THE RESEARCH ON DETECTION METHODS OF GPS ABNORMAL MONITORING DATA BASED ON CONTROL CHART

In order to effectively detect GPS abnormal monitoring data, a mathematical model for the GPS observations outlier detection is established. A new method for outlier detection and early-warning of observations by controlling a chart in the statistical process is proposed. Since the GPS monitoring data are not normally distributed, transferring them to Q statistic by Kernel density estimation of cumulative distribution functions is raised, and based on this, the control chart of Q statistic used for GPS abnormal data detection is constructed. Finally, the detection capacity of a Shewhart control chart and a cumulative sum control chart on different abnormal offsets are compared and analyzed based on the simulation data. The results show that the two control charts offer certain advantages and complement each other. The Shewhart control chart is able to provide effective early-warning for the abnormal offsets 3 times of the standard deviations, but it is lacking in the detection capacity of small offsets; while the cumulative sum control chart can accurately detect the continuous small offsets even smaller as 0.5 times of the standard deviations, but the false alarm rate may be bigger with the increase of the offsets.