Method and device for measuring void ratio of coarse aggregate based on three-dimensional point cloud features, computer program product and storage medium

By using a method based on 3D point cloud features, combined with a multilayer perceptron model and Bayesian optimization algorithm, the problems of large human error and long time consumption in coarse aggregate porosity measurement are solved, and high-precision and fast porosity prediction is achieved.

CN122244525APending Publication Date: 2026-06-19GUIZHOU RAILWAY CONSTR ENG QUALITY INSPECTION CONSULTING CO LTD +2
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
GUIZHOU RAILWAY CONSTR ENG QUALITY INSPECTION CONSULTING CO LTD
Filing Date
2026-03-23
Publication Date
2026-06-19

AI Technical Summary

Technical Problem

Existing technologies for measuring the porosity of coarse aggregates suffer from problems such as significant human influence, long processing time, and low accuracy, making it difficult to meet high-precision requirements, especially in engineering applications.

Method used

A method based on 3D point cloud features is adopted to obtain a 3D model of coarse aggregate, extract multi-dimensional morphological feature parameters and gradation information, and combine a multilayer perceptron model and Bayesian optimization algorithm to achieve rapid and accurate prediction of porosity.

Benefits of technology

It achieves high-precision prediction of the porosity of coarse aggregates, reduces human error, improves measurement efficiency, and meets the high-precision requirements of engineering applications.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122244525A_ABST
    Figure CN122244525A_ABST
Patent Text Reader

Abstract

This invention discloses a method for measuring the porosity of coarse aggregates based on three-dimensional point cloud features. The method involves acquiring the three-dimensional point cloud features of the coarse aggregate sample to be tested, and constructing a three-dimensional model of the sample based on these features. Multiple multi-dimensional morphological feature parameters of the aggregate particles in the sample are extracted from the three-dimensional model. The gradation information of the coarse aggregate sample is fused with these multi-dimensional morphological feature parameters to form a unified feature vector. This feature vector is then input into a pre-trained porosity prediction model, which is a multilayer perceptron model. The porosity prediction model outputs a predicted porosity value for the coarse aggregate sample. This invention also discloses related devices, computer programs, and storage media. Based on this method, rapid and accurate prediction of porosity can be achieved.
Need to check novelty before this filing date? Find Prior Art