• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.1
• /
• pp.135-142
• /
• 2012

In this paper, we proposed a new architecture called radial basis function-based polynomial neural networks classifier that consists of heterogeneous neural networks such as radial basis function neural networks and polynomial neural networks. The underlying architecture of the proposed model equals to polynomial neural networks(PNNs) while polynomial neurons in PNNs are composed of Fuzzy-c means-based radial basis function neural networks(FCM-based RBFNNs) instead of the conventional polynomial function. We consider PNNs to find the optimal local models and use RBFNNs to cover the high dimensionality problems. Also, in the hidden layer of RBFNNs, FCM algorithm is used to produce some clusters based on the similarity of given dataset. The proposed model depends on some parameters such as the number of input variables in PNNs, the number of clusters and fuzzification coefficient in FCM and polynomial type in RBFNNs. A multiobjective particle swarm optimization using crowding distance (MoPSO-CD) is exploited in order to carry out both structural and parametric optimization of the proposed networks. MoPSO is introduced for not only the performance of model but also complexity and interpretability. The usefulness of the proposed model as a classifier is evaluated with the aid of some benchmark datasets such as iris and liver.

• Structural Engineering and Mechanics
• /
• v.19 no.4
• /
• pp.361-379
• /
• 2005

Reinforced concrete deep beams have useful applications in tall buildings and foundations. Over the past two decades, numerous design models for deep beams were suggested. However even the latest design manuals still offer little insight into the design of deep beams in particular when complexities exist in the beams like web openings. A method commonly suggested for the design of deep beams with openings is the strut-and-tie model which is primarily used to represent the actual load transfer mechanism in a structural concrete member under ultimate load. In the present study, the development of the strut-and-tie model is transformed to the topology optimization problem of continuum structures. During the optimization process, both the stress and displacement constraints are satisfied and the performance of progressive topologies is evaluated. The influences on the strut-and-tie model in relation to different size, location and number of openings, as well as different loading and support conditions in deep beams are examined in some detail. In all, eleven deep beams with web openings are optimized and compared in nine groups. The optimal strut-and-tie models achieved are also compared with published experimental crack patterns. Numerical results have shown to confirm the experimental observations and to efficiently represent the load transfer mechanism in concrete deep beams with openings under ultimate load.

• Advances in Computational Design
• /
• v.8 no.4
• /
• pp.327-351
• /
• 2023

This article explores how multi-objective optimization techniques can be used to design cost-effective and structurally optimal spatial steel structures, highlighting that optimizing performance can be as important as minimizing costs in real-world engineering problems. The study includes the minimization of maximum horizontal displacement, the maximization of the first natural frequency of vibration, the maximization of the critical load factor concerning the first global buckling mode of the structure, and weight minimization as the objectives. Additionally, it outlines a systematic approach to selecting the best design by employing four different evolutionary algorithms based on differential evolution and a multi-criteria decision-making methodology. The paper's contribution lies in its comprehensive consideration of multiple conflicting objectives and its novel approach to simultaneous consideration of bracing system, column orientation, and commercial profiles as design variables.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.37 no.4
• /
• pp.537-545
• /
• 2013

The elastic recovery of a metal seal is a factor that can be used to assess its sealing performance. In this study, a compliant mechanism topology optimization has been performed to find a structure of a metal O-ring seal that can maintain excellent sealing performance with a maximized elastic recovery over extended operation. An evolutionary structural optimization (ESO) was used as a topology optimization algorithm with two different types of objective functions considering both flexibility and stiffness. In particular, a circular design domain was adopted to consider the outer shape of the metal O-ring seal. The elastic recovery of the optimal topology was calculated and compared to that of a commercial product.

• Journal of Ocean Engineering and Technology
• /
• v.29 no.5
• /
• pp.331-341
• /
• 2015

A degasser is a separation unit used in drilling to separate gas from the drilling mud. The degasser used in offshore drilling was developed at an early stage of drilling. Since its development, the design of the degasser’s internal structure has been optimized, with many limitations due to the restrictions of experimental and computational performance measurement methods. Despite the recent development of CFD technology for multiphase flow analysis, CFD has only been used in a limited way for degasser internal flow analysis and design optimization. In this study, a design optimization procedure for a degasser’s internal structure design was proposed, and CFD analyses of three types of internal structural designs were performed to evaluate the separation performance. The CFD result for each design type was used for the design optimization and, as the result, an optimized design is proposed.

