A study on the aerodynamic efficiency and static stability of a tailless aircraft
The design parameters for a tailless aircraft are optimized. Viscovery SOMine is used to perform trade-off analysis and to identify configurations which satisfy all static stability requirements and maximize aerodynamic performance.
Structurisation and visualisation of design space for launch vehicle with hybrid rocket engine
A single-stage launch vehicle with hybrid rocket engine and multi-time ignition is optimized. Viscovery SOMine is used to analyze the different influences of design variables and perform trade-off analysis.
An implementation of self-organizing maps for airfoil design exploration via multi-objective optimization technique
This article searches for optimal PARSEC parameters for airfoil design by using the ARMOGA genetic algorithm. Viscovery SOMine is used to identify the critical design parameters.
Efficient global optimization of vortex generators on a supercritical infinite wing
Optimization of vortex generators on a transonic infinite wing is the focus of this paper. The analysis of the five solution clusters obtained using Viscovery SOMine revealed that the balance among the three objectives (lift-to-drag ratio at low angle of attack, lift at high angle of attack, chord-wise location of flow separation) is mainly controlled by vortex generator height and spacing.
Study of aerodynamic and heat-exhaust characteristics for a high-altitude long-endurance unmanned-aerial-vehicle airfoil
The exhaust-heat characteristics of high-altitude, long-endurance drones are optimized. Viscovery SOMine is used to analyze the trade-offs between aerodynamic and heat-exhaust performance, revealing that over-all performance can be optimized by shifting the location of the laminar-turbulent transition.
Cognition of parameters' role on vertical control device for aerodynamic characteristics of aircraft using data mining
The optimization of a vertical control device for aircrafts is the focus of this paper. Viscovery SOMine is used to explore the connections between lift, drag, pitching moment and the geometry of the vertical control device.
Diversity of design knowledge for launch vehicle in view of fuels on hybrid rocket engine
In this article the influence of different fuel types on design space optimization for a hybrid rocket engine is analyzed. Viscovery SOMine is used for visualization and analysis of design space.
Influence of difference among evolutionary computations for design information
Seven different optimization methods are compared for optimizing the design of a single-stage hybrid rocket. Viscovery SOMine is used in conjunction with analysis of variance to compare the results of the different optimization methods.
Conceptual design of single-stage launch vehicle with hybrid rocket engine for scientific observation using design informatics
In this paper, a single-stage launch vehicle with hybrid rocket engine and single-time ignition is optimized, such that duration time in the lower thermosphere and range are maximized for scientific observations, whereas gross weight is kept low. Viscovery SOMine is used for design space visualization and trade-off analysis.
Identifying preferred solutions for multi-objective aerodynamic design optimization
This PhD thesis gives a thorough introduction to multi-objective aerodynamic design optimization and introduces new control measures for efficient optimization via particle swarms and the Kriging method. In this context, Viscovery SOMine is used to visualize the aerodynamic design space, analyze trade-offs between objectives and identify preferred design regions.
A comprehensive preference-based optimization framework with application to high-lift aerodynamic design
Multi-objective design optimization is used to design the airfoil of a high-lift transport aircraft. Viscovery SOMine is used for design-space visualization and trade-off analysis.
Data mining for motorsport aerodynamics
Multi-objective design optimization is used to obtain optimal design parameters for the front wing of a Formula One racing car. The visual analysis of design space is performed with Viscovery SOMine.
Review of data mining for multi-disciplinary design optimization
This review discusses several different data mining techniques which are used for multi-objective design optimization. It is shown that Viscovery SOMine’s self-organizing-map technology is one of the leading tools for this application.
Multi-objective design exploration and its application to Formula One airfoils
This paper details the design optimization of the front wing of a Formula One vehicle. Viscovery SOMine is used to visualize design space and find the region of highest fitness.
Design exploration of helicopter blades for HSI noise and aerodynamic performance
The shape of helicopter blades is optimized with respect to minimal high-speed impulsive noise and aerodynamic performance. Viscovery SOMine revealed that tip chord length and variable blade twist are important factors for low HSI noise and high aerodynamic performance.
Development and validation of an efficient direct numerical optimisation approach for aerofoil shape design
A novel variant of the direct numerical optimization approach is developed, validated and applied in the design of a low-speed airfoil using evolutionary algorithms. The convergence of the established optimal to an acceptable solution is verified by an innovative approach using Viscovery SOMine.
