This paper investigates the application of support vector machine to the modeling of high-speed interconnects with largely varying and/or highly uncertain design parameters. The proposed method relies on a robust and well-established mathematical framework, yielding accurate surrogates of complex dynamical systems. An identification procedure based on the observation of a small set of system responses allows generating compact parametric relations, which can be used for design optimization and/or stochastic analysis. The feasibility and strength of the method are demonstrated based on a benchmark function and on the statistical assessment of a realistic printed circuit board interconnect, highlighting the main features and benefits of this technique over state-of-the-art solutions. Emphasis is given to the effects of the initial sample size and of input noise on the model estimation.

In this paper, we adopt the so-called sparse polynomial chaos metamodel for the uncertainty quantification in the framework of high-dimensional problems. This metamodel is used to model a realistic electronic bus structure with a large number of uncertain input parameters such as those related to microstrip line geometries. It aims at estimating quantities of interest, such as statistical moments, probability density functions, and provides sensitivity analysis of a response. It drastically reduces the model computational cost with regard to brute force Monte Carlo (MC) simulation. The method presents a good performance and is validated in comparison with MC simulation.

This article presents a new noniterative inverse modeling technique based on machine learning regression and its applications to microwave design optimization. The proposed inverse model accepts the high-dimensional S-parameters computed at many frequency points as the input and estimates the optimal geometrical/physical parameters of the microwave component as its output. The least-squares support vector machine regression is combined with the principal component analysis to simultaneously overcome both the high-dimensional input space and ill-posed challenges of the inverse modeling. We also propose a new empirical method to find the optimum number of principal components (i.e., the compression level) for each example in an automated way. This makes our proposed model general and easy to use compared with the existing data-driven inverse modeling techniques. The inverse model is trained by a set of scattering parameters computed via a 2-D/3-D solver for few configurations of the geometrical parameters. The feasibility and the accuracy of the proposed optimization scheme are investigated by comparing its predictions with the corresponding optimal configuration estimated via a commercial solver.

In this paper, a stochastic modeling method is presented for the analysis of variability effects, induced by the manufacturing process, on interconnect structures terminated by general nonlinear loads. The technique is based on the solution of the pertinent stochastic Telegrapher's equations in time domain by means of the well-established stochastic Galerkin method, but now allows, for the first time in the literature, the inclusion of loads with arbitrary I-V characteristics at the terminals of the lines. The transient solution is obtained by combining the stochastic Galerkin method with a finite-difference time-domain scheme. The proposed technique is validated and illustrated with a meaningful application example, demonstrating its accuracy and efficiency.

In this article, machine learning (ML) metamodels have been developed in order to predict the per-unit-length parameters of hybrid copper–graphene on-chip interconnects based on their structural geometry and layout. ML metamodels within the context of this article include artificial neural networks, support vector machines (SVMs), and least-square SVMs. The salient feature of all these ML metamodels is that they exploit the prior knowledge of the p.u.l. parameters of the interconnects obtained from cheap empirical models to reduce the number of expensive full-wave electromagnetic (EM) simulations required to extract the training data. Thus, the proposed ML metamodels are referred to as prior knowledge-based machine learning (PKBML) metamodels. The PKBML metamodels offer the same accuracy as conventional ML metamodels trained exclusively by full-wave EM solver data, but at the expense of far smaller training time costs. In this article, detailed comparative analysis of the proposed PKBML metamodels have been performed using multiple numerical examples.

This letter addresses the simulation of the steady-state response of switching power converters. The proposed approach is based on the interpretation of the voltage and current variables of a periodically switched linear circuit in terms of a series expansion and on the generation of augmented time-invariant constitutive relations of the circuit elements. The circuit solution is obtained from an augmented time-invariant nodal equation generated from topological information and circuit inspection only. The feasibility and strength of the approach are demonstrated on a dc-dc boost converter.