128, 128, 192, 32, 96, 64])
    x = layers.MaxPooling2D(pool_size=3, strides=2, padding="same")(x)

    x = inception_module(x, filters=[192, 96, 208, 16, 48, 64])
    x = inception_module(x, filters=[160, 112, 224, 24, 64, 64])
    x = inception_module(x, filters=[128, 128, 256, 24, 64, 64])
    x = inception_module(x, filters=[112, 144, 288, 32, 64, 64])
    x = inception_module(x, filters=[256, 160, 320, 32, 128, 128])
    x = layers.MaxPooling2D(pool_size=3, strides=2, padding="same")(x)

    x = inception_module(x, filters=[256, 160, 320, 32, 128, 128])
    x = inception_module(x, filters=[384, 192, 384, 48, 128, 128])

    x = layers.GlobalAveragePooling2D()(x)
    x = layers.Dropout(0.4)(x)

    outputs = layers.Dense(num_classes, activation="softmax")(x)

    return models.Model(inputs, outputs)

然后，我们可以定义一些超参数并训练模型。

from tensorflow.keras import optimizers, losses, metrics
from tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping

# 定义超参数
input_shape = (64, 64, 1)
num_classes = 4
batch_size = 128
epochs = 50

# 加载数据集
train_X, train_y, test_X, test_y = load_dataset()

# 构建模型
model = build_inception10(input_shape, num_classes)

# 编译模型
model.compile(optimizer=optimizers.Adam(), loss=losses.sparse_categorical_crossentropy, metrics=[metrics.sparse_categorical_accuracy])

# 定义回调函数
callbacks = [
    ModelCheckpoint("inception10.h5", save_best_only=True),
    EarlyStopping(patience=5, restore_best_weights=True)
]

# 训练模型
history = model.fit(train_X, train_y, batch_size=batch_size, epochs=epochs, validation_data=(test_X, test_y), callbacks=callbacks)

# 评估模型
loss, accuracy = model.evaluate(test_X, test_y)
print("Test loss: {:.4f}, accuracy: {:.4f}".format(loss, accuracy))

最后，我们可以使用模型进行预测。

# 使用模型进行预测
predictions = model.predict(test_X)

# 输出预测结果
print(predictions)