A Novel Design of a Robust Ten-Port Microwave Reflectometer With Autonomous Calibration by Using Neural Networks

Abstract

Abstract-In this study, a novel ten-port waveguide microwave sensor is designed, implemented, calibrated and tested in order to obtain the reflection coefficient magnitude and phase. This reflectometer is based on the well known six-port structure but the number of detectors has been increased to eight in order to improve the sampling procedure of the standing wave present within the waveguide. In addition, a learning method based on neural networks' usage has been implemented for autonomous calibration from the data collected by a vector network analyzer. An automated procedure consisting of a moving sample within a multimode cavity has enabled different reflection coefficients to be obtained. Neural networks have been employed in order to learn the relationship between the actual reflection parameter and the acquired signals from eight power detectors. This novel device has been calibrated with a neural architecture based on radial basis functions and the error of device measurements has been analyzed. This new design and the incorporated neural network calibration allow one to avoid problems caused by fault or nonlinearity of the detectors, and to get robustness, flexibility and adaptability characteristics for the presented device.

Usage of an automated three‐stub water‐loaded impedance generator for RBF calibration of a waveguide ten‐port reflectometer

“…The ten-port reflectometer has been studied in detail in previous works [7][8]. As in previous cases, it consists of a standard WR-340 waveguide section (4.34 cm x 8.68 cm) that contains eight equally spaced coaxial probes inserted at the center of the wide wall of the waveguide.…”

“…The distance between each coaxial port is selected as function of the TE 10 wavelength, resulting in 22 mm, with separations of 35 mm from both ends. The final length of the ten-port is 222 mm [7][8]. Figure 2 shows a scheme with the dimensions of the proposed impedance generator.…”

“…A conventional Radial Basis Function (RBF) neural network has been used in order to calibrate the ten-port reflectometer due to its simplicity [7]. In this case, the input vector is formed by the eight voltage values provided by the power detectors whereas the output of the network estimates S 11 .…”

“…Due to several effects, such as noise and the non-linearity characteristics of the power detectors, a calibration procedure has to be carried out for the six-port working frequencies to ensure the accuracy of the measurements. Recently, a waveguide ten-port reflectometer has been presented [7][8] as an alternative to six-port configuration. This new design and the incorporated neural network calibration allow to avoid problems caused by the non-linearity of the detectors, and to get robustness, flexibility and adaptability characteristics for this device.…”

“…For instance, the ten-port configuration is able to keep on measuring even when some of the detectors are broken. Additionally, it offers phase measurements without needing phase detection [7][8]. However, the main drawback of the calibration process based in neural networks is that many calibration data must be produced in order to achieve good calibration levels.…”