• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.370-370
• /
• 2000

In this paper, we design a Multi-Fuzzy model by means of HCM clustering and genetic algorithms for a nonlinear system. In order to determine structure of the proposed Multi-Fuzzy model, HCM clustering method is used. The parameters of membership function of the Multi-Fuzzy ate identified by genetic algorithms. A aggregate performance index with a weighting factor is used to achieve a sound balance between approximation and generalization abilities of the model. We use simplified inference and linear inference as inference method of the proposed Multi-Fuzzy mode] and the standard least square method for estimating consequence parameters of the Multi-Fuzzy. Finally, we use some of numerical data to evaluate the proposed Multi-Fuzzy model and discuss about the usefulness.

• Proceedings of the KIEE Conference
• /
• 2000.07d
• /
• pp.3007-3009
• /
• 2000

In this paper, we design a Multi-Fuzzy model by means of clustering method and genetic algorithms for a nonlinear system. In order to determine structure of the proposed Multi-Fuzzy model. HCM clustering method is used. The parameters of membership function of the Multi-Fuzzy are identified by genetic algorithms. We use simplified inference and linear inference as inference method of the proposed Multi-Fuzzy model and the standard least square method for estimating consequence parameters of the Multi-Fuzzy. Finally, we use some of numerical data to evaluate the proposed Multi-Fuzzy model and discuss about the usefulness.

• The Korean Journal of Applied Statistics
• /
• v.24 no.1
• /
• pp.207-216
• /
• 2011

Bootstrap is a resampling technique to find an estimate of parameters or to evaluate the estimate. This technique has been used in estimating parameters in linear model(LM) and generalized linear model(GLM). In this paper, we explore the possibility of applying Bootstrapping Residuals, Pairs, and an Estimating Equation that are most widely used in LM and GLM to the generalized estimating equation(GEE) algorithm for modelling repeatedly measured regression data sets. We compared three bootstrapping methods with coefficient and standard error estimates of GEE models from one simulated and one real data set. Overall, the estimates obtained from bootstrap methods are quite comparable, except that estimates from bootstrapping pairs are somewhat different from others. We conjecture that the strange behavior of estimates from bootstrapping pairs comes from the inconsistency of those estimates. However, we need a more thorough simulation study to generalize it since those results are coming from only two small data sets.

• Computers and Concrete
• /
• v.12 no.2
• /
• pp.187-209
• /
• 2013

This paper presents a study on the prediction of transfer length of 13 mm seven-wire prestressing steel strand in pretensioned prestressed concrete members with rectangular cross-section including several material properties and design and manufacture parameters. To this end, a carefully selected database consisting of 207 different cases coming from 18 different sources spanning a variety of practical transfer length prediction situations was compiled. 16 single input features and 5 combined input features are analyzed. A widely used feedforward neural regression model was considered as a representative of several machine learning methods that have already been used in the engineering field. Classical multiple linear regression was also considered in order to comparatively assess performance and robustness in this context. The results show that the implemented model has good prediction and generalization capacity when it is used on large input data sets of practical interest from the engineering point of view. In particular, a neural model is proposed -using only 4 hidden units and 10 input variables-which significantly reduces in 30% and 60% the errors in transfer length prediction when using standard linear regression or fixed formulas, respectively.

• Structural Engineering and Mechanics
• /
• v.50 no.3
• /
• pp.323-347
• /
• 2014

This paper proposes a Particle Swarm Optimization (PSO) algorithm, which is improved by making use of the Harmony Search (HS) approach and called HS-PSO algorithm. A computer code is developed for optimal sizing design of non-linear steel frames with various semi-rigid and rigid beam-to-column connections based on the HS-PSO algorithm. The developed code selects suitable sections for beams and columns, from a standard set of steel sections such as American Institute of Steel Construction (AISC) wide-flange W-shapes, such that the minimum total cost, which comprises total member plus connection costs, is obtained. Stress and displacement constraints of AISC-LRFD code together with the size constraints are imposed on the frame in the optimal design procedure. The nonlinear moment-rotation behavior of connections is modeled using the Frye-Morris polynomial model. Moreover, the P-${\Delta}$ effects of beam-column members are taken into account in the non-linear structural analysis. Three benchmark design examples with several types of connections are presented and the results are compared with those of standard PSO and of other researches as well. The comparison shows that the proposed HS-PSO algorithm performs better both than the PSO and the Big Bang-Big Crunch (BB-BC) methods.

