基于1DCNN(一维卷积神经网络）的机械振动故障诊断

大家好，又见面了，我是你们的朋友全栈君。

基于1DCNN(一维卷积神经网络）的机械振动故障诊断

机械振动故障诊断最为经典的还是凯斯西储实验室的轴承故障诊断，开学一周了，上次改编鸢尾花分类的代码可用，但是并不准确。开学一周重新改编了别人的一篇代码，亲测好用。不多咧咧直接放上去（基于Tensorflow2.0)(Spyder4 软件上跑的）数据集时本人把凯西轴承实验驱动端内圈损坏尺寸0.14和0.21做的二分类，数据集中0代表的0.14而1代表的0.21具体看下面最后

# -*- coding: utf-8 -*-
""" Created on Tue Sep 8 19:18:38 2020 @author: pc """
import numpy as np
import pandas as pd
import keras
from keras.models import Sequential
from keras.wrappers.scikit_learn import KerasClassifier
from keras.utils import np_utils,plot_model
from sklearn.model_selection import cross_val_score,train_test_split,KFold
from sklearn.preprocessing import LabelEncoder
from keras.models import model_from_json
import matplotlib.pyplot as plt
from sklearn.metrics import confusion_matrix
import itertools
from keras.optimizers import SGD
from keras.layers import Dense, Activation, Flatten, Convolution1D, Dropout,MaxPooling1D,BatchNormalization
from keras.models import load_model
# 载入数据
df = pd.read_csv(r'C:/Users/pc/Desktop/14改.csv')
X = np.expand_dims(df.values[:, 0:1024].astype(float), axis=2)
Y = df.values[:, 1024]
# 湿度分类编码为数字
encoder = LabelEncoder()
Y_encoded = encoder.fit_transform(Y)
Y_onehot = np_utils.to_categorical(Y_encoded)
# 划分训练集，测试集
X_train, X_test, Y_train, Y_test = train_test_split(X, Y_onehot, test_size=0.3, random_state=0)
# 定义神经网络
def baseline_model():
model = Sequential()
model.add(Convolution1D(nb_filter=16, filter_length=128,strides=1, input_shape=(1024, 1),padding="same"))
model.add(Activation('tanh'))
model.add(MaxPooling1D(2,strides=2,padding='same'))
#model.add(BatchNormalization(axis=-1, momentum=0.99, epsilon=0.001, center=True, scale=True, beta_initializer='zeros', gamma_initializer='ones', moving_mean_initializer='zeros', moving_variance_initializer='ones', beta_regularizer=None, gamma_regularizer=None, beta_constraint=None, gamma_constraint=None))
model.add(Convolution1D(32,3,padding='same'))
model.add(BatchNormalization(axis=-1, momentum=0.99, epsilon=0.001, center=True, scale=True, beta_initializer='zeros', gamma_initializer='ones', moving_mean_initializer='zeros', moving_variance_initializer='ones', beta_regularizer=None, gamma_regularizer=None, beta_constraint=None, gamma_constraint=None))
model.add(Activation('tanh'))
model.add(MaxPooling1D(2,strides=2,padding='same'))
model.add(Flatten())
model.add(Dropout(0.3))
model.add(Dense(60, activation='tanh'))
model.add(Dense(2, activation='softmax'))
print(model.summary())
sgd = SGD(lr=0.01, nesterov=True, decay=1e-6, momentum=0.9)
model.compile(loss='categorical_crossentropy',optimizer='adam', metrics=['accuracy'])
return model
# 训练分类器
estimator = KerasClassifier(build_fn=baseline_model, epochs=3, batch_size=1, verbose=1)
history=estimator.fit(X_train, Y_train)
import matplotlib.pyplot as plt
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.plot(history.history['loss'],label=u'train_loss')
#plt.plot(history.history['val_loss'],label=u'val_loss')
plt.plot(history.history['accuracy'],label=u'train_acc')
#plt.plot(history.history['val_accuracy'],label=u'val_acc')
plt.show()
# 卷积网络可视化
def visual(model, data, num_layer=1):
layer = keras.backend.function([model.layers[0].input], [model.layers[num_layer].output])
f1 = layer([data])[0]
print(f1.shape)
num = f1.shape[-1]
print(num)
plt.figure(figsize=(8, 8))
for i in range(num):
plt.subplot(np.ceil(np.sqrt(num)), np.ceil(np.sqrt(num)), i+1)
plt.imshow(f1[:, :, i] * 255, cmap='gray')
plt.axis('off')
plt.show()
# 混淆矩阵定义
def plot_confusion_matrix(cm, classes,title='Confusion matrix',cmap=plt.cm.jet):
cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
plt.imshow(cm, interpolation='nearest', cmap=cmap)
plt.rcParams['font.sans-serif'] = ['SimHei']  # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False  # 用来正常显示负号
plt.colorbar()
tick_marks = np.arange(len(classes))
plt.xticks(tick_marks,('good','bad'))
plt.yticks(tick_marks,('good','bad'))
thresh = cm.max() / 2.
for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
plt.text(j, i, '{:.2f}'.format(cm[i, j]), horizontalalignment="center",color="white" if cm[i, j] > thresh else "black")
plt.tight_layout()
plt.ylabel('真实类别')
plt.xlabel('预测类别')
plt.savefig('test_xx.png', dpi=200, bbox_inches='tight', transparent=False)
plt.show()
# 显示混淆矩阵
def plot_confuse(model, x_val, y_val):
predictions = model.predict_classes(x_val)
truelabel = y_val.argmax(axis=-1)   # 将one-hot转化为label
conf_mat = confusion_matrix(y_true=truelabel, y_pred=predictions)
plt.figure()
plot_confusion_matrix(conf_mat, range(np.max(truelabel)+1))
# 将其模型转换为json
model_json = estimator.model.to_json()
with open('C:/Users/pc/Desktop/model', 'w')as json_file:
json_file.write(model_json)# 权重不在json中,只保存网络结构
estimator.model.save_weights('C:/Users/pc/Desktop/model.json.h5')
# 加载模型用做预测
json_file = open(r'C:/Users/pc/Desktop/model')
loaded_model_json = json_file.read()
json_file.close()
loaded_model = model_from_json(loaded_model_json)
loaded_model.load_weights('C:/Users/pc/Desktop/model.json.h5')
print("loaded model from disk")
loaded_model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
# 分类准确率
print("The accuracy of the classification model:")
scores = loaded_model.evaluate(X_test, Y_test, verbose=0)
print('%s: %.2f%%' % (loaded_model.metrics_names[1], scores[1] * 100))
# 输出预测类别
predicted = loaded_model.predict(X)
predicted_label = loaded_model.predict_classes(X)
print("predicted label:\n " + str(predicted_label))
#显示混淆矩阵
plot_confuse(estimator.model, X_test, Y_test)
# 可视化卷积层
visual(estimator.model, X_train, 1)在这里插入代码片

