Evolutionary learning algorithms for neural adaptive control
The book considers the problem of control in nonlinear physical systems with unknown parameters. Instead of the conventional control methods, which do not solve some tasks successfully, neural networks and genetic algorithms are proposed and employed. The book presents both a technique for modeling complex dynamical systems and a general control architecture using the previously mentioned methods. Chapter 2 gives an overview of system theory, including nonlinear and chaotic systems. Traditional methods of control and a method developed for controlling chaos are summarized here. In Chapter 3, the attitude control problem, which serves as an example throughout the book, is described. Attitude control is the process of orienting a satellite in a specified, predetermined direction. The Euler equations are derived and their chaotic behaviour is shown. This chapter is concluded with a review of numerical methods for solving ordinary differential equations. Chapter 4 reviews the basic forms of artificial neural networks and their properties. Namely, the feedforward networks and the back-propagation algorithm are presented. An algorithm for modeling dynamical systems using artificial neural networks is given in Chapter 5 and in Chapter 6 the techniques for developing neural network controllers are studied. Chapter 7 introduces genetic algorithms and genetic programming and their basic properties. These are used for the attitude control and simulation results are given. Chapters 8 and 9 are devoted to a hybrid adaptive control architecture which combines the two approaches described. The book has a very extensive list of references and the number of illustrations helping to understand the theory is impressive.
- Intelligent control. A hybrid approach based on fuzzy logic, neural networks and genetic algorithms. With a foreword by Bernard Widrow
- Neurocontrol. Learning control systems inspired by neuronal architectures and human problem solving strategies
- Soft computing for control of non-linear dynamical systems
- scientific article; zbMATH DE number 1284659
- Neurocontrol. Learning control systems inspired by neuronal architectures and human problem solving strategies
- Neural robot path planning: The maze problem
- Flight control system design using neural networks and genetic algorithms
- The effect of neuromodulations on the adaptability of evolved neurocontrollers
- scientific article; zbMATH DE number 6136565 (Why is no real title available?)
- Stabilization of the fluidic pinball with gradient-enriched machine learning control
- Neural network-based adaptive control of uncertain nonlinear systems
- Artificial intelligence control of a turbulent jet
- Linear genetic programming control for strongly nonlinear dynamics with frequency crosstalk
- Turbulence control: from model-based to machine learned
- Neural networks, fuzzy logic and genetic algorithms for intelligent control of nonlinear dynamical systems
This page was built for publication: Evolutionary learning algorithms for neural adaptive control
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4344486)
