• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.36 no.4
• /
• pp.59-63
• /
• 2013

In biomass gasification, efficiency of energy quantification is a difficult part without finishing the process. In this article, a radial basis function neural network (RBFN) is proposed to predict biomass efficiency before gasification. RBFN will be compared with a principal component regression (PCR) and a multilayer perceptron neural network (MLPN). Due to the high dimensionality of data, principal component transform is first used in PCR and afterwards, ordinary regression is applied to selected principal components for modeling. Multilayer perceptron neural network (MLPN) is also used without any preprocessing. For this research, 3 wood samples and 3 other feedstock are used and they are near infrared (NIR) spectrum data with high-dimensionality. Ash and char are used as response variables. The comparison results of two responses will be shown.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2010.09a
• /
• pp.416-422
• /
• 2010

Estimating condition of geotechnical structures are difficult because of nonlinear time dependency and seasonal effects. Measuring data of structure failure is highly variable in time and space, and a unique approach cannot be defined to model structure movements. Characteristics of movements are obtained by using a statistical method called Principal Component Analysis(PCA). The PCA is a non-parametric method to separate unknown, statistically uncorrelated source processes from observed mixed processes. Instead, since the "best" mathematical relationship is estimated for given data sets of the input and output measured from target systems. As a consequence, this method is advantageous in modeling systems whose geomechanical properties are unknown or difficult to be measured.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.10a
• /
• pp.830-835
• /
• 1995

To quickly determine the effect of the substitute component on the machine's performance is very important in the defign and the manufacturing processes. And minimizing machine cost and maximizing machine quality mandata predictability of machine accuracy. In the study, in order to evaluate the effects of the component's geometric errors and dimensions on the machining accuracy of gantry-type 5-axis machining centers, a geometric error analysis and virtual manufacturing system is developed based on the mathematical model for the shape generation motion of machine tool considering the component's geometric errors and dimensions, the solid modeling techniques and so on.

• IE interfaces
• /
• v.15 no.1
• /
• pp.10-19
• /
• 2002

New trends such as electronic commerce, virtual organizations, e-business applications, etc. increase the dependence of production management on information software systems and contribute to the needs for global, distributed object systems. This paper presents a component based approach for production management systems under the multi-tier distributed information system architecture using UML(Unified Modeling Language), CORBA(Common Object Request Broker Architecture) and XML(eXtensible Markup Language) technologies, and propose rules for mapping a UML class diagram to a XML DTD (Document Type Definition). And we adapt it to the prototype system implementation. The components are implemented by CORBA and we use XML messages for the information exchange between components.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2001.05a
• /
• pp.535-539
• /
• 2001

In these days. the finite element method(FEM) is a very common method for not only a simple vibration analysis but also the optimization of structures. Since the finite element model may contain thousands of degree of freedom, the eigensolutions require extreme computing power, which will result in a serious time-consuming problem. Thus, many researchers have challenged to find more improved modeling techniques and calculating methods to overcome such problems. The Guyan reduction method and the substructure synthesis method are typical examples of such methods. Of the substructure synthesis method, the component mode synthesis method (CMS) is widely used for dynamic analysis of structure. In this study. for the efficient analysis of jet loom structure. Component Mode Synthesis was carried out. The results of the finite element program developed are compared with those of the commercial package program ANSYS for the validation of the program. The results obtained by the program showed a good agreement with those of ANSYS. The program will be further refined and verified by test to yield more accurate results.

• 제어로봇시스템학회:학술대회논문집
• /
• 1990.10b
• /
• pp.884-889
• /
• 1990

In this paper, a new hybrid position control algorithm for the direct drive arm is proposed. The proposed control is composed of discrete feedforward component and continuous feedback component. The discrete component is the nominal torque which approximately compensates the strong nonlinear coupling torques between the links, while the continuous control is a modified version of sliding mode control which is known to have a robust property to the disturbances of system. For the proposed control law, we give sufficient condition which guarantees the bounded tracking error in spite of the modeling errors, and the efficiency of the proposed algorithm is demonstrated by the numerical simulation of a three link manipulator position control with payloads and parameter errors.

• Communications for Statistical Applications and Methods
• /
• v.24 no.1
• /
• pp.97-113
• /
• 2017

This paper proposes a method for sufficient dimension reduction (SDR) of mixture data. We consider mixture data containing more than one component that have distinct central subspaces. We adopt an approach of a model-based sliced inverse regression (MSIR) to the mixture data in a simple and intuitive manner. We employed mixture probabilistic principal component analysis (MPPCA) to estimate each central subspaces and cluster the data points. The results from simulation studies and a real data set show that our method is satisfactory to catch appropriate central spaces and is also robust regardless of the number of slices chosen. Discussions about root selection, estimation accuracy, and classification with initial value issues of MPPCA and its related simulation results are also provided.

• 제어로봇시스템학회:학술대회논문집
• /
• 1990.10a
• /
• pp.7-12
• /
• 1990

In this paper, we propose a new manipulator control scheme based on the CMAG neural network. The proposed control consists of two components. The feedforward component is an output of trained CMAC neural network and the feedback component is a modified sliding mode control. The CMAC accepts the position, velocity and acceleration of manipulator as input and outputs two values for the controller : One is the nominal torque used for feedforward compensation(M1 network) and the other is the inertia matrix related information used for the feedback component(M2 network). Since the used control algorithm guarantees the robust trajectory tracking in spite of modeling errors, the CMAC mapping errors due to the memory limitation are little worth consideration.

• Communications for Statistical Applications and Methods
• /
• v.13 no.1
• /
• pp.113-123
• /
• 2006

Normal mixture model(NMM) frequently used to cluster genes on microarray gene expression data. In this paper some of component means of NMM are modelled by a linear regression model so that its design matrix presents the pattern between sample classes in microarray matrix. This modelling for the component means by given design matrices certainly has an advantage that we can lead the clusters that are previously designed. However, it suffers from 'overfitting' problem because in practice genes often are highly dimensional. This problem also arises when the NMM restricted by the linear model for component-means is fitted. To cope with this problem, in this paper, the use of the factor analyzer NMM restricted by linear model is proposed to cluster genes. Also several design matrices which are useful for clustering genes are provided.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.439-442
• /
• 2002

Powertrain simulation is important far the analysis of a vehicle performance. Automotive powertrain has been considered as the unified system and should be remodeled, whenever a powertrain system is changed. In this study, a new method is proposed far the synthetic modeling for the automotive powertrain. Components are separated from the powertrain system and constructed the matrix through dynamic relationships. The dynamic equation of the total powertrain system can be driven from the combination of each component. In order to combine each component, the superposition method is modified for the powertrain composition.