Intelligent detection method for concrete pouring compactness

By integrating multi-source sensor fusion and deep learning models, combined with BIM models and blockchain technology, high-precision, full-cycle, blind-spot-free compaction detection and intelligent defect identification in the concrete pouring process have been achieved. This solves the problems of low detection accuracy and insufficient closed-loop process control in existing technologies, thereby improving construction quality and efficiency.

CN122361597APending Publication Date: 2026-07-10刘明丽
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202610462930.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-04-09
Publication Date
2026-07-10

AI Technical Summary

Technical Problem

Existing concrete pouring density testing technologies suffer from several drawbacks, including low accuracy of single-sensor detection, poor anti-interference capability, strong detection lag, inability to achieve full-cycle dynamic monitoring and closed-loop control of the pouring process, strong subjectivity in manual interpretation, and insufficient accuracy in locating and quantifying internal defects.

Method used

A multi-source sensor fusion scheme is adopted, including ultrasonic guided waves, ultra-wideband microwave radar, vibration acoustics and temperature gradient sensors. Combined with a deep learning model, multi-scale feature fusion is performed to achieve full-cycle dynamic monitoring and intelligent defect identification. Spatial coordinate matching and visual management are achieved through BIM model, and data traceability is achieved by combining blockchain technology.

Benefits of technology

It has achieved high-precision, full-cycle, blind-spot-free concrete density detection, with detection accuracy improved to relative error ≤3%, defect type identification accuracy ≥95%, and defect three-dimensional positioning accuracy ≤5mm, realizing closed-loop optimization of the pouring process and digital control of project quality.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122361597A_ABST
    Figure CN122361597A_ABST
Patent Text Reader

Abstract

This invention provides an intelligent detection method for concrete pouring density, belonging to the field of intelligent detection technology for concrete engineering quality. First, this invention generates a detection point matrix with spatial coordinates using a BIM model, completing the benchmark calibration of multi-source sensing components and the scenario-based migration and adaptation of the detection model. Then, throughout the entire concrete pouring cycle, it simultaneously collects four types of multi-source detection data: ultrasonic guided wave, microwave radar, vibration acoustics, and temperature gradient. After spatiotemporal registration, adaptive noise reduction, and multi-dimensional feature extraction, a deep learning model with a cross-dimensional attention weighting mechanism is used to complete multi-scale feature fusion and intelligent density inversion. Finally, it achieves visualized binding of detection results with the BIM model, hierarchical early warning, and closed-loop optimization of the pouring process. This invention achieves high-precision non-destructive testing of the entire cross-section and entire lifecycle of concrete components, with strong anti-interference capabilities and a high degree of intelligence. It can be widely applied to the intelligent detection and full-process control of concrete pouring quality in various building engineering projects.
Need to check novelty before this filing date? Find Prior Art