An efficient online outlier recognition method of dam monitoring data based on improved M-robust regression. (January 2023)

• Record Type: Journal Article
• Authors: Han, Zhang; Chen, Jiankang; Zhang, Fang; Gao, Zhiliang; Huang, Huibao; Li, Yanling
• Is Part Of: Structural health monitoring. Volume 22:Number 1(2023)
• Page Start: 581
• Page End: 599
• Publication Date: 2023-01
• Subjects: Outlier recognitions -- robust assessment -- AR model -- online dam safety monitoring -- data mining; Structural health monitoring -- Periodicals; Structural stability -- Periodicals; Strength of materials -- Periodicals; Nondestructive testing -- Periodicals; Constructions -- Stabilité -- Périodiques; Résistance des matériaux -- Périodiques; Contrôle non destructif -- Périodiques; Electronic journals; 624.17
• DOI: 10.1177/14759217221102060
• Languages: English
• ISSNs: 1475-9217

Abstract

Common anomaly recognition methods are easy to misjudge and miss outliers for the online monitoring data. This is a bottleneck problem that needs to be overcome in dam safety management moving toward informatization. Based on the data of nine hydropower stations along Dadu River Basin, this paper analyzed existing problems of the common anomaly identification method and an algorithm was proposed based on improved M-robust regression recognition. In this algorithm, the AR factor was introduced to avoid the defect that the traditional model cannot simulate random variables. The extreme value method and robust estimation were utilized to avoid the leverage effect. The model collapse caused by maximum measured value was avoided through improving the residual calculation model of M-robust and optimizing the weight distribution function. The maximum of the three values, residual quartile difference, discrete quartile difference, and measurement accuracy, was used as an anomaly recognition criterion to improve the evaluation criteria. The algorithm compiled was used in the Dadu River Company since 2017. The statistics showed that for the 150, 000 measured values per day, the evaluation time could be within 15 min, the missed judgment rate was 0%, and the misjudgment rate was less than 2%. The proposed algorithm achieved a great improvement and can meet the needs of online outlier recognition in dam safety management.