Similarity analysis of dam behavior characterized by multi-monitoring points based on Cloud model

Abstract

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 the expectation, entropy, and hyper-entropy of the monitoring data are obtained through a backward cloud generator to represent the operational state of the dam. The monitoring points are then treated as vectors, and the cloud similarity is calculated using the cosine value of the angle between them. The cloud similarity coefficient is then determined to characterize the similarity of dam behavior. Experimental analysis shows that the process of identifying cloud parameters has a good effect on the discovery of abnormal monitoring values regarding dam safety and demonstrates the feasibility of characterizing the dam behavior. Clustering analysis is applied to the similarity coefficients to further achieve the hierarchical management of dam monitoring points.