• Communications for Statistical Applications and Methods
• /
• 제24권1호
• /
• pp.43-65
• /
• 2017

We propose a flexible cure rate survival model by assuming that the number of competing causes of the event of interest has the Poisson distribution and the time for the event follows the gamma-G family of distributions. The extended family of gamma-G failure-time models with long-term survivors is flexible enough to include many commonly used failure-time distributions as special cases. We consider a frequentist analysis for parameter estimation and derive appropriate matrices to assess local influence on the parameters. Further, various simulations are performed for different parameter settings, sample sizes and censoring percentages. We illustrate the performance of the proposed regression model by means of a data set from the medical area (gastric cancer).

• Journal of the Korean Statistical Society
• /
• 제25권3호
• /
• pp.347-358
• /
• 1996

A new test for goodness-of-fit is presented. It is a modification of a test of LaRiccia (1991). These tests are applicable to continuous lo-cation/scale models. The new test statistic is based on a few selected order statistics taken from the sample, while the LaRiccia test is based directly on the full sample. Each test embeds the hypothesized model in a larger linear model and proceeds to test the goodness-of-fit hy-pothesis by testing the coefficients of this linear model appropriately. The general theory is presented. The tests are compared via computer simulation to a related test of Ali and Umbach (1989) for distributions that could be used as lifetime models. An important aspect of all these tests is that only standard $X_2$ tables are used. Selection of the spacings of the order statistics is discussed.

• Wind and Structures
• /
• 제3권2호
• /
• pp.133-142
• /
• 2000

Engineered structures such as buildings and bridges in certain regions of the world need to be designed to withstand tropical cyclone winds, otherwise known as typhoons or hurricanes. In order to carry out this design, it is necessary to be able to estimate the maximum wind speeds likely to be encountered by the structure over its expected lifetime, say 100 years. Estimation of the maximum wind involves not only the overall strength of the tropical cyclone, but the variation of wind speed with radius from the centre, circumferential position, and with height above the ground surface. In addition, not only the mean wind speed, but also the gust factor must usually be estimated as well. This paper investigates a number of recent mathematical models of tropical cyclone structure and comments on their suitability for these purposes in a variety of scenarios.

• International Journal of Safety
• /
• 제1권1호
• /
• pp.36-42
• /
• 2002

This paper is aimed at predicting the life of rubber insulating gloves under normal operating stresses from relatively rapid test performed at higher stresses. Specimens of rubber insulating gloves are subject to multiple stress conditions, i.e. combined electrical and thermal stresses. Two modes of electrical stress, step voltage stress and constant voltage stress are used in specimen aging. There are two types of test for electrical stress in this experiment: the one is Breakdown Voltage (BDV) test under step voltage stress and thermal stress and the other is lifetime test under constant voltage stress and temperature stress. The ac breakdown voltage defined as the break-down point of insulation that leakage current excesses a limit value, l0mA in this experiment, is determined. Because the very high variability of aging data requires the application of statistical model, Weibull distribution is used to represent the failure times as the straight line on Weibull probability paper. Weibull parameters are deter-mined by three statistical methods i.e. maximum likelihood method, graphical method and least squares method, which employ SAS package, Weibull probability paper and FORTRAN, respectively. Two chosen models for predicting the life under simultaneous electrical and thermal stresses are inverse power model and exponential model. And the constants of life equation for multistress aging are calculated using numerical method, such as Gauss Jordan method etc.. The completion of life equation enables to estimate the life at normal stress based on the data collected from accelerated aging test. Also the comparison of the calculated lifetimes between the inverse power model and the exponential model is carried out. And the lifetimes calculated by three statistical methods with lower voltage than test voltage are compared. The results obtained from the suggested experimental method are presented and discussed.

• Smart Structures and Systems
• /
• 제14권1호
• /
• pp.39-54
• /
• 2014

Node layout optimization of structural wireless systems is investigated as a means to prolong the network lifetime without, if possible, compromising information quality of the measurement data. The trade-off between these antagonistic objectives is studied within a multi-objective layout optimization framework. A Genetic Algorithm is adopted to obtain a set of Pareto-optimal solutions from which the end user can select the final layout. The information quality of the measurement data collected from a heterogeneous WSN is quantified from the placement quality indicators of strain and acceleration sensors. The network lifetime or equivalently the network energy consumption is estimated through WSN simulation that provides realistic results by capturing the dynamics of the wireless communication protocols. A layout optimization study of a monitoring system on the Great Belt Bridge is conducted to evaluate the proposed approach. The placement quality of strain gauges and accelerometers is obtained as a ratio of the Modal Clarity Index and Mode Shape Expansion values that are computed from a Finite Element model of the monitored bridge. To estimate the energy consumption of the WSN platform in a realistic scenario, we use a discrete-event simulator with stochastic communication models. Finally, we compare the optimization results with those obtained in a previous work where the network energy consumption is obtained via deterministic communication models.

