作者: J.L. Pedreño-Molina , M. Pinzolas , J. Monzó-Cabrera
DOI: 10.1016/J.NEUCOM.2006.01.008
关键词:
摘要: In this work, a neural network-based software sensor is proposed for determining the reflection coefficient from measurements obtained by six-port reflectometer. The able to cope with nonlinearities and noise inherent measurement electronics, without needing additional calibration. To extract data calibration, new method that allows in situ calibration applied. Experimental evidence of feasibility given using simulation testbench. r 2006 Published Elsevier B.V.