Imaging of industrial processes have been accomplished with better efficiency and better control since the introduction of process tomography in several industries. This technique enables a deeper look into the internal conditions of a process without invading the process. In tomographic techniques, process information such as the distribution and velocity of the particles conveying at a particular plane can be obtained by placing sensors around the periphery of the plane. This paper is a continuation of a previous paper entitled Flow Regime Identification Using Neural Network–based Electrodynamic Tomography System in Jurnal Teknologi 40(D). This paper presents the results of sensors output in comparison to that of prediction models, concentration profiles and flow regimes identification obtained from the system described in the previous paper.
Key words: Electrodynamic tomography, neural network, concentration profile, flow regimes