• Journal of Astronomy and Space Sciences
• /
• 제34권4호
• /
• pp.289-302
• /
• 2017

The key risk analysis technologies for the re-entry of space objects into Earth's atmosphere are divided into four categories: cataloguing and databases of the re-entry of space objects, lifetime and re-entry trajectory predictions, break-up models after re-entry and multiple debris distribution predictions, and ground impact probability models. In this study, we focused on reentry prediction, including orbital lifetime assessments, for space situational awareness systems. Re-entry predictions are very difficult and are affected by various sources of uncertainty. In particular, during uncontrolled re-entry, large spacecraft may break into several pieces of debris, and the surviving fragments can be a significant hazard for persons and properties on the ground. In recent years, specific methods and procedures have been developed to provide clear information for predicting and analyzing the re-entry of space objects and for ground-risk assessments. Representative tools include object reentry survival analysis tool (ORSAT) and debris assessment software (DAS) developed by National Aeronautics and Space Administration (NASA), spacecraft atmospheric re-entry and aerothermal break-up (SCARAB) and debris risk assessment and mitigation analysis (DRAMA) developed by European Space Agency (ESA), and semi-analytic tool for end of life analysis (STELA) developed by Centre National d'Etudes Spatiales (CNES). In this study, various surveys of existing re-entry space objects are reviewed, and an efficient re-entry prediction technique is suggested based on STELA, the life-cycle analysis tool for satellites, and DRAMA, a re-entry analysis tool. To verify the proposed method, the re-entry of the Tiangong-1 Space Lab, which is expected to re-enter Earth's atmosphere shortly, was simulated. Eventually, these results will provide a basis for space situational awareness risk analyses of the re-entry of space objects.

• 한국수소및신에너지학회논문집
• /
• 제24권1호
• /
• pp.50-60
• /
• 2013

High temperature proton exchange membrane fuel cells (PEMFCs) using phosphoric acid (PA) doped polybenzimidazole (PBI) membranes have been concentrated as one of solutions to the limits with traditional low temperature PEMFCs. However, the amount of reported experimental data is not enough to catch the operational characteristics correlated with cell performance and durability. In this study, design of experiments (DOE) based operational optimization method for high temperature PEMFCs has been proposed. Response surface method (RSM) is very useful to effectively analyze target system's characteristics and to optimize operating conditions for a short time. Thus RSM using central composite design (CCD) as one of methodologies for design of experiments (DOE) was adopted. For this work, the statistic models which predict the performance and degradation rate with respect to the operating conditions have been developed. The developed performance and degradation models exhibit a good agreement with experimental data. Compared to the existing arbitrary operation, the expected cell lifetime and average cell performance during whole operation could be improved by optimizing operating conditions. Furthermore, the proposed optimization method could find different new optimal solutions for operating conditions if the target lifetime of the fuel cell system is changed. It is expected that the proposed method is very useful to find optimal operating conditions and enhance performance and durability for many other types of fuel cell systems.

• 한국수소및신에너지학회논문집
• /
• 제30권6호
• /
• pp.556-566
• /
• 2019

Recently, as the supply of residential polymer electrolyte membrane fuel cells (PEMFCs) increases, the durability and lifetime of the PEMFC system are becoming important. The related studies have been mainly focused on the durability and lifetime of materials while the research on the durability and maintenance of the system level is insufficient. In this paper, a model-based fault detection method is developed considering an air supply system that is dominant to the system performance and efficiency. A commercial 1 kW residential fuel cell system is built, and experiments are conducted under various operation loads and states (normal, 6 faults). From the experimental data, nominal models and residuals are generated. With the residual pattern obtained from real-time data, the detection and classification of various faults can be possible. The technical importance of this paper is to minimize extra sensor installation by using the empirical model rather than a complex mathematical model, and to decrease the number of models by using the applicable model at three loads. Finally, the model-based fault detection method for the air supply system of a PEMFC is established and is expected to be applicable to other subsystems.

• 공업화학
• /
• 제35권1호
• /
• pp.48-53
• /
• 2024

전기화학 기반의 SEI 성장 모델을 이용하여 리튬이온 배터리의 캘린더 노화 및 장기 수명을 예측하였다. 네 가지 유형의 장기 SEI 성장 모델(용매 확산 제한 모델, 전자 이동 제한 모델, 리튬-간극 확산 제한 모델, 반응 제한 모델)을 적용하여 수치해석이 이루어졌고, 캘린더 에이징 동안의 용량 감소와 리튬 재고 손실을 계산하였다. 수치해석 결과, 전자 이동 제한 모델과 리튬-간극 확산 제한 모델이 낮은 용량 감소를 보였으며, 용매 확산 제한 모델과 반응 제한 모델은 10년이내에 80%의 용량 감소를 보였다. 캘린더 노화 중 저온 보관 시 SEI의 성장을 저하시켜 용량 감소가 적었다. 사이클링 중 C-rate가 증가할수록 SEI 두께 증가로 수명 하락이 크게 나타났으나 그 차이는 크지 않았다.

• Communications for Statistical Applications and Methods
• /
• 제25권3호
• /
• pp.245-261
• /
• 2018

Attempts have been made to define new classes of distributions that provide more flexibility for modelling skewed data in practice. In this work we define a new extension of the generalized gamma distribution (Stacy, The Annals of Mathematical Statistics, 33, 1187-1192, 1962) for Marshall-Olkin generalized gamma (MOGG) distribution, based on the generator pioneered by Marshall and Olkin (Biometrika, 84, 641-652, 1997). This new lifetime model is very flexible including twenty one special models. The main advantage of the new family relies on the fact that practitioners will have a quite flexible distribution to fit real data from several fields, such as engineering, hydrology and survival analysis. Further, we also define a MOGG mixture model, a modification of the MOGG distribution for analyzing lifetime data in presence of cure fraction. This proposed model can be seen as a model of competing causes, where the parameter associated with the Marshall-Olkin distribution controls the activation mechanism of the latent risks (Cooner et al., Statistical Methods in Medical Research, 15, 307-324, 2006). The asymptotic properties of the maximum likelihood estimation approach of the parameters of the model are evaluated by means of simulation studies. The proposed distribution is fitted to two real data sets, one arising from measuring the strength of fibers and the other on melanoma data.