• Journal of applied mathematics & informatics
• /
• v.28 no.3_4
• /
• pp.913-921
• /
• 2010

The derivative influence measure is adapted to the Cholesky decomposition of a covariance matrix. Formulas for the derivative influence of observations on the Cholesky root and the inverse Cholesky root of a sample covariance matrix are derived. It is easy to implement this influence diagnostic method for practical use. A numerical example is given for illustration.

• Journal of Power System Engineering
• /
• v.21 no.5
• /
• pp.48-54
• /
• 2017

The transfer influence coefficient method which is an vibration analysis algorithm based on the transfer of influence coefficient is applied to the free vibration analysis of double cylindrical shells. After the computational programs for the free vibration analysis of double cylindrical shells were made using the transfer influence coefficient method and the transfer matrix method, we compared the results using the transfer influence coefficient method with those by the transfer matrix method. The transfer influence coefficient method provided the good computational results in the free vibration analysis of double cylindrical shells. In particular, The results of the transfer influence coefficient method are superior to those of the transfer matrix method when the stiffness of internal springs connecting a inside cylindrical shell and a outside cylindrical shell is very large.

• Journal of the Society of Naval Architects of Korea
• /
• v.58 no.5
• /
• pp.330-338
• /
• 2021

This paper focuses on the improvement of the influence coefficient matrix method for estimation of local ice load on the icebreaking research vessel ARAON. The influence coefficient matrix relates ice pressure on the hull plate to the measured/calculated hull strain/stress. Conventionally von Mises equivalent stresses representing hull stresses and ice pressure acting on the hull plate are utilized to assemble the influence coefficient matrix. Because of the three dimensional features of the ship-ice collision process, an enhanced method to assemble the influence coefficient matrix is derived considering ice loads in the X, Y, and Z direction simultaneously. Furthermore the location of ice loads acting on hull-plate may fall outside the measuring sensor area, and the enhanced influence coefficient matrix is modified to reduce the difference between the actual and the estimated ice loads by expanding the domain outward from the sensor area. The developed method for enhanced influence coefficient matrix is applied to IBRV ARAON during the 2019 Antarctic ice field test and the local ice loads in three directions are efficiently calculated compared to those by a conventional method.

• 한국데이터정보과학회:학술대회논문집
• /
• 2001.10a
• /
• pp.13-16
• /
• 2001

We compare methods for detecting influential observations that have a large influence on the likelihood ratio test statistics that the two sets of variables are uncorrelated with one another. For this purpose we derive results of the deletion diagnostic, the influence function, the standardized influence matrix and the local influence. An illustrative example is given.

• Journal of the Korean Statistical Society
• /
• v.36 no.4
• /
• pp.457-469
• /
• 2007

Many procedures are available to identify a single outlier or an isolated influential point in linear regression and logistic regression. But the detection of influential points or multiple outliers is more difficult, owing to masking and swamping problems. The multiple outlier detection methods for logistic regression have not been studied from the points of direct procedure yet. In this paper we consider the direct methods for logistic regression by extending the $Pe\tilde{n}a$ and Yohai (1995) influence matrix algorithm. We define the influence matrix in logistic regression by using Cook's distance in logistic regression, and test multiple outliers by using the mean shift model. To show accuracy of the proposed multiple outlier detection algorithm, we simulate artificial data including multiple outliers with masking and swamping.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.10a
• /
• pp.528-533
• /
• 1995

An analyical method is proposed to construct a clamp jointed structure as an equivalent stiffness matrix element in the finite element modal analysis of a complex beam structure. Static structural analysis was first made for the detail finite element model of the clamp joint. Utilizing the results of this analysis, the equivalent stiffness matrix element was buildup by using the flexibility influence coefficient method and Guyan condensation. The proposed method was applied to finite element modal analysis of a clamp jointed cantilever beam. And the finite element analysis results were compared to those experimental modal analysis. Comparison shows doog agreement each other Furthermore the effects of normal contact(or clamping) load on the equivalent stiffness matrix was also examined. The equivalent stiffness matrix showed little change in spite of the remakable increase in the contact load on the clamp joint.

