Fault diagnosis of bearing based on relevance vector machine classifier with improved binary bat algorithm for feature selection and parameter optimization

In this article, fault diagnosis of bearing based on relevance vector machine classifier with improved binary bat algorithm is proposed, and the improved binary bat algorithm is used to select the appropriate features and kernel parameter of relevance vector machine. In the improved binary bat algorithm, the new velocities updating method of the bats is presented in order to ensure the decreasing of the probabilities of changing their position vectors’ elements when the position vectors’ elements of the bats are equal to the current best location’s element, and the increasing of the probabilities of changing their position vectors’ elements when the position vectors’ elements of the bats are unequal to the current best location’s element, which are helpful to strengthen the optimization ability of binary bat algorithm. The traditional relevance vector machine trained by the training samples with the unreduced features can be used to compare with the proposed improved binary bat algorithm–relevance vector machine method. The experimental results indicate that improved binary bat algorithm–relevance vector machine has a stronger fault diagnosis ability of bearing than the traditional relevance vector machine trained by the training samples with the unreduced features, and fault diagnosis of bearing based on improved binary bat algorithm–relevance vector machine is feasible.

Download Full-text

Inverse Classification Problem of Quantitative Attributes

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.44-47.3538 ◽

2010 ◽

Vol 44-47 ◽

pp. 3538-3542

Author(s):

Ai Guo Li ◽

Xin Zhou ◽

Jiu Long Zhang

Keyword(s):

Feature Selection ◽

Missing Values ◽

Main Idea ◽

Classification Problem ◽

Experimental Results ◽

Classification Algorithms ◽

Selection Algorithm ◽

Feature Selection Algorithm ◽

Class Label ◽

Training Samples

In order to overcome the disadvantage of most inverse classification algorithms address discrete attributes and can not deal with quantitative attributes. The discretization algorithms are applied to the inverse classification algorithms, and the main idea is: firstly, a group of feature attributes are selected by using feature selection algorithm; then, the quantitative attributes are discretized by using discretization algorithms, and the inverted statistics are constructed on the training samples; finally, the test samples are analyzed. Experimental results on IRIS and Ecoli datasets show that this method could find the class label effectively and estimate the missing values accurately, and the results were not worse than ISGNN and kNN.

Download Full-text

Compound feature selection and parameter optimization of ELM for fault diagnosis of rolling element bearings

ISA Transactions ◽

10.1016/j.isatra.2016.08.022 ◽

2016 ◽

Vol 65 ◽

pp. 556-566 ◽

Cited By ~ 53

Author(s):

Meng Luo ◽

Chaoshun Li ◽

Xiaoyuan Zhang ◽

Ruhai Li ◽

Xueli An

Keyword(s):

Feature Selection ◽

Fault Diagnosis ◽

Parameter Optimization ◽

Rolling Element Bearings ◽

Rolling Element

Download Full-text

Multiclass Feature Selection Via Kernel Parameter Optimization

2012 Fifth International Conference on Intelligent Computation Technology and Automation ◽

10.1109/icicta.2012.60 ◽

2012 ◽

Author(s):

Tinghua Wang ◽

Shaoyuan Xu

Keyword(s):

Feature Selection ◽

Parameter Optimization ◽

Kernel Parameter

Download Full-text

Fault Diagnosis of Bearing Based on Cauchy Kernel Relevance Vector Machine Classifier with SIWPSO

Shock and Vibration ◽

10.1155/2015/129361 ◽

2015 ◽

Vol 2015 ◽

pp. 1-7 ◽

Cited By ~ 1

Author(s):

Sheng-wei Fei ◽

Yong He

Keyword(s):

Fault Diagnosis ◽

Mechanical System ◽

Particle Swarm Optimization Algorithm ◽

Vibration Signal ◽

Relevance Vector Machine ◽

Cauchy Kernel ◽

Inertia Weight ◽

Kernel Parameter ◽

Diagnosis Method ◽

Selection Of

Bearing is an important component of mechanical system; any defects of bearing will lead to serious damage for the entire mechanical system. In this paper, Cauchy kernel relevance vector machine with stochastic inertia weight particle swarm optimization algorithm (SIWPSO-CauchyRVM) is proposed to fault diagnosis for bearing. As the selection of the Cauchy kernel parameter has a certain influence on the diagnosis result of relevance vector machine, stochastic inertia weight PSO is used to select the Cauchy kernel parameter. The relative energies of 16 wavelet coefficients of the forth layer of vibration signal of bearing can be used as the diagnosis features of bearing. The experimental results indicate that fault diagnosis method of bearing based on SIWPSO-CauchyRVM has excellent diagnosis ability.

Download Full-text

A New Fault Diagnosis Method of Bearings Based on Structural Feature Selection

Electronics ◽

10.3390/electronics8121406 ◽

2019 ◽

Vol 8 (12) ◽

pp. 1406 ◽

Cited By ~ 4

Author(s):

Wentao Mao ◽

Liyun Wang ◽

Naiqin Feng

Keyword(s):

Feature Selection ◽

Fault Diagnosis ◽

Structural Feature ◽

Group Structure ◽

Experimental Results ◽

Selection Strategy ◽

Multi Objective ◽

Fault Features ◽

Diagnosis Method ◽

Diagnosis Model

By using signal processing and statistical analysis methods simultaneously, many heterogeneous features can be produced to describe the bearings fault with more comprehensive and discriminant information. At same time, there may exist redundant or irrelevant information which will instead reduce the diagnosis performance. To solve this problem, it is necessary to conduct feature selection which tries to choose the most typical and discriminant features by evaluating their effect on fault status. However, if the structural relationship between features has not been considered well, some similar or redundant features are still probably chosen, which would introduce bias into the final diagnosis model. In this paper, a new fault diagnosis method of bearings based on structural feature selection is proposed to solve the aforementioned problem. Obeying the hypothesis that the features with strong relatedness have close coefficient distance, the proposed method aims to improve diagnosis performance via determining group structure in fault features. First, a new feature selection strategy is proposed by introducing a group identification matrix. Using this matrix, two evaluation criteria about intra-group feature correlation and inter-group feature difference are constructed by means of coefficient’s distance. Consequently, we get a multi-objective 0–1 integer programming problem by minimizing intra-group distance and maximizing inter-group distance simultaneously. Second, we use the multi-objective particle swarm optimization algorithm to solve this problem, and then determine the optimal group structure of features adaptively. Finally, a diagnosis model can be trained by support vector machine on the typical features extracted from these groups. Experimental results on four UCI datasets show the effectiveness of the proposed group feature selection strategy. Moreover, the experimental results on two bearing datasets (i.e., CWRU and IMS datasets) demonstrate that the proposed method can identify the inherent group structure in fault features, and then has better diagnosis performance compared with several state-of-the-art methods.

Download Full-text