Center for Machine Learning and Intelligent Systems
About  Citation Policy  Donate a Data Set  Contact


Repository Web            Google
View ALL Data Sets

× Check out the beta version of the new UCI Machine Learning Repository we are currently testing! Contact us if you have any issues, questions, or concerns. Click here to try out the new site.

Accelerometer Data Set
Download: Data Folder, Data Set Description

Abstract: Accelerometer data from vibrations of a cooler fan with weights on its blades. It can be used for predictions, classification and other tasks that require vibration analysis, especially in engines.

Data Set Characteristics:  

Multivariate

Number of Instances:

153000

Area:

Computer

Attribute Characteristics:

Integer, Real

Number of Attributes:

5

Date Donated

2021-05-02

Associated Tasks:

Classification, Regression

Missing Values?

N/A

Number of Web Hits:

3741


Source:

Gustavo Scalabrini Sampaio
gustavo.sampaio '@' mackenzista.com.br
Postgraduate Program in Electrical Engineering and Computing, Mackenzie Presbyterian University, São Paulo, Brazil.

Arnaldo Rabello de Aguiar Vallim Filho
arnaldo.aguiar '@' mackenzie.br
Computer Science Dept., Mackenzie Presbyterian University, São Paulo, Brazil.

Leilton Santos da Silva
leilton '@' emae.com.br
EMAE—Metropolitan Company of Water & Energy, São Paulo, Brazil.

Leandro Augusto da Silva
leandroaugusto.silva '@' mackenzie.br
Postgraduate Program in Electrical Engineering and Computing, Mackenzie Presbyterian University, São Paulo, Brazil.


Donator:

Gustavo Scalabrini Sampaio


Data Set Information:

This dataset was generated for use on 'Prediction of Motor Failure Time Using An Artificial Neural Network' project (DOI: 10.3390/s19194342). A cooler fan with weights on its blades was used to generate vibrations. To this fan cooler was attached an accelerometer to collect the vibration data. With this data, motor failure time predictions were made, using an artificial neural networks. To generate three distinct vibration scenarios, the weights were distributed in three different ways: 1) 'red' - normal configuration: two weight pieces positioned on neighboring blades; 2) 'blue' - perpendicular configuration: two weight pieces positioned on blades forming a 90° angle; 3) 'green' - opposite configuration: two weight pieces positioned on opposite blades. A schematic diagram can be seen in figure 3 of the paper.

Devices used:
Akasa AK-FN059 12cm Viper cooling fan (Generate the vibrations)
MMA8452Q accelerometer (Measure vibration)

Data collection method:
17 rotation speeds were set up, ranging from 20% to 100% of the cooler maximum speed at 5% intervals; for the three weight distribution configurations in the cooler blades. Note that the Akasa AK-FN059 cooler has 1900 rpm of max rotation speed.

The vibration measurements were collected at a frequency of 20 ms for 1 min for each percentage, generating 3000 records per speed. Thus, in total, 153,000 vibration records were collected from the simulation model.


Attribute Information:

There are 5 attributes in the dataset: wconfid,pctid,x,y and z.

wconfid: Weight Configuration ID (1 - 'red' - normal configuration; 2 - 'blue' - perpendicular configuration; 3 - 'green' - opposite configuration)
pctid: Cooler Fan RPM Speed Percentage ID (20 means 20%, and so on).
x: Accelerometer x value.
y: Accelerometer y value.
z: Accelerometer z value.


Relevant Papers:

Scalabrini Sampaio, Gustavo; Vallim Filho, Arnaldo R.d.A.; Santos da Silva, Leilton; Augusto da Silva, Leandro. 2019. Prediction of Motor Failure Time Using An Artificial Neural Network. Sensors 2019, 19, 4342. DOI: 10.3390/s19194342



Citation Request:

If you have used this dataset in your work, please cite ([Web Link]):

Bib:
@article{ScalabriniSampaio2019,
doi = {10.3390/s19194342},
url = {[Web Link]},
author = {Gustavo Scalabrini Sampaio and Arnaldo Rabello de Aguiar Vallim Filho and Leilton Santos da Silva and Leandro Augusto da Silva},
title = {Prediction of Motor Failure Time Using An Artificial Neural Network},
journal = {Sensors}
year = {2019},
month = oct,
publisher = {{MDPI} {AG}},
volume = {19},
number = {19},
pages = {4342},
}


Supported By:

 In Collaboration With:

About  ||  Citation Policy  ||  Donation Policy  ||  Contact  ||  CML