Multi Fidelity Surrogates

This book investigates two types of static multi-fidelity surrogates modeling approaches, sequential multi-fidelity surrogates modeling approaches, the multi-fidelity surrogates-assisted efficient global optimization, reliability analysis, robust design optimization, and evolutionary optimization. Multi-fidelity surrogates have attracted a significant amount of attention in simulation-based design and optimization in recent years. Some real-life engineering design problems, such as prediction of angular distortion in the laser welding, optimization design of micro-aerial vehicle fuselage, and optimization design of metamaterial vibration isolator, are also provided to illustrate the ability and merits of multi-fidelity surrogates in support of engineering design. Specifically, lots of illustrative examples are adopted throughout the book to help explain the approaches in a more “hands-on” manner. This book is a useful reference for postgraduates and researchers of mechanical engineering, as well as engineers of enterprises in related fields.

This book covers some of the most popular methods in design space sampling, ensembling surrogate models, multi-fidelity surrogate model construction, surrogate model selection and validation, surrogate-based robust design optimization, and surrogate-based evolutionary optimization. Surrogate or metamodels are now frequently used in complex engineering product design to replace expensive simulations or physical experiments. They are constructed from available input parameter values and the corresponding output performance or quantities of interest (QOIs) to provide predictions based on the fitted or interpolated mathematical relationships. The book highlights a range of methods for ensembling surrogate and multi-fidelity models, which offer a good balance between surrogate modeling accuracy and building cost. A number of real-world engineering design problems, such as three-dimensional aircraft design, are also provided to illustrate the ability of surrogates for supporting complex engineering design. Lastly, illustrative examples are included throughout to help explain the approaches in a more “hands-on” manner.

Surrogate models expedite the search for promising designs by standing in for expensive design evaluations or simulations. They provide a global model of some metric of a design (such as weight, aerodynamic drag, cost, etc.), which can then be optimized efficiently. Engineering Design via Surrogate Modelling is a self-contained guide to surrogate models and their use in engineering design. The fundamentals of building, selecting, validating, searching and refining a surrogate are presented in a manner accessible to novices in the field. Figures are used liberally to explain the key concepts and clearly show the differences between the various techniques, as well as to emphasize the intuitive nature of the conceptual and mathematical reasoning behind them. More advanced and recent concepts are each presented in stand-alone chapters, allowing the reader to concentrate on material pertinent to their current design problem, and concepts are clearly demonstrated using simple design problems. This collection of advanced concepts (visualization, constraint handling, coping with noisy data, gradient-enhanced modelling, multi-fidelity analysis and multiple objectives) represents an invaluable reference manual for engineers and researchers active in the area. Engineering Design via Surrogate Modelling is complemented by a suite of Matlab codes, allowing the reader to apply all the techniques presented to their own design problems. By applying statistical modelling to engineering design, this book bridges the wide gap between the engineering and statistics communities. It will appeal to postgraduates and researchers across the academic engineering design community as well as practising design engineers. Provides an inclusive and practical guide to using surrogates in engineering design. Presents the fundamentals of building, selecting, validating, searching and refining a surrogate model. Guides the reader through the practical implementation of a surrogate-based design process using a set of case studies from real engineering design challenges. Accompanied by a companion website featuring Matlab software at http://www.wiley.com/go/forrester

This book introduces readers to an evolutionary learning approach, specifically genetic programming (GP), for production scheduling. The book is divided into six parts. In Part I, it provides an introduction to production scheduling, existing solution methods, and the GP approach to production scheduling. Characteristics of production environments, problem formulations, an abstract GP framework for production scheduling, and evaluation criteria are also presented. Part II shows various ways that GP can be employed to solve static production scheduling problems and their connections with conventional operation research methods. In turn, Part III shows how to design GP algorithms for dynamic production scheduling problems and describes advanced techniques for enhancing GP’s performance, including feature selection, surrogate modeling, and specialized genetic operators. In Part IV, the book addresses how to use heuristics to deal with multiple, potentially conflicting objectives in production scheduling problems, and presents an advanced multi-objective approach with cooperative coevolution techniques or multi-tree representations. Part V demonstrates how to use multitask learning techniques in the hyper-heuristics space for production scheduling. It also shows how surrogate techniques and assisted task selection strategies can benefit multitask learning with GP for learning heuristics in the context of production scheduling. Part VI rounds out the text with an outlook on the future. Given its scope, the book benefits scientists, engineers, researchers, practitioners, postgraduates, and undergraduates in the areas of machine learning, artificial intelligence, evolutionary computation, operations research, and industrial engineering.

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.

Computer simulation experiments are essential to modern scientific discovery, whether that be in physics, chemistry, biology, epidemiology, ecology, engineering, etc. Surrogates are meta-models of computer simulations, used to solve mathematical models that are too intricate to be worked by hand. Gaussian process (GP) regression is a supremely flexible tool for the analysis of computer simulation experiments. This book presents an applied introduction to GP regression for modelling and optimization of computer simulation experiments. Features: • Emphasis on methods, applications, and reproducibility. • R code is integrated throughout for application of the methods. • Includes more than 200 full colour figures. • Includes many exercises to supplement understanding, with separate solutions available from the author. • Supported by a website with full code available to reproduce all methods and examples. The book is primarily designed as a textbook for postgraduate students studying GP regression from mathematics, statistics, computer science, and engineering. Given the breadth of examples, it could also be used by researchers from these fields, as well as from economics, life science, social science, etc.

Computational optimization is an important paradigm with a wide range of applications. In virtually all branches of engineering and industry, we almost always try to optimize something - whether to minimize the cost and energy consumption, or to maximize profits, outputs, performance and efficiency. In many cases, this search for optimality is challenging, either because of the high computational cost of evaluating objectives and constraints, or because of the nonlinearity, multimodality, discontinuity and uncertainty of the problem functions in the real-world systems. Another complication is that most problems are often NP-hard, that is, the solution time for finding the optimum increases exponentially with the problem size. The development of efficient algorithms and specialized techniques that address these difficulties is of primary importance for contemporary engineering, science and industry. This book consists of 12 self-contained chapters, contributed from worldwide experts who are working in these exciting areas. The book strives to review and discuss the latest developments concerning optimization and modelling with a focus on methods and algorithms for computational optimization. It also covers well-chosen, real-world applications in science, engineering and industry. Main topics include derivative-free optimization, multi-objective evolutionary algorithms, surrogate-based methods, maximum simulated likelihood estimation, support vector machines, and metaheuristic algorithms. Application case studies include aerodynamic shape optimization, microwave engineering, black-box optimization, classification, economics, inventory optimization and structural optimization. This graduate level book can serve as an excellent reference for lecturers, researchers and students in computational science, engineering and industry.

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.