An automatic data process line identification method for dam safety monitoring data outlier detection

Abstract

Summary In order to discover anomalies of dam structure behaviors and evaluate the operation status timely, it is quite demanding to analyze the dam safety monitoring data that has been collected from the instruments. However, outliers in original monitoring data may affect the accuracy of dam performance assessment, which need to be detected before analyzing monitoring data. Model‐based methods have been applied in outlier detection as a kind of common method for a long time, but they generally rely heavily on model accuracy and easily lead to misjudgment of outliers once the data structure is complex. Considering the monitoring data of dam effect variables (e.g., deformation, cracking, or seepage) tend to show strong continuity, complex periodic and trending changes with the environment, valid monitoring data can reflect the variation trend by forming a data process line. Therefore, data that deviate from the process line can be detected as outliers. In this paper, an automatic process line identification method for dam safety monitoring data outlier detection is proposed. First, after drawing a scatter plot of the dam monitoring data, a binary image of the scatter plot is inputted into the computer program. Afterwards, the binary image would be processed by Gaussian blur and image binarization techniques, and then the continuous points could be identified. After constant adjustment of the vertical ordinate range and introducing Cuckoo Search (CS) algorithm, the optimal process line identification and outlier detection were finally completed. The case studies demonstrate the proposed method can enhance the efficiency of outlier detection.

A collapse risk assessment method for subway foundation pit based on cloud model and improved Dempster-Shafer evidence theory

“…Instrument monitoring index system. Combining the risk characteristics of this project and related literature [24][25][26] , this paper selects surface settlement (F1), groundwater level (F2), horizontal displacement of wall top (F3) and vertical displacement of column (F4) as the risk assessment indexes of this pit, which are jointly controlled by cumulative values and change rates, as shown in Table 3. Considering that the risk assessment results and the actual monitoring value (the ratio K between the measured value and the early warning value) have the same trend, this paper takes the early warning value as the benchmark and converts each indicator into a dimensionless quantity through the value of K in order to realize the unification of risk indicators.…”

Deformation Prediction System of Concrete Dam Based on IVM-SCSO-RF

“…The maximum number of iterations of the PSO algorithm was set to 200, the total number of particles was set to 30, and the fitness function was set to be the OOB error of RF. Before optimization, the ranges of parameters n and m were set as [100, 1000] and [1,12], respectively.…”

“…The relevant parameters of the SCSO algorithm were set as follows: the maximum number of iterations was 200, the number of sand cats was 30, and the maximum sensitivity range was 2. Similarly, the ranges of parameters n and m were set as [100, 1000] and [1,12], respectively, and the fitness function was the OOB error of RF. The specific iterative process of SCSO-RF is shown in Figure 12.…”

“…Deformation monitoring is intuitive and reliable, which is the main content of concrete dam safety monitoring at home and abroad. The deformation prediction system of concrete dams built according to the monitoring values of deformation and environment factors can effectively reflect the change law of dam displacement and predict the development trend of deformation, and then scientifically analyze the evolution of its structural properties and evaluate the service state of the dam accordingly [11,12]. At present, the most commonly used deformation prediction method is the statistical model, which is easy to understand and realize, and its accuracy can meet the needs of the project.…”

Ordinary Kriging Interpolation Method Combined with FEM for Arch Dam Deformation Field Estimation

“…Meanwhile, the service performances of arch dams have a significant impact on people's lives and property [1][2][3]. Deformation can intuitively reflect the arch dam performance, and continuous deformation monitoring data in space can help to analyze and forecast the operational status of arch dam structure safety in real time [4,5]. Nevertheless, the number of dam monitoring points is limited, which is caused by some financial, logistical, and geological factors [6].…”