Performance Driven Surrogate Modeling Of High Frequency Structures

This book discusses surrogate modeling of high-frequency structures including antenna and microwave components. The focus is on constrained or performance-driven surrogates. The presented techniques aim at addressing the limitations of conventional modeling methods, pertinent to the issues of dimensionality and parameter ranges that need to be covered by the surrogate to ensure its design utility. Within performance-driven methodologies, mitigation of these problems is achieved through appropriate confinement of the model domain, focused on the regions promising from the point of view of the relevant design objectives. This enables the construction of reliable surrogates at a fraction of cost required by conventional methods, and to accomplish the modeling tasks where other techniques routinely fail. The book provides a broad selection of specific frameworks, extensively illustrated using examples of real-world microwave and antenna structures along with numerous design examples. Furthermore, the book contains introductory material on data-driven and physics-based surrogates. The book will be useful for the readers working in the area of high-frequency electronics, including microwave engineering, antenna design, microwave photonics, magnetism, especially those that utilize electromagnetic (EM) simulation models in their daily routines. Covers performance-driven and constrained modeling methods, not available in other books to date; Discusses of a wide range of practical case studies including a variety of microwave and antenna structures; Includes design applications of the presented modeling frameworks, including single- and multi-objective parametric optimization.

Contemporary high-frequency engineering design heavily relies on full-wave electromagnetic (EM) analysis. This is primarily due to its versatility and ability to account for phenomena that are important from the point of view of system performance. Unfortunately, versatility comes at the price of a high computational cost of accurate evaluation. Consequently, utilization of simulation models in the design processes is challenging although highly desirable. The aforementioned problems can be alleviated by means of surrogate modeling techniques, the most popular of which are data-driven models. Although a large variety of methods are available, they are all affected by the curse of dimensionality. This is especially pronounced in high-frequency electronics, where typical system responses are highly nonlinear. Construction of practically useful surrogates covering wide ranges of parameters and operating conditions is a considerable challenge.Surrogate Modeling for High-Frequency Design presents a selection of works representing recent advancements in surrogate modeling and their applications to high-frequency design. Some chapters provide a review of specific topics such as neural network modeling of microwave components, while others describe recent attempts to improve existing modeling methodologies. Furthermore, the book features numerous applications of surrogate modeling methodologies to design optimization and uncertainty quantification of antenna, microwave, and analog RF circuits.

This book discusses response feature technology and its applications to modeling, optimization, and computer-aided design of high-frequency structures including antenna and microwave components. By exploring the specific structure of the system outputs, feature-based approaches facilitate simulation-driven design procedures, both in terms of improving their computational efficiency and reliability. These benefits are associated with the weakly nonlinear relationship between feature point coordinates and design variables, which—in the context of optimization—leads to inherent regularization of the objective functions. The book provides an overview of the subject, a definition and extraction of characteristic points, and feature-based design problem reformulation. It also outlines a number of numerical algorithms developed to handle local, global, and multi-criterial design, surrogate modeling, as well as uncertainty quantification. The discussed frameworks are extensively illustrated using examples of real microwave and antenna structures, along with numerous design cases. Introductory material on simulation-driven design, numerical optimization, as well as behavioral and physics-based surrogate modeling is also included. The book will be useful for readers working in the area of high-frequency electronics, including microwave engineering, antenna design, microwave photonics, magnetism and especially those who utilize electromagnetic (EM) simulation models in their daily routines.

Authoritative reference on the state of the art in the field with additional coverage of important foundational concepts Advances in Electromagnetics Empowered by Artificial Intelligence and Deep Learning presents cutting-edge research advances in the rapidly growing areas in optical and RF electromagnetic device modeling, simulation, and inverse-design. The text provides a comprehensive treatment of the field on subjects ranging from fundamental theoretical principles and new technological developments to state-of-the-art device design, as well as examples encompassing a wide range of related sub-areas. The content of the book covers all-dielectric and metallodielectric optical metasurface deep learning-accelerated inverse-design, deep neural networks for inverse scattering, applications of deep learning for advanced antenna design, and other related topics. To aid in reader comprehension, each chapter contains 10-15 illustrations, including prototype photos, line graphs, and electric field plots. Contributed to by leading research groups in the field, sample topics covered in Advances in Electromagnetics Empowered by Artificial Intelligence and Deep Learning include: Optical and photonic design, including generative machine learning for photonic design and inverse design of electromagnetic systems RF and antenna design, including artificial neural networks for parametric electromagnetic modeling and optimization and analysis of uniform and non-uniform antenna arrays Inverse scattering, target classification, and other applications, including deep learning for high contrast inverse scattering of electrically large structures Advances in Electromagnetics Empowered by Artificial Intelligence and Deep Learning is a must-have resource on the topic for university faculty, graduate students, and engineers within the fields of electromagnetics, wireless communications, antenna/RF design, and photonics, as well as researchers at large defense contractors and government laboratories.