• 정보저장시스템학회:학술대회논문집
• /
• 2005.10a
• /
• pp.204-209
• /
• 2005

Load/Unload(L/UL) technology includes the benefits, that is, increased areal density, reduced power consumption and improved shock resistance contrary to contact-start-stop(CSS). It has been widely used in portable hard disk drive and will become the key technology far developing the small form factor hard disk drive. The main object of L/UL is no slider-disk contact or no media damage. For realizing those, we must consider many design parameters in L/UL system. In this paper, we focus on lift-off force. The 'lift-off' force, defined as the minimum air bearing force, is another very important indicator of unloading performance. A large amplitude of lift-off force increases the ramp force, the unloading time, the slider oscillation and contact-possibility. To minimize 'lift-off' force we optimizes the slider and suspension using the integrated optimization frame, which automatically integrates the analysis with the optimization and effectively implements the repetitive works between them. In particular, this study is carried out the optimal design considering the process of modes tracking through the entire optimization processes. As a result, we yield the equation which can easily find a lift-off force and structural optimization for suspension.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.28 no.1
• /
• pp.63-69
• /
• 2015

In this paper, infrared reflector design targeting infrared stealth effect is presented using structural optimization based on the phase field method. The analysis model was determined to accomplish the design that an incident infrared wave was reflected to a desired direction. The design process was to maximize the objective value at the measuring domain located in a target region and the design objective was set to the Poynting vector value which represents the energy flux. Optimization results were obtained according to the variation of some parameter values related to the phase field method. The model with a maximum objective value was selected as the final optimal model. The optimal model was modified to eliminate the gray scale using the cut-off method and it confirmed improved performance. In addition, to check the desired effect in the middle wave infrared range(MWIR), the analysis was performed by changing the input wavelength. The finite element analysis and optimization process were performed by using the commercial package COMSOL combined with the Matlab programming.

• Structural Engineering and Mechanics
• /
• v.65 no.3
• /
• pp.303-314
• /
• 2018

Shear walls are a typical member under a complex stress state and have complicated mechanical properties and failure modes. The separated-elements model Genetic Evolutionary Structural Optimization (GESO), which is a combination of an elastic-plastic stress method and an optimization method, has been introduced in the literature for designing such members. Although the separated-elements model GESO method is well recognized due to its stability, feasibility, and economy, its adequacy has not been experimentally verified. This paper seeks to validate the adequacy of the separated-elements model GESO method against experimental data and demonstrate its feasibility and advantages over the traditional elastic stress method. Two types of reinforced concrete shear wall specimens, which had the location of an opening in the middle bottom and the center region, respectively, were utilized for this study. For each type, two specimens were designed using the separated-elements model GESO method and elastic stress method, respectively. All specimens were subjected to a constant vertical load and an incremental lateral load until failure. Test results indicated that the ultimate bearing capacity, failure modes, and main crack types of the shear walls designed using the two methods were similar, but the ductility indexes including the stiffness degradation, deformability, reinforcement yielding, and crack development of the specimens designed using the separated-elements model GESO method were superior to those using the elastic stress method. Additionally, the shear walls designed using the separated-elements model GESO method, had a reinforcement layout which could closely resist the actual critical stress, and thus a reduced amount of steel bars were required for such shear walls.

• 한국신재생에너지학회:학술대회논문집
• /
• 2008.10a
• /
• pp.286-289
• /
• 2008

Mass of generator is one of the most important characteristic value especially direct drive type wind turbine. This paper introduce how to decease mass of generator rotor frame without declining generator performance. To obtain optimal design of rotor frame, sensitivity analysis using Taguchi method and RSM(response surface method) are have been performed.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.31 no.6
• /
• pp.301-308
• /
• 2018

This paper presents an optimal design method of a hybrid structural control system considering multi-hazard. Unlike a typical structural control system in which one system is designed for one specific type of hazard, a simultaneous optimal design method for both active and passive control systems is proposed for the mitigation of seismic and wind induced vibration responses of structures. As a numerical example, an optimal design problem is illustrated for a hybrid mass damper(HMD) and 30 viscous dampers which are installed on a 30 story building structure. In order to solve the optimization problem, a self-adaptive Harmony Search(HS) algorithm is adopted. Harmony Search algorithm is one of the meta-heuristic evolutionary methods for the global optimization, which mimics the human player's tuning process of musical instruments. A self-adaptive, dynamic parameter adjustment algorithm is also utilized for the purpose of broad search and fast convergence. The optimization results shows that the performance and effectiveness of the proposed system is superior with respect to a reference hybrid system in which the active and passive systems are independently optimized.