Anomaly Detection in Dam Behaviour with Machine Learning Classification Models

Abstract

Dam safety assessment is typically made by comparison between the outcome of some predictive model and measured monitoring data. This is done separately for each response variable, and the results are later interpreted before decision making. In this work, three approaches based on machine learning classifiers are evaluated for the joint analysis of a set of monitoring variables: multi-class, two-class and one-class classification. Support vector machines are applied to all prediction tasks, and random forest is also used for multi-class and two-class. The results show high accuracy for multi-class classification, although the approach has limitations for practical use. The performance in two-class classification is strongly dependent on the features of the anomalies to detect and their similarity to those used for model fitting. The one-class classification model based on support vector machines showed high prediction accuracy, while avoiding the need for correctly selecting and modelling the potential anomalies. A criterion for anomaly detection based on model predictions is defined, which results in a decrease in the misclassification rate. The possibilities and limitations of all three approaches for practical use are discussed.

A Spatial Model for Repairing of the Dam Safety Monitoring Data Combining the Variable Importance for Projection (VIP) and Cokriging Methods

“…Overall error analysis represented the cross-validation results of all measuring points in each measurement by calculating the mean absolute error (MAE). It analyzed the error sequence of each measurement as a whole, as seen in Equation (9). The lower the MAE, the higher the overall accuracy.…”

“…At present, the repair of safety monitoring data mainly starts from the dimension of time and mostly adopts linear regression analysis [6,7], principal component analysis [8], machine learning algorithm [9,10], and so on. Among them, Vazifehdan et al [11] proposed a method of combining a naive Bayesian network with tensor decomposition to repair missing data.…”

Intelligent Anomaly Identification of Uplift Pressure Monitoring Data and Structural Diagnosis of Concrete Dam

“…On the other hand, some scholars have studied the anomaly identification of uplift pressure during the operation period of concrete dams, and the applicability of various anomaly identification methods is compared [19]. The membership cloud method was proposed for identifying abnormal data by Zhu et al [20], and the uplift pressure monitoring data of the Gongzui gravity dam is identified.…”

Methodology for Monitoring Dams During Their Life Cycle in the Republic of Iraq Based on Digital Methods of Engineering Surveys and Information Modeling

“…Мониторинг нагрузок на конструкцию и ее реакцию на них может помочь в определении ненормального поведения этой конструкции. В целом мониторинг состоит как из измерений, так и из визуальных осмотров [2]. Для облегчения наблюдения за гидротехническими сооружениями они должны быть постоянно оборудованы соответствующими контрольноизмерительными приборами и/или пунктами наблюдения в соответствии с целями наблюдения, типом и размером сооружения, а также условиями площадки.…”