Evolutionary Design of Antennas
Antennas are necessary in everything from mobile phones to spacecraft and antenna design is very much an art form that requires years of training and experience. By combining some human expertise with Evolutionary Algorithms, antenna designs can be automatically produced that are as good or better than what just a stand-alone human expert could create. An advantage of the automated design approach is that redesign -- such as for a change in requirements -- is much easier and faster.
Evolved Antenna for NASA's Space Technology 5 Mission
Here we describe our work in using an evolutionary algorithm (EA) to automatically design an antenna for NASA's Space Technology 5 (ST5) mission. ST5 is one of NASA's New Millennium Program missions to launch multiple miniature spacecraft to test, demonstrate and flight-qualify innovative concepts and technologies in the harsh environment of space for application on future space missions.
To produce an antenna for the ST5 mission we used two EAs, each using different representations and different fitness functions, to evolve antenna designs. The EA which evolved the antenna used on the mission uses an open-ended, generative representation to construct an antenna from a genetic programming (GP) style, tree-structured encoding that allows branching in the wire forms.
Based on past experience in designing and evolving wire antennas we decided to constrain our evolutionary design to a monopole wire antenna with four identical arms. For this, we evolved one arm of the antenna and then put copies of it in each quadrant. To encode antennas we used a tree-structured representation which allowed branching and with this we evolved an antenna that met the original mission specifications.
While the antenna were undergoing space-qualification testing, the launch vehicle for the ST5 spacecraft was changed, resulting in a new, lower orbit and different antenna requirements. In total, it took us approximately four weeks to both modify our EA and evolve a new antenna for these revised mission requirements.
On March 22, 2006 at 9:04 a.m.\ E.S.T., NASA's Space Technology 5 mission successfully launched from Vandenberg Air Force Base, California on a Pegasus XL rocket. At 9:27 a.m. E.S.T. initial contact with the spacecraft was made using the evolved antennas as they passed over the McMurdo Ground Station in Antarctica. This mission lasted for three months, over which time the evolved antennas performed successfully and to the mission manager's satisfaction. This evolved antenna design has become the first computer-evolved antenna to be deployed for any application and is the first computer-evolved hardware in space.
In addition to being the first evolved hardware in space, the evolved antennas demonstrate several advantages over the conventionally designed antenna and over manual design in general. The evolutionary algorithms used were not limited to variations of previously developed antenna shapes but generated and tested thousands of completely new types of designs, many of which have unusual structures that expert antenna designers would not be likely to produce. By exploring such a wide range of designs EAs may be able to produce designs of previously unachievable performance. With the evolutionary design approach it took approximately 3 person-months of work to generate the initial evolved antennas versus 5 person-months for the conventionally designed antenna and when the mission orbit changed, with the evolutionary approach we were able to modify our algorithms and re-evolve new antennas specifically designed for the new orbit and prototype hardware in 4 weeks. The faster design cycles of an evolutionary approach results in less development costs and allows for an iterative ``what-if'' design and test approach for different scenarios. This ability to rapidly respond to changing requirements is of great use to NASA since NASA mission requirements frequently change. As computer hardware becomes increasingly more powerful and as computer modeling packages become better at simulating different design domains we expect evolutionary design systems to become more useful in a wider range of design problems and gain wider acceptance and industrial usage.
"Computer-Automated Evolution of an X-Band Antenna for NASA's Space Technology Mission" , Evolutionary Computation, MIT Press, 19:1, pp 1-23. (The official version from MIT Press is here.)(2011)
"Steady-State ALPS for Real-Valued Problems", Proc. of the Genetic and Evolutionary Computation Conference, ACM Press.(2009)
"A Steady-State Version of the Age-Layered Population Structure EA", Genetic Programming Theory & Practice VII.(2009)
"Human-competitive evolved antennas", Artificial Intelligence for Engineering Design, Analysis and Manufacturing, Cambridge University Press, 22:3, pp 235-247.(2008)
"Evolvable Hardware: Using Evolutionary Computation to Design and Optimize Hardware Systems", Computation Intelligence Magazine, Feb. 2006. IEEE Press.(2006)
"ALPS: The Age-Layered Population Structure for Reducing the Problem of Premature Convergence", Proc. of the Genetic and Evolutionary Computation Conference, ACM Press.(2006)
"Automated Antenna Design with Evolutionary Algorithms", Proc. of the AAIA Space 2006 Conference(2006)
"Evolution, Re-evolution, and Prototype of an X-Band Antenna for NASA's Space Technology 5 Mission", Sixth International Conference on Evolvable Systems: From Biology to Hardware.(2005)
"Rapid Re-evolution of an X-Band Antenna for NASA's Space Technology 5 Mission", Genetic Programming Theory Practice III, U.-M. O'Reilly and R. L. Riolo and T. Yu and B. Worzel (eds).(2005)
"Evolutionary Design of a Single-Wire Circularly-polarized X-Band Antenna for NASA's Space Technology 5 Mission", Proc. IEEE Antennas and Propagation Society Symposium.(2005)
"An Evolved Antenna for Deployment on NASA's Space Technology 5 Mission", Genetic Programming Theory and Practice II, U.-M. O'Reilly and R. L. Riolo and T. Yu and B. Worzel (eds). Chapter 18, Kluwer.(2004)
"Evolvable Hardware for Space Applications", Proc. AIAA 1st Intelligent Systems Technical Conference.(2004)
"Evolutionary Design of an X-band antenna for NASA's Space Technology 5 Mission", Proc. IEEE Antennas and Propagation Society Symposium, Vol. 3, 2313-2316.(2004)