Applications of Artificial Neural Network Techniques in Microwave Filter Modeling, Optimization and Design

Abstract

This paper reviews state-of-the-art microwave fllter modeling, optimization and design methods using artiflcial neural network (ANN) technique. Innovative methodologies of using ANN in microwave fllter analysis and synthesis are discussed. Various ANN structures including wavelet and radial basis function have been utilized for this purpose. ANN also flnds application in fllter yield prediction and optimization. The results from difierent work demon- strate that ANN technique can reduce the cost of computation signiflcantly and thus can produce fast and accurate result compared to the conventional electromagnetic (EM) methods. DOI: 10.2529/PIERS060907172141 Microwave fllters are widely used in satellite and ground based communication systems. The full wave EM solvers have been utilized to design these kinds of fllters for a long time. Usually several simulations are required to meet the fllter speciflcations which takes considerable amount of time. In order to achieve flrst pass success with only minor tuning and adjustment in the manufacturing process, precise electromagnetic modeling is an essential condition. The design procedure usually involves iterating the design parameters until the flnal fllter response is realized. The whole process needs to be repeated even with a slight change in any of the design speciflcations. The modeling time increases as the fllter order increases. With the increasing complexity of wireless and satellite communication hardware, there is a need for faster method to design this kind of fllters. Artiflcial neural network (ANN) or simply neural network (NN) has been proven to be a fast and efiective means of modeling complex electromagnetic devices. It has been recognized as a powerful tool for predicting device behavior for which no mathematical model is available or the device has not been analyzed properly yet. ANN can be trained to capture arbitrary input-output relationship to any degree of accuracy. Once a model is developed it can be used over and over again. The trained model delivers the output parameters very quickly. This avoids any EM simulation where a simple change in the physical dimension requires a complete simulation. For these attractive qualities, ANN has been applied to difierent areas of engineering and biomedical. While the present state of the art neural network modeling technique for EM modeling and optimization is available in detail in (1{3), it is beyond the scope of this paper. This paper reviews the ANN techniques dealing with microwave fllter. Waveguide cavity fllters are very popular in microwave applications. Several results have been reported using neural network techniques to model cavity fllters including E-plane metal-insert fllter (4), rectangular waveguide H-plane iris bandpass fllter (5{8), dual mode pseudo elliptic fllter (9), cylindrical posts in waveguide fllter (10) and etc. The simplest form of modeling is the direct approach where the geometrical parameters are related to its frequency response. Response of a fllter is sampled at difierent frequency points to generate the training data. Result shows that ANN can provide accurate design parameters and after learning phase the computational cost is lower than the one associated with full wave model analysis (4). In a similar work the performance of fllter obtained from the ANN was much better than obtained from parametric curve and faster than flnite element method (FEM) analysis (5). Simpler structure or lower order fllter is feasible to realize the whole model in a single NN model. For higher order fllter several assumptions and simpliflcations are required to lower the number of NN inputs. Filter can be modeled by segmentation flnite element (SFE) method and using ANN (6). Filter structure was segmented into small regions connected by arbitrary cross section and then the smaller sections were analyzed separately. The generalized scattering matrix (GSM) was computed by FEM and the response of the complete circuit was obtained by connecting the smaller sections in proper order. In general the optimization of microwave circuits is time consuming. To attain a circuit response by analytical method is too slow. Therefore, ANN based analytical models were used. The method was applied to a three-cavity fllter. The response of the fllter rigorously found