Monitoring data analysis method based on hierarchical network structure

Abstract

The invention discloses a monitoring data analysis method based on a hierarchical network structure. The method comprises the following steps of step 1, constructing a dam hierarchical tree accordingto a physical network structure of a monitoring instrument; step 2, carrying out recombination and allocation on the weight according to the initial local weight and the dam hierarchical tree proposedin the step 1; step 3, carrying out single-point analysis on each leaf node of a bottom layer of the dam hierarchical tree according to a 3sigma judgment standard in order to obtain an analysis result of each leaf node; step 4, constructing an analysis result matrix and a weight matrix of child nodes, multiplying the matrixes to obtain an analysis result of a parent node, and computing analysis results of all network nodes from the leaf nodes of the dam hierarchical tree to a root node layer by layer according to the method; and step 5, constructing an artificial neural network analysis model, and training the analysis model by using the analysis results obtained in the step 4 as sample data, wherein the model analysis results can provide a basis for comprehensive evaluation of dam safety.

Description

technical field [0001] The invention relates to a monitoring data analysis method based on a layered network structure, which belongs to the technical field of dam safety analysis, specifically constructs a dam layered tree based on the physical network structure of the monitoring instrument of the dam, and constructs a dam layered tree in the dam layered tree structure Next, a method for security analysis of monitoring data through artificial neural network. Background technique [0002] The sensor monitoring network is a window for data collection. It can continuously perceive a large amount of data, and collect, store and transmit the data, laying the foundation for data analysis. Due to the different areas where the sensors are distributed and multiple interference factors from the outside world, the data collected by the sensors may be abnormal. The main reasons for the abnormal data are: (1) specific events occurred in the area where the sensor nodes are distributed; (...

AI Technical Summary

Problems solved by technology

Due to the different areas where the sensors are distributed and multiple interference factors from the outside world, the data collected by the sensors may be abnormal. The main reasons for the abnormal data are: (1) specific events occurred in the area where the sensor nodes are distributed; (2) Due to its own software and hardware failure or energy exhaustion, it causes work errors; (3) Due to the influence of external factors, the data collected by sensor nodes is deviated (measurement error)

Images