• The Transactions of the Korean Institute of Electrical Engineers C
• /
• v.52 no.7
• /
• pp.424-424
• /
• 2003

Evolutionary design related to the optimal design of Polynomial Neural Networks (PNNs) structure for model identification of complex and nonlinear system is studied in this paper. The PNN structure is consisted of layers and nodes like conventional neural networks but is not fixed and can be changable according to the system environments. three types of polynomials such as linear, quadratic, and modified quadratic is used in each node that is connected with various kinds of multi-variable inputs. Inputs and order of polynomials in each node are very important element for the performance of model. In most cases these factors are decided by the background information and trial and error of designer. For the high reliability and good performance of the PNN, the factors must be decided according to a logical and systematic way. In the paper evolutionary algorithm is applied to choose the optimal input variables and order. Evolutionary (genetic) algorithm is a random search optimization technique. The evolved PNN with optimally chosen input variables and order is not fixed in advance but becomes fully optimized automatically during the identification process. Gas furnace and pH neutralization processes are used in conventional PNN version are modeled. It shows that the designed PNN architecture with evolutionary structure optimization can produce the model with higher accuracy than previous PNN and other works.

• Journal of KIBIM
• /
• v.9 no.1
• /
• pp.42-51
• /
• 2019

Maintenance of aging structures has attracted societal attention. Maintenance of the aging structure can be efficiently performed with a digital twin. In order to maintain the structure based on the digital twin, it is required to accurately detect the damage of the structure. Meanwhile, deep learning-based damage detection approaches have shown good performance for detecting damage of structures. However, in order to develop such deep learning-based damage detection approaches, it is necessary to use a large number of data before and after damage, but there is a problem that the amount of data before and after the damage is unbalanced in reality. In order to solve this problem, this study proposed a method based on Generative adversarial network, one of Generative Model, for generating acceleration data usually used for damage detection approaches. As results, it is confirmed that the acceleration data generated by the GAN has a very similar pattern to the acceleration generated by the simulation with structural analysis software. These results show that not only the pattern of the macroscopic data but also the frequency domain of the acceleration data can be reproduced. Therefore, these findings show that the GAN model can analyze complex acceleration data on its own, and it is thought that this data can help training of the deep learning-based damage detection approaches.

• Earthquakes and Structures
• /
• v.17 no.3
• /
• pp.271-282
• /
• 2019

Knowing the response of buildings to earthquakes is very important in order to ensure that a structure is able to withstand a given level of ground shaking. Thus, nonlinear dynamic earthquake engineering analyses are unavoidable and are preferable procedure in the seismic assessment of buildings. In order to estimate seismic performance on the basis of the hazard at the site where the structure is located, the selection of appropriate seismic input is known to be a critical step while performing this kind of analysis. In this paper, seismic analysis is performed for a four-story reinforced concrete ISPRA frame structure which is designed according to Eurocode 8 (EC8). A total of 90 different earthquake scenarios were selected, 30 for each of three target spectrums, EC8 spectrum, Uniform Hazard Spectrum (UHS), and Conditional Mean Spectrum (CMS). The aim of this analysis was to evaluate the average maximum Inter-story Drift Ratio (IDR) for each target spectrum. Time history analysis for every earthquake record was obtained and, as a result, IDR as the main measure of damage were presented in order to compare with defined performance levels of reinforced concrete bare frames.

• Journal of IKEEE
• /
• v.25 no.2
• /
• pp.371-375
• /
• 2021

In this paper, a SiC-based LIGBT structure that can be used at high voltage and high temperature is presented. In order to improve the low current characteristic, a dual-emitter symmetrical around the gate is inserted. In order to verify the characteristics of the proposed device, simulation and design were conducted using Sentaurus TCAD simulation, and a comparative study was conducted with a general LIGBT. In addition, splitting was performed by designating a variable for the length of the N-drift region in order to verify the electrical characteristics of the minority carriers. As a result of the simulation it was confirmed that the proposed dual-emitter structure flows a higher current at the same voltage than the conventional LIGBT.

