凯斯西储大学轴承故障数据集官方网址:https://engineering.case.edu/bearingdatacenter/download-data-file
官方数据集整理版(不用挨个下了):
链接:https://pan.baidu.com/s/1RAmPFmxdsLhs_hhMMnmklA 提取码:fr5r
处理好的十分类数据集(含源文件与代码):
链接:https://pan.baidu.com/s/1_3C7e2tAb_bQbl4FcV0EMQ 提取码:7tna
十分类数据集文件说明:
1)100、108~等十个数据文件是从官方的数据集摘出来的
2)之后用matlab(classes10code.m)处理为层c10signals.mat文件
3) 再用python(datasetSample.py)将其处理为十分类数据c10classes.mat
c10classes.mat文件中包含打乱顺序的训练集(900×2048)、测试集(300×2048)
训练集(900×2048): 900个样本,每个样本包含2048个数据点。
4) 十分类数据集所含内容为如下图片:
数据格式:轴承故障数据文件为Matlab格式
每个文件包含风扇和驱动端振动数据,以及电机转速,文件中文件变量命名如下:
DE - drive end accelerometer data 驱动端振动数据
FE - fan end accelerometer data 风扇端振动数据
BA - base accelerometer data 基座振动数据
time - time series data 时间序列数据
RPM- rpm during testing 单位转每分钟 除以60则为转频
数据采集频率分别为:数据集A:在12Khz采样频率下的驱动端轴承故障数据
数据集B:在48Khz采样频率下的驱动端轴承故障数据
数据集C:在12Khz采样频率下的风扇端轴承故障数据
数据集D:以及正常的轴承数据(采样频率应该是48k的)
数据集B解读:在48Khz采样频率下的驱动端轴承故障直径又分为0.007英寸、0.014英寸、0.028英寸三种类别,每种故障下负载又分为0马力、1马力、2马力、3马力。在每种故障的每种马力下有轴承内圈故障、轴承滚动体故障、轴承外环故障(由于轴承外环位置一般比较固定,因此外环故障又分为3点钟、6点钟和12点钟三种类别)。
在48Khz采样频率下的驱动端轴承故障数据如图:
注:每个文件打开后,如IR007_1文件(48Khz的驱动端内环轴承故障数据下)打开后还会包含 BA:基座;DE:驱动端,FE:风扇端,RPM:转速四个数据,个人理解应该是在 驱动端轴承故障的情况下 包含BA,DE,FE三个不同位置传感器采集到的数据。
matlab代码:
clc;
clear all;
close all;
drive_100 = load('100.mat');
drive_108 = load('108.mat');
drive_121 = load('121.mat');
drive_133 = load('133.mat');
drive_172 = load('172.mat');
drive_188 = load('188.mat');
drive_200 = load('200.mat');
drive_212 = load('212.mat');
drive_225 = load('225.mat');
drive_237 = load('237.mat');
% de_100 = drive_100.X100_DE_time(1:121048);
de_100 = drive_100.X100_DE_time(1:4:484192);
de_108 = drive_108.X108_DE_time(1:121048);
de_121 = drive_121.X121_DE_time(1:121048);
de_133 = drive_133.X133_DE_time(1:121048);
de_172 = drive_172.X172_DE_time(1:121048);
de_188 = drive_188.X188_DE_time(1:121048);
de_200 = drive_200.X200_DE_time(1:121048);
de_212 = drive_212.X212_DE_time(1:121048);
de_225 = drive_225.X225_DE_time(1:121048);
de_237 = drive_237.X237_DE_time(1:121048);
de_signals = [de_100,de_108,de_121,de_133,de_172,de_188,de_200,de_212,de_225,de_237];
signals = de_signals.';
save('c10signals.mat','signals');
whos('-file','c10signals.mat')
python:
import numpy as np
import scipy.io as scio
from random import shuffle
def normalize(data):
'''(0,1)normalization
:param data : the object which is a 1*2048 vector to be normalized
'''
s= (data-min(data)) / (max(data)-min(data))
return s
def cut_samples(org_signals):
''' get original signals to 10*120*2048 samples, meanwhile normalize these samples
:param org_signals :a 10* 121048 matrix of ten original signals
'''
results=np.zeros(shape=(10,120,2048))
temporary_s=np.zeros(shape=(120,2048))
for i in range(10):
s=org_signals[i]
for x in range(120):
temporary_s[x]=s[1000*x:2048+1000*x]
temporary_s[x]=normalize(temporary_s[x]) #顺道对每个样本归一化
results[i]=temporary_s
return results
def make_datasets(org_samples):
'''输入10*120*2048的原始样本,输出带标签的训练集(占75%)和测试集(占25%)'''
train_x=np.zeros(shape=(10,90,2048))
train_y=np.zeros(shape=(10,90,10))
test_x=np.zeros(shape=(10,30,2048))
test_y=np.zeros(shape=(10,30,10))
for i in range(10):
s=org_samples[i]
# 打乱顺序
index_s = [a for a in range(len(s))]
shuffle(index_s)
s=s[index_s]
# 对每种类型都划分训练集和测试集
train_x[i]=s[:90]
test_x[i]=s[90:120]
# 填写标签
label = np.zeros(shape=(10,))
label[i] = 1
train_y[i, :] = label
test_y[i, :] = label
#将十种类型的训练集和测试集分别合并并打乱
x1 = train_x[0]
y1 = train_y[0]
x2 = test_x[0]
y2 = test_y[0]
for i in range(9):
x1 = np.row_stack((x1, train_x[i + 1]))
x2 = np.row_stack((x2, test_x[i + 1]))
y1 = np.row_stack((y1, train_y[i + 1]))
y2 = np.row_stack((y2, test_y[i + 1]))
index_x1= [i for i in range(len(x1))]
index_x2= [i for i in range(len(x2))]
shuffle(index_x1)
shuffle(index_x2)
x1=x1[index_x1]
y1=y1[index_x1]
x2=x2[index_x2]
y2=y2[index_x2]
return x1, y1, x2, y2 #分别代表:训练集样本,训练集标签,测试集样本,测试集标签
def get_timesteps(samples):
''' get timesteps of train_x and test_X to 10*120*31*128
:param samples : a matrix need cut to 31*128
'''
s1 = np.zeros(shape=(31, 128))
s2 = np.zeros(shape=(len(samples), 31, 128))
for i in range(len(samples)):
sample = samples[i]
for a in range(31):
s1[a]= sample[64*a:128+64*a]
s2[i]=s1
return s2
# 读取原始数据,处理后保存
dataFile= 'G://study of machine learing//deep learning//LSTM//datasets//十个原始信号.mat'
data=scio.loadmat(dataFile)
org_signals=data['signals']
org_samples=cut_samples(org_signals)
train_x, train_y, test_x, test_y=make_datasets(org_samples)
train_x= get_timesteps(train_x)
test_x= get_timesteps(test_x)
saveFile = 'G://study of machine learing//deep learning//LSTM//datasets//datasets.mat'
scio.savemat(saveFile, {'train_x':train_x, 'train_y':train_y, 'test_x':test_x, 'test_y':test_y})
引用:
利用python整理凯斯西储大学(CWRU)轴承数据,制作数据集_Victor`Wu的博客-CSDN博客