• Communications for Statistical Applications and Methods
• /
• 제5권3호
• /
• pp.905-926
• /
• 1998

We propose a modified mid P-value method to reduce the conservativeness for the inference of conditional associations in three-way contingency tables. This improves the ordinary mfd P-value method. For $2{\times} 2${\times} K$ tables, we propose confidence intervals for an assumed common odds ratio based on inverting two separate one-sided tests using the modified mid P-value. Also, an alternative and usually even better ways of constructing intervals, based on Inverting a two-sided test, are presented. The actual probability of coverage of a 100($1-\alpha$)% confidence interval is centered about the nominal level, but the modified mid P-value approach gives actual coverage probability even closer to the nominal level than the ordinary mid P-value approach.

• Wind and Structures
• /
• 제8권4호
• /
• pp.295-307
• /
• 2005

The paper describes the work of the IAWE Working Group WBG - Reliability and Code Level, one of the International Codification Working Groups set up at ICWE10 in Copenhagen. The following topics are covered: sources of uncertainties in the design wind load, appropriate design target values for the exceedance probability of the design wind load for different structural classes with different consequences of a failure, yearly exceedance probability of the design wind speed and specification of the design aerodynamic coefficient for different design purposes. The recommendations from the working group are summarized at the end of the paper.

• 동력기계공학회지
• /
• 제20권3호
• /
• pp.29-35
• /
• 2016

Because of the severe service environment of the large marine vessel, the fatigue strength and its evaluation play an important role in design and maintenance of marine crankshaft. The aim of this work is to investigate the probability distribution of fatigue lives in crank throw forged steel and to develop the methodology for estimation of the probabilistic design fatigue strength. Detailed studies were performed on the constant amplitude axial loading fatigue test. The experiments were controlled by stress ratio of -1 and 15Hz frequency for each stress level. The considerable variability of fatigue life was observed in each stress level under rigidly controlled constant fatigue testing conditions. The fatigue life of crank throw forged steel was well followed the log-normal and Weibull distribution. In addition, it can be used for the estimation of probabilistic design fatigue strength by using the proposed methodology.

• Journal of the Korean Statistical Society
• /
• 제28권1호
• /
• pp.125-133
• /
• 1999

We consider a FIFO single-server queueing model in which both the arrival and service processes are modulated by the amount of work in the system. The arrival process is a non-homogeneous Poisson process(NHPP) modulated by work, that is, with an intensity that depends on the work in the system. Each customer brings a job consisting of an exponentially distributed amount of work to be processed. The server processes the work at various service rates which also depend on the work in the system. Under the stability conditions obtained by Browne and Sigman(1992) we derive the exact stationary distribution of the work W(t) and the first exit probability that the work level b is exceeded before the work level a is reached, starting from x$\in$[a, b].

• 대한기계학회논문집A
• /
• 제25권10호
• /
• pp.1651-1658
• /
• 2001

It is necessary to evaluate fatigue strength and reliability of the connecting rod which is core part in automotive engine to assure the high level of durability of automobile. For this purpose, the loading conditions in automotive engine is obtained by the dynamic analysis. Based on these results, the critical section was identified by the finite element analysis. The fatigue strength under constant amplitude was evaluated and the mean of the fatigue limit at R = -2.27 derived from the staircase method was 311.2MPa. And the failure probability( F$\sub$p/ ) derived from the strength-stress interference model is 0.0003% at the 99.99% confidence level and the mean factor of safety was 4.2.

• 한국국방경영분석학회지
• /
• 제29권1호
• /
• pp.8-27
• /
• 2003

This paper develops a methodology that can be used to quantify the assesment of power improvement effectiveness of corps level C4I system applied to integrated fire operation by adapting Schuzer's C2 theory. This paper first describes how C4I systers can enhance the battle outcome in three way. : (1) Enhanced unit probability of survival; (2) Enhanced unit's individual effectiveness; improved exchange ratios; (3) Improved task force allocations : increased percentage of assets that can be assigned to a given engagement These enhancements are then show to result from improved probability of detection through information sharing; improved survivability and lethality through battle force coordination; and enhanced force allocation and prepositioning through improved timeliness of information(more advanced warning). It demonstrates that well-designed C4I systems can be shown to represent a significant force multiplier on the outcome of the battle.

