Concrete structure durability prediction method based on random forest and intelligent algorithm

Abstract

The invention belongs to the technical field of concrete structure impermeability prediction, and particularly discloses a method for predicting durability of a concrete structure based on a random forest and an intelligent algorithm. The method comprises the following steps: constructing a concrete impermeability index system, establishing an original sample set, taking the training number set asthe input of a random forest regression model; carrying out importance evaluation on influence factors of the impermeability index system; selecting an influence factor set with the minimum error ofthe random forest regression model; taking the optimal characteristic variable set as an input variable of the least squares support vector machine model, taking a concrete chloride ion diffusion coefficient prediction result as an output variable, training the least squares support vector machine model, and then verifying the prediction result of the trained least squares support vector machine model by adopting the test number set; and analyzing the prediction result, and verifying the effect of predicting the impermeability of the concrete structure by the least square support vector machine model. The method is high in prediction speed and accurate and reliable in prediction result.

Description

technical field [0001] The invention belongs to the technical field of predicting the impermeability of concrete structures, and more specifically relates to a method for predicting the durability of concrete structures based on random forests and intelligent algorithms. Background technique [0002] In recent years, in actual engineering, the incidents of structural damage due to insufficient durability of concrete have occurred frequently. As a widely used building material, the durability of concrete has attracted more and more attention at home and abroad. The early durability of concrete is generally reflected by indicators such as frost resistance, impermeability, and erosion resistance, among which impermeability is one of the important indicators reflecting the durability of concrete. Therefore, it is necessary to quickly and effectively predict the early impermeability of concrete It has important engineering application value. [0003] At present, many experts at ...

AI Technical Summary

Problems solved by technology

[0003] At present, many experts at home and abroad have conducted relevant research on the impermeability of concrete, but most of the research generally uses traditional experimental methods, and traditional experimental methods are affected by factors such as randomness of measurement data and systematic errors. There are many uncertainties in the permeation laws of the country. Using general statistical methods, the discreteness of experimental observation data is large, which often causes distortion of analysis results. Moreover, traditional experimental methods are often a long-term and complicated process, and the experimental period is long. Huge workload and relatively low research efficiency

[0004] With the continuous advancement of computer technology, some experts have also begun to turn their attention to the field of intelligent algorithms, trying to combine intelligent algorithms to conduct research on concrete impermeability, but the application of intelligent algorithms is still in its infancy, and most of them use a single Although intelligent prediction models such as convolutional neural network and BP neural network have effectively solved some complex problems in research, reduced errors, and improved research efficiency, the existence of a single intelligent model is highly dependent on the accuracy of the database. Inherent defects such as slow convergence and easy to fall into local optimum may lead to inappropriate and unreliable prediction results

In addition, the prediction of concrete impermeability has the characteristics of many influencing factors and complex noise interference. It is necessary to effectively select useful influencing factors in order to obtain more accurate prediction results

Images