Figure 1 - available via license: CC BY
Content may be subject to copyright.
Source publication
The availability of massive amount of dam safety monitoring data can make it difficult to analyze and characterize dam behavior. This article describes the use of the Cloud model to transform quantitative monitoring data into qualitative information. Each monitoring point returning dam safety data is regarded as a cloud drop, and parameters such as...
Context in source publication
Context 1
... backward cloud generator 32,33 is used to realize the conversion from quantitative representation to qualitative concept (Figure 1), that is, the numerical characteristics of the Cloud model can be obtained from the quantitative concept of cloud droplets (e.g. quantitative dataset of samples), thus realizing the mapping from quantitative to qualitative. ...
Citations
... Various ML methods have been utilized for data-driven modeling of dam structural behavior, such as feed-forward neural networks [6][7][8][9], extreme learning machines [10][11][12], recurrent neural network (RNN) [13][14][15], support vector regression (SVR) [16][17][18][19], Gaussian process regression [20][21][22], and decision treesbased ensemble models [23][24][25]. Besides, some novel datadriven methods or models have been proposed for dam health monitoring, including switching Kalman flter [26], dynamic time warping [27], panel data model [28], cloud model [29], correlated multi-target stacking [30], and spatiotemporal association mining [31]. Recently, the concept of automated machine learning (AutoML) has been also applied in dam response prediction. ...
Machine learning has become increasingly popular for modeling dam behavior due to its ability to capture complex relationships between input parameters and dam behavior responses. However, the use of sophisticated machine learning methods for monitoring dam behaviors and making decisions is often hindered by model uncertainty and a lack of interpretability. This paper introduces a novel model for dam health monitoring, focused on monitoring radial displacement and seepage, using optimized sparse Bayesian learning and sensitivity analysis. The model hyperparameters are optimized using an intelligent optimization method integrating the multi-population Rao algorithm and blocked cross-validation, while sensitivity analysis is employed to calculate the relative importance of input variables for a better understanding of the dam’s state. The effectiveness of the proposed model is verified by using long-term monitoring data of a prototype concrete arch dam. The results confirm that the proposed model provides satisfactory performance on both the point predictions and the interval predictions for dam structural behaviors while obtaining effective explainability.
... The similarity computing of cloud concept has been widely used in classification, clustering, similarity search, collaborative filtering, target recognition, watermarking technology research, system evaluation, similarity analysis of DNA sequence, data mining of stock time series and other fields [36][37][38][39][40][41][42]. At present, there are three main methods to calculate the similarity of cloud concepts. ...
Based on the characteristics of human cognition and the cloud model, the excursion of uncertain concepts by the similarity between uncertain concepts from the perspective of conceptual cognition is studied. Firstly, considering the different meanings of the numerical characters in cloud concept, the properties of cloud concepts similarity are given. Furthermore, in order to reflect the various similarities that may exist in uncertain concept, five similarities between cloud concepts are constructed, specifically include the similarity between concept expectations, the similarity between concept entropy, the similarity between concept hyper entropy, the shape similarity and the overall similarity. Secondly, the rationality of these proposed similarity measurements is illustrated by comparing with the existing methods through the specific data analysis. Finally, two cognitive experiments, including concept cognitive processes without prior knowledge and concept cognitive processes with prior knowledge (including positive prior knowledge and negative prior knowledge), are designed. These experiments are all used to study the excursion in the process of concept cognition by the similarity of cloud concepts. The experiment results show that the proposed similarities are reasonable by comparing the proposed method with the existing ones, and the effectiveness of the proposed method is also verified by the excursion of concept cognition.
It is significant to adopt scientific temperature control criteria for high concrete dams in the construction period according to practical experience and theoretical calculation. This work synthetically uses information entropy and a cloud model and develops novel in situ observation data-based temperature control indexes from the view of a spatial field. The order degree and the disorder degree of observation values are defined according to the probability principle. Information entropy and weight parameters are combined to describe the distribution characteristics of the temperature field. Weight parameters are optimized via projection pursuit analysis (PPA), and then temperature field entropy (TFE) is constructed. Based on the above work, multi-level temperature control indexes are set up via a cloud model. Finally, a case study is conducted to verify the performance of the proposed method. According to the calculation results, the change law of TFEs agrees with actual situations, indicating that the established TFE is reasonable, the application conditions of the cloud model are wider than those of the typical small probability method, and the determined temperature control indexes improve the safety management level of high concrete dams. Research results offer scientific reference and technical support for temperature control standards adopted at other similar projects.
The seepage field of tailings dam is closely related to the safety state. Real-time evaluation of seepage field safety based on monitoring data is of great significance to ensure the safe operation of tailings pond. The premise of accurately evaluating the safety status is to ensure reliability of the data, and it is necessary to identify the anomalies of the monitoring data. Because of the complex influence factors of seepage field of tailings dam, the traditional anomaly identification method based on regression model fails due to its low fitting accuracy. Therefore, a novel abnormal identification method of monitoring data based on improved cloud model and radial basis function neural network model, which can accurately identify anomaly data and distinguish the environmental quantity response. Based on the coupling relationship between the seepage field and the slope stability, the surrogate model between the depth of saturation line and the safety factor of slope stability is constructed, and the real-time safety evaluation method of seepage field is put forward. The proposed methods are applied to an engineering example. The misjudgment rates of the abnormal data identification method are less than 5%, and it has better applicability than the traditional regression model. The constructed real-time safety evaluation model accurately reflected the health status of the seepage field, and realized the quantitative assessment of the safety of tailings dam. This provides reliable data support for the operation management and the risk control of tailings pond.
A 3D tailings dam visualization early warning system was developed based on GIS (geographic information system) combining ARIMA (autoregressive integrated moving average model) and 3S (RS, GIS, GPS) technology for prediction of phreatic line changes and tailing dam deformation. It was applied for monitoring and early warning for the gold–copper tailing dam in Zijinshan Dadongbei tailing pond. The system consists of equipment management, data management, prediction, monitoring and early warning, and 3D visualization modules. It is able to do data management, visualization and disaster prediction, and early warning based on 79 monitoring points of rainfall, infiltration line, and deformation of the tailing dam in the Zijinshan mine. The design and application of the system reflect its features of rich functionality, high practicality, intuitive effect, and high reference value. The system solves the problems of low visualization of monitoring data, poor management of multiple data, and feasible prediction and early warning of point–surface combination. It realizes high-precision prediction of key factors and real-time warning of disaster.
