Automated antenna design using normalized steady state genetic algorithm

A group of NASA had designed an evolved X-band antenna for NASA's Space Technology 5 (ST5) spacecraft in 2003 which then became the first evolved hardware in space. However they didn't consider too much about the efficiency of algorithm. In this paper we focus more on the algorithm. Firstly we borrow the concept of dominance to handle constraints and balance different constraints and objectives via normalization. The ultimate comparison is based on the product of these normalized values. Then we test the algorithm carefully using the 24 constrained benchmark problems on CEC2006 The experimental results show it works better than or competitive to a known effective algorithm. Finally we take ST5 antenna design as a real world test problem to verify its ability of solving real world problem. The simulation results are quite promising. Our approach is simple and straightforward, yet effective. Moreover, it has the potential of reducing parameter numbers in objective functions which are quite time consuming to be tuned In our future work we will apply the algorithm in real antenna design.