Abstract
Deformation is the most intuitive indicator of the actual working status of a concrete dam. Zoning the variation regulation of dam deformation is one of the key parts of dam safety evaluation and risk assessment. However, the sample points reflecting deformation and variation characteristic information are non-uniformly distributed, thus it is difficult to cluster the data samples by traditional clustering methods. To solve this problem, a spatio-temporal zoning method of dam deformation considering non-uniform distribution of monitoring information is proposed. Firstly, the preprocessed deformation data are utilized to establish the similarity-distance zoning indicators using the absolute deformation, the deformation increase and the relative deformation increase respectively; then the deformation data are transferred into the Cartesian coordinate system, known as sample points. Secondly, utilize the improved Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm to cluster the points. The clustering parameters $M$ and $\delta $ are determined by an optimization algorithm with an evaluation index as the objective function, then the sample points representing time sections or spatial monitoring points are clustered through dynamically updating the neighborhood radius value $\varepsilon $ . Moreover, several artificial data sets are selected to demonstrate that the improved DBSCAN algorithm is with more obvious superiority in non-uniform clustering compared to traditional algorithms. Deformation data of an existing concrete dam are presented and discussed to validate the established zoning method.
Highlights
Concrete dam is one of the most important dam types, which takes more than 60% of high dams over 200m in the world, it is of great significance to ensure its operation safety [1]
A spatio-temporal zoning method of dam deformation considering non-uniform distribution of monitoring information is proposed by taking deformation amplitude heterogeneity into account and improving the traditional Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering algorithm
The main conclusions are drawn as follows: 1) Based on the dam deformation characteristics and the zoning indicators in the traditional dam deformation zoning method, a similarity-distance zoning indicator characterizing the relative deformation increase is proposed, in order to objectively reflect the influence of deformation amplitudes of different deformation monitoring points
Summary
Concrete dam is one of the most important dam types, which takes more than 60% of high dams over 200m in the world, it is of great significance to ensure its operation safety [1]. Based on the temporal and spatial similarity-distance zoning indicators determined, the prototype monitoring data of dam deformation could be mapped to the Cartesian coordinate system as sample points, the clustering algorithm can be implemented. The proposed zoning method takes full advantage of the improved DBSCAN algorithm, including: a) high efficiency and capacity to find the irregularly shaped (e.g., non-spherical) and non-uniformly distributed clusters, like the sample point distribution shown in Figure 4(b); b) being able to effectively identify the noise sample points, the gross errors in the deformation sequence or the abnormal monitoring points could hardly affect the zoning results, improving the quality of the zoning results and reasonably demonstrating the overall variation regulation of dam deformation; c) automatic determination of the zone number without manually specifying the number beforehand. Higher precision rate and recall rate leads to larger F value, representing better zoning effect
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
