Applications of Neural Networks in Electromagnetics

• Authors: Christos Christodoulou;Michael Georgiopoulos
• Venue: Applications of Neural Networks in Electromagnetics
• Year: 2000

From the Book:Since the early 1990s, a plethora of electromagnetic problems have been tackled using neural networks, some more successfully than others. Because neural networks and electromagnetics are two different scientific fields, not too many electromagnetic scientists are aware of the capabilities of neural networks. This book's purpose is to bridge these two fields and make it easier for electromagnetic s experts to understand how to use neural networks in their applications of interest. To achieve this goal, this book introduces several neural network architectures and examples of how they have been used to solve a variety of electromagnetic problems. These solutions are then compared to some of the classical solutions to demonstrate the merits of using neural networks. This book contains 10 chapters. Chapter 1 is an introduction to neural networks. The reader is introduced to the basic building blocks of a neural network and its functions. It is shown how simple processors (neurons) are interconnected massively with each other (as in the human brain). Based on information in this chapter, the engineer will realize how the inherent nature of neural networks to act as distributed or massively parallel computers can be employed to speed up complex optimization problems in electromagnetics. Chapters 2 through 5 introduce some of the main neural architectures used today in electromagnetics and other applications. These architectures include the single-layer perceptron, the multilayer perceptron, the radial basis function, the Kohonen network, the ART neural networks, and the recurrent neural networks. Chapters 2 through 5 examine the basics of these architectures, their respective strengths and limitations, and the algorithms that allow us to train these architectures to perform their required tasks. These chapters conclude with an application where one of these architectures has been used with success. Several simple MATLAB examples are included to show the reader how to effectively use MATLAB commands to train and test this architecture on a problem of interest. Chapters G through 10 discuss applications in electromagnetics that are solved by using neural networks. The emphasis in Chapter 6 is on problems related to antennas. The inherent nonlinearities associated with antenna radiation patterns make antennas suitable candidates for neural networks. Several examples dealing with reflector, microstrip, and other antennas are presented. Chapter 7 deals with applications in remote sensing and target classification. In this chapter, the neural network tasks of association, pattern classification, prediction, and clustering are used primarily to classify radar targets. It is shown how measured data from scaled models can be used to train neural networks for any possible scenarios that may exist in real life. Some of these scenarios may not be possible to model by existing analytical or even numerical techniques. In Chapter 8, the high-speed capability of the neural networks is utilized in problems where real-time performance is required. Examples with adaptive array antennas for beamforming and null steering are presented and discussed in detail. These applications can be incorporated into both military and civilian systems, including GPS, cellular, and mobile communications. Chapter 9 deals primarily with the modeling of microwave devices and circuits. Here, neural networks are used as a distributed computer employed to speed up optimization problems. It is shown how neural networks can be used to achieve a more practical and interactive optimization process. And finally, in Chapter 10 it is demonstrated how neural networks can be used in conjunction with other standard methods used in electromagnetics, such as the finite element method (FEM), the finite difference method, and the method of moments. This book is intended for students, engineers, and researchers in electromagnetics with minimal background in neural networks. We hope that these readers find in this book the necessary tools and examples that can help to them in applying neural networks to some of their research problems. This book can also serve as a basic reference book for courses such as "Advanced Topics in Electromagnetics," "Applications of Neural Networks in Communications," and others.