讨论了随机参数服从非正态分布前轴的可靠性优化设计问题。
This paper examines the reliability optimization design for front-axle with non-normal distribution parameters.
计量资料差异性比较采用单因素方差分析，非正态分布资料经正态转换后再作统计学处理。
Difference of measurement data was compared with single factor analysis of variance. After normal transformation, the non-normal distribution data were conducted with statistical disposal.
可避免的不一致性可能导致多重模态分布或非正态分布，可能会对应用程序性能造成可度量的影响。
Avoidable inconsistencies may lead to multimodal or non-normal distributions and may have a measurable impact on application performance.
对非正态分布、相关变量随机场进行了处理，依据可靠指标的几何意义建立了可靠度计算的优化算法。
Based on the geometric meaning of the reliability index, the optimization method for the reliability computation is constructed, and the correlated abnormal distribution random fields are addressed.
因此，本文选择了R／S分析法，它不仅能对正态分布序列进行分析，还能对非正态分布序列进行分析。
So this paper selects Rescaled Range (R/S) Analysis which not only analyses normal distribution series but also analyses non-normal distribution series.
结果当应变量非正态分布时，直接应用现有回归树算法不能得出正确的分析结论；而当存在极端值时这一问题更为严重。
Results Default arithmetic of regression tree can't be used directly under the condition of non-normal distribution, existence of outlier would make the problem more severity.
本文在对非正态分布过程控制方法分析的基础上，提出了适用范围更广、操作更简便的约翰逊曲线拟合非正态分布数据的过程控制方法。
On the basis of that, it provides a wider and easier method - using Johnson curves to describe non - normal data in process control.
结果：在数据服从正态和对数正态分布时，次序统计量回归效果明显优于简单替换法；资料服从非正态分布资料时，次序统计量回归方法没有明显优势。
Objective: the purpose of this study was to compare the performance of regression on order statistics(ROS) and substitution methods in estimation of nondetects.
结果：在数据服从正态和对数正态分布时，次序统计量回归效果明显优于简单替换法；资料服从非正态分布资料时，次序统计量回归方法没有明显优势。
Objective: the purpose of this study was to compare the performance of regression on order statistics(ROS) and substitution methods in estimation of nondetects.
应用推荐