An online anomaly recognition and early warning model for dam safety monitoring data

Abstract

Anomaly recognition and early warning of monitoring data are of great significance in the field of modern dam safety management. Multidimensional least-squares regression model with the Pauta criterion is a well-known traditional method, but it is easy to misjudge the normal value and miss the outliers. Thereby, an online robust recognition and early warning model combining robust statistics and confidence interval is proposed to detect outliers. The threshold is set based on the derived confidence interval and the scale estimator (derived from the location M-estimator). Monitoring data obtained from a gravity dam and a rockfill dam were taken as examples to demonstrate the robust recognition and early warning model. The results show that the proposed method can effectively improve the reliability of anomaly recognition and early warnings, which is valuable in engineering applications.