Influence of sample size on strength distribution of advanced ceramics
Influence of sample size on strength distribution of advanced ceramics
复制标题
DOI：
10.1016/j.ceramint.2013.08.093
复制
发表时间：
2014-04
影响因子：
5.2
通讯作者：
Serkan Nohut
中科院分区：
文献类型：
--
作者：
Serkan Nohut
先进陶瓷材料的强度分布大多采用威布尔分布函数来表征。威布尔分布是否总是对强度数据给出最佳拟合的问题在过去几年中一直被考虑。样本量影响不同分布函数（例如，正态分布、对数正态分布、伽马分布或威布尔分布）区分的可靠决策。本文利用5100个氧化铝强度实验数据和Monte Carlo模拟生成的虚拟强度数据，研究了试样尺寸对先进陶瓷强度分布的影响。建议至少用150-200个样品来确定最佳拟合分布函数，统计误差为10%。对试验强度数据进行的极值分析表明，威布尔分布与试验强度数据拟合最好，威布尔分布与Gumbel分布之间的差异出现在尾部。
Strength distribution of advanced ceramics is mostly characterized by Weibull distribution function. The question whether the Weibull distribution always gives the best fit to strength data has been being considered in the last years. The sample size affects the reliable decision of discrimination of different distribution functions (e.g. normal, log-normal, gamma or Weibull). In this paper, 5100 experimental alumina strength data and virtual strength data generated by Monte Carlo simulations are used in order to investigate the effect of sample size on strength distribution of advanced ceramics. It is suggested that, at least 150–200 samples should be used for determination of best fitting distribution function with a statistical fallibility of 10%. Extreme Value Analysis performed with the experimental strength data showed that the Weibull distribution fits the data best and difference between the Weibull and Gumbel distributions appear at the tails.