BJEST: A reverse algorithm for the real-time predictive maintenance system

Dheeraj Bansal*, David J. Evans, Barrie Jones

*Corresponding author for this work

Research output: Contribution to journalArticle

Abstract

An algorithm, to estimate the machine system parameters from the motion current signature, based upon non-linear time series techniques for use in the real-time predictive maintenance system is presented in this paper. Earlier work has introduced the use of a neural-network approach to learn non-linear mapping functions for condition monitoring systems. However, the performance of the neural-network largely depends upon the quality of the training data, and that of the quality and type of the pre-processing of the input data. A reverse algorithm called BJEST (Bansal-Jones Estimation), for estimating the machine input parameters using the motion current signature, has been designed and proven to be successful in estimating the macro-dynamics of the motion current signature. This motivated the enhancement of the predictive analysis to incorporate non-linear characteristic of the motion current signature. The results show considerable improvement in the estimation of the parameters using the enhanced BJEST algorithm due to estimation consistency, hence, improving the real-time predictive maintenance system.

Original languageEnglish
Pages (from-to)1068-1078
Number of pages11
JournalInternational Journal of Machine Tools and Manufacture
Volume46
Issue number10
DOIs
Publication statusPublished - 1 Aug 2006

Fingerprint

Neural networks
Condition monitoring
Macros
Time series
Processing
Predictive analytics

Keywords

  • Machine parameter
  • Motion current signature
  • Neural-network
  • Non-linear time series
  • Predictive maintenance
  • Surrogate data test

Cite this

Bansal, Dheeraj ; Evans, David J. ; Jones, Barrie. / BJEST : A reverse algorithm for the real-time predictive maintenance system. In: International Journal of Machine Tools and Manufacture. 2006 ; Vol. 46, No. 10. pp. 1068-1078.
@article{6bbaa60c32734c5882cf8f38a204c061,
title = "BJEST: A reverse algorithm for the real-time predictive maintenance system",
abstract = "An algorithm, to estimate the machine system parameters from the motion current signature, based upon non-linear time series techniques for use in the real-time predictive maintenance system is presented in this paper. Earlier work has introduced the use of a neural-network approach to learn non-linear mapping functions for condition monitoring systems. However, the performance of the neural-network largely depends upon the quality of the training data, and that of the quality and type of the pre-processing of the input data. A reverse algorithm called BJEST (Bansal-Jones Estimation), for estimating the machine input parameters using the motion current signature, has been designed and proven to be successful in estimating the macro-dynamics of the motion current signature. This motivated the enhancement of the predictive analysis to incorporate non-linear characteristic of the motion current signature. The results show considerable improvement in the estimation of the parameters using the enhanced BJEST algorithm due to estimation consistency, hence, improving the real-time predictive maintenance system.",
keywords = "Machine parameter, Motion current signature, Neural-network, Non-linear time series, Predictive maintenance, Surrogate data test",
author = "Dheeraj Bansal and Evans, {David J.} and Barrie Jones",
year = "2006",
month = "8",
day = "1",
doi = "10.1016/j.ijmachtools.2005.08.009",
language = "English",
volume = "46",
pages = "1068--1078",
journal = "International Journal of Machine Tools and Manufacture",
issn = "0890-6955",
publisher = "Elsevier",
number = "10",

}

BJEST : A reverse algorithm for the real-time predictive maintenance system. / Bansal, Dheeraj; Evans, David J.; Jones, Barrie.

In: International Journal of Machine Tools and Manufacture, Vol. 46, No. 10, 01.08.2006, p. 1068-1078.

Research output: Contribution to journalArticle

TY - JOUR

T1 - BJEST

T2 - A reverse algorithm for the real-time predictive maintenance system

AU - Bansal, Dheeraj

AU - Evans, David J.

AU - Jones, Barrie

PY - 2006/8/1

Y1 - 2006/8/1

N2 - An algorithm, to estimate the machine system parameters from the motion current signature, based upon non-linear time series techniques for use in the real-time predictive maintenance system is presented in this paper. Earlier work has introduced the use of a neural-network approach to learn non-linear mapping functions for condition monitoring systems. However, the performance of the neural-network largely depends upon the quality of the training data, and that of the quality and type of the pre-processing of the input data. A reverse algorithm called BJEST (Bansal-Jones Estimation), for estimating the machine input parameters using the motion current signature, has been designed and proven to be successful in estimating the macro-dynamics of the motion current signature. This motivated the enhancement of the predictive analysis to incorporate non-linear characteristic of the motion current signature. The results show considerable improvement in the estimation of the parameters using the enhanced BJEST algorithm due to estimation consistency, hence, improving the real-time predictive maintenance system.

AB - An algorithm, to estimate the machine system parameters from the motion current signature, based upon non-linear time series techniques for use in the real-time predictive maintenance system is presented in this paper. Earlier work has introduced the use of a neural-network approach to learn non-linear mapping functions for condition monitoring systems. However, the performance of the neural-network largely depends upon the quality of the training data, and that of the quality and type of the pre-processing of the input data. A reverse algorithm called BJEST (Bansal-Jones Estimation), for estimating the machine input parameters using the motion current signature, has been designed and proven to be successful in estimating the macro-dynamics of the motion current signature. This motivated the enhancement of the predictive analysis to incorporate non-linear characteristic of the motion current signature. The results show considerable improvement in the estimation of the parameters using the enhanced BJEST algorithm due to estimation consistency, hence, improving the real-time predictive maintenance system.

KW - Machine parameter

KW - Motion current signature

KW - Neural-network

KW - Non-linear time series

KW - Predictive maintenance

KW - Surrogate data test

UR - http://www.scopus.com/inward/record.url?scp=33646695692&partnerID=8YFLogxK

UR - https://www.sciencedirect.com/science/article/pii/S0890695505002208?via%3Dihub

U2 - 10.1016/j.ijmachtools.2005.08.009

DO - 10.1016/j.ijmachtools.2005.08.009

M3 - Article

AN - SCOPUS:33646695692

VL - 46

SP - 1068

EP - 1078

JO - International Journal of Machine Tools and Manufacture

JF - International Journal of Machine Tools and Manufacture

SN - 0890-6955

IS - 10

ER -