2018
DOI: 10.1016/j.jsv.2018.03.032
|View full text |Cite
|
Sign up to set email alerts
|

Variable predictive model class discrimination using novel predictive models and adaptive feature selection for bearing fault identification

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
5

Citation Types

0
12
0

Year Published

2018
2018
2024
2024

Publication Types

Select...
10

Relationship

0
10

Authors

Journals

citations
Cited by 27 publications
(12 citation statements)
references
References 27 publications
0
12
0
Order By: Relevance
“…This method makes RBFNN have excellent recognition performance for bearing fault diagnosis by DE/BBO. Tang et al (2018) proposed an adaptive feature selection method to reduce the dimensions and multiple correlations of the feature space. The method was based on variable predictive model class discrimination (VPMCD), affinity propagation (AP) clustering, RReliefF, sequential forward search, and was combined with RBFNN to construct a new fault diagnosis model variable predictive model class discrimination-radial basis function (VPMCD-RBF) for fault diagnosis of rolling bearings.…”
Section: Introductionmentioning
confidence: 99%
“…This method makes RBFNN have excellent recognition performance for bearing fault diagnosis by DE/BBO. Tang et al (2018) proposed an adaptive feature selection method to reduce the dimensions and multiple correlations of the feature space. The method was based on variable predictive model class discrimination (VPMCD), affinity propagation (AP) clustering, RReliefF, sequential forward search, and was combined with RBFNN to construct a new fault diagnosis model variable predictive model class discrimination-radial basis function (VPMCD-RBF) for fault diagnosis of rolling bearings.…”
Section: Introductionmentioning
confidence: 99%
“…With timefrequency domain analysis methods, the evolvement of the local frequency components can be obtained [18] [19]. There are many time-frequency domain analysis methods, such as wavelet analysis [20] [21] [22], empirical mode decomposition [23] [24], ReliefF algorithm [25] and other methods. Fault identification is also called fault pattern recognition.…”
Section: Introductionmentioning
confidence: 99%
“…In general, feature selection algorithms include filter models, wrapper models, and embedded models. 19,20,22,23,34,35 Filter models evaluate the general characteristics of the training data to select a feature subset without employing any learning algorithm; thus, it has less computation cost. 23 Nevertheless, it might obtain the feature subsets irrelevant to classes.…”
Section: Introductionmentioning
confidence: 99%