Feature selection by merging sequential bidirectional search into relevance vector machine in condition monitoring

Kui Zhang, Yu Dong, Andrew Ball

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

For more accurate fault detection and diagnosis, there is an increasing trend to use a large number of sensors and to collect data at high frequency. This inevitably produces large-scale data and causes difficulties in fault classification. Actually, the classification methods are simply intractable when applied to high-dimensional condition monitoring data. In order to solve the problem, engineers have to resort to complicated feature extraction methods to reduce the dimensionality of data. However, the features transformed by the methods cannot be understood by the engineers due to a loss of the original engineering meaning. In this paper, other forms of dimensionality reduction technique(feature selection methods) are employed to identify machinery condition, based only on frequency spectrum data. Feature selection methods are usually divided into three main types: filter, wrapper and embedded methods. Most studies are mainly focused on the first two types, whilst the development and application of the embedded feature selection methods are very limited. This paper attempts to explore a novel embedded method. The method is formed by merging a sequential bidirectional search algorithm into scale parameters tuning within a kernel function in the relevance vector machine. To demonstrate the potential for applying the method to machinery fault diagnosis, the method is implemented to rolling bearing experimental data. The results obtained by using the method are consistent with the theoretical interpretation, proving that this algorithm has important engineering significance in revealing the correlation between the faults and relevant frequency features. The proposed method is a theoretical extension of relevance vector machine, and provides an effective solution to detect the fault-related frequency components with high efficiency.

LanguageEnglish
Pages1248-1253
Number of pages6
JournalChinese Journal of Mechanical Engineering (English Edition)
Volume28
Issue number6
DOIs
Publication statusPublished - 1 Nov 2015

Fingerprint

Condition monitoring
Merging
Feature extraction
Failure analysis
Machinery
Bearings (structural)
Engineers
Fault detection
Tuning
Sensors

Cite this

@article{36147c76563f4480a88039722b7354bc,
title = "Feature selection by merging sequential bidirectional search into relevance vector machine in condition monitoring",
abstract = "For more accurate fault detection and diagnosis, there is an increasing trend to use a large number of sensors and to collect data at high frequency. This inevitably produces large-scale data and causes difficulties in fault classification. Actually, the classification methods are simply intractable when applied to high-dimensional condition monitoring data. In order to solve the problem, engineers have to resort to complicated feature extraction methods to reduce the dimensionality of data. However, the features transformed by the methods cannot be understood by the engineers due to a loss of the original engineering meaning. In this paper, other forms of dimensionality reduction technique(feature selection methods) are employed to identify machinery condition, based only on frequency spectrum data. Feature selection methods are usually divided into three main types: filter, wrapper and embedded methods. Most studies are mainly focused on the first two types, whilst the development and application of the embedded feature selection methods are very limited. This paper attempts to explore a novel embedded method. The method is formed by merging a sequential bidirectional search algorithm into scale parameters tuning within a kernel function in the relevance vector machine. To demonstrate the potential for applying the method to machinery fault diagnosis, the method is implemented to rolling bearing experimental data. The results obtained by using the method are consistent with the theoretical interpretation, proving that this algorithm has important engineering significance in revealing the correlation between the faults and relevant frequency features. The proposed method is a theoretical extension of relevance vector machine, and provides an effective solution to detect the fault-related frequency components with high efficiency.",
keywords = "Fault diagnosis, Feature selection, Relevance vector machine, Sequential bidirectional search",
author = "Kui Zhang and Yu Dong and Andrew Ball",
year = "2015",
month = "11",
day = "1",
doi = "10.3901/CJME.2015.0706.087",
language = "English",
volume = "28",
pages = "1248--1253",
journal = "Chinese Journal of Mechanical Engineering (English Edition)",
issn = "1000-9345",
publisher = "Springer Verlag",
number = "6",

}

TY - JOUR

T1 - Feature selection by merging sequential bidirectional search into relevance vector machine in condition monitoring

AU - Zhang, Kui

AU - Dong, Yu

AU - Ball, Andrew

PY - 2015/11/1

Y1 - 2015/11/1

N2 - For more accurate fault detection and diagnosis, there is an increasing trend to use a large number of sensors and to collect data at high frequency. This inevitably produces large-scale data and causes difficulties in fault classification. Actually, the classification methods are simply intractable when applied to high-dimensional condition monitoring data. In order to solve the problem, engineers have to resort to complicated feature extraction methods to reduce the dimensionality of data. However, the features transformed by the methods cannot be understood by the engineers due to a loss of the original engineering meaning. In this paper, other forms of dimensionality reduction technique(feature selection methods) are employed to identify machinery condition, based only on frequency spectrum data. Feature selection methods are usually divided into three main types: filter, wrapper and embedded methods. Most studies are mainly focused on the first two types, whilst the development and application of the embedded feature selection methods are very limited. This paper attempts to explore a novel embedded method. The method is formed by merging a sequential bidirectional search algorithm into scale parameters tuning within a kernel function in the relevance vector machine. To demonstrate the potential for applying the method to machinery fault diagnosis, the method is implemented to rolling bearing experimental data. The results obtained by using the method are consistent with the theoretical interpretation, proving that this algorithm has important engineering significance in revealing the correlation between the faults and relevant frequency features. The proposed method is a theoretical extension of relevance vector machine, and provides an effective solution to detect the fault-related frequency components with high efficiency.

AB - For more accurate fault detection and diagnosis, there is an increasing trend to use a large number of sensors and to collect data at high frequency. This inevitably produces large-scale data and causes difficulties in fault classification. Actually, the classification methods are simply intractable when applied to high-dimensional condition monitoring data. In order to solve the problem, engineers have to resort to complicated feature extraction methods to reduce the dimensionality of data. However, the features transformed by the methods cannot be understood by the engineers due to a loss of the original engineering meaning. In this paper, other forms of dimensionality reduction technique(feature selection methods) are employed to identify machinery condition, based only on frequency spectrum data. Feature selection methods are usually divided into three main types: filter, wrapper and embedded methods. Most studies are mainly focused on the first two types, whilst the development and application of the embedded feature selection methods are very limited. This paper attempts to explore a novel embedded method. The method is formed by merging a sequential bidirectional search algorithm into scale parameters tuning within a kernel function in the relevance vector machine. To demonstrate the potential for applying the method to machinery fault diagnosis, the method is implemented to rolling bearing experimental data. The results obtained by using the method are consistent with the theoretical interpretation, proving that this algorithm has important engineering significance in revealing the correlation between the faults and relevant frequency features. The proposed method is a theoretical extension of relevance vector machine, and provides an effective solution to detect the fault-related frequency components with high efficiency.

KW - Fault diagnosis

KW - Feature selection

KW - Relevance vector machine

KW - Sequential bidirectional search

UR - http://www.scopus.com/inward/record.url?scp=84949936584&partnerID=8YFLogxK

U2 - 10.3901/CJME.2015.0706.087

DO - 10.3901/CJME.2015.0706.087

M3 - Article

VL - 28

SP - 1248

EP - 1253

JO - Chinese Journal of Mechanical Engineering (English Edition)

T2 - Chinese Journal of Mechanical Engineering (English Edition)

JF - Chinese Journal of Mechanical Engineering (English Edition)

SN - 1000-9345

IS - 6

ER -