• Journal of the Korean Data and Information Science Society
• /
• 제2권
• /
• pp.11-21
• /
• 1991

A different approach to the evaluation of mean residual life function under the random censorship model is presented. For small sample sizes, the performances between the proposed estimator and other estimators for men residual life function are compared in terms of bias and mean square error via a Monte Carlo study.

• 대한수학회지
• /
• 제43권2호
• /
• pp.225-239
• /
• 2006

In [5], Csorgo and Zitikis exposed the strong $uniform-over-[0,\;{\infty}]$ consistency, and weak $uniform-over-[0,\;{\infty}]$ approximation of the empirical mean residual life process by employing weight functions. We carry on the uniform asymptotic behaviors of the empirical mean residual life process over the whole positive half line by representing the process as an integral form. We compare our results with those of Yang [15], Hall and Wellner [8], and Csorgo and Zitikis [5].

• 설비공학논문집
• /
• 제10권6호
• /
• pp.658-665
• /
• 1998

This paper investigates local exhaust effectiveness in a room with a supply and an exhaust slots on the ceiling. The mean age of air is an indicator of supply effectiveness, while the mean residual life time can be used as an indicator of exhaust effectiveness. The distribution of local mean residual life time in a space is calculated by four different numerical procedures. The reverse-flow calculation method has been proved to show quite accurate results while it can save considerable amount of computation time and efforts, compared to the method by its original definition. It is concluded that the diffusion term in the equation of mean residual life time can be neglected. The spatial and temporal diffusion characteristics of the contaminant are also discussed.

• International Journal of Reliability and Applications
• /
• 제7권2호
• /
• pp.177-186
• /
• 2006

Typical confidence intervals for a mean or mean residual life (MRL) are centered about the mean or mean residual life. We discuss novel confidence intervals that produce statements like "we are 95% confident that the MRL function, e(t), is greater than a prespecified $\mu_o$ for all t in the interval [0, $\hat{\theta})$)" where $\hat{\theta}$ is determined from the sample data, confidence level, and $\mu_o$. Also, we can have statements like 'we are 95% confident that the MRL of population 1, namely $e_1$(t), is greater than the MRL of population 2, $e_2$(t), for all t in the interval [0, $\hat{\theta}$)" where $\hat{\theta}$ is determined from the sample data and confidence level. We illustrate these one and two sample confidence intervals on internal bonds (tensile strengths) for an important modem engineered wood product, called medium density fiberboard (MDF), used internationally.

• International Journal of Air-Conditioning and Refrigeration
• /
• 제10권4호
• /
• pp.177-183
• /
• 2002

A pulsed tracer gas technique is applied to measure the distributions of local mean age and local mean residual-life-time of air in a half-scale experimental chamber, The airflow patterns in the chamber are visualized by a Helium bubble generator for three different exhaust locations. A supply slot is located at the top of a right wall, and an exhaust slot is at either bottom-left (Case 1), bottom-right (Case 2), or top-left (Case 3) location. Results show that the distributions of local mean age and local mean residual-life-time are different from each other, but both of them are closely related to the airflow pattern in the space. Included are discussions on explaining the variations of overall room ventilation effectiveness depending upon airflow rates for three different supply-exhaust configurations.

• 대한기계학회논문집A
• /
• 제27권1호
• /
• pp.175-182
• /
• 2003

The fatigue life of welded joints is sensitive to welding residual stress and complexity of their geometric shapes. To predict the fatigue life more reasonably. the effects of welding residual stress and its relaxation on their fatigue strengths should be considered quantitatively, which are often regarded to be equivalent to the effects of mean stresses by external loads. The hot-spot stress concept should be also adopted which can reduce the dependence of fatigue strengths for various welding details. Considering the factors mentioned above, a fatigue life prediction model using the modified Goodman's diagram was proposed. In this model, an equivalent stress was introduced which is composed of the mean stress based on the hot-spot stress concept and the relaxed welding residual stress. From the verification of the proposed model to real welding details, it is proved that this model can be applied to predict reasonably their fatigue lives.

• International Journal of Reliability and Applications
• /
• 제7권1호
• /
• pp.1-11
• /
• 2006

The better mean residual life at $t_0\;(BMRL-t_0)$ class of life distribution is introduced by Kulasekara and Park (1987). They proved that the $BMRL-t_0$ class contains the DMRL class, but it is a proper subclass of the NBUE class. In this paper we develop a new family of tests for testing exponentiality against the $BMRL-t_0\;(WMRL-t_0)$ alternatives based on the goodness of fit approach. It is shown that the suggested test is better than the one introduced by Kulasekara and Park (1987) in the sense of Pitman asymptotic efficiency values.

• Journal of the Korean Statistical Society
• /
• 제22권2호
• /
• pp.147-157
• /
• 1993

In the survivla analysis the problem of estimating mean residual life function (MRLF) under random censoring is very important. In this paper we propose and study a nonparametric estimator of MRLF, which is a functional form based on the estimator of the survival function due to Susarla and Van Ryzin (1980). The proposed estimator is shown to be better than some other estimators in terms of mean square errors for the exponential and Weibull cases via Monte Carlo simulation studies.

• 대한기계학회논문집A
• /
• 제21권9호
• /
• pp.1498-1506
• /
• 1997

Procedures are presented for influence of shot peening on fatigue strength, fatigue life and effects of shot peening are discussed from experiments were taken between shot peened and unpeened SPS5, SM45C specimens. After the residual stress on shot peened specimens was measured by X-ray diffractometer, rotating bending fatigue tests were carried out. In addition, the compressive residual stress profile was obtained by the superposition method of three stresses which is based on Al-Obaid's equation. Predicted fatigue life considering residual stress profile which was obtained by the Al-Obaid's equation and another predicted fatigue life considering residual stress profile which was measured in test were compared. For the purpose of predicting fatigue life, Morrow's equation considering the residual stress and mean stress was used.

• 한국신뢰성학회지:신뢰성응용연구
• /
• 제18권3호
• /
• pp.220-228
• /
• 2018

Purpose: The purpose of this study is to investigate the tail behavior of the life distribution which exhibits an increasing failure rate or other positive aging effects after a certain time point. Methods: We characterize the tail behavior of the life distribution with regard to certain reliability measures such as failure rate, mean residual life and reliability function and derive several stochastic properties regarding such life distributions. Also, utilizing an L-statistic and its asymptotic normality, we propose new nonparametric testing procedures which verify if the life distribution has an increasing tail failure rate. Results: We propose the IFR-Tail (Increasing Failure Rate in Tail), DMRL-Tail (Decreasing Mean Residual Life in Tail) and NBU-Tail (New Better than Used in Tail) classes, all of which represent the tail behavior of the life distribution. And we discuss some stochastic properties of these proposed classes. Also, we develop a new nonparametric test procedure for detecting the IFR-Tail class and discuss its relative efficiency to explore the power of the test. Conclusion: The results of our research could be utilized in the study of wide range of applications including the maintenance and warranty policy of the second-hand system.