• Korea-Australia Rheology Journal
• /
• v.16 no.4
• /
• pp.213-218
• /
• 2004

Linear high-density polyethylene (PE) was controlled to induce strain-hardening behavior by introducing a small amount of second component with an anisotropic structure. In order to form an anisotropic structure in the PE matrix, the polymer was extruded through a twin-screw extruder, and the structure was controlled by varying the extrusion conditions. Depending on conditions, the second component formed a film, thread and droplet structure. If the second component was kept rigid, the morphology evolution could be delayed and the second component could maintain its film or thread structure without further relaxation. In par­ticular, the second component of the thread structure made a physical network and gave rise to remarkable strain hardening behavior under high extension. This study suggests a new method that induces strain hard­ening behavior by introducing a physically networked second component into the linear polymer melt. This result is anticipated to improve the processibility of linear polymers especially when extensional flow is dominant, and to contribute to our understanding of strain hardening behavior.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.25 no.5
• /
• pp.337-344
• /
• 2015

As many of armored vehicles are seriously exposed to threat of IEDs(Improvised Explosive Devices) in the Afghanistan war and the Iraq war. V-shaped military vehicles are deeply studied in order to protect crews and mounted soldiers against land mines. Generally the experiment on full-scaled V-shaped structure needs excessively high cost, which becomes a huge barrier to study. In this paper, we explore the possibility to make a half-scaled model of the V-shaped structure by using the geometric similarity scaling. We demonstrate the geometric similarity scaling between the original model and the half-scaled model is established on the momentum and deflections of structure via computer simulations and experiments. At this stage, we conduct only numerical analysis of predicting vibration of V-shaped structure because measuring vibration of structure is difficult in the mass-explosion experiment, which is remained as future work.

• Special Issue of the Society of Naval Architects of Korea
• /
• 2006.09a
• /
• pp.53-58
• /
• 2006

When the vibration troubles occur on the ship structure during the sea trial, the rectification work is very restricted because of in-situ limitation. Usually the finite element method is used to improve vibration characteristics of the structure, but it takes lots of time and effort in modeling the structure and adjusting the finite element model in order to consider appropriate boundary conditions of a complex ship structure. Therefore, experimental methods have been in general suggested to obtain proper countermeasures without time-consuming in modeling. In this paper, FRF(frequency response function) synthesis method is applied to estimate natural frequency of the modified ship structure, which is obtained from experimental and numerical methods.

• Transactions of Materials Processing
• /
• v.26 no.6
• /
• pp.372-377
• /
• 2017

In this paper, an effective design procedure was proposed to design the rib of die structure for auto-body member with ultra-high strength steel (UHSS) having ultimate tensile strength (UTS) of 1.5 GPa. From analysis results of the die structure, structural safety of the die was evaluated with information such as displacement and von-Mises stress. It was concluded that the casting part could be designed in order to reduce tool deformation. A design guideline of the die structure was proposed, especially for the rib structure in the casting part with an optimization scheme and local reinforcement concept. Simulation result following the design guideline fully explained that stability of the tool structure could be obtained simultaneously with weight minimization.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2006.05a
• /
• pp.176-180
• /
• 2006

When the vibration troubles occur on the ship structure during the sea trial, the rectification work is very restricted because of in-situ limitation. Usually, the finite element method is used to improve vibration characteristics of the structure, but it takes lots of time and effort in modeling the structure and adjusting the finite element model in order to consider appropriate boundary conditions of a complex ship structure. Therefore, experimental methods have been in general suggested to obtain proper countermeasures without time-consuming in modeling. In this paper, FRE(frequency response function) synthesis method is applied to estimate natural frequency of the modified ship structure, which is obtained from experimental and numerical methods.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2002.10a
• /
• pp.557-564
• /
• 2002

One of the primary factors like plate structure In ship is redundancy structure that is comparable with ocean structure and frame structure. The more component material becomes buckling collapsed locally the less structure stiffness becomes accordingly. As a result, by increasing the load distribution of any other subsidiary structure continually component member collapses, therefore the structure could be in danger of collapse. So, in order to interpret this phenomenon precisely, the study on boundary condition of the ship's Plate and post-buckling analysis must be considered. In this study, the rectangular plate is compressed by the in-plane load. Buckling ＆ Ultimate strength characteristics we applied to be the elasto-plasticity large deformation by F.E.M. On this basis, elasto-plasticity of the plain plate are investigated. This study proved elasto-plasticity behaviour of tile ship's plate In accordance with boundary condition based on the series analysis In case of the compressive load operation.