Durable concrete mix proportion optimization method based on RF-NSGA-II

Abstract

The invention belongs to the technical field of concrete mix proportion optimization design, and particularly discloses a durable concrete mix proportion optimization method based on RF-NSGA-II. The method comprises the following steps: constructing a concrete durability index system, collecting sample data of each variable in the concrete durability index system, and establishing an original sample set according to the sample data; training a random forest regression calculation model by adopting the original sample set; evaluating the trained random forest regression calculation model to respectively generate random forest prediction models of concrete relative dynamic elastic modulus and chloride ion permeability coefficient; and taking the random forest prediction models as target functions, taking a value range of concrete materials and a mix proportion relationship among the materials as constraint conditions, and performing durable concrete mix proportion multi-target global optimization by adopting an NSGA-II model. The method is high in prediction precision, high in generalization capability and anti-noise capability, high in optimization precision, high in robustness andcapable of rapidly obtaining a globally optimal solution.

Description

technical field [0001] The invention belongs to the technical field of concrete mix ratio optimization design, and more specifically relates to a method for optimizing the mix ratio of durable concrete based on RF-NSGA-II. Background technique [0002] With the increasing application of concrete structures in various engineering practices, the durability of concrete in high-cold corrosive environments has become increasingly prominent, and single or coupled environmental effects such as freeze-thaw and salt intrusion have an increasing impact on the durability of concrete. The deterioration and damage of the concrete structure caused by this cannot be ignored. Concrete frost resistance and impermeability are two important indicators for evaluating the durability of concrete and predicting its life. They are related to raw materials and mix ratio factors. Therefore, it is important to study the optimization of concrete mix ratio based on frost resistance and impermeability. ...

AI Technical Summary

Problems solved by technology

[0003] At present, the research methods of concrete durability and mix ratio optimization mainly focus on the traditional orthogonal design test method. This method has many restrictions, the experimental search range is limited, and the research is time-consuming and costly. It is impossible to obtain ideal and realistic results. Mix ratio optimization results

With the rise of artificial intelligence technology and machine learning algorithms, some researchers use methods such as artificial neural networks and BP neural networks combined with particle swarm optimization for mix ratio optimization, but due to the network structure parameters of neural networks are not easy to determine and the learning speed is slow , the problem of low prediction accuracy, and the particle swarm algorithm cannot obtain the global optimal solution more accurately when searching for the optimal solution, so the existing methods have certain defects, and the research objects that have been achieved so far have not When it comes to the durability of concrete, there are few applications for intelligent optimization of mix ratios for multiple objectives

Images