• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.8
• /
• pp.551-560
• /
• 2004

In this paper, we propose a new architecture of Self-Organizing Fuzzy Polynomial Neural Networks (SOFPNN) that is based on a genetically optimized multilayer perceptron with fuzzy polynomial neurons (FPNs) and discuss its comprehensive design methodology involving mechanisms of genetic optimization, especially genetic algorithms (GAs). The proposed SOFPNN gives rise to a structurally optimized structure and comes with a substantial level of flexibility in comparison to the one we encounter in conventional SOFPNNs. The design procedure applied in the construction of each layer of a SOFPNN deals with its structural optimization involving the selection of preferred nodes (or FPNs) with specific local characteristics (such as the number of input variables, the order of the polynomial of the consequent part of fuzzy rules, and a collection of the specific subset of input variables) and addresses specific aspects of parametric optimization. Through the consecutive process of such structural and parametric optimization, an optimized and flexible fuzzy neural network is generated in a dynamic fashion. To evaluate the performance of the genetically optimized SOFPNN, the model is experimented with using two time series data(gas furnace and chaotic time series), A comparative analysis reveals that the proposed SOFPNN exhibits higher accuracy and superb predictive capability in comparison to some previous models available in the literatures.

• Journal of the Korean Society for Precision Engineering
• /
• v.30 no.10
• /
• pp.1061-1068
• /
• 2013

In this research, the design optimization of a composite sandwich has been performed for using as an airplane wing skin. Automated analysis framework for aero-structure interaction is used for calculating load data on the wing. For automated analysis framework, FLUENT is used for computational fluid dynamics (CFD) analysis. CFD mesh is generated automatically by using parametric modeling of CATIA and GAMBIT. A computational structure mechanics (CSM) mesh is generated automatically by the parametric method of the CATIA and visual basic script of NASTRAN-FX. The structure is analyzed by ABAQUS. Composite sandwich optimization is performed by NASTRAN SOL200. Design variables are thicknesses of the sandwich core and composite skin panel plies. The objective is to minimize the weight of the wing and constraints are applied for wing tip displacement, global failure index and local failure indexes.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.7 no.6
• /
• pp.995-1006
• /
• 2015

Underwater glider, as a new kind of autonomous underwater vehicles, has many merits such as long-range, extended-duration and low costs. The shape of underwater glider is an important factor in determining the hydrodynamic efficiency. In this paper, a high lift to drag ratio configuration, the Blended-Wing-Body (BWB), is used to design a small civilian under water glider. In the parametric geometric model of the BWB underwater glider, the planform is defined with Bezier curve and linear line, and the section is defined with symmetrical airfoil NACA 0012. Computational investigations are carried out to study the hydrodynamic performance of the glider using the commercial Computational Fluid Dynamics (CFD) code Fluent. The Kriging-based genetic algorithm, called Efficient Global Optimization (EGO), is applied to hydrodynamic design optimization. The result demonstrates that the BWB underwater glider has excellent hydrodynamic performance, and the lift to drag ratio of initial design is increased by 7% in the EGO process.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.13 no.1
• /
• pp.478-492
• /
• 2021

In this study, hull dimensions of an FPSO were optimized to maximize its operability at Brazil field. In contrast with the previous works which have used simplified models to evaluate some indicators related to stability and hydrodynamic performances of FPSOs for its own optimal design, we developed a generic hull and compartment modeler and sophisticated stability and hydrodynamic calculation modules. With the aid of the developed tools, the hull optimization was performed with initial dimensions of an FPSO originally designed for west Africa field. The optimization results indicated the relative importance of hydrodynamic performances compared with stability performances for the FPSO hull dimensioning by showing that there were 3 active constraints related to them, which were the natural periods of heave and roll and the maximum pitch angle under 1-year return period waves at full load condition. To the author's knowledge, this study is the first attempt to combine altogether the hull and compartment modeling and full set of stability and hydrodynamic calculations precisely to optimize an FPSO's hull dimensions within 30 min. Also, it is worthwhile to mention that the developed methods are generic enough to be applied to all types of ship-shaped offshore platforms.

• Wind and Structures
• /
• v.31 no.3
• /
• pp.241-253
• /
• 2020

The inerter-based vibration absorber (IVA) is an enhanced variation of Tuned Mass Damper (TMD). The parametric optimization of absorbers in the previous research mainly considered only two decision variables, namely frequency ratio and damping ratio, and aimed to minimize peak displacement and acceleration individually under the excitation of the across-wind load. This paper extends these efforts by minimizing two conflicting objectives simultaneously, i.e., the extreme displacement and acceleration at the top floor, under the constraint of the physical mass. Six decision variables are optimized by adopting a constrained multi-objective evolutionary algorithm (CMOEA), i.e., NSGA-II, under fluctuating across- and along-wind loads, respectively. After obtaining a set of optimal individuals, a decision-making approach is employed to select one solution which corresponds to a Tuned Mass Damper Inerter/Tuned Inerter Damper (TMDI/TID). The optimization procedure is applied to parametric optimization of TMDI/TID installed in a 340-meter-high building under wind loads. The case study indicates that the optimally-designed TID outperforms TMDI and TMD in terms of wind-induced vibration mitigation under different wind directions, and the better results are obtained by the CMOEA than those optimized by other formulae. The optimal TID is proven to be robust against variations in the mass and damping of the host structure, and mitigation effects on acceleration responses are observed to be better than displacement control under different wind directions.

