A three-stage advanced online identification method for abnormality of dam safety monitoring data

Abstract

The invention discloses a three-stage advanced online identification method for dam safety monitoring data anomalies, comprising the following steps: 1) data anomaly identification, including dividing data types, constructing data identification model clusters, matching data types and identification models; 2) Measurement error reduction, including single accidental error reduction and instrument troubleshooting; 3) Change-induced variation reduction in environmental quantities, including data sequence construction for environmental quantity reduction, construction of data sequence early warning thresholds for environmental quantity reduction, and environmental response identification. The invention solves the problem that the traditional single data anomaly identification method is prone to misjudgment of normal measurement value and omission of abnormal measurement value, improves the accuracy of online identification of data anomaly, and at the same time realizes accidental errors, monitoring instrument failures, environmental quantity changes, etc. Classification and online identification of non-structural mutations and structural mutations induced by structural behavior deterioration.

Description

technical field [0001] The invention relates to the field of dam safety monitoring, in particular to a three-stage progressive online identification method for abnormal dam safety monitoring data. Background technique [0002] At present, there are many methods for abnormal identification of dam safety monitoring data, including Lait criterion method, statistical regression model, catastrophe theory, fuzzy cluster analysis, etc. The statistical regression model method based on Lait’s criterion is most commonly used in the online identification of dam safety monitoring data anomalies because it can comprehensively reflect the impact of environmental quantities, is convenient to calculate, has low programming difficulty, and has high reliability. This method adopts the Rait criterion to set the abnormal early warning threshold for the residual sequence. For the data sequence with large sample size, normal distribution and moderate value, the effect of online abnormality identi...

AI Technical Summary

Problems solved by technology

Traditional methods cannot identify the causes of data anomalies online, and cannot classify and identify non-structural changes induced by monitoring instrument failures, changes in environmental quantities, etc., and structural changes induced by deterioration of structural behavior. Screening and abnormal identification have low recognition and poor timeliness, which is not conducive to real-time monitoring and evaluation of dam safety performance

Images