scholarly journals A Combined Nonstationary Kriging and Support Vector Machine Method for Stochastic Eigenvalue Analysis of Brake Systems

2019 ◽  
Vol 10 (1) ◽  
pp. 245
Author(s):  
Gil-Yong Lee ◽  
Yong-Hwa Park
Keyword(s):  
Support Vector Machine ◽  
Eigenvalue Problems ◽  
Element Model ◽  
Support Vector ◽  
Machine Method ◽  
Bifurcation Phenomenon ◽  
Numerical Studies ◽  
Heterogeneous Behavior ◽  
Mode Coupling Instability ◽  
Simplified Finite Element Model

This paper presents a new metamodel approach based on nonstationary kriging and a support vector machine to efficiently predict the stochastic eigenvalue of brake systems. One of the difficulties in the mode-coupling instability induced by friction is that stochastic eigenvalues represent heterogeneous behavior due to the bifurcation phenomenon. Therefore, the stationarity assumption in kriging, where the response is correlated over the entire random input space, may not remain valid. In this paper, to address this issue, Gibb’s nonstationary kernel with step-wise hyperparameters was adopted to reflect the heterogeneity of the stochastic eigenvalues. In predicting the response for unsampled input, the support vector machine-based classification is utilized. To validate the performance, a simplified finite element model of the brake system is considered. Under various types of uncertainties, including different friction coefficients and material properties, stochastic eigenvalue problems are investigated. Through numerical studies, it is seen that the proposed method improves accuracy and robustness compared to conventional stationary kriging.

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

2017 ◽  
Vol 9 (1) ◽  
pp. 168781401668596 ◽  
Author(s):  
Fuqiang Sun ◽  
Xiaoyang Li ◽  
Haitao Liao ◽  
Xiankun Zhang
Keyword(s):  
Support Vector Machine ◽  
Least Squares ◽  
Remaining Useful Life ◽  
Lifetime Prediction ◽  
Support Vector ◽  
Machine Method ◽  
Support Vector Machine Method ◽  
Microwave Component ◽  
Useful Life ◽  
Bayesian Least Squares

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.

IMPROVEMENT OF DOSE ESTIMATION PROCESS USING ARTIFICIAL NEURAL NETWORKS

2018 ◽  
Vol 184 (1) ◽  
pp. 36-43 ◽  
Author(s):  
Gal Amit ◽  
Hanan Datz
Keyword(s):  
Neural Networks ◽  
Support Vector Machine ◽  
Artificial Neural Networks ◽  
Support Vector ◽  
Physical Parameters ◽  
Machine Method ◽  
Algorithm Performance ◽  
Artificial Neural ◽  
First Time ◽  
Automatic Algorithm

Abstract We present here for the first time a fast and reliable automatic algorithm based on artificial neural networks for the anomaly detection of a thermoluminescence dosemeter (TLD) glow curves (GCs), and compare its performance with formerly developed support vector machine method. The GC shape of TLD depends on numerous physical parameters, which may significantly affect it. When integrated into a dosimetry laboratory, this automatic algorithm can classify ‘anomalous’ (having any kind of anomaly) GCs for manual review, and ‘regular’ (acceptable) GCs for automatic analysis. The new algorithm performance is then compared with two kinds of formerly developed support vector machine classifiers—regular and weighted ones—using three different metrics. Results show an impressive accuracy rate of 97% for TLD GCs that are correctly classified to either of the classes.

Sign in / Sign up

Export Citation Format

Share Document