论文部分内容阅读
Q控制图的异常检出时间远长于参数已知时控制图的异常检出时间,对此提出了一种加权Q控制图方法.基于单容量样本度量和多容量样本度量,分别给出了相应算法,对算法的正确性给出了数学证明.加权Q控制图方法根据差分递减的权系数构造加权Q控制图的Q统计量,随后对该Q统计量使用Q控制图进行异常分析.仿真结果表明:加权Q控制图的异常检出时间短于Q控制图的异常检出时间,且与参数已知时的控制图的异常检出时间相差不大,综合考虑实用性和检测灵敏度这两个指标,加权Q控制图优于Q控制图和参数已知时的控制图.
Q control chart anomaly detection time is much longer than the known control chart anomaly detection time, this paper presents a weighted Q control chart method based on the single-capacity sample measurement and multi-capacity sample measurement, respectively, given the corresponding Algorithm is used to prove the correctness of the algorithm.Weighted Q control chart method constructs the Q statistic of the weighted Q control chart according to the differential descending weight coefficient and then analyzes the Q statistic using the Q control chart for the anomaly analysis. The results show that the abnormality detection time of the weighted Q control chart is shorter than the abnormal detection time of the Q control chart and there is not much difference between the abnormality detection time and the control chart when the parameters are known. Considering both practicality and detection sensitivity Indicators, weighted Q control charts are better than Q charts and control charts with known parameters.