Prediction of Motor Failure Time Using An Artificial Neural Network

Industry is constantly seeking ways to avoid corrective maintenance so as to reduce costs. Performing regular scheduled maintenance can help to mitigate this problem, but not necessarily in the most efficient way. In the context of condition-based maintenance, the main contributions of this work wer...

Full description

Bibliographic Details
Main Authors: Gustavo Scalabrini Sampaio, Arnaldo Rabello de Aguiar Vallim Filho, Leilton Santos da Silva, Leandro Augusto da Silva
Format: Article
Language:English
Published: MDPI AG 2019-10-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/19/19/4342
_version_ 1811187177510404096
author Gustavo Scalabrini Sampaio
Arnaldo Rabello de Aguiar Vallim Filho
Leilton Santos da Silva
Leandro Augusto da Silva
author_facet Gustavo Scalabrini Sampaio
Arnaldo Rabello de Aguiar Vallim Filho
Leilton Santos da Silva
Leandro Augusto da Silva
author_sort Gustavo Scalabrini Sampaio
collection DOAJ
description Industry is constantly seeking ways to avoid corrective maintenance so as to reduce costs. Performing regular scheduled maintenance can help to mitigate this problem, but not necessarily in the most efficient way. In the context of condition-based maintenance, the main contributions of this work were to propose a methodology to treat and transform the collected data from a vibration system that simulated a motor and to build a dataset to train and test an Artificial Neural Network capable of predicting the future condition of the equipment, pointing out when a failure can happen. To achieve this goal, a device model was built to simulate typical motor vibrations, consisting of a computer cooler fan and several magnets. Measurements were made using an accelerometer, and the data were collected and processed to produce a structured dataset. The neural network training with this dataset converged quickly and stably, while the tests performed, <i>k</i>-fold cross-validation and model generalization, presented excellent performance. The same tests were performed with other machine learning techniques, to demonstrate the effectiveness of neural networks mainly in their generalizability. The results of the work confirm that it is possible to use neural networks to perform predictive tasks in relation to the conditions of industrial equipment. This is an important area of study that helps to support the growth of smart industries.
first_indexed 2024-04-11T13:59:00Z
format Article
id doaj.art-2a36b07ad77c42d5b2771e3523c06c33
institution Directory Open Access Journal
issn 1424-8220
language English
last_indexed 2024-04-11T13:59:00Z
publishDate 2019-10-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj.art-2a36b07ad77c42d5b2771e3523c06c332022-12-22T04:20:11ZengMDPI AGSensors1424-82202019-10-011919434210.3390/s19194342s19194342Prediction of Motor Failure Time Using An Artificial Neural NetworkGustavo Scalabrini Sampaio0Arnaldo Rabello de Aguiar Vallim Filho1Leilton Santos da Silva2Leandro Augusto da Silva3Postgraduate Program in Electrical Engineering and Computing, Mackenzie Presbyterian University, Rua da Consolação, 896, Prédio 30—Consolação, São Paulo 01302-907, BrazilComputer Science Dept., Mackenzie Presbyterian University, Rua da Consolação, 896, Prédio 31—Consolação, São Paulo 01302-907, BrazilEMAE—Metropolitan Company of Water &amp; Energy, Avenida Nossa Senhora do Sabará, 5312—Vila Emir, São Paulo 04447-902, BrazilPostgraduate Program in Electrical Engineering and Computing, Mackenzie Presbyterian University, Rua da Consolação, 896, Prédio 30—Consolação, São Paulo 01302-907, BrazilIndustry is constantly seeking ways to avoid corrective maintenance so as to reduce costs. Performing regular scheduled maintenance can help to mitigate this problem, but not necessarily in the most efficient way. In the context of condition-based maintenance, the main contributions of this work were to propose a methodology to treat and transform the collected data from a vibration system that simulated a motor and to build a dataset to train and test an Artificial Neural Network capable of predicting the future condition of the equipment, pointing out when a failure can happen. To achieve this goal, a device model was built to simulate typical motor vibrations, consisting of a computer cooler fan and several magnets. Measurements were made using an accelerometer, and the data were collected and processed to produce a structured dataset. The neural network training with this dataset converged quickly and stably, while the tests performed, <i>k</i>-fold cross-validation and model generalization, presented excellent performance. The same tests were performed with other machine learning techniques, to demonstrate the effectiveness of neural networks mainly in their generalizability. The results of the work confirm that it is possible to use neural networks to perform predictive tasks in relation to the conditions of industrial equipment. This is an important area of study that helps to support the growth of smart industries.https://www.mdpi.com/1424-8220/19/19/4342predictive maintenancecondition-based maintenanceartificial neural networkvibratory analysissmart industryindustry maintenance
spellingShingle Gustavo Scalabrini Sampaio
Arnaldo Rabello de Aguiar Vallim Filho
Leilton Santos da Silva
Leandro Augusto da Silva
Prediction of Motor Failure Time Using An Artificial Neural Network
Sensors
predictive maintenance
condition-based maintenance
artificial neural network
vibratory analysis
smart industry
industry maintenance
title Prediction of Motor Failure Time Using An Artificial Neural Network
title_full Prediction of Motor Failure Time Using An Artificial Neural Network
title_fullStr Prediction of Motor Failure Time Using An Artificial Neural Network
title_full_unstemmed Prediction of Motor Failure Time Using An Artificial Neural Network
title_short Prediction of Motor Failure Time Using An Artificial Neural Network
title_sort prediction of motor failure time using an artificial neural network
topic predictive maintenance
condition-based maintenance
artificial neural network
vibratory analysis
smart industry
industry maintenance
url https://www.mdpi.com/1424-8220/19/19/4342
work_keys_str_mv AT gustavoscalabrinisampaio predictionofmotorfailuretimeusinganartificialneuralnetwork
AT arnaldorabellodeaguiarvallimfilho predictionofmotorfailuretimeusinganartificialneuralnetwork
AT leiltonsantosdasilva predictionofmotorfailuretimeusinganartificialneuralnetwork
AT leandroaugustodasilva predictionofmotorfailuretimeusinganartificialneuralnetwork