Surrogate modeling of impedance matching transformers by means of<scp>variable‐fidelity</scp>electromagnetic simulations and nested<scp>cokriging</scp>

Pietrenko‐Dabrowska, Anna; Koziel, Slawomir

doi:10.1002/mmce.22268

Cited by 29 publications

(14 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A typical way of incorporating low-fidelity data is through appropriate correction (e.g., space mapping [40], adaptive response correction [75], manifold mapping [76]). Another approach is to enable reduced-cost parameter space exploration within machine learning frameworks [49], or to exploit model correlations in variable-fidelity modelling methods such as co-kriging [77]. Perhaps the most serious inconvenience associated with these methods is a need to properly set up (or construct for that matter) the low-fidelity model.…”

Section: Multi-resolution Em Simulationsmentioning

confidence: 99%

Reduced-Cost Microwave Design Closure by Multi-Resolution EM Simulations and Knowledge-Based Model Management

2021

Self Cite

View full text Add to dashboard Cite

Parameter adjustment through numerical optimization has become a commonplace of contemporary microwave engineering. Although circuit theory methods are ubiquitous in the development of microwave components, the initial designs obtained with such tools have to be further tuned to improve the system performance. This is particularly pertinent to miniaturized structures, where the cross-coupling effects cannot be adequately accounted for using equivalent networks. For the sake of reliability, design closure is normally performed using full-wave electromagnetic (EM) simulation models, which entails considerable computational expenses, often impractically excessive. Available mitigation techniques include acceleration of the conventional (e.g., gradient-based) routines using adjoint sensitivities or sparse sensitivity updates, surrogate-assisted and machine learning algorithms, the latter often combined with nature-inspired procedures. Another alternative is the employment of variable-fidelity simulations (e.g., space mapping, co-kriging), which is most often limited to two levels of accuracy (coarse/fine). This work discusses an EM model management approach coupled with trust-region gradient-based routine, which exploits problem-specific knowledge for continuous (multi-level) modification of the discretization density of the microwave structure at hand in the course of the optimization run. The optimization process is launched at the lowest discretization level, thereby allowing for low-cost exploitation of the knowledge about the device under study. Subsequently, based on the convergence indicators, the model fidelity is gradually increased to ensure reliability. The simulation fidelity selection is governed by the algorithm convergence indicators. Computational speedup (i.e., reduction in the number of EM simulations required by the optimization process to converge) is achieved by maintaining low resolution in the initial stages of the optimization run, whereas design quality is secured by eventually switching to the high-fidelity model when close to concluding the process. Numerical verification is carried out using two microstrip circuits, a dual-band power divider and a dual-band branch-line coupler, with the average savings of almost sixty percent when compared to single-fidelity optimization.

show abstract

Section: Multi-resolution Em Simulationsmentioning

confidence: 99%

Reduced-Cost Microwave Design Closure by Multi-Resolution EM Simulations and Knowledge-Based Model Management

2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the context of modeling of highfrequency structures, it is more suitable for handling components that exhibit wideband characteristics where the discrepancies between the models of various fidelities are mostly vertical (i.e., concern the response levels rather than frequency shifts). In [83] and [88], the nested kriging was combined with co-kriging, which is rather straightforward: the first-level model is constructed in a traditional manner (cf. Section II), whereas the final surrogate is a co-kriging one, using a limited number of high-fidelity data.…”

Section: E Nested Kriging With Variable-fidelity Modelsmentioning

confidence: 99%

Recent Advances in High Frequency Modeling by Means of Domain Confinement and Nested Kriging

Koziel

Pietrenko‐Dabrowska

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Development of modern high-frequency components and circuits is heavily based on full-wave electromagnetic (EM) simulation tools. Some phenomena, although important from the point of view of the system performance, e.g., EM cross-coupling effects, feed radiation in antenna arrays, substrate anisotropy, cannot be adequately accounted for using simpler means such as equivalent network representations. Consequently, the involvement of EM analysis, especially for tuning of geometry parameters, has become imperative in high-frequency electronics. Notwithstanding, excessive computational costs associated with massive full-wave simulations required by these procedures and even more by tasks such as uncertainty quantification or multi-criterial optimization, constitute a practical bottleneck. Repetitive evaluations of a structure can be facilitated by the use of fast replacement models (surrogates). Among available methods, approximation models are by far the most popular due to their flexibility and accessibility. Unfortunately, surrogate modeling of high-frequency structures is hindered by the curse of dimensionality and nonlinearity of system responses, primarily frequency characteristics. The recently proposed performance-driven techniques attempt to address this issue by appropriate confinement of the model domain to focus the modeling process only on the relevant part of the parameter space, i.e., containing the designs that are of high quality from the point of view the assumed performance figures. The nested kriging framework is perhaps the most advanced of these methods and allows for constructing reliable surrogates over broad ranges of the system parameters and operating conditions. This paper summarizes the recent developments of the technique, including the basic formulation and several advancements aiming at the improvement of the surrogate predictive power or lowering the computational cost of training data acquisition. These include the incorporation of sensitivity data, as well as dimensionality reduction through principal component analysis. The problem of uniform data sampling in confined domains is also discussed. Our considerations are comprehensively illustrated using several examples of antennas and microwave circuits.

show abstract

“…Some popular methods of this category include space mapping 39 , cognition-driven design 40 , or various response correction methods 41 , 42 . A related class of techniques are those based on variable- and multi-fidelity simulations, e.g., co-kriging 43 , multi-fidelity procedures 44 , as well as optimization frameworks involving supervised learning 45 , 46 .…”

Section: Introductionmentioning

confidence: 99%

Design specification management with automated decision-making for reliable optimization of miniaturized microwave components

Kozieł

Pietrenko‐Dabrowska

Płotka

2022

Sci Rep

Self Cite

View full text Add to dashboard Cite

The employment of numerical optimization techniques for parameter tuning of microwave components has nowadays become a commonplace. In pursuit of reliability, it is most often carried out at the level of full-wave electromagnetic (EM) simulation models, incurring considerable computational expenses. In the case of miniaturized microstrip circuits, densely arranged layouts with strong cross-coupling effects make EM-driven tuning imperative to achieve the optimum performance. The process is even more challenging due to a typically large number of geometry parameters, and the lack of reasonable initial designs. The latter often encourages the use of global search procedures, which may be prohibitively expensive. In this paper, a novel automated framework for reliable optimization of miniaturized microwave components is proposed. Our methodology is based on design specification management, where the performance requirements imposed on the system are temporarily relaxed if the current design is unlikely to be improved (e.g., due to being away from the target operating frequency). The specifications are re-adjusted at each iteration of the algorithm, and eventually converge to their original values. Using two examples of compact microstrip couplers and a power divider, the presented technique is demonstrated to significantly improve the efficacy of local search routines under challenging design scenarios.

show abstract

Surrogate modeling of impedance matching transformers by means ofvariable‐fidelityelectromagnetic simulations and nestedcokriging

Cited by 29 publications

References 46 publications

Reduced-Cost Microwave Design Closure by Multi-Resolution EM Simulations and Knowledge-Based Model Management

Reduced-Cost Microwave Design Closure by Multi-Resolution EM Simulations and Knowledge-Based Model Management

Recent Advances in High Frequency Modeling by Means of Domain Confinement and Nested Kriging

Design specification management with automated decision-making for reliable optimization of miniaturized microwave components

Contact Info

Product

Resources

About