Application of PSO algorithm and RBF neural network in electrical impedance tomography

To measure the resistivity distribution of semiconductor wafers, this article applies electrical impedance tomography (EIT) technology to semiconductor resistivity measurements. A new method of Image reconstruction algorithm based on RBF neural network for EIT is proposed. The particle swarm optimization algorithm (PSO) is designed to optimize the RBF network´s connection weights. The simulation experiment results for 32 electrodes EIT data collecting system indicate that the PSO-RBF algorithm can improve the reconstruction image quality and the accuracy obviously, and that it is feasible of using RBF neural network to measure the resistivity distribution of semiconductor wafers.