Machine condition prognosis using multi-step ahead prediction and neuro-fuzzy systems

V.T. Tran, Bo-Suk Yang

Research output: Contribution to conferencePaperAcademicpeer-review

7 Downloads (Pure)

Abstract

This paper presents an approach to predict the operating conditions of machine based on adaptive neuro-fuzzy inference system (ANFIS) in association with direct prediction strategy for multi-step ahead prediction of time series techniques. In this study, the number of available observations and the number of predicted steps are initially determined by using false nearest neighbor method and auto mutual information technique, respectively. These values are subsequently utilized as inputs for prediction models to forecast the future values of the machine’s operating conditions. The performance of the proposed approach is then evaluated by using real trending data of low methane compressor. The results show that the ANFIS prediction model can track the change in machine conditions and has the potential for using as a tool to machine fault prognosis.
Original languageEnglish
Number of pages6
Publication statusPublished - 2008
EventInternational Symposium on Advanced Mechanical and Power Engineering, ISAMPE 2008 - Pukyoung National University, Busan, Korea, Republic of
Duration: 9 Oct 200812 Oct 2008

Conference

ConferenceInternational Symposium on Advanced Mechanical and Power Engineering, ISAMPE 2008
Abbreviated titleISAMPE
CountryKorea, Republic of
CityBusan
Period9/10/0812/10/08

Fingerprint

Fuzzy systems
Fuzzy inference
Compressors
Time series
Methane

Cite this

Tran, V. T., & Yang, B-S. (2008). Machine condition prognosis using multi-step ahead prediction and neuro-fuzzy systems. Paper presented at International Symposium on Advanced Mechanical and Power Engineering, ISAMPE 2008, Busan, Korea, Republic of.
Tran, V.T. ; Yang, Bo-Suk . / Machine condition prognosis using multi-step ahead prediction and neuro-fuzzy systems. Paper presented at International Symposium on Advanced Mechanical and Power Engineering, ISAMPE 2008, Busan, Korea, Republic of.6 p.
@conference{3221b96ec37249cfa0bae8e3110db8d0,
title = "Machine condition prognosis using multi-step ahead prediction and neuro-fuzzy systems",
abstract = "This paper presents an approach to predict the operating conditions of machine based on adaptive neuro-fuzzy inference system (ANFIS) in association with direct prediction strategy for multi-step ahead prediction of time series techniques. In this study, the number of available observations and the number of predicted steps are initially determined by using false nearest neighbor method and auto mutual information technique, respectively. These values are subsequently utilized as inputs for prediction models to forecast the future values of the machine’s operating conditions. The performance of the proposed approach is then evaluated by using real trending data of low methane compressor. The results show that the ANFIS prediction model can track the change in machine conditions and has the potential for using as a tool to machine fault prognosis.",
author = "V.T. Tran and Bo-Suk Yang",
year = "2008",
language = "English",
note = "International Symposium on Advanced Mechanical and Power Engineering, ISAMPE 2008, ISAMPE ; Conference date: 09-10-2008 Through 12-10-2008",

}

Tran, VT & Yang, B-S 2008, 'Machine condition prognosis using multi-step ahead prediction and neuro-fuzzy systems' Paper presented at International Symposium on Advanced Mechanical and Power Engineering, ISAMPE 2008, Busan, Korea, Republic of, 9/10/08 - 12/10/08, .

Machine condition prognosis using multi-step ahead prediction and neuro-fuzzy systems. / Tran, V.T.; Yang, Bo-Suk .

2008. Paper presented at International Symposium on Advanced Mechanical and Power Engineering, ISAMPE 2008, Busan, Korea, Republic of.

Research output: Contribution to conferencePaperAcademicpeer-review

TY - CONF

T1 - Machine condition prognosis using multi-step ahead prediction and neuro-fuzzy systems

AU - Tran, V.T.

AU - Yang, Bo-Suk

PY - 2008

Y1 - 2008

N2 - This paper presents an approach to predict the operating conditions of machine based on adaptive neuro-fuzzy inference system (ANFIS) in association with direct prediction strategy for multi-step ahead prediction of time series techniques. In this study, the number of available observations and the number of predicted steps are initially determined by using false nearest neighbor method and auto mutual information technique, respectively. These values are subsequently utilized as inputs for prediction models to forecast the future values of the machine’s operating conditions. The performance of the proposed approach is then evaluated by using real trending data of low methane compressor. The results show that the ANFIS prediction model can track the change in machine conditions and has the potential for using as a tool to machine fault prognosis.

AB - This paper presents an approach to predict the operating conditions of machine based on adaptive neuro-fuzzy inference system (ANFIS) in association with direct prediction strategy for multi-step ahead prediction of time series techniques. In this study, the number of available observations and the number of predicted steps are initially determined by using false nearest neighbor method and auto mutual information technique, respectively. These values are subsequently utilized as inputs for prediction models to forecast the future values of the machine’s operating conditions. The performance of the proposed approach is then evaluated by using real trending data of low methane compressor. The results show that the ANFIS prediction model can track the change in machine conditions and has the potential for using as a tool to machine fault prognosis.

M3 - Paper

ER -

Tran VT, Yang B-S. Machine condition prognosis using multi-step ahead prediction and neuro-fuzzy systems. 2008. Paper presented at International Symposium on Advanced Mechanical and Power Engineering, ISAMPE 2008, Busan, Korea, Republic of.