Haroldo Fraga de Campos Velho – författare

This book presents a methodology based on inverse problems for use in solutions for fault diagnosis in control systems, combining tools from mathematics, physics, computational and mathematical modeling, optimization and computational intelligence. This methodology, known as fault diagnosis – inverse problem methodology or FD-IPM, unifies the results of several years of work of the authors in the fields of fault detection and isolation (FDI), inverse problems and optimization. The book clearly and systematically presents the main ideas, concepts and results obtained in recent years. By formulating fault diagnosis as an inverse problem, and by solving it using metaheuristics, the authors offer researchers and students a fresh, interdisciplinary perspective for problem solving in these fields. Graduate courses in engineering, applied mathematics and computing also benefit from this work.

This book offers a careful selection of studies in optimization techniques based on artificial intelligence, applied to inverse problems in radiative transfer. In this book, the reader will find an in-depth exploration of heuristic optimization methods, each meticulously described and accompanied by historical context and natural process analogies.From simulated annealing and genetic algorithms to artificial neural networks, ant colony optimization, and particle swarms, this volume presents a wide range of heuristic methods. Additional approaches such as generalized extreme optimization, particle collision, differential evolution, Luus-Jaakola, and firefly algorithms are also discussed, providing a rich repertoire of tools for tackling challenging problems.While the applications showcased primarily focus on radiative transfer, their potential extends to various domains, particularly nonlinear and large-scale problems where traditional deterministic methods fall short. With clear and comprehensive presentations, this book empowers readers to adapt each method to their specific needs. Furthermore, practical examples of classical optimization problems and application suggestions are included to enhance your understanding.This book is suitable to any researcher or practitioner whose interests lie on optimization techniques based in artificial intelligence and bio-inspired algorithms, in fields like Applied Mathematics, Engineering, Computing, and cross-disciplinary areas.

This book offers a careful selection of studies in optimization techniques based on artificial intelligence, applied to inverse problems in radiative transfer. In this book, the reader will find an in-depth exploration of heuristic optimization methods, each meticulously described and accompanied by historical context and natural process analogies.From simulated annealing and genetic algorithms to artificial neural networks, ant colony optimization, and particle swarms, this volume presents a wide range of heuristic methods. Additional approaches such as generalized extreme optimization, particle collision, differential evolution, Luus-Jaakola, and firefly algorithms are also discussed, providing a rich repertoire of tools for tackling challenging problems.While the applications showcased primarily focus on radiative transfer, their potential extends to various domains, particularly nonlinear and large-scale problems where traditional deterministic methods fall short. With clear and comprehensive presentations, this book empowers readers to adapt each method to their specific needs. Furthermore, practical examples of classical optimization problems and application suggestions are included to enhance your understanding.This book is suitable to any researcher or practitioner whose interests lie on optimization techniques based in artificial intelligence and bio-inspired algorithms, in fields like Applied Mathematics, Engineering, Computing, and cross-disciplinary areas.

This book offers a careful selection of studies in optimization techniques based on artificial intelligence, applied to inverse problems in radiative transfer. In this book, the reader will find an in-depth exploration of heuristic optimization methods, each meticulously described and accompanied by historical context and natural process analogies.From simulated annealing and genetic algorithms to artificial neural networks, ant colony optimization, and particle swarms, this volume presents a wide range of heuristic methods. Additional approaches such as generalized extreme optimization, particle collision, differential evolution, Luus-Jaakola, and firefly algorithms are also discussed, providing a rich repertoire of tools for tackling challenging problems.While the applications showcased primarily focus on radiative transfer, their potential extends to various domains, particularly nonlinear and large-scale problems where traditional deterministic methods fall short. With clear and comprehensive presentations, this book empowers readers to adapt each method to their specific needs. Furthermore, practical examples of classical optimization problems and application suggestions are included to enhance your understanding.This book is suitable to any researcher or practitioner whose interests lie on optimization techniques based in artificial intelligence and bio-inspired algorithms, in fields like Applied Mathematics, Engineering, Computing, and cross-disciplinary areas.

This book presents a methodology based on inverse problems for use in solutions for fault diagnosis in control systems, combining tools from mathematics, physics, computational and mathematical modeling, optimization and computational intelligence. This methodology, known as fault diagnosis – inverse problem methodology or FD-IPM, unifies the results of several years of work of the authors in the fields of fault detection and isolation (FDI), inverse problems and optimization. The book clearly and systematically presents the main ideas, concepts and results obtained in recent years. By formulating fault diagnosis as an inverse problem, and by solving it using metaheuristics, the authors offer researchers and students a fresh, interdisciplinary perspective for problem solving in these fields. Graduate courses in engineering, applied mathematics and computing also benefit from this work.