Outlier Detection Based on Multivariable Panel Data and K-Means Clustering for Dam Deformation Monitoring Data

A dam is a super-structure widely used in water conservancy engineering fields, and its long-term safety is a focus of social concern. Deformation is a crucial evaluation index and comprehensive reflection of the structural state of dams, and thus there are many research papers on dam deformation data analysis. However, the accuracy of deformation data is the premise of dam safety monitoring analysis, and original deformation data may have some outliers caused by manual errors or instruments aging after long-time running. These abnormal data have a negative impact on the evaluation of dam structural safety. In this study, an analytical method for detecting outliers of dam deformation data was established based on multivariable panel data and K-means clustering theory. First, we arranged the original spatiotemporal monitoring data into the multivariable panel data format. Second, the correlation coefficients between the deformation signals of different measuring points were studied based on K-means clustering theory. Third, the outlier detection rules were established through the changes of the correlation coefficients. Finally, the proposed model was applied to the Jinping-I Arch Dam in China which is the highest dam in the world, and results indicate that the detection method has high accuracy detection ability, which is valuable in dam safety monitoring applications.

A three-stage online anomaly identification model for monitoring data in dams

The monitoring of data anomaly identification is an important basis for dam safety online monitoring and evaluation. In this research, a cluster of anomaly identification models for dam safety monitoring data was constructed, and a three-stage online anomaly identification method was proposed to discriminate outliers. The proposed method combined anomaly detection for measured values based on a single-point time series simulation, measurement error reduction based on remote retesting and spatio-temporal analysis, and environmental response mutation recognition. It brought about efficient and accurate detection for data mutation and online classified identification for its inducement. Additionally, problems such as missing outliers, misjudging normal values induced by the environmental response, and difficulty in online identification for measurement errors were effectively solved. The research productions were applied to the online monitoring system for the safety risk of reservoirs and dams in the Dadu River Basin. The results showed that the proposed method could effectively improve the accuracy of anomaly identification and reduce the misjudgment and omission rate to less than 2%. It could also successfully recognize and subtract nonstructural anomalies such as accidental errors, instrument faults, and environmental responses online, which provided reliable data for online dam safety monitoring.

Processing Method of Missing Data in Dam Safety Monitoring

A large amount of data obtained by dam safety monitoring provides the basis to evaluate the dam operation state. Due to the interference caused by equipment failure and human error, it is common or even inevitable to suffer the loss of measurement data. Most of the traditional data processing methods for dam monitoring ignore the actual correlation between different measurement points, which brings difficulties to the objective diagnosis of dam safety and even leads to misdiagnosis. Therefore, it is necessary to conduct further study on how to process the missing data in dam safety monitoring. In this study, a data processing method based on partial distance combining fuzzy C-means with long short-term memory (PDS-FCM-LSTM) was proposed to deal with the data missing from dam monitoring. Based on the fuzzy clustering performed for the measurement points of the same category deployed on the dam, the membership degree of each measurement point to cluster center was described by using the fuzzy C-means clustering algorithm based on partial distance (PDS-FCM), so as to determine the clustering results and preprocess the missing data of corresponding measurement points. Then, the bidirectional long short-term memory (LSTM) network was applied to explore the pattern of changes of measurement values under identical clustering conditions, thus processing the data missing from monitoring effectively.

Development of Dam Safety Remote Monitoring and Evaluation System

More than 4,000 dams are constructed in Thailand for several purposes, including water supply, flood control, irrigation, and hydropower generation. Among these dams, 14 large dams are operated by the Electricity Generating Authority of Thailand (EGAT). As a dam operator, EGAT is committed to ensuring dam safety by regularly conducting dam inspections and maintenance. This paper presents the development and practical applications of the Dam Safety Remote Monitoring System (DS-RMS). The objective of DS-RMS is to enhance the EGAT’s implementation of its dam safety program in terms of dam monitoring by instrumentation to satisfy international recommendations. DS-RMS consists of five subsystems: Dam Behavior, Reservoir Operation, Earthquake Monitoring, Expert System and Public Communication. DS-RMS has been deployed at 14 large EGAT-operated dams across the country since 2016. Results show that the novel features of DS-RMS enable faster and more reliable dam safety monitoring and evaluation processes.

Dam Safety: Monitoring of Tailings Dams and Safety Reviews

The awareness to tailings dam safety monitoring and reviews has increased by the catastrophes resulting from failures of such dams worsened by increasing tailings waste and construction of larger dams. The losses born by the mining industry from high costs of compensations and environmental rehabilitation work have brought this matter into focus. In the present article the need for safety monitoring programs of tailings dam is highlighted and mode of failures and factors leading to them are described. Basic principles of such programs are investigated with all phenomena needing observation described and their impacts explained. As in conventional dams this work is carried out by visual inspections and use of similar methods and instruments. In similar manners in both types of dams’ observation and measurements are done for measuring seepage water quantity and quality, phreatic surface level and pore pressure and total earth pressure values in addition to deformation measurements; and all are done by similar devices and methods such as weirs, piezometers, inclinometers, settlement plates and geodetic surveying. Basic differences between safety monitoring systems of the two types of dam, however, are presented in a tabular form. The continuity of safety monitoring of tailings dams is emphasized not only during the long construction phase but also after that in the abandonment and closure phase which can last indefinitely in order to watch for possible adverse effects on the environment and ecosystem due to the winds eroding and carrying of poisonous tailings contents, in addition to contaminated seepage water entering surface water streams and ground water. Justifications for using real time monitoring systems for recording and transmitting all data to the control center are presented with emphasis given on savings in both labor and time and need for the discovery of warning signs enabling raising earlier the alarm of possible failure or incident and the early taking of preventive measures. In this article it is argued that, in spite of the large investment of installing and running cost of comprehensive dam safety monitoring systems in tailings dams, such costs are justified as they form only a small percentage of the total investment in the tailings facilities projects, and may save huge costs if failure does happen. Such systems may be considered as an additional insurance against such events.