基于置信度议混凝土强度批量检测

Discussion on batch inspection of concrete strength based on confidence

在对混凝土强度进行批量检测时,需根据样本的平均值、标准差推定检验批的混凝土强度。国家现行规范有三种方法推定混凝土强度:①计算推定区间,并以推定区间的上限值作为混凝土强度推定值;②计算推定区间,并根据实际情况在推定区间取值;③用样本平均值减去1.645倍标准差作为推定值。本文通过分析三种方法的计算的理论依据,发现以推定区间上限值作为批量评定值会导致评定结果偏大,根据实际情况在推定区间取值随意性较大;用样本均值减去1.645倍标准差作为推定值不准确。本文建议用样本平均值减去k倍样本标准差,k值取为置信度γ=0.5所对应的单侧规范限k系数。

When inspecting the strength of concrete in batches,it is necessary to estimate the concrete strength of the inspection lot based on the average value and standard deviation of the sample.There are three methods to estimate concrete strength in the current national standards:①Calculate the estimated interval,and use the upper limit of the estimated interval as the inferred concrete strength;②Calculate the estimated value Interval,and determine the inferred interval according to the actual situation;③Subtract 1.645 times the standard deviation from the sample average.The article analyzes the theoretical basis of the three calculation methods and finds that using the upper limit of the presumption interval as the batch evaluation value will cause the evaluation result to be too large.According to the actual situation,the value of the presumption interval is more arbitrary;the sample mean is subtracted by 1.645 times the standard The difference is not accurate as an estimated value.The article recommends subtracting k times the sample standard deviation from the sample mean,and the k value is taken as the one-sided normative limit k coefficient corresponding to the confidence.