Analysis of Parameter Variability in an Integrated Wireless Power Transfer System via Partial Least-Squares Regression

Abstract

This paper deals with the application of the partial least squares (PLS) regression to the uncertainty quantification of an integrated wireless power transfer with 30 random variables. It considers the development of surrogate models using a limited set of training samples in order to estimate statistical quantities of the converter efficiency with a relatively low computational cost compared to the standard brute force Monte Carlo (MC) simulation. The strength, the performance and the features of the proposed modeling approach are then compared with the ones of an advanced probabilistic surrogate model combining the Leastsquares Support Vector Machine (LS-SVM) and the Gaussian Process (GP) regression. The MC simulation is considered as reference.

Uncertainty Quantification and Optimal Design of EV-WPT System Efficiency based on Adaptive Gaussian Process Regression

“…The high walking strategy depends on t ≤ T /4, the belly walking strategy depends on t ⩽ T /2, and t > T /4. The position update equation for the encircling phase is shown in (13):…”

“…Trinchero et al [12] examined leastsquares support vector machine (LS-SVM) regression and its optimized form for WPT efficiency UQ and demonstrated that LS-SVM regression, based on kernel technology, can effectively solve the high-dimensional spatial nonlinear UQ problem, but the hyperparameter selection lacks a priori knowledge and cannot be realized based on a rigorous mathematical basis. Larbi et al [13] employed LS-SVM regression, combined with Gaussian process regression (GPR), for WPT system UQ. Based on the quantification results, the authors used partial least squares regression for the sensitivity analysis of the parameters and system efficiency optimization but obtained poor prediction results for the regions with a low probability of occurrence.…”

Comparative Study of Surrogate Modeling Methods for Signal Integrity and Microwave Circuit Applications

“…PLS fixes this limitation, it iteratively projects input and output onto the most significant components but the projection happens in a leapfrog scheme so that there is cross-information exchange between input and output while doing projections. Process details can be found in [29], [30]. After L projections, we obtain an L-component decomposition of X and Y , V , U ∈ R N ×L and P ∈ R d×L , Q ∈ R q×L .…”

“…[28] uses Gaussian Process (GP) building a surrogate model to study the behavior of a bandpass filter under the variation of its design parameters. Also solving the forward problem, [29]- [32] use Partial Least-square Regression (PLS) and Leastsquare Support Vector Machine (LS-SVM) to perform not only predictions but sensitivity anlysis on design problems with as many as 30 design parameters. In addition, realizing that LS-SVM has a deterministic nature, [31] proposes to combine LS-SVM and GP to create a fully statistical model which, in addition to predictive modeling, provides a confidence measure for its predictions.…”

Uncertainty Quantification of Electromagnetic Exposure of Human Body with Medical Aortic Valve Stent Implants under an EV-WPT Device

“…At present, research on the uncertainty quantification of human electromagnetic exposure to EV-WPT-containing medical implants has not been conducted. Many, uncertainty quantification methods, such as deep learning [20], partial least squares regression [21], and adaptive sparse polynomial chaos expansion (PCE) [22], have been applied to optimize the transmission efficiency design of EV-WPT devices. The research on the uncertainty quantification of human electromagnetic exposure mainly includes the use of optimized random greedy PCE in the uncertainty quantification of the electromagnetic exposure indicators of the human body and multiple organs under different exposure scenarios [23].…”