Phase boundary estimation in electrical resistance tomography with weighted multilayer neural networks

This work presents a boundary estimation approach in electrical resistance imaging for binary mixture fields based on weighted multilayer neural network. The interfacial boundaries are expressed with the truncated Fourier series and the unknown Fourier coefficients are estimated with the weighted multilayer neural network. In doing so, normalized boundary voltages are used for training the neural network and the results from real experiments show that the proposed approach has strong possibility for real-time monitoring of binary mixtures.