A genetic algorithm based aerothermal optimization of tip carving for an axial turbine blade

Maral, Hıdır; Alpman, Emre; Kavurmacıoğlu, Levent; Camcı, Cengiz

doi:10.1016/j.ijheatmasstransfer.2019.07.069

Cited by 35 publications

(7 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, the ANN model was applied in an optimization procedure, which resulted in a 1% increase in isentropic efficiency and 10% reduction in the blade stress. In another study investigating a carved blade tip [20], 55 CFD runs were conducted to generate ANN meta models, which were then used in a genetic algorithm routine to optimize the blade tip shape. In a missile control surface optimization study [21], machine learning, reinforcement learning, and transfer learning were integrated into the optimization procedure and leveraged CFD in the evaluation iterations.…”

Section: Introductionmentioning

confidence: 99%

Optimization of Turbine Blade Aerodynamic Designs Using CFD and Neural Network Models

Zhang

Janeway

2022

IJTPP

View full text Add to dashboard Cite

Optimization methods have been widely applied to the aerodynamic design of gas turbine blades. While applying optimization to high-fidelity computational fluid dynamics (CFD) simulations has proven capable of improving engineering design performance, a challenge has been overcoming the prolonged run-time due to the computationally expensive CFD runs. Reduced-order models and, more recently, machine learning methods have been increasingly used in gas turbine studies to predict performance metrics and operational characteristics, model turbulence, and optimize designs. The application of machine learning methods allows for utilizing existing knowledge and datasets from different sources, such as previous experiments, CFD, low-fidelity simulations, 1D or system-level studies. The present study investigates inserting a machine learning model that utilizes such data into a high-fidelity CFD driven optimization process, and hence effectively reduces the number of required evaluations of the CFD model. Artificial Neural Network (ANN) models were trained on data from over three thousand two-dimensional (2D) CFD analyses of turbine blade cross-sections. The trained ANN models were then used as surrogates in a nested optimization process alongside a full three-dimensional Navier–Stokes CFD simulation. The much lower evaluation cost of the ANN model allows for tens of thousands of design evaluations to guide the search of the best blade profiles to be used in the more expensive, high-fidelity CFD runs, improving the progress of the optimization while reducing the required computation time. It is estimated that the current workflow achieves a five-fold reduction in computational time in comparison to an optimization process that is based on three-dimensional (3D) CFD simulations alone. The methodology is demonstrated on the NASA/General Electric Energy Efficient Engine (E3) high pressure turbine blade and found Pareto front designs with improved blade efficiency and power over the baseline. Quantitative analysis of the optimization data reveals that some design parameters in the present study are more influential than others, such as the lean angle and tip scaling factor. Examining the optimized designs also provides insight into the physics, showing that the optimized designs have a lower amount of pressure drop near the trailing edge, but have an earlier onset of pressure drop on the suction side surface when compared to the baseline design, contributing to the observed improvements in efficiency and power.

show abstract

Section: Introductionmentioning

confidence: 99%

Optimization of Turbine Blade Aerodynamic Designs Using CFD and Neural Network Models

Zhang

Janeway

2022

IJTPP

View full text Add to dashboard Cite

show abstract

“…The selected geometric modelling platform was CAESES® while the numerical flow solver was MISES. Many authors have used the commercial flow solver ANSYS CFX to simulate the aerodynamic performance in their optimisation models [12][13][14][15][16] while the optimisation solver is commonly genetic algorithm (GA) and multi-objective genetic algorithm (MOGA) [17][18][19]. Various optimisation objectives have been presented through the published studies, however the common target is achieving higher aerodynamic performance.…”

Section: Introductionmentioning

confidence: 99%

“…In some specific applications, decision variables are limited to certain parameters that define a part of the blade to minimise a specific source of loss; e.g. optimising the blade tip to minimise tip leakage characteristics [12].…”

Section: Introductionmentioning

confidence: 99%

Integrated Aerodynamic and Structural Blade Shape Optimization of Axial Turbines Operating With Supercritical Carbon Dioxide Blended With Dopants