• ETRI Journal
• /
• 제29권1호
• /
• pp.95-98
• /
• 2007

A low-profile phased array antenna with a low sidelobe was designed and fabricated using a genetic algorithm (GA). The subarray distances were optimized by GA with chromosomes of 78 bits, a population of 100, a crossover probability of 0.9, and a mutation probability of 0.005. The array antenna has 24 subarrays in 14 rows, and is designed as a mobile terminal for Ku-band satellite communication. The sidelobe level was suppressed by 6.5 dB after optimization, compared to the equal spacing between subarrays. The sidelobe level was verified from the far-field pattern measurement by using the fabricated array antenna with optimized distance.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2009년도 세계 도시지반공학 심포지엄
• /
• pp.584-590
• /
• 2009

One of the critical design problems involved in deep tunnelling in brittle rock, is the creation of surface spalling damage and breakouts. If weak fault zone is developed in deep tunnel, squeezing problem is added to the problems. According to the results of ground investigation in the study area, hard granitic rockmass and distinguished high angle fault zone are distributed on the tunnel level over 400m depth. To analyse the probability of brittle failure and squeezing, ground characterization with special lab. and field test were carried out. By the results, probability of brittle failures like spalling and rock burst is very low. But squeezing may be probable, if weak fault zone observed surface and drill core is extended to designed tunnel level.

• Journal of information and communication convergence engineering
• /
• 제9권1호
• /
• pp.38-43
• /
• 2011

This paper proposes a centralized backoff control scheme for guaranteeing fair packet transmissions in S-ALOHA CDMA system. In S-ALOHA CDMA system, simultaneously transmitted packets act as multiple access interferences, so that unsuccessful packet transmissions are caused entirely by multiple access interferences. Therefore, in order to maximize the system performance, the levels of MAI should be kept at an optimal level. In the proposed scheme, the base station broadcasts the packet transmission probability, which is calculated based on the level of MAI. Mobile stations attempt to transmit their packet with the received probability. Simulation results show that the proposed scheme can guarantee a good fairness among all the mobile stations.

• 한국해안해양공학회지
• /
• 제17권3호
• /
• pp.188-201
• /
• 2005

본 논문은 동해항 방파제를 대상으로 신뢰성 설계법을 비교하는 한 쌍의 논문의 첫 번째 부분이다. 제1부인 본 논문의 내용은 피복 블록의 안정성에 국한되며, 제 2부에서는 케이슨의 활동을 다룬다. 1980년대 중반이후 방파제에 대한 신뢰성 설계법이 본격적으로 제안되기 시작하였다. 신뢰성 설계법은 사용되는 확률적 개념의 정도에 따라 세 가지로 분류된다. Level 1 방법은 허용파괴확률에 따라 미리 계산된 부분안전계수를 이용하여 방파제를 설계하며, Level 2 방법은 하중과 저항 변수들의 정규분포를 가정하고 이들의 평균 및 표준편차로부터 신뢰도지수와 파괴확률을 계산한다. Level 3 방법은 하중과 저항 변수들에 대한 정규분포의 가정 없이 방파제 수명 동안의 누져 파괴량(예로서 피복 블록의 누적 피해)을 계산한다. 각 방법들은 서로 다른 설계 변수들을 계산하지만 이들을 모두 파괴확률로 나타내어 방법들 간의 차이를 비교할 수 있다. 본 연구에서는 기존의 결정론적 방법으로 설계, 시공된 후 1987년 피해를 입었던 동해항 방파제의 피복 블록 안정성에 대하여 피해 전과 보강 후의 단면에 대해서 각각 신뢰성 해석을 수행하였다. 그 결과 피해 전 단면의 파괴확률은 허용파괴확률을 크게 초과하는 반면 보강 후 단면의 파괴확률은 이보다 매우 작아서, 피해 전과 보강 후에 각각 과소 및 과대 설계되었음을 나타냈다. 한편, 서로 다른 세 가지 신뢰성 설계법의 결과가 대체로 잘 일치함을 보임으로써 각 방법 간에 큰 차이가 없음을 확인하였다.