The book presents a detailed and unified treatment of the theory and applications of optimization applied to control and modeling, focusing on nature-inspired optimization algorithms to optimally tune the parameters of linear and nonlinear controllers and models, with emphasis on tower crane systems and other representative applications.
Classical and Modern Optimization Techniques Applied to Control and Modeling combines classical and modern approaches to optimization, based on the authors’ experience in the field, and presents in a unified structure the essential aspects of optimization in control and modeling from a control engineer’s point of view. It covers linear and nonlinear controllers, and neural networks based on reinforcement learning are considered and analyzed because of the need to reduce the complexity of the controllers and their design so that they can be practical to implement as low-cost automation solutions. The chapters are designed to quickly make the concepts of optimization, control, reinforcement learning, and neural networks understandable to readers with limited experience.
This book is intended for a broad audience, including undergraduate and graduate students, engineers (designers, practitioners, and researchers), and anyone facing challenging control problems.
The book presents a detailed and unified treatment of the theory and applications of optimization applied to control and modeling, focusing on nature-inspired optimization algorithms to optimally tune the parameters of linear and nonlinear controllers and models, with emphasis on tower crane systems and other representative applications.
Classical and Modern Optimization Techniques Applied to Control and Modeling combines classical and modern approaches to optimization, based on the authors’ experience in the field, and presents in a unified structure the essential aspects of optimization in control and modeling from a control engineer’s point of view. It covers linear and nonlinear controllers, and neural networks based on reinforcement learning are considered and analyzed because of the need to reduce the complexity of the controllers and their design so that they can be practical to implement as low-cost automation solutions. The chapters are designed to quickly make the concepts of optimization, control, reinforcement learning, and neural networks understandable to readers with limited experience.
This book is intended for a broad audience, including undergraduate and graduate students, engineers (designers, practitioners, and researchers), and anyone facing challenging control problems.
Classical and Modern Optimization Techniques Applied to Control and Modeling
362
Classical and Modern Optimization Techniques Applied to Control and Modeling
362Related collections and offers
