基于深度学习的自密实混凝土早期裂缝预测方法及装置
By using deep learning-based methods, R-CNN and LSTM models are used to extract video features of self-compacting concrete and predict its early cracks. This solves the problem of the difficulty in predicting early cracks in self-compacting concrete and improves the safety and reliability of concrete structures.
CN114693669BActive Publication Date: 2026-07-17中电建路桥集团有限公司
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- 中电建路桥集团有限公司
- Filing Date
- 2022-04-20
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing technologies cannot effectively predict early cracks in self-compacting concrete, affecting the safety and stability of concrete structures.
Method used
By employing a deep learning-based approach, and acquiring videos of the slump expansion test and pouring process of self-compacting concrete, spatial and temporal features are extracted using R-CNN and LSTM models to establish an early crack prediction model, thereby predicting the crack resistance of concrete in real time.
Benefits of technology
It enables rapid, real-time prediction of early-stage cracks in self-compacting concrete, improving the safety and reliability of concrete structures while reducing experimental time and costs.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN114693669B_ABST
Abstract
本发明提供了一种基于深度学习的自密实混凝土早期裂缝预测方法及装置，方法包括：获取自密实混凝土坍落扩展度测试过程视频和自密实混凝土浇筑过程视频；对自密实混凝土坍落扩展度测试过程视频和自密实混凝土浇筑过程视频进行随机抽帧获得图像输入数据；将图像输入数据输入预先训练的混凝土早期裂缝预测模型中获得裂缝混凝土抗裂性能预测结果。
Need to check novelty before this filing date? Find Prior Art