摘要
首次将统计方法应用于射频仿真系统的可靠性分析中,总结出其应采用的一般方法。采用Grubbs准则对校准系统测得的实验数据中的粗大数据进行滤除,接着分别采用数据比较法和阿贝检验法对定值和变值两种系统误差是否显著进行检验,如果系统误差显著,则应采用实验比对的方法消除之,使随机性成为数据的主导因素。采用χ2-分析法确定数据概率分布,对合格区间进行概率密度的积分以确定可信度。这种方法易于通过编程实现,并由校准系统自动完成可信度评估。给出了它的算法描述与应用效果实例。
The statistical method was used in error analysis of a Radio Frequency Simulation System （RFSS） for the first time, A general method was summarized from sstudying specific systems in which statistics is applied. After data collection by calibration equipment, gross error data were eliminated on Grubbs＇s criterion, Then the significance of the invariable and variable errors of the system was tested separately by groups＇ data compassion and Abbe criterion, If the errors are significant, the systematical errors will be mitigated by comparison with more precise system so that the data can have a pure random character. After that, the X^2 method was used to get the probability density function （PDF） of the data. The reliability of the study object was estimated by integral calculation in the qualified interval on PDE This method can be easily carried out by programming and can be evaluated by the calibrating equipment, in addition, the arithmetic for programming was described with examples.
出处
《系统仿真学报》
EI
CAS
CSCD
北大核心
2007年第7期1548-1550,1585,共4页
Journal of System Simulation
