Neural network analysis of pulp flow speed in low coherence Doppler flowmetry measurement

Low Coherence Doppler Flowmetry (LCDF) measurement produces a signal, which frequency domain characteristics are in connection to the speed of the flow. In this study a LCDF measurement data of pulp flow in a capillary was analyzed with a simple Artificial Neural Network (ANN) method to estimate the flow speed. The accuracy of the method proved to be good, validation of the method resulted in absolute error of 14 ± 11 percentage units (mean±std) in flow speed estimation. The results of the study can be utilized in development of industrial pulp flow speed measurement instruments.