接触网几何参数检测重复性评价方法

Repeatability Evaluation Method for OCS Geometric Parameter Detection

从接触网几何参数检测系统原理出发分析测量误差的影响因素,结合实际检测数据误差分布情况,指出测量误差服从正态分布并进行了正态性检验。在正态分布条件下构造了仅包含总体标准差一个未知量且服从卡方分布的统计变量,通过该统计变量对总体标准差的分布范围进行假设检验。推导样本数量与2类错误发生概率的关系,给出重复性评价所需样本数量的解析表达式。最后结合相关标准要求与实际情况给出样本数量、总体标准差上限等关键参数建议值,并通过实际检测数据对方法的有效性进行检验。

The influencing factors of the measurement error are analyzed based on the OCS geometric parameter detection system.According to the actual distribution of measurement data errors,the errors are indicated to follow the normal distribution,and the normality test is carried out.A statistical variable is constructed,containing only one unknown of the overall standard deviation and subject to the chi-square distribution under normal distribution conditions,through which hypothesis testing is carried out to evaluate the distribution range of the overall standard deviation.The relationship between the number of samples and the probability of occurrence of Type 2 errors is derived and the analytical expression of the number of samples required for repeatability evaluation is given.Finally,the recommended values of key parameters such as the number of samples and the upper limit of overall standard deviation are given in combination with the relevant standard requirements and the actual situation,and the validity of the proposed method is tested through the actual test data.