Method for determining rebound modulus of BP neural network based on multi-population genetic algorithm optimization

Abstract

The embodiment of the invention provides a method for determining the rebound modulus of a BP neural network based on multi-population genetic algorithm optimization, and the method comprises the steps: firstly selecting a soil sample, and determining various physical indexes, including the liquid limit, plastic limit, plasticity index, maximum dry density, optimal moisture content, fine particlecontent and matrix suction of the soil sample, affecting the rebound modulus of the soil sample; measuring the true value of the rebound modulus of the selected soil sample; establishing a BP neural network rebound modulus determination model according to the measured various physical indexes influencing the rebound modulus of the soil sample; optimizing a BP neural network rebound modulus determination model based on a multi-population genetic algorithm to obtain a weight and a threshold which enable an error norm between a rebound modulus value output by the BP neural network and a true value of the rebound modulus value to be minimum and enable the accuracy to be highest; and finally, determining a rebound modulus value of the soil sample to be measured by adopting a BP neural network rebound modulus determination model optimized based on a multi-population genetic algorithm. The method is high in accuracy and efficiency and high in generalization.

Description

technical field [0001] The invention belongs to the technical field of road engineering, and relates to a method for determining a modulus of resilience based on a BP neural network optimized by a multi-population genetic algorithm. Background technique [0002] The modulus of resilience is used as a characterization parameter of the anti-deformation ability of subgrade soil, which describes the nonlinear stress-strain characteristics of subgrade soil under different loads, and can also reflect the dynamic characteristics of subgrade soil under driving loads. The modulus of resilience is particularly important in pavement design and is widely used in pavement structure design and performance evaluation. At present, my country's "Code for Design of Highway Cement Concrete Pavement" (JTG D40-2015) and "Code for Design of Highway Asphalt Pavement" (JTG D50-2017) both use the modulus of resilience as an important parameter in the design. [0003] The methods for determining the...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the embodiments of the present invention is to provide a method for determining the modulus of resilience based on a BP neural network optimized by a multi-population genetic algorithm, so as to solve the cumbersome establishment process and low accuracy of the modulus of resilience determination model established by the traditional method , the problem of large determination deviation, and the existing elastic modulus determination method can only determine the elastic modulus of one soil sample, and the problem of poor generalization

Images