Classification of Flow Regimes Using Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM).

Abstract

This dissertation project presents a novel method for the classification of vertical and horizontal two-phase flow regimes through pipes. For gas-liquid vertical and horizontal two-phase flows, the goal of the study is to predict the transition region between the flow regimesusing the data generated by empirical correlations. The transition region is determined with respect to pipe diameter, superficial gas velocity, and superficial liquid velocity. Accurate determination of the flow regime is critical in the design of multiphase flow systems, which are used in various industrial processes, including boiling and condensation, oil and gas pipelines, and cooling systems for nuclear reactors.