A Classification and regression trees (CART) model of parallel structure and long‐term prediction prognosis of machine condition

V.T. Tran, Bo-Suk Yang, Andy Chit Chiow Tan

Research output: Contribution to journalArticleAcademicpeer-review

2 Citations (Scopus)

Abstract

This article presents a combined prediction model involving the parallel of classification and regression trees (CART) model, namely p-CART, and a long-term direct prediction methodology of time series techniques to predict the future stages of the machine's operating conditions. p-CART model consists of multiple CART models which are connected in parallel. Each sub-model in the p-CART is trained independently. Based on the observations, these sub-models are subsequently used to predict the future values of the machine's operating conditions separately with the same embedding dimension but different observations' indices. Finally, the predicted results of sub-models are combined to produce the final results of the predicting process. Real trending data acquired from condition monitoring routine of compressor are employed to evaluate the proposed method. A comparative study of the predicted results obtained from traditional CART and p-CART models is also carried out to appraise the prediction capability of the proposed model.
Original languageEnglish
Pages (from-to)121-132
JournalStructural health monitoring
Volume9
Issue number2
DOIs
Publication statusPublished - 2010
Externally publishedYes

Fingerprint

Condition monitoring
Compressors
Time series

Keywords

  • Machine fault prognosis
  • Long-term time series prediction
  • CART
  • Direct prediction methodology

Cite this

@article{a551fbbd4274484d811f3bbede929729,
title = "A Classification and regression trees (CART) model of parallel structure and long‐term prediction prognosis of machine condition",
abstract = "This article presents a combined prediction model involving the parallel of classification and regression trees (CART) model, namely p-CART, and a long-term direct prediction methodology of time series techniques to predict the future stages of the machine's operating conditions. p-CART model consists of multiple CART models which are connected in parallel. Each sub-model in the p-CART is trained independently. Based on the observations, these sub-models are subsequently used to predict the future values of the machine's operating conditions separately with the same embedding dimension but different observations' indices. Finally, the predicted results of sub-models are combined to produce the final results of the predicting process. Real trending data acquired from condition monitoring routine of compressor are employed to evaluate the proposed method. A comparative study of the predicted results obtained from traditional CART and p-CART models is also carried out to appraise the prediction capability of the proposed model.",
keywords = "Machine fault prognosis, Long-term time series prediction, CART, Direct prediction methodology",
author = "V.T. Tran and Bo-Suk Yang and Tan, {Andy Chit Chiow}",
year = "2010",
doi = "10.1177/1475921709352148",
language = "English",
volume = "9",
pages = "121--132",
journal = "Structural health monitoring",
issn = "1475-9217",
publisher = "SAGE Publications",
number = "2",

}

A Classification and regression trees (CART) model of parallel structure and long‐term prediction prognosis of machine condition. / Tran, V.T.; Yang, Bo-Suk ; Tan, Andy Chit Chiow.

In: Structural health monitoring, Vol. 9, No. 2, 2010, p. 121-132.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - A Classification and regression trees (CART) model of parallel structure and long‐term prediction prognosis of machine condition

AU - Tran, V.T.

AU - Yang, Bo-Suk

AU - Tan, Andy Chit Chiow

PY - 2010

Y1 - 2010

N2 - This article presents a combined prediction model involving the parallel of classification and regression trees (CART) model, namely p-CART, and a long-term direct prediction methodology of time series techniques to predict the future stages of the machine's operating conditions. p-CART model consists of multiple CART models which are connected in parallel. Each sub-model in the p-CART is trained independently. Based on the observations, these sub-models are subsequently used to predict the future values of the machine's operating conditions separately with the same embedding dimension but different observations' indices. Finally, the predicted results of sub-models are combined to produce the final results of the predicting process. Real trending data acquired from condition monitoring routine of compressor are employed to evaluate the proposed method. A comparative study of the predicted results obtained from traditional CART and p-CART models is also carried out to appraise the prediction capability of the proposed model.

AB - This article presents a combined prediction model involving the parallel of classification and regression trees (CART) model, namely p-CART, and a long-term direct prediction methodology of time series techniques to predict the future stages of the machine's operating conditions. p-CART model consists of multiple CART models which are connected in parallel. Each sub-model in the p-CART is trained independently. Based on the observations, these sub-models are subsequently used to predict the future values of the machine's operating conditions separately with the same embedding dimension but different observations' indices. Finally, the predicted results of sub-models are combined to produce the final results of the predicting process. Real trending data acquired from condition monitoring routine of compressor are employed to evaluate the proposed method. A comparative study of the predicted results obtained from traditional CART and p-CART models is also carried out to appraise the prediction capability of the proposed model.

KW - Machine fault prognosis

KW - Long-term time series prediction

KW - CART

KW - Direct prediction methodology

U2 - 10.1177/1475921709352148

DO - 10.1177/1475921709352148

M3 - Article

VL - 9

SP - 121

EP - 132

JO - Structural health monitoring

JF - Structural health monitoring

SN - 1475-9217

IS - 2

ER -