运行代码会出来Loss拟合曲线、混淆矩阵、第一个卷积层可视化

这个训练的图像还蛮漂亮的

准确率可以通过混淆矩阵计算出来（1+1）/（1+0+1+0）=100%
即对角线相加除以每个相加
召回率100%

这个图就看不懂了，看文献里，人家振动信号训练第一个卷积层出来还是振动信号曲线，然而我做出来是这个MMP了，由于要用一个框架结构做实验写小论文，所以卷积层只给一层，感兴趣的可以参考VGG16模式改造卷积层。
下面展示用保存的模型预测未知信号

# -*- coding: utf-8 -*-
""" Created on Thu Sep 10 09:29:15 2020 @author: pc """
import numpy as np
import pandas as pd
import keras
from keras.models import Sequential
from keras.wrappers.scikit_learn import KerasClassifier
from keras.utils import np_utils,plot_model
from sklearn.model_selection import cross_val_score,train_test_split,KFold
from sklearn.preprocessing import LabelEncoder
from keras.layers import Dense, Activation, Flatten, Convolution1D, Dropout,MaxPooling1D,BatchNormalization
from keras.models import load_model
#from keras.layers import Dense,Dropout,Flatten,Conv1D,MaxPooling1D
from keras.models import model_from_json
import matplotlib.pyplot as plt
from sklearn.metrics import confusion_matrix
import itertools
from keras.optimizers import SGD
json_file = open(r'C:/Users/pc/Desktop/model')
loaded_model_json = json_file.read()
json_file.close()
loaded_model = model_from_json(loaded_model_json)
loaded_model.load_weights('C:/Users/pc/Desktop/model.json.h5')
print("loaded model from disk")
loaded_model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
# 分类准确率
#print("The accuracy of the classification model:")
#scores = loaded_model.evaluate(X_test, Y_test, verbose=0)
#print('%s: %.2f%%' % (loaded_model.metrics_names[1], scores[1] * 100))
# 输出预测类别
a= pd.read_csv(r'C:/Users/pc/Desktop/8-4.csv')
b=np.array(a)
X=b.reshape(958,1024,1)
model=Sequential()
predicted = loaded_model.predict(X)
predicted_label = loaded_model.predict_classes(X)
print("predicted label:\n " + str(predicted_label))在这里插入代码片

嗯，得劲
下面展示数据集
训练数据集https://pan.baidu.com/s/1WVChuo5d5eNLvctXpWNfEA
密码iulk
用来预测的未知代码
https://pan.baidu.com/s/1F-DYRwdicbfArHXIezMYCA
密码a672
永久有效放心用
直接下载好将两个CSV文件拖到桌面即可使用
数据集最后一行是标签，0代表0.14，1代表0.21
跑代码过程中可能会遇到的问题就是缺少插件报错误，这种情况就直接CSDN上搜索相关解决办法把
毕竟作为一个双非研究生，导师出国留学未归的情况下缺乏指导，技术有限??????
上次发完帖子有感兴趣的加我微信了，聊了半天感觉自己好牛逼哈哈哈哈哈哈哈哈哈哈
这个代码也是我无意间找到的，经过修改可以运行了
关于如何研究模型的抗噪声能力，等有机会了再写一篇CSDN，虽然已经做了，但是不太理想，故此还需要研究研究网络结构和参数调整。本人邮箱983401858@qq.com