Parameter characterization method for gradation and shape of coarse-grained soil in compaction construction

By screening and analyzing the grading and shape parameters of coarse-grained soil, combining machine learning algorithms to establish a regression model, identifying key parameters that affect the compaction effect, solving the problem that it is difficult to accurately identify factors affecting the compaction effect of coarse-grained soil in the existing technology, and achieving a more efficient compaction process and better compaction quality.

CN119720806AActive Publication Date: 2025-03-28CENT SOUTH UNIV
3 Cites 0 Cited by

Patent Information

Application Number
CN202510216275.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-02-26
Publication Date
2025-03-28
Estimated Expiration
2045-02-26

AI Technical Summary

Technical Problem

The prior art is difficult to accurately identify the main factors affecting the compaction effect of coarse-grained soil, and cannot effectively guide the scientific selection of construction equipment, resulting in high energy consumption, low construction efficiency during compaction process, and difficult to ensure compaction quality.

Method used

By obtaining coarse-grained soil for screening and recombination, representative grading and shape parameters were screened in combination with hierarchical clustering and principal component analysis methods, and then a vibration compaction test was performed. A machine learning algorithm was used to establish a regression model between grading parameters and shape parameters and dry density, and identify key parameters that affect the compaction effect.

Benefits of technology

The precise identification of coarse soil particles grading and shape parameters is achieved, and suitable materials and parameters can be selected reasonably, and the compaction process can be optimized, thereby improving compaction efficiency and ensuring better compaction effect.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a parameter characterization method for gradation and shape of coarse-grained soil in compaction construction. The parameter characterization method comprises the following steps: S1, acquiring the coarse-grained soil; s2, combining a plurality of coarse-grained soil with different grades; carrying out primary screening on the grading parameters to obtain representative grading parameters; s3, performing three-dimensional scanning to obtain the particle shape of the coarse-grained soil; primarily screening the shape parameters to obtain representative shape parameters; s4, preparing a plurality of groups of coarse-grained soil, and representing the coarse-grained soil by adopting representative grading parameters and representative shape parameters; respectively carrying out a vibration compaction test; s5, based on vibration compaction test data, adopting a machine learning algorithm to establish a regression model between the grading parameters and the dry density and between the shape parameters and the dry density; key parameters influencing the compaction effect are recognized through the SHAP value obtained through the regression model. According to the method, the key parameters having remarkable influence on the compaction effect are screened out, proper materials and parameters can be reasonably selected in the construction process, and the compaction technology is optimized.
Need to check novelty before this filing date? Find Prior Art