CN-122024109-A - Intelligent monitoring method and equipment for building structure cracks

CN122024109ACN 122024109 ACN122024109 ACN 122024109ACN-122024109-A

Abstract

The invention discloses an intelligent monitoring method and equipment for cracks of a building structure. Belongs to the technical field of building structure monitoring. The method comprises the steps of constructing a digital twin model, planning an automatic inspection path based on the digital twin model, carrying out image acquisition according to the automatic inspection path planning, carrying out correction processing on the acquired image, carrying out crack identification on the corrected image based on a semantic segmentation model, mapping the identified crack into a three-dimensional space and correlating with a component in the digital twin model, accumulating crack data, carrying out trend analysis, and generating early warning information. The invention realizes automation, high precision, three-dimensional space positioning and long-term intelligent monitoring of the building structure cracks, and solves the problems that the traditional manual inspection is low in efficiency and insufficient in precision, and the structural safety risk cannot be dynamically evaluated in real time.

Inventors

YE DAN
Yue Yangxinling
YANG MAO
FAN YONGHUI
XIAO HANLIN
YAO YUSHAN
LI YAWEI
ZHOU JIANTING
ZHANG HONG
LIU JINGJU
HUANG LING
AN SIYU
XIANG BINGBING

Assignees

重庆第二师范学院
重庆市急救医疗中心(重庆市第四人民医院、重庆市急救医学研究所)
重庆交通大学
重庆建筑工程职业学院

Dates

Publication Date: 20260512
Application Date: 20260212

Claims (8)

1. An intelligent monitoring method for cracks of a building structure is characterized by comprising the following steps: Constructing a digital twin model; planning an automatic inspection path based on the digital twin model; image acquisition is carried out according to the automatic routing inspection path planning; Correcting the acquired image; Carrying out crack recognition on the corrected image based on the semantic segmentation model; Mapping the identified fracture to a three-dimensional space and correlating with a component in the digital twin model; and accumulating the crack data and carrying out trend analysis to generate early warning information.
2. The intelligent monitoring method for cracks in a building structure according to claim 1, wherein the digital twin model comprises a BIM model and a live three-dimensional grid model, and each component in the digital twin model is provided with a unique identifier.
3. The intelligent monitoring method for cracks in a building structure according to claim 1, wherein the correcting the acquired image comprises: acquiring an incidence angle of a camera and a structure surface, a material reflectivity parameter of the structure surface and an ambient light influence function during image acquisition; correcting the original pixel intensity of the image, wherein the expression is: In the formula, 、 Respectively correcting the pixel intensity values before and after correction; An included angle between a surface normal corresponding to a target point in an image and the sight direction of a camera; , The geometric attenuation coefficient is obtained through imaging experiment calibration; Normalized reflectivity of the target point surface texture obtained by querying a texture attribute library associated with the digital twin; And the dynamic illumination compensation factor is calculated based on the illumination parameters of the current scene.
4. The intelligent monitoring method for cracks in a building structure according to claim 2, wherein S5 comprises: S510, carrying out intersection calculation on two-dimensional coordinates of crack pixels in a two-dimensional image and triangular patches of the live-action three-dimensional grid model through a ray projection algorithm, and determining the three-dimensional space position of the triangular patches; s520, associating the crack to a specific BIM component according to the inclusion relation between the three-dimensional space position and the BIM model, and creating a unique identifier for the crack.
5. The intelligent monitoring method for cracks in a building structure according to claim 4, wherein S510 comprises: s511, for the crack pixels identified in the corrected image, back-projecting the two-dimensional coordinates of each crack pixel according to the internal and external parameters of the camera when the image is acquired to generate a three-dimensional ray starting from the optical center of the camera; S512, performing intersection calculation on the three-dimensional rays and triangular patches of the live-action three-dimensional grid model, and selecting an intersection point closest to a camera as a three-dimensional space point corresponding to the crack pixel; s513, aggregating three-dimensional space points corresponding to all the crack pixels to form a three-dimensional point cloud representing the crack space morphology.
6. The intelligent monitoring method for cracks in a building structure according to claim 5, wherein S520 comprises: S521, carrying out space analysis on the crack three-dimensional point cloud, judging the geometric containing relation with each component in the BIM model, and determining one or more main structural components to which the crack belongs; S522, creating and assigning a globally unique crack identifier for each crack associated with the component, and constructing a crack data object; And S523, storing the crack data object into a structural database associated with the digital twin model, and visually marking the crack on a corresponding component in a graphical interface of the BIM model.
7. The intelligent monitoring method for cracks in a building structure according to claim 6, wherein the crack data object comprises: the method comprises the steps of a crack identifier, an belonging component ID, a crack three-dimensional point cloud, geometric characteristic parameters calculated based on the three-dimensional point cloud and a first discovery time stamp.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements a method for intelligent monitoring of cracks in a building structure according to any one of claims 1 to 7 when executing the computer program.

