Similar distance discrimination-based single index data quality control method

Abstract

The invention relates to a similar distance discrimination-based single index data quality control method. The above single index is an atmosphere environment single index. The method includes the following steps: S1, comparing the PM2.5 concentration with the PM10 concentration in each station, judging whether the concentrations are abnormal detection values or not, and carrying out next step calculation if not; S2, introducing detection data in a timed sequence; S3, screening normal values through the outlier degree P, and judging the remaining detection values as suspected abnormal values; S4, judging the suspected abnormal values screened in step S3 as normal monitoring values when the suspected abnormal values are in a 1 standard deviation range, and confirming the suspected abnormal values if the suspected abnormal values are not in the above range; S5, calculating the fluctuation degree q of the suspected abnormal values determined in S4, judging whether the suspected abnormal values are normal monitoring values or not, and confirming the suspected abnormal values if not; S6, calculating the volatility w of the detection data in each station at the suspected abnormal value confirmation time, and judging whether the detection data are abnormal or not through the w95% value; and S7, finally judging the values confirmed in step 1 and step 6 as abnormal values. The existence or not of the abnormal phenomenon of the data is judged from the data distance, the data fluctuation and the correlation among the stations. The method achieves the automatic auditing mechanism of the data, and effectively guarantees the data quality.

Description

technical field [0001] The invention relates to the technical field of quality control of monitored objects, in particular to a single-index data quality control method based on similarity distance discrimination. Background technique [0002] In view of the lack of automatic quality control means for atmospheric monitoring data, an algorithm is designed based on the data monitoring and compound adoption of the environmental monitoring station to realize the automatic intelligent quality control technology of atmospheric environmental monitoring data and solve the problem of lack of automatic quality control means for multi-source monitoring data To solve the problem, make the quality control of atmospheric monitoring equipment follow the same method system, and promote the development of remote automatic quality control technology for monitoring equipment. [0003] At this stage, due to the inconsistent data structure, type, and quality of various environmental observation ...

AI Technical Summary

Problems solved by technology

This method adds a lot of human resources, and manual review on the basis of massive data often leads to omissions or misjudgments.

Images