Elman Recurrent Neural Network-based Digital Electrical Measuring Unit for Transmitter Antenna Underground Imaging System

Abstract

Underground imaging equipment is a non-destructive technology for scanning of subsurface which is composed of transmitter and receiver antennae used for measuring underground resistivity. Real-time monitoring of output electrical parameters of the transmitted signals is required since these are significant in the computation of subsurface resistivity. This study aims to develop a digital measuring circuit for monitoring of transmitter antenna output current and voltage and to simulate prediction models that can be implemented in the circuit. Three neural network models-Elman recurrent neural network (ERNN), long short-term memory (LSTM), and gated recurrent unit (GRU) were explored to make prediction models for current and voltage of the transmitter circuit. The performance of the prediction models was assessed using mean squared error (MSE), which is reduced to its absolute lowest value. The result shows that the best-trained models both for current and voltage prediction are the ERNN models with configurations of 900-600-500 hidden neurons network with training MSE of 9.82 × 10-9 and the configured 1300-1000-900 hidden neurons with training MSE of 0.465, respectively. With the help of the prediction models, it would be possible to measure current and voltage output more precisely while avoiding the need for separate and bulky measuring devices