Description

Intelligent monitoring method and equipment for building structure cracks Technical Field The invention relates to the technical field of building structure monitoring, in particular to an intelligent monitoring method and equipment for cracks of a building structure. Background At present, in the long-term use process of a building structure, cracks are easily generated on the surface and inside of the structure under the influence of factors such as load change, environmental erosion, material aging and the like. If the cracks are not monitored and treated in time, the cracks can be continuously expanded, the safety, stability and durability of the building structure are seriously threatened, and even serious safety accidents such as collapse and the like can be possibly caused, so that casualties and property loss are caused. Therefore, effective monitoring of cracks in building structures is of great importance. However, the traditional building structure crack monitoring relies on manual inspection, and has the problems of low efficiency, insufficient precision and incapability of dynamically assessing risks in real time. The prior art respectively relates to a finite element simulation model, a BIM three-dimensional model, unmanned aerial vehicle monitoring and the like, but the combination of the three-dimensional space positioning of cracks and long-term intelligent monitoring is not realized. Therefore, how to provide a method and a device for intelligently monitoring cracks of a building structure is a problem to be solved by those skilled in the art. Disclosure of Invention In view of the above, the invention provides an intelligent monitoring method and equipment for building structural cracks, which can realize the automation, high precision, three-dimensional space positioning and long-term intelligent monitoring of the building structural cracks, and solve the problems of low efficiency, insufficient precision and incapability of dynamically evaluating structural safety risks in real time in the traditional manual inspection. In order to achieve the above purpose, the present invention adopts the following technical scheme: Referring to fig. 1, an intelligent monitoring method for cracks of a building structure includes: Constructing a digital twin model; planning an automatic inspection path based on the digital twin model; image acquisition is carried out according to the automatic routing inspection path planning; Correcting the acquired image; Carrying out crack recognition on the corrected image based on the semantic segmentation model; Mapping the identified fracture to a three-dimensional space and correlating with a component in the digital twin model; and accumulating the crack data and carrying out trend analysis to generate early warning information. Further, the digital twin model comprises a BIM model and a live three-dimensional grid model, and each component in the digital twin model is provided with a unique identifier. Further, the correcting process for the acquired image includes: acquiring an incidence angle of a camera and a structure surface, a material reflectivity parameter of the structure surface and an ambient light influence function during image acquisition; correcting the original pixel intensity of the image, wherein the expression is: In the formula, 、Respectively correcting the pixel intensity values before and after correction; An included angle between a surface normal corresponding to a target point in an image and the sight direction of a camera; , The geometric attenuation coefficient is obtained through imaging experiment calibration; Normalized reflectivity of the target point surface texture obtained by querying a texture attribute library associated with the digital twin; And the dynamic illumination compensation factor is calculated based on the illumination parameters of the current scene. . Further, S5 includes: S510, carrying out intersection calculation on two-dimensional coordinates of crack pixels in a two-dimensional image and triangular patches of the live-action three-dimensional grid model through a ray projection algorithm, and determining the three-dimensional space position of the triangular patches; s520, associating the crack to a specific BIM component according to the inclusion relation between the three-dimensional space position and the BIM model, and creating a unique identifier for the crack. Further, S510 includes: s511, for the crack pixels identified in the corrected image, back-projecting the two-dimensional coordinates of each crack pixel according to the internal and external parameters of the camera when the image is acquired to generate a three-dimensional ray starting from the optical center of the camera; S512, performing intersection calculation on the three-dimensional rays and triangular patches of the live-action three-dimensional grid model, and selecting an intersection point closest to a camera as a three-dimen