### Abstract

Rapid and accurate lifetime prediction of critical components in a system is important to maintaining the system's reliable operation. To this end, many lifetime prediction methods have been developed to handle various failure-related data collected in different situations. Among these methods, machine learning and Bayesian updating are the most popular ones. In this article, a Bayesian least-squares support vector machine method that combines least-squares support vector machine with Bayesian inference is developed for predicting the remaining useful life of a microwave component. A degradation model describing the change in the component's power gain over time is developed, and the point and interval remaining useful life estimates are obtained considering a predefined failure threshold. In our case study, the radial basis function neural network approach is also implemented for comparison purposes. The results indicate that the Bayesian least-squares support vector machine method is more precise and stable in predicting the remaining useful life of this type of components.

Language | English (US) |
---|---|

Journal | Advances in Mechanical Engineering |

Volume | 9 |

Issue number | 1 |

DOIs | |

State | Published - Jan 1 2017 |

Externally published | Yes |

### Fingerprint

### Keywords

- Bayesian least-squares support vector machine
- confidence bands
- microwave component
- Remaining useful life

### ASJC Scopus subject areas

- Mechanical Engineering

### Cite this

*Advances in Mechanical Engineering*,

*9*(1). DOI: 10.1177/1687814016685963

**A Bayesian least-squares support vector machine method for predicting the remaining useful life of a microwave component.** / Sun, Fuqiang; Li, Xiaoyang; Liao, Haitao; Zhang, Xiankun.

Research output: Contribution to journal › Article

*Advances in Mechanical Engineering*, vol 9, no. 1. DOI: 10.1177/1687814016685963

}

TY - JOUR

T1 - A Bayesian least-squares support vector machine method for predicting the remaining useful life of a microwave component

AU - Sun,Fuqiang

AU - Li,Xiaoyang

AU - Liao,Haitao

AU - Zhang,Xiankun

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Rapid and accurate lifetime prediction of critical components in a system is important to maintaining the system's reliable operation. To this end, many lifetime prediction methods have been developed to handle various failure-related data collected in different situations. Among these methods, machine learning and Bayesian updating are the most popular ones. In this article, a Bayesian least-squares support vector machine method that combines least-squares support vector machine with Bayesian inference is developed for predicting the remaining useful life of a microwave component. A degradation model describing the change in the component's power gain over time is developed, and the point and interval remaining useful life estimates are obtained considering a predefined failure threshold. In our case study, the radial basis function neural network approach is also implemented for comparison purposes. The results indicate that the Bayesian least-squares support vector machine method is more precise and stable in predicting the remaining useful life of this type of components.

AB - Rapid and accurate lifetime prediction of critical components in a system is important to maintaining the system's reliable operation. To this end, many lifetime prediction methods have been developed to handle various failure-related data collected in different situations. Among these methods, machine learning and Bayesian updating are the most popular ones. In this article, a Bayesian least-squares support vector machine method that combines least-squares support vector machine with Bayesian inference is developed for predicting the remaining useful life of a microwave component. A degradation model describing the change in the component's power gain over time is developed, and the point and interval remaining useful life estimates are obtained considering a predefined failure threshold. In our case study, the radial basis function neural network approach is also implemented for comparison purposes. The results indicate that the Bayesian least-squares support vector machine method is more precise and stable in predicting the remaining useful life of this type of components.

KW - Bayesian least-squares support vector machine

KW - confidence bands

KW - microwave component

KW - Remaining useful life

UR - http://www.scopus.com/inward/record.url?scp=85013634106&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85013634106&partnerID=8YFLogxK

U2 - 10.1177/1687814016685963

DO - 10.1177/1687814016685963

M3 - Article

VL - 9

JO - Advances in Mechanical Engineering

T2 - Advances in Mechanical Engineering

JF - Advances in Mechanical Engineering

SN - 1687-8132

IS - 1

ER -