Time Series Prediction Algorithm for Intelligent Predictive Maintenance

Chin Yi Lin, Yu Ming Hsieh, Fan Tien Cheng, Hsien Cheng Huang, Muhammad Adnan

Research output: Contribution to journalArticle

Abstract

Predictive maintenance aims to find out when the target device (TD) is in the sick state and almost entering the dead state before its actual occurrence to conduct just-in-time maintenance, so as to avoid unexpected TD down time. In this way, not only tool availability and manufacturing quality are improved, but the additional cost of excessive maintenance in preventive maintenance strategy can also be reduced. Among the predictive maintenance technologies proposed by many scholars, exponential model was commonly applied to predict the remaining useful life (RUL) of TD. However, due to the algorithm limitations, when TD is about to die, whether the TD's aging feature suddenly rises or becomes smooth, the exponential model may not be able to keep up with the real-time prediction or even falsely predicts long RUL. To solve the problem of inaccurate RUL prediction, the authors propose the time series prediction (TSP) algorithm. TSP applies the time series analysis model built by information criterion to adapt to the complicated future trend of solving TD fault prediction. Also, the Pre-Alarm Module (PreAM) to make alert of immediate maintenance when a TD is likely to shut down shortly as well as the Death Correlation Index (DCI) to reveal the possibility of entering the dead state are proposed in this work. How to select the most effective predictors and adjust the predictor weights to construct high-performance prediction model are also illustrated in this letter with the tools in various industries (such as solar-cell manufacturing and machine tool industry) being the examples of the TSP algorithm.

Original languageEnglish
Article number8721101
Pages (from-to)2807-2814
Number of pages8
JournalIEEE Robotics and Automation Letters
Volume4
Issue number3
DOIs
Publication statusPublished - 2019 Jul

Fingerprint

Time Series Prediction
Time series
Maintenance
Target
Exponential Model
Predictors
Manufacturing
Industry
Life Prediction
Predict
Preventive Maintenance
Information Criterion
Prediction
Machine Tool
Time Series Analysis
Performance Prediction
Solar Cells
Performance Model
Inaccurate
Time series analysis

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Biomedical Engineering
  • Human-Computer Interaction
  • Mechanical Engineering
  • Computer Vision and Pattern Recognition
  • Computer Science Applications
  • Control and Optimization
  • Artificial Intelligence

Cite this

@article{e54353b1e90b4fc08939c6a7217837b8,
title = "Time Series Prediction Algorithm for Intelligent Predictive Maintenance",
abstract = "Predictive maintenance aims to find out when the target device (TD) is in the sick state and almost entering the dead state before its actual occurrence to conduct just-in-time maintenance, so as to avoid unexpected TD down time. In this way, not only tool availability and manufacturing quality are improved, but the additional cost of excessive maintenance in preventive maintenance strategy can also be reduced. Among the predictive maintenance technologies proposed by many scholars, exponential model was commonly applied to predict the remaining useful life (RUL) of TD. However, due to the algorithm limitations, when TD is about to die, whether the TD's aging feature suddenly rises or becomes smooth, the exponential model may not be able to keep up with the real-time prediction or even falsely predicts long RUL. To solve the problem of inaccurate RUL prediction, the authors propose the time series prediction (TSP) algorithm. TSP applies the time series analysis model built by information criterion to adapt to the complicated future trend of solving TD fault prediction. Also, the Pre-Alarm Module (PreAM) to make alert of immediate maintenance when a TD is likely to shut down shortly as well as the Death Correlation Index (DCI) to reveal the possibility of entering the dead state are proposed in this work. How to select the most effective predictors and adjust the predictor weights to construct high-performance prediction model are also illustrated in this letter with the tools in various industries (such as solar-cell manufacturing and machine tool industry) being the examples of the TSP algorithm.",
author = "Lin, {Chin Yi} and Hsieh, {Yu Ming} and Cheng, {Fan Tien} and Huang, {Hsien Cheng} and Muhammad Adnan",
year = "2019",
month = "7",
doi = "10.1109/LRA.2019.2918684",
language = "English",
volume = "4",
pages = "2807--2814",
journal = "IEEE Robotics and Automation Letters",
issn = "2377-3766",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

Time Series Prediction Algorithm for Intelligent Predictive Maintenance. / Lin, Chin Yi; Hsieh, Yu Ming; Cheng, Fan Tien; Huang, Hsien Cheng; Adnan, Muhammad.

