Abnormal value detection method and device for volatile organic compound observation data, equipment and medium

Abstract

The invention discloses an abnormal value detection method and device for volatile organic compound observation data, equipment and a medium. The method comprises the following steps: acquiring historical observation data of volatile organic compounds for a period of time; determining the abnormal thresholds and the normal data of the concentrations of the components in the historical observationdata of the volatile organic compounds; respectively training an isolated forest algorithm model and a local abnormal factor detection algorithm model by utilizing the normal data; and detecting single-time volatile organic compound observation data by using the abnormal threshold, the trained isolated forest algorithm model and the trained local abnormal factor detection algorithm model. According to the method, the volatile organic compound observation data is detected by using the abnormal threshold, the trained isolated forest algorithm model and the trained local abnormal factor detectionalgorithm model, so that the accuracy of a detection result can be greatly improved, and the application blank of a machine learning algorithm in the aspect of volatile organic compound observation data anomaly detection is filled.

Description

technical field [0001] The present application relates to the technical field of environmental monitoring, in particular to a method, device, equipment and medium for detecting abnormal values ​​of observation data of volatile organic compounds. Background technique [0002] Volatile organic compounds (Volatile Organic Compounds, referred to as VOCs) refer to organic compounds with high saturated vapor pressure and volatile at normal temperature and pressure. High concentrations of VOCs will have adverse effects on human activities and the ecological environment. Exposure to VOCs with a concentration exceeding a certain threshold can cause adverse symptoms such as headaches, nausea, and vomiting. Long-term exposure can cause convulsions, coma, memory loss, and even It has adverse effects on the human liver, kidneys and central nervous system; at the same time, as an important precursor of secondary organic aerosols and ozone, high concentrations of VOCs are one of the main f...

AI Technical Summary

Problems solved by technology

By setting the maximum and minimum thresholds for the observed values ​​of different species of VOCs, the observed data that are not within this range are marked as abnormal data and eliminated; this empirical method is difficult to take into account the differences between regions, and its thresholds cannot be reused at each observation point , and seldom consider the constraints between components (such as isobutane and n-butane, isopentane and n-pentane, m-p-xylene and o-xylene, acetylene and benzene, trans-2-butene and cis-2- The isomers of butene, trans-2-pentene and cis-2-pentene should have good correlation, and the components with good correlation are called characteristic correlation component pairs), while passing the global threshold It is also difficult to take into account the temporal variation characteristics of pollutant concentrations (threshold differences in different seasons) when performing outlier detection and elimination

Images