• Proceedings of the KIPE Conference
• /
• 1998.10a
• /
• pp.107-112
• /
• 1998

In this paper, we introduce the design method using CAE(Computer Aided Engineering) which is profitable in the compatibility and standardization of the developed product, and the reduction of construction time and price to develop and design a machine equipment. Particularly, we select the standard model to design or develop from the large machinery to the super precision one, extract the peculiar characters of the model by the close analysis on the physical and technical part, the experiment for the characteristics of objective dimensions by analogical mathematical analysis for previous results, and can induce the design model demanded by user investigating optimal data in the design previous. We present the analogical algorithms and process method of design factors and restriction factors in the systematization design with computer. Then we analyze step functions for each systematization equipment and induce the process of technical data with actuator model.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1996.11a
• /
• pp.851-856
• /
• 1996

In this paper, we introduce the design method using CAE(Computer Aided Engineering) which is profitable in the compatability and standardization of the developed product, and the reduction of construction time and price to develop and design a machine equipment. Particularly, we select the standard model to design or develop from the large machinery to the super precision one, extract the peculiar characters of the model by the close analysis of the physical and technical part, the experiment for the characteristics of objective dimensions by analogical mathematical analysis for previous results, and can induce the design model demanded by user investigating optimal data in the design previous We present the analogical algorithms and process method of design factors and restriction factors in the systematization design with computer. Then we analyze step functions for each systematization equipment and induce the process of technical data with actuator model.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.26 no.1
• /
• pp.141-149
• /
• 2002

A numerical simulation is performed for the cooling heat transfer of a heated cylindrical pedestal by an axisymmetric jet impingement. Based on the k- $\varepsilon$- f$\sub$${\mu}$/ model of Park et at., the linear and nonlinear stress-strain relations are extended. The Reynolds number based on the jet diameter(D) is fixed at Re$\sub$D/ = 23000. The local heat transfer coefficients are compared with available experimental data. The predictions by k- $\varepsilon$-f$\sub$${\mu}$/ model are in good agreement with the experiments, whereas the standard 7- f model does not properly resolve the flow structures.

• Structural Engineering and Mechanics
• /
• v.37 no.4
• /
• pp.385-399
• /
• 2011

The aim of this research is to model the behaviour of recently developed high force to volume (HF2V) passive energy dissipation devices using a simple finite element (FE) model. Thus, the end result will be suitable for use in a standard FE code to enable computationally fast and efficient analysis and design. Two models are developed. First, a detailed axial model that models an experimental setup is created to validate the approach versus experimental results. Second, a computationally and geometrically simpler equivalent rotational hinge element model is presented. Both models are created in ABAQUS, a standard nonlinear FE code. The elastic, plastic and damping properties of the elements used to model the HF2V devices are based on results from a series of quasi-static force-displacement loops and velocity based tests of these HF2V devices. Comparison of the FE model results with the experimental results from a half scale steel beam-column sub-assembly are within 10% error. The rotational model matches the output of the more complex and computationally expensive axial element model. The simpler model will allow computationally efficient non-linear analysis of large structures with many degrees of freedom, while the more complex and physically accurate axial model will allow detailed analysis of joint connection architecture. Their high correlation to experimental results helps better guarantee the fidelity of the results of such investigations.

• Geomechanics and Engineering
• /
• v.13 no.3
• /
• pp.475-488
• /
• 2017

Geotechnical data contributes substantially to the cost of engineering projects due to increasing cost of site investigations. Existing information in the form of soil maps can save considerable time and expenses while deciding the scope and extent of site exploration for a proposed project site. This paper presents spatial interpolation of data obtained from soil investigation reports of different construction sites and development of soil maps for geotechnical characterization of Multan area using ArcGIS. The subsurface conditions of the study area have been examined in terms of soil type and standard penetration resistance. The Inverse Distance Weighting method in the Spatial Analyst extension of ArcMap10 has been employed to develop zonation maps at different depths of the study area. Each depth level has been interpolated as a surface to create zonation maps for soil type and standard penetration resistance. Correlations have been presented based on linear regression of standard penetration resistance values with depth for quick estimation of strength and stiffness of soil during preliminary planning and design stage of a proposed project in the study area. Such information helps engineers to use data derived from nearby sites or sites of similar subsoils subjected to similar geological process to build a preliminary ground model for a new site. Moreover, reliable information on geometry and engineering properties of underground layers would make projects safer and economical.