Gaussian-Process-Regression-Based Design of Ultrawide-Band and Dual-Band CPW-FED Slot Antennas

Abstract

The applicability of Gaussian process (GP) regression as modeling tool within a genetic algorithm (GA) antenna optimization scheme is demonstrated. GP regression has recently been shown to be an efficient alternative to artificial neural networks (ANNs) when many accurate and fast estimates of antenna performance parameters, usually only obtainable from computationally intensive full-wave analyses, are required. GP regression has the important advantage that far fewer free parameters need to be determined; it furthermore is not subject to the implementation issues associated with neural nets. By using genetic algorithm optimization, two kinds of CPW-fed slot antennas were designed to operate within pre-specified frequency bands: an ultrawide-band (UWB) slot antenna with U-shaped tuning stub, and a dual-band slot loop antenna with separate T-shaped and insert tuning stubs. In both cases, the associated modeling problems were challenging, involving highly nonlinear mappings of several tunable geometry variables and frequency to S ₁₁. This was especially so for the dual-band antenna, which had to operate in precisely positioned, comparatively narrow (compared to the UWB case) frequency bands (GSM and DECT) delineated by rapid changes in |S ₁₁|. Despite using relatively few training data points given the dimensionality of the input spaces (a highly desirable model feature), the respective Gaussian process models were sufficiently accurate for the GA optimizer to yield antenna geometries that met the bandwidth specifications with ease, as was confirmed by comparison to moment-method-based simulations.