A Method for Predicting the Durability of Concrete Structures Based on Random Forest and Intelligent Algorithm

Abstract

The invention belongs to the technical field of anti-seepage prediction of concrete structures, and specifically discloses a method for predicting the durability of concrete structures based on random forests and intelligent algorithms. Including: constructing the concrete impermeability index system, establishing the original sample set, using the training data set as the input of the random forest regression model, evaluating the importance of the influencing factors of the anti-seepage index system, and selecting the one with the smallest error in the random forest regression model Factor set, the optimal feature variable set is used as the input variable of the least squares support vector machine model, the prediction result of the concrete chloride ion diffusion coefficient is used as the output variable, the least squares support vector machine model is trained, and then the test is adopted The prediction result of the least squares support vector machine model after training is verified by the data set; the prediction result is analyzed to verify the effect of the least squares support vector machine model on predicting the impermeability of the concrete structure. The prediction speed of the method of the invention is fast, and the prediction result is accurate and reliable.

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