Design exploration for vortex generators for boundary-layer-ingesting inlet
Vortex generators for airplane inlets are optimized based on Navier–Stokes airflow simulations. Viscovery SOMine is used to analyze solutions obtained by genetic algorithms in design space.
Structurization and visualization of design space by fluid informatics
A combination of the Kriging model, genetic algorithms, analysis of variance and self-organizing map is used to optimize a regional jet wing design. Viscovery SOMine is used to analyze the Pareto optima considering drag, shock strength at wing-pylon junction and structural weight of the main wing in a 30-dimensional design space.
Multi-objective design exploration and its applications
This review paper describes multi-objective design exploration in aerodynamic engineering. Viscovery SOMine is used for visual data mining and trade-off analysis for the optimizations of a regional jet wing, a silent supersonic technology demonstrator and a centrifugal diffuser.
Performance map construction for a centrifugal diffuser with data mining techniques
The aim of this paper is to optimize the airflow through a centrifugal diffuser. To this end, the design space is visualized with Viscovery SOMine and the interdependencies with performance functions are assessed.
Evolutionary-based multidisciplinary design exploration for silent supersonic technology demonstrator wing
A silent supersonic technology demonstrator is optimized with respect to minimal pressure and friction drags, boom intensity at the supersonic condition and composite structural weight, as well as maximal lift at subsonic low-speed condition. Particle swarm optimization and a hybrid genetic algorithm are used to find non-dominated solutions. Viscovery SOMine is used to obtain design knowledge and perform trade-off analysis.
Knowledge discovery for flyback-booster aerodynamic wing using data mining
Three different data mining techniques (self-organizing map, analysis of variance, rough set theory) are applied to analyze the 71-dimensional wing-shape design space for a two-stage-to-orbit reusable launch vehicle flyback-booster. Viscovery SOMine produced the best results in analyzing the 302 solutions obtained by Reynolds-averaged Navier–Stokes simulation.
Knowledge discovery for transonic regional jet wing through multidisciplinary design exploration
The shape of a jet wing is optimized with respect to minimal fuel consumption, maximal takeoff weight and minimal drag coefficient. Through the design-space analysis with Viscovery SOMine, a non-gull wing geometry was found, which performs better than solutions identified in the conventional manner.
Application of swarm approach and artificial neural networks for airfoil shape optimization
The direct numerical optimization approach for airfoil-shape design is presented with a discussion of the required integration of the following modules: a geometrical shape function, a computational flow solver and a search model for shape optimization. The Particle Swarm Optimization (PSO) algorithm is introduced as the search agent. Viscovery SOMine is applied to illustrate trade-offs between PSO search variables.
A study on flapping motion for MAV design using design exploration
The aim of this work is to find an optimal design for a flapping-wing micro air vehicle, simultaneously acquiring maximal lift and thrust while minimizing required power. Two-dimensional Navier–Stokes simulations are conducted and Pareto-optimal solutions are obtained via evolutionary optimization. Viscovery SOMine is used to analyze the Pareto-optima with respect to five design parameters.
Design exploration of high-lift airfoil using Kriging model and data mining technique
Viscovery SOMine is used for a multi-objective design exploration of a three-element airfoil consisting of a slat, a main wing and a flap. A total of 90 sample points are evaluated using the Reynolds-averaged Navier–Stokes simulation for the construction of the Kriging model. Self-organizing-map analysis is used to obtain qualitative information of the design space.
Data mining for aerodynamic design space
Viscovery SOMine is applied to identify the effect of different design variables on various aerodynamic objective functions. Self-organizing maps are well suited to visualize the trade-offs among objective functions, and this information is helpful for designers to determine the final design from non-dominated solutions of multi-objective problems. These methods are applied to two design results: a flyback booster in reusable-launch-vehicle design, which has four objective functions and 71 design variables, and a transonic-airfoil design performed with the adaptive search region method.
Visualization and data mining of Pareto solutions using self-organizing map
Viscovery SOMine is used to visualize tradeoffs of Pareto solutions in the objective-function space for engineering design obtained by evolutionary computation. Based on the codebook vectors of cluster-averaged values of corresponding design variables obtained from the self-organizing map, the design variable space is mapped onto another self-organizing map. The resulting self-organizing map generates clusters of design variables, which indicate roles of the design variables for design improvements and tradeoffs. These processes — data mining of the engineering design — are applied to supersonic wing and supersonic wing-fuselage design.