Artificial Neural Networks for Optimal Design Parameters Prediction of Microstrip Patch Antenna with Wideband Harmonic Suppression

A compact rectangular slit-cut patch (RSP) antenna with wideband harmonic suppression (HMS) is presented and analyzed. By inserting two rectangular slits symmetrically on either side of the patch and insert-feeding with a defective ground structure, a broadband impedance bandwidth (IBW) and a wideband HMS are achieved. The proposed RSP antenna achieves a wideband HMS up to 4.62 f<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">o</inf> (f<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">o</inf> = fundamental frequency of the antenna) characteristics with simulated IBW from 2.235–3.027 GHz (30.1%). With a wideband HMS, the design antenna is compact and used for WiMAX applications at 2.5 GHz. In addition, predicting the optimal design parameters using a machine learning (ML) method evolved an artificial neural networks (ANN) algorithm.