Improving the unsteady aerodynamic performance of transonic turbines using neural networks

Mohan, Man; Madavan, Nateri K.; Hüber, Frank

doi:10.2514/6.2000-169

Cited by 20 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Constructing an SM has proven to be very efficient, and SMs are employed in many scientific fields in which evaluating the original fitness function would represent a major obstacle. For instance, SMs have been applied to rotor blade design and optimization [19], high-speed civil transport [20], airfoil shape optimization [21], and diffuser shape optimization [22].…”

Section: Surrogate Modelingmentioning

confidence: 99%

Combining Genetic Programming and Particle Swarm Optimization to Simplify Rugged Landscapes Exploration

Pietropolli¹,

Menara²,

Castelli³

2022

Preprint

View full text Add to dashboard Cite

Most real-world optimization problems are difficult to solve with traditional statistical techniques or with metaheuristics. The main difficulty is related to the existence of a considerable number of local optima, which may result in the premature convergence of the optimization process. To address this problem, we propose a novel heuristic method for constructing a smooth surrogate model of the original function. The surrogate function is easier to optimize but maintains a fundamental property of the original rugged fitness landscape: the location of the global optimum. To create such a surrogate model, we consider a linear genetic programming approach enhanced by a self-tuning fitness function. The proposed algorithm, called the GP-FST-PSO Surrogate Model, achieves satisfactory results in both the search for the global optimum and the production of a visual approximation of the original benchmark function (in the 2dimensional case).

show abstract

Section: Surrogate Modelingmentioning

confidence: 99%

Combining Genetic Programming and Particle Swarm Optimization to Simplify Rugged Landscapes Exploration

Pietropolli¹,

Menara²,

Castelli³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Surrogate based analysis and optimisation (SBAO) has already been an effective approach for the design and optimisation of computationally expensive models, like air foil shape optimisation [11], [12], [14] and machine structure. Typically, a surrogate model can be comprehended as a non-linear inverse problem, which is used for determining a continuous function ( f ) of a set of design variables from a limited amount of available data f. So two problems about surrogate model appeared, one is constructing a model fˆ from the available data f (model estimation); another one is assessing the errors ε attached to it (model appraisal).…”

Section: Proposed Algorithmmentioning

confidence: 99%

“…But the statistical methods are quite useful to investigate the correlative relationship between input parameters and numerical simulation outputs to recognize which parameters are significant for an efficient optimal design. A wide variety of statistical methods and analysis called "experimental design" have been developed [11], [12], for agricultural or industrial applications. In most design situations, it is important to decrease the optimisation time and increase the reliability during electrical machine design.…”

Section: Introductionmentioning

confidence: 99%

Novel optimisation algorithm of electrical machines

Baker

Cao

2016

8th IET International Conference on Power Electronics, Machines and Drives (PEMD 2016)

View full text Add to dashboard Cite

This paper presents a case study for multi-variable and multimodal design optimisation of a doubly fed induction generator (DFIG) based on surrogate-model optimisation algorithm. The DFIG's winding of stator and rotor are optimised to obtain higher efficiency for rewinding purposes. First, a Latin hypercube design is selected as the design of experiments to obtain sampling points. Then, the surrogate model is constructed using Kriging Model (KRG) method based on the Latin hypercube design. Finally, the particle swarm optimisation algorithm is applied in conjunction with the finite element method to achieve the machine design optimisation.

show abstract

“…Other methods have been introduced to optimize the main elements of LRPSs (Shyy et al, 1999;Papila et al, 2000;Rai and Madavan, 2000;Matlock et al, 2001); however, system optimization is not considered. The "FORDY" software is developed by Kazlov (1987Kazlov ( , 1999 to achieve the highest possible "final velocity" to assess the parameters such as engine mixture ratio, pumps inlet pressures and engine mass.…”

Section: Introductionmentioning

confidence: 99%

Cycle optimization of the staged combustion rocket engines

Ramesh

Karimi

Shahheidari

2017

AEAT

View full text Add to dashboard Cite

Purpose The purpose of this paper is to introduce new and modified “staged combustion” cycles in the form of engineering algorithm as a possible propulsion contender for future aerospace vehicle to achieve the highest possible “total impulse” to “mass” of propulsion system. Design/methodology/approach In this regard, the mathematical cycle model is formed to calculate the engine’s parameters. In addition, flow conditions (pressure, temperature, flow rate, etc). in the chamber, nozzle and turbopump are assessed based on the results of turbo machinery power balance and initial data such as thrust, propellant mixture ratio and specifications. The developed code has been written in the modern, object-oriented C++ programming language. Findings The results of the developed code are compared with the Russian RD180 engine which demonstrates the superiority and capability of new “thermodynamic diagrams”. Research limitations/implications This algorithm is under constraint to control the critical variation of combustion pressure, turbine rpm, pump cavitation and turbine temperature. It is imperative to emphasize that this paper is limited to “oxidizer-rich staged combustion” engines with “single pre-burner”. Originality/value This study sheds light on using fuel booster turbopump and the second-stage fuel pump to moderate the effect of cavitation on pumps which reduces tank pressure and, as a consequence, decreases the propulsion system weight.

show abstract

Improving the unsteady aerodynamic performance of transonic turbines using neural networks

Cited by 20 publications

References 15 publications

Combining Genetic Programming and Particle Swarm Optimization to Simplify Rugged Landscapes Exploration

Combining Genetic Programming and Particle Swarm Optimization to Simplify Rugged Landscapes Exploration

Novel optimisation algorithm of electrical machines

Cycle optimization of the staged combustion rocket engines

Contact Info

Product

Resources

About