A novel neural-based approach for design of microstrip filters

This paper presents an intelligent design methodology of microstrip filters in which a dynamic neural network model based on Bayesian Regularization Back-Propagation (BRBP) learning algorithm is used. In this approach, a Low-Pass Filter (LPF) composed of multiple open stubs, and stepped impedance resonators is initially designed for which an Artificial Neural Network (ANN) is trained to improve the performance of the filter. The predicted and measured results of the filter verify the effectiveness of the presented method, suggesting an excellent in and out-of-band performance. According to the measurement, the filter has a very small transition band from 2.087 to 2.399 GHz with 3 and 40 dB attenuation points, respectively, leading to a sharp roll-off rate of 118.6 dB/GHz. In addition the optimized filter has an ultra-wide stopband, extending from 2.399 to 15.01 GHz with attenuation level of 22 dB are The overall size of the fabricated filter is only 0.190λg×0.094λg, where λg is the guided wavelength at 3 dB cut-off frequency (2.087 GHz). A performance comparison with some of the recent published LPFs presented, showing the superiority of the proposed filter.