Dam crack influence factor dynamic contribution rate analysis method

Abstract

The invention discloses a dam crack influence factor dynamic contribution rate analysis method. The dam crack influence factor dynamic contribution rate analysis method comprises the following steps:(1) normalizing dam crack influence factors and crack width sequence data respectively; (2) constructing a dam crack analysis model based on a random forest algorithm, wherein the dam crack analysis model takes the influence factors such as water level, temperature and aging factors as independent variables and takes crack width as dependent variables; (3) adjusting two important parameters of ntree and mtry in the dam crack analysis model, so that the model fitting effect is optimal; (4) utilizing the established model to discuss the influence of the water level factor, the temperature factorand the aging factor on the dam crack; and (5) analyzing the dynamic contribution rate of the water level, the temperature and the aging factor to the dam crack by using a sliding window method. Thedam crack influence factor dynamic contribution rate analysis method has important significance for dam crack analysis and monitoring, dam durability safety evaluation, dam construction and the like,and can provide effective guidance for safe use of the dam and reduction of property loss caused by dam failure.

Description

technical field [0001] The invention relates to the field of dam crack analysis, in particular to a dynamic contribution rate analysis method of dam crack influencing factors based on a random forest algorithm. Background technique [0002] As one of the main facilities of water conservancy and hydropower projects, dams are important projects related to the national economy and people's livelihood. Affected by load and environmental factors, cracks will inevitably appear in the dam during long-term service. The continuous expansion of cracks will seriously affect the overall safety of the dam body. If real-time and effective control measures cannot be taken for it, it may lead to Disastrous consequences such as dam breaks and floods have seriously threatened the lives and economic development of people downstream of the dam. Therefore, it is of great practical significance to monitor and analyze dam cracks. In the past analysis of dam cracks, most of them used multiple lin...

AI Technical Summary

Problems solved by technology

Generally speaking, the traditional multiple regression focuses on the linear and nonlinear relationship between variables, ignoring the interaction between variables. There may be a certain gap between the analysis of dam cracks and the actual situation, and it is impossible to analyze The dynamic change of influencing factors in the process of fracture development gives the corresponding change relationship

Images