Accelerometer

Donated on 8/13/2023

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.

Dataset Characteristics

Multivariate

Subject Area

Physics and Chemistry

Associated Tasks

Classification, Regression

Feature Type

Real, Integer

# Instances

153000

# Features

5

Dataset Information

Additional 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.

Has Missing Values?

No

Introductory Paper

Prediction of Motor Failure Time Using An Artificial Neural Network

By Gustavo Scalabrini Sampaio, A. R. A. V. Filho, Leilton Santos da Silva, L. A. Silva. 2019

Published in Italian National Conference on Sensors

Variables Table

Variable NameRoleTypeDescriptionUnitsMissing Values
wconfidFeatureInteger1 - 'red' - normal configuration; 2 - 'blue' - perpendicular configuration; 3 - 'green' - opposite configurationno
pctidFeatureIntegerCooler Fan RPM Speed Percentage ID (20 means 20%, and so on)no
xFeatureContinuousAccelerometer x valueno
yFeatureContinuousAccelerometer y valueno
zFeatureContinuousAccelerometer z valueno

0 to 5 of 5

Additional Variable 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.

Reviews

There are no reviews for this dataset yet.

Login to Write a Review
Download
1 citations
6330 views

Keywords

accelerometer

Creators

Gustavo Scalabrini Sampaio

gustavo.sampaio@mackenzista.com.br

Postgraduate Program in Electrical Engineering and Computing, Mackenzie Presbyterian University

Arnaldo Rabello de Aguiar Vallim Filho

arnaldo.aguiar@mackenzie.br

Computer Science Dept., Mackenzie Presbyterian University

Leilton Santos de Silva

leilton@emae.com.br

EMAE Metropolitan Company of Water & Energy

Leandro Augusto da Silva

leandroaugusto.silva@mackenzie.br

Postgraduate Program in Electrical Engineering and Computing, Mackenzie Presbyterian University

License

By using the UCI Machine Learning Repository, you acknowledge and accept the cookies and privacy practices used by the UCI Machine Learning Repository.

Read Policy