• Structural Engineering and Mechanics
• /
• v.55 no.3
• /
• pp.555-581
• /
• 2015

Triangular pyramid and Quadrangular pyramid elements for partial double-layer spherical reticulated shells of pyramidal system are investigated in the present study. Macro programs for six typical partial double-layer spherical reticulated shells of pyramidal system are compiled by using the ANSYS Parametric Design Language (APDL). Internal force analysis of six spherical reticulated shells is carried out. Distribution regularity of the stress and displacement are studied. A shape optimization program is proposed by adopting the sequence two-stage algorithm (RDQA) in FORTRAN environment based on the characteristics of partial double-layer spherical reticulated shells of pyramidal system and the ideas of discrete variable optimization design. Shape optimization is achieved by considering the objective function of the minimum total steel consumption, global and locality constraints. The shape optimization of six spherical reticulated shells is calculated with the span of 30m~120m and rise to span ratio of 1/7~1/3. The variations of the total steel consumption along with the span and rise to span ratio are discussed with contrast to the results of shape optimization. The optimal combination of main design parameters for six spherical reticulated shells is investigated, i.e., the number of the optimal grids. The results show that: (1) The Kiewitt and Geodesic partial double-layer spherical reticulated shells of triangular pyramidal system should be preferentially adopted in large and medium-span structures. The range of rise to span ratio is from 1/6 to 1/5. (2) The Ribbed and Schwedler partial double-layer spherical reticulated shells of quadrangular pyramidal system should be preferentially adopted in small-span structures. The rise to span ratio should be 1/4. (3) Grids of the six spherical reticulated shells can be optimized after shape optimization and the total steel consumption is optimized to be the least.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.27 no.5
• /
• pp.451-458
• /
• 2014

This study is a practical research for setting a process of making references of design decision and guidlines of limitation in the movement from the design development to the construction design by StrAuto. StrAuto, as a parametric modeling and optimization tool for building structure, enables a quantity of design cases to be analyzed automatically by changing parameters of sturctural properties. So the designer using StrAuto can check a lot of analysis data crossing thousands of cases, see which case is out of acceptable range, and make a decision for design and optimization. In this thesis, the application of StrAuto optimization process to the residence tower UIC project shows the practical applicability in the construction design and value engineering. StrAuto optimized ideally volume of core walls by 31.3% and lead the final revised model applied to the construction design to reduce volume by 18.1%. The significance of this research is the implementation of process that the designer can quickly review a number of cases and get a direction for construction design and optimization after design development.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.30 no.2
• /
• pp.103-110
• /
• 2017

In this paper, it is covered in detail the process of generating structural alternatives with geometry change and its optimization by StrAuto. The main roof structure of the Exhibition Center is modelled parametrically and the optimal alt is derived by observing volume changes according to geometry change of main roof truss. Existing studies performed optimization process through sections and properties due to the limitations of shape change, but this study have meaning of performing the optimization with geometry changes which is the most critical skills of StrAuto. By the process of securing a sufficient margin by geometry changes and reducing volume with the optimization of sections, despite of a partial optimization of large space structure, it could be reduced by 11.7% of the total volume.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2003.10a
• /
• pp.341-345
• /
• 2003

This study develops modeling processes for alignment optimization considering characteristics of intersections using genetic algorithms and GIS for road alignment optimization. Since existing highway alignment optimization models have neglected the characteristics of intersections, they have shown serious weaknesses for real applications. In this paper, intersection costs include earthwork, right-of-way, pavement, accident, delay and fuel consumption costs that are sensitive and dominating to alignments. Also, local optimization of intersections for saving good alignment alternatives is developed and embedded. A highway alignment is described by parametric representation in space and vector manipulation is used to find the coordinates of intersections and other interesting points. The developed intersection cost estimation model is sufficiently precise for estimating intersection costs and eventually enhancing the performance of highway alignment optimization models. Also, local optimization of intersections can be used for improving search flexibility, thus allowing more effective intersections. It also provides a basis for extending the alignment optimization from single highways to networks. The presented two artificial examples show that the total intersection costs are substantial and sensitive to highway alignments.

• Advances in Computational Design
• /
• v.3 no.1
• /
• pp.35-47
• /
• 2018

Design of settlement space is a complicated process while reasonable spatial layout bears great significance on the development and resource allocation of a settlement. The study proposes a weighted L-system generation algorithm based on CA (Cellular Automation) model which tags the spatial attributes of cells through changes in their state during the evolution of CA and thus identifies the spatial growth mode of a settlement. The entrance area of the Caidian Botanical and Animal Garden is used a case study for the model. A design method is proposed which starts from the internal logics of spatial generation, explores possibility of spatial rules and realizes the quantitative analysis and dynamic control of the design process. Taking a top-down approach, the design method takes into account the site information, studies the spatial generation mechanism of settlements and further presents a engine for the generation of multiple layout proposals based on different rules. A optimal solution is acquired using GA (Genetic Algorithm) which generates a settlement spatial layout carrying site information and dynamically linked to the surround environment. The study aims to propose a design method to optimize the spatial layout of the complex settlement system based on parametric generation.