Nature-based Antenna Design: Interpolating the Input Impedance of Fractal Dipole Antennas via a Genetic Algorithm Trained Neural Network

Over the years engineers have often looked to nature for inspiration when seeking new and innovative ways to solve complex design problems. For instance, the development of fractal geometry was originally inspired by studying the shapes of natural objects such as trees, leaves, ferns, terrain, coastlines, snowflakes, and cloud boundaries. Neural Networks (NN) have been developed to mimic the human decision-making process. Similarly, Genetic Algorithms (GA) are based on the Darwinian notion of survival of the fittest and evolution. In fact the origin of several commonly used analysis techniques of modern day electromagnetics may be traced to processes found in the natural world. This paper will focus on developing a powerful nature-based antenna engineering design tool that combines together for the first time aspects of fractal geometry, neural networks and genetic algorithms. More specifically, an efficient method will be introduced for interpolating the driving point impedance of fractal dipole antennas using a genetic algorithm trained neural network.