A Multidimensional Extension of Balje Chart for Axial Flow Turbomachinery Using Artificial Intelligence-Based Meta-Models

Abstract

Abstract The main intent of this work is the exploration of the rotor-only fan design space to identify the correlations between fan performance and enriched geometric and kinematic parameters. In particular, the aim is to derive a multidimensional “Balje chart,” where the main geometric and operational parameters are taken into account in addition to the specific speed and diameter, to guide a fan designer toward the correct choice of parameters such as hub solidity, blade number, hub-to-tip ratio (HR). This multidimensional chart was built using performance data derived from a quasi-3D in-house software for axisymmetric blade analysis and then explored by means of machine learning techniques suitable for big data analysis. Principal component analysis (PCA) and projection to latent structure (PLS) allowed finding optimal values of the main geometric parameters required by each specific speed/specific diameter pair.