The five-volume set LNCS 14073-14077 constitutes the proceedings of the 23rd International Conference on Computational Science, ICCS 2023, held in Prague, Czech Republic, during July 3-5, 2023. The total of 188 full papers and 94 short papers presented in this book set were carefully reviewed and selected from 530 submissions. 54 full and 37 short papers were accepted to the main track; 134 full and 57 short papers were accepted to the workshops/thematic tracks. The theme for 2023, "Computation at the Cutting Edge of Science", highlights the role of Computational Science in assisting multidisciplinary research. This conference was a unique event focusing on recent developments in scalable scientific algorithms, advanced software tools; computational grids; advanced numerical methods; and novel application areas. These innovative novel models, algorithms, and tools drive new science through efficient application in physical systems, computational and systems biology, environmental systems, finance, and others.

The four-volume set LNCS 13350, 13351, 13352, and 13353 constitutes the proceedings of the 22ndt International Conference on Computational Science, ICCS 2022, held in London, UK, in June 2022.* The total of 175 full papers and 78 short papers presented in this book set were carefully reviewed and selected from 474 submissions. 169 full and 36 short papers were accepted to the main track; 120 full and 42 short papers were accepted to the workshops/ thematic tracks. *The conference was held in a hybrid format Chapter “GPU Accelerated Modelling and Forecasting for Large Time Series” is available open access under a Creative Commons Attribution 4.0 International License via link.springer.com.

Contemporary engineering design is heavily based on computer simulations. Accurate, high-fidelity simulations are used not only for design verification but, even more importantly, to adjust parameters of the system to have it meet given performance requirements. Unfortunately, accurate simulations are often computationally very expensive with evaluation times as long as hours or even days per design, making design automation using conventional methods impractical. These and other problems can be alleviated by the development and employment of so-called surrogates that reliably represent the expensive, simulation-based model of the system or device of interest but they are much more reasonable and analytically tractable. This volume features surrogate-based modeling and optimization techniques, and their applications for solving difficult and computationally expensive engineering design problems. It begins by presenting the basic concepts and formulations of the surrogate-based modeling and optimization paradigm and then discusses relevant modeling techniques, optimization algorithms and design procedures, as well as state-of-the-art developments. The chapters are self-contained with basic concepts and formulations along with applications and examples. The book will be useful to researchers in engineering and mathematics, in particular those who employ computationally heavy simulations in their design work.

The seven-volume set LNCS 12137, 12138, 12139, 12140, 12141, 12142, and 12143 constitutes the proceedings of the 20th International Conference on Computational Science, ICCS 2020, held in Amsterdam, The Netherlands, in June 2020.* The total of 101 papers and 248 workshop papers presented in this book set were carefully reviewed and selected from 719 submissions (230 submissions to the main track and 489 submissions to the workshops). The papers were organized in topical sections named: Part I: ICCS Main Track Part II: ICCS Main Track Part III: Track of Advances in High-Performance Computational Earth Sciences: Applications and Frameworks; Track of Agent-Based Simulations, Adaptive Algorithms and Solvers; Track of Applications of Computational Methods in Artificial Intelligence and Machine Learning; Track of Biomedical and Bioinformatics Challenges for Computer Science Part IV: Track of Classifier Learning from Difficult Data; Track of Complex Social Systems through the Lens of Computational Science; Track of Computational Health; Track of Computational Methods for Emerging Problems in (Dis-)Information Analysis Part V: Track of Computational Optimization, Modelling and Simulation; Track of Computational Science in IoT and Smart Systems; Track of Computer Graphics, Image Processing and Artificial Intelligence Part VI: Track of Data Driven Computational Sciences; Track of Machine Learning and Data Assimilation for Dynamical Systems; Track of Meshfree Methods in Computational Sciences; Track of Multiscale Modelling and Simulation; Track of Quantum Computing Workshop Part VII: Track of Simulations of Flow and Transport: Modeling, Algorithms and Computation; Track of Smart Systems: Bringing Together Computer Vision, Sensor Networks and Machine Learning; Track of Software Engineering for Computational Science; Track of Solving Problems with Uncertainties; Track of Teaching Computational Science; Track of UNcErtainty QUantIficatiOn for ComputationAl modeLs *The conference was canceled due to the COVID-19 pandemic.