• Journal of Power System Engineering
• /
• v.17 no.1
• /
• pp.50-57
• /
• 2013

This describes the formulation for the free vibration of joined conical-cylindrical shells with uniform thickness using the transfer of influence coefficient. This method was developed based on successive transmission of dynamic influence coefficients, which were defined as the relationships between the displacement and the force vectors at arbitrary nodal circles of the system. The two edges of the shell having arbitrary boundary conditions are supported by several elastic springs with meridional/axial, circumferential, radial and rotational stiffness, respectively. The governing equations of vibration of a conical shell, including a cylindrical shell, are written as a coupled set of first order differential equations by using the transfer matrix of the shell. Once the transfer matrix of a single component has been determined, the entire structure matrix is obtained by the product of each component matrix and the joining matrix. The natural frequencies and the modes of vibration were calculated numerically for joined conical-cylindrical shells. The validity of the present method is demonstrated through simple numerical examples, and through comparison with the results of previous researchers.

• Journal of Power System Engineering
• /
• v.19 no.5
• /
• pp.52-59
• /
• 2015

This paper is presented for the free vibration of a conical shell with annular plates or circular plate using the transfer of influence coefficient. The governing equations of vibration of a conical shell, including annular plate, are written as a coupled set of first order differential equations by using the transfer matrix of the shell. Once the transfer matrix of a single component has been determined, the entire structure matrix is obtained by the product of each component matrix and the joining matrix. The natural frequencies and the modes of vibration were calculated numerically for joined conical-annular plates. The validity of the present method is demonstrated through simple numerical examples, and through comparison with the results of finite element method, transfer matrix method and ANSYS. The conclusion show that the present method can accurately obtain natural vibration characteristics of the conical shell with annular or circle end plates.

• Carbon letters
• /
• v.19
• /
• pp.57-65
• /
• 2016

Isroaniso matrix precursor synthesized from commercially available petroleum pitch was stabilized in air. The influence of oxygen mass gain during stabilization on the yield of matrix precursor was studied. Additionally, the influence of pressure on the yield of the stabilized matrix precursor in a real system was studied. The fourier transform infrared spectrometry (FTIR), thermogravimetric analysis (TGA), yield, yield rate, and yield impact were used to check the effect of stabilization and pressure on the yield of the matrix precursor and the end properties of the composite thereafter. The results showed that the yield increased with stabilization duration up to 20 h whereas it decreased for stabilization duration beyond 20 h. Further results showed that the stabilized matrix precursor for a duration of 5 h could withstand almost two-fold greater hot-pressing pressure without resulting in exudation as compared to that of a 1 h stabilized matrix precursor. The enhanced hot-pressing pressure significantly improved the yield of the matrix precursor. As a consequence, the densification and mechanical properties were increased significantly. Further, the matrix precursor stabilized for a duration of 20 h or more failed to provide proper and uniform binding of the reinforcement.

• KIEAE Journal
• /
• v.16 no.1
• /
• pp.47-55
• /
• 2016

Purpose: Long-life housing causes unavoidable cost increase while providing higher durability, flexibility, and repair easiness compare to those of normal apartment. The effectiveness should be evaluated considering the level of passing mandatory Long-life housing Certification System when supplying specific size of apartment complex. Thus, it is essential to identify the estimated costs and the obtainable grade by applying the optional element technologies selectively during the design phase. This study aimed to suggest the technology influence matrix(TIM) to support decision-making of element technologies in planning stage of long-life housing. Method: The technology influence matrix was established based on the property information about applicable element technologies for long-life housing such as construction methods, interface types, cost data, and certification-related characteristics. The usefulness of TIM was verified through case study, in which TIM was applied to the exclusive housing unit and the influences from four areas of quantity, cost, certification, and schedule were identified and calculated. Result: TIMs covering four areas representing the essential planning factors were developed, and are expected to contribute to sound decision-making in planning long-life housing.