A self-matching model for online anomaly recognition of safety monitoring data in dams

Abstract

The online anomaly recognition of real-time dam safety monitoring data, such as deformation and seepage data from the automatic sensing instruments (e.g., the osmometer and the multi-point displacement meter), has the premise of ensuring data reliability, and it is also one of the core functional modules of online dam safety monitoring. To compensate for the limitation of a single method to identify outliers and further improve the reliability and the rapidity of the anomaly recognition of dam safety monitoring data, a self-matching model based on data-types for online anomaly recognition (SMM) was proposed in this paper. Based on a detailed classification of dam safety monitoring data sequences, this article describes a comparison and analysis of the applicability of a statistical regression model based on the least-squares regression (LSR) model and the online robust recognition and early warning (RREW) model for different datatype sequences. For the single-step-type sequences and normal-type sequences with low fitting accuracy, which could not be completely identified by the two models above, an improved cloud model recognition method based on the diurnal variation rate (ICM) was proposed to compensate for the limitations. Finally, the SMM was determined, that is, the LSR model was used for the multi-point-outlier-type and normal-type sequences with high fitting accuracy, the RREW model method was used for the double-step-type and oscillatory-type sequences, and the ICM method was used for the single-step-type sequences and normal-type sequences with low fitting accuracy. The engineering application of the Dadu River Basin showed that this method effectively solved the problems of low calculation efficiency and a 2% misjudgment rate when using the RREW model alone, and this method greatly improved the accuracy and timeliness of the anomaly recognition of dam safety monitoring data, so it had important theoretical significance and engineering application value.

A Dam Safety State Prediction and Analysis Method Based on EMD-SSA-LSTM

“…This involves learning and summarizing the evolving patterns of measured data through empirical data analysis [10][11][12]. By establishing appropriate monitoring data prediction models, it is possible to simulate and predict the dam's own behavior, providing proactive measures for the safe operation of the dam [13][14][15][16]. The research on monitoring models primarily focuses on three main aspects: (1) mathematical relationships between dependent and independent variables; (2) rational selection of independent variables and addressing multicollinearity; and (3) improving model accuracy, robustness, and generalization.…”

An LSTM-based anomaly detection model for the deformation of concrete dams

“…This method has been widely used. 1,19,26,[27][28][29][30][31] In addition, the typical small probability method is to make the probability distribution statistics of the monitoring data under different load combinations to determine the control limits of the target variable using the probability density function and the probability of dam failure. 32 Based on the idea of typical small probability, Prakash et al 33 calculated the distribution of the squared prediction error (SPE) and determined two control limits based on its cumulative distribution curve.…”