In: IEEE Robotics and Automation Letters, Vol. 4, No. 3, 8721101, 07.2019, p. 2807-2814.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Time Series Prediction Algorithm for Intelligent Predictive Maintenance

AU - Lin, Chin Yi

AU - Hsieh, Yu Ming

AU - Cheng, Fan Tien

AU - Huang, Hsien Cheng

AU - Adnan, Muhammad

PY - 2019/7

Y1 - 2019/7

N2 - Predictive maintenance aims to find out when the target device (TD) is in the sick state and almost entering the dead state before its actual occurrence to conduct just-in-time maintenance, so as to avoid unexpected TD down time. In this way, not only tool availability and manufacturing quality are improved, but the additional cost of excessive maintenance in preventive maintenance strategy can also be reduced. Among the predictive maintenance technologies proposed by many scholars, exponential model was commonly applied to predict the remaining useful life (RUL) of TD. However, due to the algorithm limitations, when TD is about to die, whether the TD's aging feature suddenly rises or becomes smooth, the exponential model may not be able to keep up with the real-time prediction or even falsely predicts long RUL. To solve the problem of inaccurate RUL prediction, the authors propose the time series prediction (TSP) algorithm. TSP applies the time series analysis model built by information criterion to adapt to the complicated future trend of solving TD fault prediction. Also, the Pre-Alarm Module (PreAM) to make alert of immediate maintenance when a TD is likely to shut down shortly as well as the Death Correlation Index (DCI) to reveal the possibility of entering the dead state are proposed in this work. How to select the most effective predictors and adjust the predictor weights to construct high-performance prediction model are also illustrated in this letter with the tools in various industries (such as solar-cell manufacturing and machine tool industry) being the examples of the TSP algorithm.

AB - Predictive maintenance aims to find out when the target device (TD) is in the sick state and almost entering the dead state before its actual occurrence to conduct just-in-time maintenance, so as to avoid unexpected TD down time. In this way, not only tool availability and manufacturing quality are improved, but the additional cost of excessive maintenance in preventive maintenance strategy can also be reduced. Among the predictive maintenance technologies proposed by many scholars, exponential model was commonly applied to predict the remaining useful life (RUL) of TD. However, due to the algorithm limitations, when TD is about to die, whether the TD's aging feature suddenly rises or becomes smooth, the exponential model may not be able to keep up with the real-time prediction or even falsely predicts long RUL. To solve the problem of inaccurate RUL prediction, the authors propose the time series prediction (TSP) algorithm. TSP applies the time series analysis model built by information criterion to adapt to the complicated future trend of solving TD fault prediction. Also, the Pre-Alarm Module (PreAM) to make alert of immediate maintenance when a TD is likely to shut down shortly as well as the Death Correlation Index (DCI) to reveal the possibility of entering the dead state are proposed in this work. How to select the most effective predictors and adjust the predictor weights to construct high-performance prediction model are also illustrated in this letter with the tools in various industries (such as solar-cell manufacturing and machine tool industry) being the examples of the TSP algorithm.

UR - http://www.scopus.com/inward/record.url?scp=85067086222&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067086222&partnerID=8YFLogxK

U2 - 10.1109/LRA.2019.2918684

DO - 10.1109/LRA.2019.2918684

M3 - Article

AN - SCOPUS:85067086222

VL - 4

SP - 2807

EP - 2814

JO - IEEE Robotics and Automation Letters

JF - IEEE Robotics and Automation Letters

SN - 2377-3766

IS - 3

M1 - 8721101

ER -