CN-121094263-B - BIM and unmanned aerial vehicle cooperation-based intelligent detection method for structural defects

CN121094263BCN 121094263 BCN121094263 BCN 121094263BCN-121094263-B

Abstract

The invention provides a structural defect intelligent detection method based on cooperation of BIM and an unmanned aerial vehicle, which belongs to the technical field of intelligent detection of buildings, and comprises the steps of acquiring a BIM model of a structure to be detected, analyzing the BIM model to obtain BIM data, carrying out three-dimensional grid division on the BIM model, determining component detection priority, marking key detection areas, setting safe flight parameters of the unmanned aerial vehicle, and obtaining an initial detection path through calculation; optimizing an initial detection path by utilizing a multi-objective optimization algorithm to generate a three-dimensional optimized path, dynamically adjusting the three-dimensional optimized route to obtain an optimal detection path of the unmanned aerial vehicle, acquiring detection data, and associating the detection data with a BIM model to generate a structured detection report. The method solves the problems of insufficient deep fusion between the traditional detection method and the BIM model, disjointed detection planning and building information, difficult update of the back feeding model of the detection result, low efficiency, poor precision and high risk.

Inventors

JIA PENGFEI
ZHAO RONGXIN
HUANG FAN
XING YUN
WU HUAYONG
WANG FENG
CAI JUEWEI
ZHAO LIN
YU WEILEI

Assignees

上海市建筑科学研究院有限公司
建科(武汉)勘测设计有限公司

Dates

Publication Date: 20260505
Application Date: 20250902

Claims (4)

1. The intelligent detection method for the structural defects based on the cooperation of the BIM and the unmanned aerial vehicle is characterized by comprising the following steps of: S1, acquiring and analyzing a BIM model of a structure to be detected to obtain BIM data, carrying out three-dimensional grid division on the BIM model to obtain three-dimensional space data, determining component detection priority based on component types, marking key detection areas and setting unmanned aerial vehicle safe flight parameters; The calculation expression of the unmanned plane safety distance parameter in the unmanned plane safety flight parameters is as follows: Wherein, the Representing the minimum distance of the drone from the structure surface, Representing the vertical distance of the drone to the sampling point, Representing the camera sensor pixel size, Representing the focal length of the camera, Representing the angle of view of the camera, Representing a material correction coefficient; S2, calculating an initial detection path by utilizing an improved A star algorithm based on three-dimensional space data, key detection areas and component detection priorities of the BIM model; The cost function of the improved a-star algorithm is as follows: Wherein, the Representing the overall priority of node n, Representing the actual cost from the start point to node n, Representing the heuristic estimated cost of node n to the endpoint, Represents a BIM building element priority item, Indicating BIM member detection priority over the radius R of node n, A shooting quality constraint term is represented as such, Representing the unmanned aerial vehicle camera orientation vector, Representing the normal vector of the surface of the component, Indicating the angle of incidence of the shot, Representing the minimum photographing incident angle, The angle penalty coefficient is represented as such, All represent weight coefficients; S3, optimizing the initial detection path through a multi-objective optimization algorithm, generating a three-dimensional optimized path by combining the safe flight parameters of the unmanned aerial vehicle, and dynamically adjusting the three-dimensional optimized path by combining BIM data to obtain an optimal detection path of the unmanned aerial vehicle, wherein the method specifically comprises the following steps: Establishing a multi-target optimization model comprising minimized flight time and maximized detection coverage rate through a multi-target optimization algorithm, optimizing the distance and the path of each detection point on the surface of a structure in an initial detection path, combining with unmanned aerial vehicle safe flight parameters based on shooting quality requirements, and utilizing a genetic algorithm to solve an optimal detection scheme to generate and obtain a three-dimensional optimization path; S4, acquiring detection data according to the optimal detection path, correlating the detection data with the BIM model, marking the defect position, obtaining a detected BIM model and generating a structured detection report.
2. The intelligent detection method for structural defects based on cooperation of BIM and unmanned aerial vehicle according to claim 1, wherein the step S1 includes the steps of: S101, acquiring a BIM model of a structure to be detected, and analyzing the BIM model to obtain BIM data comprising geometric data, component attribute information and history detection records; S102, carrying out three-dimensional grid division on the BIM model, establishing a detection space coordinate system, and obtaining three-dimensional space data by generating a three-dimensional space map; s103, setting the priorities of the bearing components and the connection nodes as the highest level based on the component types, and determining the component detection priority; S104, marking the heavy point detection area in the BIM according to the historical defect data in the historical detection record, and setting the safe flight parameters of the unmanned aerial vehicle.
3. The intelligent detection method for structural defects based on cooperation of BIM and unmanned aerial vehicle according to claim 1, wherein the step S3 includes the steps of: S301, optimizing an initial detection path through a multi-objective optimization algorithm, optimizing the distance and the path of each navigation point in the initial detection path on the surface of the structure, and generating a three-dimensional optimized path; S302, performing flight detection by using an unmanned aerial vehicle based on a three-dimensional optimized path; the unmanned aerial vehicle flight detection mode comprises single-machine flight detection and multi-unmanned aerial vehicle cooperative detection; S303, responding to the flight process of the unmanned aerial vehicle, monitoring environmental changes in real time by using an unmanned aerial vehicle-mounted sensor, and dynamically adjusting the three-dimensional optimized path by combining BIM data to obtain an optimal detection path of the unmanned aerial vehicle.
4. The intelligent detection method for structural defects based on cooperation of BIM and unmanned aerial vehicle according to claim 1, wherein the step S4 includes the steps of: s401, acquiring data by using an unmanned aerial vehicle according to an optimal detection path to obtain detection data containing images and point cloud data; s402, associating the detection data with components in the BIM model to obtain an associated BIM model; S403, marking the defect position by utilizing an image recognition algorithm based on the associated BIM model to obtain a detected BIM model and generating a structured detection report.

