Measurement and prediction of dielectric for liquids based artificial nerve network

Effective complex permittivity measurements of liquids are important in microwave engineering, microwave material processing, microwave chemistry, and electrobiology. Artificial neural network computational modules have recently gained recognition as an unconventional and useful tool for microwave technology. Neural networks can be trained to learn the behavior of the effective complex permittivity of the liquids under irradiation of microwave. It can provide a fast and accurate answer to the task when it has learned. In this paper, we present a simple and convenient method for determining the effective complex permittivity. First, we use a resonant coaxial sensor to measure the reflection coefficients, to check its performance, the electromagnetic field distribution near the sensor and the reflection coefficient is calculated employing the frequency dependent finite difference time domain method. Second, we develop an artificial nerve network and enough simulated materials are utilized to train the networks. Finally, the trained network is employed to predict the effective complex permittivity of liquids, and compare the parameter with pure water obtained from Debye's equation. Results are presented and discussed.