Determination of multi-component flow process parameters based on electricalcapacitance tomography data using artificial neural networks

Abstract

Artificial neural networks (ANNs) have been used to investigate their capabilitiesat estimating key parameters for the characterization of flow processes, based onelectrical capacitance-sensed tomographic (ECT) data. The estimations of theparameters are made directly, without recourse to tomographic images. Theparameters of interest include component height and interface orientation oftwo-component flows, and component fractions of two-component andthree-component flows. Separate multi-layer perceptron networks were trainedwith patterns consisting of pairs of simulated ECT data and the correspondingcomponent heights, interface orientations and component fractions. Thenetworks were then tested with patterns consisting of unlearned simulatedECT data of various flows and with real ECT data of gas–water flows.The neural systems provided estimations having mean absolute errors ofless than 1% for oil and water heights and fractions and less than 10°for interface orientations. When tested with real plant ECT data, themean absolute errors were less than 4% for water height, less than 15°for gas–water interface orientation and less than 3% for water fraction,respectively. The results demonstrate the feasibility of the application of ANNsfor flow process parameter estimations based upon tomography data.