Machine Learning Methods in CFD for Turbomachinery: A Review

  title={Machine Learning Methods in CFD for Turbomachinery: A Review},
  author={James Hammond and Nick Pepper and Francesco Montomoli and Vittorio Michelassi},
  journal={International Journal of Turbomachinery, Propulsion and Power},
Computational Fluid Dynamics is one of the most relied upon tools in the design and analysis of components in turbomachines. From the propulsion fan at the inlet, through the compressor and combustion sections, to the turbines at the outlet, CFD is used to perform fluid flow and heat transfer analyses to help designers extract the highest performance out of each component. In some cases, such as the design point performance of the axial compressor, current methods are capable of delivering good… 

Machine learning-based CFD simulations: a review, models, open threats, and future tactics

This review targets various scenarios where CFD could be used and the logical parts needed for exemplary computations and outlines the advantages, disadvantages, and tools used for computing the algorithm.



Fluid Dynamics of Axial Turbomachinery: Blade- and Stage-Level Simulations and Models

The current generation of axial turbomachines are the culmination of decades of experience, and detailed understanding of the underlying flow physics has been a key factor for achieving high

Challenges and opportunities for artificial intelligence and high-fidelity simulations in turbomachinery applications: A perspective

Recent trends in design methods that take advantage of both artificial intelligence and high-fidelity simulations techniques that guide the design process by harvesting design data from multiple sources and improve the accuracy of design verification respectively are discussed.

Machine Learning for the Development of Data Driven Turbulence Closures in Coolant Systems

This work shows the application of Gene Expression Programming to augment RANS turbulence closure modelling for flows through complex geometry, designed for additive manufacturing. Specifically,

Computational fluid dynamics for turbomachinery design

Abstract Computational fluid dynamics (CFD) probably plays a greater part in the aerodynamic design of turbomachinery than it does in any other engineering application. For many years the design of a

Transfer Optimization in Accelerating the Design of Turbomachinery Cascades

A Cokriging based transfer optimization framework for the design of turbomachinery cascades is proposed, which is demonstrated by optimization to re-design the first-stage vane of GEE3 and can reduce the computational cost by much as 50%.

The Current State of High-Fidelity Simulations for Main Gas Path Turbomachinery Components and Their Industrial Impact

The key challenges of simulating and modelling turbomachinery flows are introduced and an overview of possible simulation strategies are presented and it is argued that industrial impact from high-fidelity simulations can be achieved in two ways, either by conducting design-of-experiment-like studies that can provide designers with insight into certain physical mechanisms and phenomena.

Machine-Learnt Turbulence Closures for Low-Pressure Turbines With Unsteady Inflow Conditions

The design of low-pressure turbines (LPTs) must account for the losses generated by the unsteady interaction with the upstream blade row. The estimation of such unsteady wake-induced losses

Global Optimisation of a Transonic Fan Blade Through AI-Enabled Active Subspaces

A novel strategy is presented that leverages the capabilities of Artificial Neural Networks for regressing complex unstructured data, while coupling them with dimensionality reduction algorithms to enable employing global-based optimisation methods on high-dimensional applications through a reduced computational cost.