A method and system for evaluating the particle size distribution of rock debris in complex strata double-mode shield construction

By combining deep learning and 3D reconstruction technologies with laser particle size analysis, dynamic adaptive algorithms, and error accumulation models, the problem of accurately evaluating the particle size distribution of rock debris in dual-mode shield tunneling in complex strata was solved, improving the evaluation accuracy and reliability and supporting engineering decision-making.

CN120411057BActive Publication Date: 2026-05-29CHINA TIESIJU CIVIL ENGINEERING GROUP CO LTD +2
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
CHINA TIESIJU CIVIL ENGINEERING GROUP CO LTD
Filing Date
2025-04-30
Publication Date
2026-05-29

AI Technical Summary

Technical Problem

In dual-mode shield tunneling in complex strata, existing technologies struggle to accurately evaluate the particle size distribution of rock debris. This is especially true when there are significant differences in the fracturing characteristics of different lithologies, and when the rock debris has irregular morphology and uneven distribution. Traditional measurement methods are unable to dynamically adapt to changes in rock debris fracturing mechanisms. Furthermore, nonlinear abrupt changes exist at the interfaces of geological units in complex strata, leading to insufficient evaluation accuracy.

Method used

We employ deep learning-based image segmentation algorithms and 3D reconstruction techniques, combined with laser particle size analysis, dynamic adaptive algorithms, and error accumulation models, to perform multi-step data processing on rock cinder particle size distribution. This includes image preprocessing, shape correction, data fusion, adhering particle detection, and nonlinear mutation detection, ensuring the accuracy of the evaluation results.

Benefits of technology

Through multi-step data processing and analysis, the accuracy of rock debris particle size distribution evaluation has been significantly improved, providing a reliable basis for engineering decision-making and ensuring construction quality and efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120411057B_ABST
    Figure CN120411057B_ABST
Patent Text Reader

Abstract

The application discloses a kind of complex stratum dual-mode shield construction rock debris particle size distribution evaluation method and system, comprising: obtaining rock debris image and pretreatment denoising, obtain the first image;Utilize deep learning algorithm to identify rock debris edge, separate overlapping rock debris, obtain the second image;Through morphological parameter analysis rock debris shape, carry out three-dimensional reconstruction correction to non-spherical particle, obtain the third image;In combination with laser particle size analysis data, data fusion is carried out to the third image, and preliminary particle size distribution is obtained;For fine particle adhesion phenomenon, adopt detection algorithm to correct particle size distribution;According to the change of crushing mechanism when shield mode switches, dynamically update particle size distribution;Through mutation detection algorithm analysis non-linear mutation in complex stratum, carry out data smoothing processing;Finally, error accumulation model is used to analyze error, if exceed threshold value, then reprocess, until error meets requirements.The application significantly improves the accuracy and reliability of rock debris particle size distribution evaluation.
Need to check novelty before this filing date? Find Prior Art