Inverse Aerodynamic Design of Gas Turbine Blades using Probabilistic Machine Learning

Abstract One of the critical components in Industrial Gas Turbines (IGT) is turbine blade. Design blades needs to consider multiple aspects like aerodynamic efficiency, durability, safety and manufacturing, which make design process sequential iterative. The nature these iterations forces a long cycle time, ranging from several months years. Due reactionary iterations, little effort has been made accumulate data manner that allows for deep exploration understanding total space. This exemplified designing individual IGT resulting potential unrealized efficiency. To overcome aforementioned challenges, we demonstrate probabilistic inverse machine learning framework, namely PMI (PMI), carry out an explicit design. calculates explicitly without costly iteration overcomes challenges associated with ill-posed problems. In this work framework will be demonstrated on three-dimensional blades.