Neural Network Inverse Modeling and Applications to Microwave Filter Design

TLDR

Training a neural network inverse model is challenging because the input‑output relationship is nonunique. The paper proposes systematic neural network inverse modeling techniques for microwave design, aiming to map electrical parameters to geometrical parameters while addressing nonuniqueness by detecting multivalued solutions. The method detects multivalued solutions, partitions training data by derivative information using a forward model, builds separate inverse models for each group, and combines them into a complete model, integrating direct inverse modeling, segmentation, derivative division, and model combining. Applied to Ku‑band circular waveguide dual‑mode pseudoelliptic bandpass filters, the methodology yields more accurate modeling results than direct inverse modeling, as confirmed by full electromagnetic simulation and measurement data.

Abstract

In this paper, systematic neural network modeling techniques are presented for microwave modeling and design using the concept of inverse modeling where the inputs to the inverse model are electrical parameters and outputs are geometrical parameters. Training the neural network inverse model directly may become difficult due to the nonuniqueness of the input-output relationship in the inverse model. We propose a new method to solve such a problem by detecting multivalued solutions in training data. The data containing multivalued solutions are divided into groups according to derivative information using a neural network forward model such that individual groups do not have the problem of multivalued solutions. Multiple inverse models are built based on divided data groups, and are then combined to form a complete model. A comprehensive modeling methodology is proposed, which includes direct inverse modeling, segmentation, derivative division, and model combining techniques. The methodology is applied to waveguide filter modeling and more accurate results are achieved compared to the direct neural network inverse modeling method. Full electromagnetic simulation and measurement results of Ku-band circular waveguide dual-mode pseudoelliptic bandpass filters are presented to demonstrate the efficiency of the proposed neural network inverse modeling methodology.