Abdeldayem

White

Paggini³

et al. 2022

Journal of Engineering for Gas Turbines and Power

View full text Add to dashboard Cite

Within this study, the blade shape of a large-scale axial turbine operating with sCO2 blended with dopants is optimised using an integrated aerodynamic-structural numerical model to maximise the aerodynamic efficiency whilst meeting stress constraints. Three candidate mixtures are considered, namely CO2 blended with titaniumtetrachloride (TiCl4), hexafluorobenzene (C6F6) or sulfur dioxide (SO2) defined by the EU project, SCARABEUS. The aerodynamic performance is simulated using a single passage, 3D, steady-state, viscous computational fluid dynamic (CFD) model while the blade stress distribution is obtained from a static structural finite element analysis (FEA). A genetic algorithm is used to optimise parameters defining the blade angle and thickness distributions along the chord line while a surrogate model is used to provide fast and reliable model predictions during optimisation using genetic aggregation response surface. The uncertainty of the surrogate model is evaluated using a set of verification points and found less than 0.3% for aerodynamic efficiency and 1% for both the mass flow rate and the maximum equivalent stresses. The comparison between the final optimised blade cross-sections have shown some common trends in optimising the blade design by decreasing stator and rotor trailing edge thickness, increasing stator thickness near the trailing edge, decreasing rotor thickness near the trailing edge and decreasing the rotor outlet angle. Further investigations of the loss breakdown of the optimised and reference blade designs are presented. It has been noted that the performance improvement achieved is mainly due to decreasing the endwall losses of both blade rows.

show abstract

“…1−3 They are fantastic tools to strengthen any study dealing with varying parameters, as they allow weight to be given to all observations and trends in order to enable the pinpointing of optimal conditions. DoE have been used extensively in a very wide range of fields, from mechanical engineering 4,5 to numerical simulations. 2 The pharmaceutical, 6 medical, 7 and chemical engineering 8−12 fields also make broad use of DoE in their research.…”

Section: ■ Introductionmentioning

confidence: 99%

“…DoE have been used extensively in a very wide range of fields, from mechanical engineering , to numerical simulations . The pharmaceutical, medical, and chemical engineering − fields also make broad use of DoE in their research.…”

Section: Introductionmentioning

confidence: 99%

Exploiting Materials to Their Full Potential, a Li-Ion Battery Electrode Formulation Optimization Study

Rynne

Dubarry

Molson

et al. 2020

ACS Appl. Energy Mater.

View full text Add to dashboard Cite

Today, energy conversion devices typically rely on composite electrodes made of several materials interacting with one another. Understanding their individual and combined impacts on performance is essential in the pursuit of optimized systems. Unfortunately, this investigation is often disregarded in favor of quick publishable results. Here, designs of experiments are shown as capable of meeting both ends. Less than 100 different electrode formulations are defined with two active materials (LiFePO 4 and Li 4 Ti 5 O 12 ), two carbonaceous additives (carbon black and carbon nanofibers), and three binders (polyvinylidene fluoride, polyethylene-co-ethyl acrylate-co-maleic anhydride (Lotader 5500), and a hydrogenated nitrile butadiene rubber). Correlations with strong descriptive statistics are found between formulation and different limitations, indicating that maximum active material content should always be favored with a small fraction of both conductive additives and minimal binder content. With the help of designs of experiments, Lotader 5500-bound electrodes are optimized beyond typical formulations found in the literature.

show abstract

A genetic algorithm based aerothermal optimization of tip carving for an axial turbine blade

Cited by 35 publications

References 28 publications

Optimization of Turbine Blade Aerodynamic Designs Using CFD and Neural Network Models

Optimization of Turbine Blade Aerodynamic Designs Using CFD and Neural Network Models

Integrated Aerodynamic and Structural Blade Shape Optimization of Axial Turbines Operating With Supercritical Carbon Dioxide Blended With Dopants

Exploiting Materials to Their Full Potential, a Li-Ion Battery Electrode Formulation Optimization Study

Contact Info

Product

Resources

About