Description

BIM and unmanned aerial vehicle cooperation-based intelligent detection method for structural defects Technical Field The invention belongs to the technical field of intelligent detection of buildings, and particularly relates to an intelligent detection method for structural defects based on cooperation of BIM and an unmanned aerial vehicle. Background The construction of the buildings and bridge engineering in China achieves remarkable achievement, and the complex structures such as super high-rise buildings, large-span bridges and the like break through the technical limit continuously. However, in the engineering operation and maintenance stage, the structure detection still faces serious challenges that the traditional manual detection is low in efficiency and high in cost, great potential safety hazards exist in high-altitude operation, the accessibility problem is partially solved by the introduction of unmanned aerial vehicle technology, but the fixed route detection mode cannot adapt to complex building forms, so that the detection dead zone appears frequently, and the defects of unstable data quality, poor repeatability and the like exist in the manual flight detection depending on the flight experience, so that the standardized requirements of engineering detection are difficult to meet. Meanwhile, with the large-scale popularization and application of BIM technology in the field of engineering construction in China, the digital management of the whole life cycle of the building has become an industry trend, but the deep fusion of the existing detection means and the BIM model is still insufficient, and the problems that the detection planning and the building information are disjointed and the detection result is difficult to update the back feeding model are increasingly prominent. Disclosure of Invention Aiming at the defects in the prior art, the intelligent detection method for the structural defects based on the cooperation of the BIM and the unmanned aerial vehicle solves the problems that the conventional detection method is insufficient in deep fusion with a BIM model, detection planning and building information are disjointed, a detection result is difficult to update a feedback model, the efficiency is low, the precision is poor and the risk is high. In order to achieve the purpose, the technical scheme adopted by the invention is that the intelligent detection method for the structural defects based on the cooperation of BIM and unmanned aerial vehicle comprises the following steps: S1, acquiring and analyzing a BIM model of a structure to be detected to obtain BIM data, carrying out three-dimensional grid division on the BIM model to obtain three-dimensional space data, determining component detection priority based on component types, marking key detection areas and setting unmanned aerial vehicle safe flight parameters; S2, calculating an initial detection path by utilizing an improved A star algorithm based on three-dimensional space data, key detection areas and component detection priorities of the BIM model; S3, optimizing the initial detection path through a multi-objective optimization algorithm, generating a three-dimensional optimized path by combining the safe flight parameters of the unmanned aerial vehicle, and dynamically adjusting the three-dimensional optimized route by combining BIM data to obtain an optimal detection path of the unmanned aerial vehicle; S4, acquiring detection data according to the optimal detection path, correlating the detection data with the BIM model, marking the defect position, obtaining a detected BIM model and generating a structured detection report. The method has the advantages that BIM data are extracted by analyzing the BIM model, the detection priority is automatically marked, an initial route is generated, a multi-objective optimization algorithm is adopted to optimize the flight path, automation and intellectualization of the detection process are realized, the flight parameters are dynamically adjusted according to the real-time environment, the detection data are automatically associated with the BIM model, the efficiency and the quality of structure detection are remarkably improved, and the risk of high-altitude operation is remarkably reduced; the method realizes the full depth fusion of the structural defect detection method and the BIM model, the tight connection of the detection plan and the building information, and the update of the detection result back feeding model. Further, the step S1 includes the steps of: S101, acquiring a BIM model of a structure to be detected, and analyzing the BIM model to obtain BIM data comprising geometric data, component attribute information and history detection records; S102, carrying out three-dimensional grid division on the BIM model, establishing a detection space coordinate system, and obtaining three-dimensional space data by generating a three-dimensional space map; s103, setting th