CN-122015853-A - Unmanned aerial vehicle inspection method, equipment and medium for reservoir side slope defects

CN122015853ACN 122015853 ACN122015853 ACN 122015853ACN-122015853-A

Abstract

The invention discloses an unmanned aerial vehicle inspection method, equipment and medium for a storage side slope defect, the method comprises the steps of obtaining defect point position data of the storage side slope, dividing the defect point positions according to defect types, numbering each defect point position, establishing a three-dimensional live-action model of the storage side slope, inquiring and recording three-dimensional coordinates of each defect point position, constructing a TSP model for a three-dimensional coordinate set of the same type of defect point positions, solving to obtain a shortest flight path covering all defect point positions, converting the shortest flight path into an unmanned aerial vehicle executable route and downloading the unmanned aerial vehicle executable route to an unmanned aerial vehicle flight control system, controlling the unmanned aerial vehicle to execute inspection on the corresponding type of defect point positions according to the route and collecting image data. The intelligent inspection system and the intelligent inspection method realize the intelligent inspection of the bank side slope with high efficiency, accuracy and low energy consumption.

Inventors

LI KE
LIU ZHAO
CHEN ZHONGZHI
YUAN PENG
ZHANG HONGWEI
SHI QINGHONG
WANG JUNTENG
ZHAO GUOLIANG
YANG BAOQUAN

Assignees

三峡金沙江川云水电开发有限公司

Dates

Publication Date: 20260512
Application Date: 20260204

Claims (10)

1. The unmanned aerial vehicle inspection method for the reservoir bank slope defects is characterized by comprising the following steps of: s1, acquiring defect point position data of a bank slope, dividing the defect point positions according to defect types, and numbering each defect point position; S2, establishing a three-dimensional live-action model of the bank slope, and inquiring and recording three-dimensional coordinates of each defect point of each type; S3, constructing a TSP model for the three-dimensional coordinate set of the defect points of the same class, and solving to obtain the shortest flight path covering all the defect points of the class; s4, converting the shortest flight path into an executable route of the unmanned aerial vehicle, downloading the executable route to a flight control system of the unmanned aerial vehicle, controlling the unmanned aerial vehicle to execute inspection on corresponding defect points according to the route, and collecting image data.
2. The unmanned aerial vehicle inspection method for the reservoir bank slope defects according to claim 1, wherein in the step S1, the defect point location data is obtained by fusing manual inspection record data and unmanned aerial vehicle aerial image data.
3. The unmanned aerial vehicle inspection method for the reservoir side slope defects according to claim 2, wherein in the step S1, the defect points are divided into three categories, namely cracking or breakage and falling of sprayed concrete, local breakage or clogging of drainage ditches and apparent water precipitation calcium.
4. The unmanned aerial vehicle inspection method for the reservoir bank slope defects according to claim 1, wherein the construction of a three-dimensional live-action model and the acquisition of three-dimensional coordinates of each defect point are carried out by the following steps: S201, acquiring overall three-dimensional data of a target reservoir bank side slope; s202, constructing a three-dimensional live-action model of a reservoir bank slope according to the collected three-dimensional data; s203, marking the determined defect point positions in the three-dimensional live-action model; s204, inquiring and recording the coordinates of each numbered defect point of each class.
5. The unmanned aerial vehicle inspection method of the reservoir bank slope defect according to claim 1, wherein the TSP model is constructed by taking a defect point as a necessary node, taking an unmanned aerial vehicle take-off and landing point as a starting node and a termination node, wherein the distance between the nodes is a three-dimensional euclidean distance, and the objective function is a minimum total path length.
6. The unmanned aerial vehicle inspection method for the reservoir bank slope defects according to claim 5, wherein in the construction of the TSP model, if the number of the defect points is less than or equal to a first threshold, the defect points are grouped according to defect categories, so that the number of each group of nodes is less than or equal to the first threshold, each group of independent TSP models is obtained, and each group of independent TSP models is solved, so that a plurality of sub-airlines are obtained.
7. The unmanned aerial vehicle inspection method of a reservoir bank slope defect according to any one of claims 1 to 6, further comprising: and acquiring a plurality of inspection data, detecting point-to-point changes of close-range images of the same defect point at different inspection periods, and evaluating the slope stability.
8. The unmanned aerial vehicle inspection method for the reservoir bank slope defects according to claim 7, wherein the point-to-point change detection comprises the steps of automatically pairing images of different periods according to defect numbers, measuring crack width change or water seepage area expansion through pixel level alignment, and triggering safety early warning when the change exceeds a preset threshold.
9. The unmanned aerial vehicle inspection equipment for the bank slope defect is characterized by comprising a memory, a processor and an unmanned aerial vehicle inspection program which is stored on the memory and can run on the processor, wherein the unmanned aerial vehicle inspection program for the bank slope defect realizes the steps of the unmanned aerial vehicle inspection method for the bank slope defect according to any one of claims 1-8 when the unmanned aerial vehicle inspection program for the bank slope defect is executed by the processor.
10. A storage medium, wherein a storage medium stores an unmanned aerial vehicle inspection program of a bank slope defect, and the unmanned aerial vehicle inspection program of the bank slope defect, when executed by a processor, implements the steps of the unmanned aerial vehicle inspection method of the bank slope defect according to any one of claims 1 to 8.

Description

Unmanned aerial vehicle inspection method, equipment and medium for reservoir side slope defects Technical Field The invention relates to the technical field of unmanned aerial vehicle defect inspection, in particular to an unmanned aerial vehicle inspection method, unmanned aerial vehicle inspection equipment and unmanned aerial vehicle inspection medium for a reservoir bank slope defect. Background The reservoir bank side slope is used as an important component of a reservoir dam and is influenced by wind, sun, rain wash and water level fluctuation for a long time, so that the defects of cracking, breakage and falling of sprayed concrete, local breakage and blockage of a drainage ditch, apparent calcium precipitation and the like are extremely easy to occur. If the defects cannot be found and treated in time, slope instability and landslide can be caused, and even dam safety is endangered, so that regular inspection of the reservoir bank slope is required. The traditional inspection mode relies on manual field inspection or unmanned aerial vehicle full-area aerial photography, the former is low in efficiency and high in risk, the latter is large in data acquisition amount and time-consuming in post-treatment, and the slope safety state is difficult to evaluate rapidly. The existing unmanned plane path planning is mostly based on a two-dimensional plane model, and the characteristics of large elevation drop of a bank side slope (tens of meters to hundreds of meters) and irregular three-dimensional distribution of defect points are not considered, so that the flight path redundancy and high energy consumption are caused, and key defect points are easy to miss. Therefore, there is a need for an efficient, optimal path unmanned inspection method for the points where defects have occurred, in combination with three-dimensional terrain. Disclosure of Invention In order to solve the problems, the invention provides the unmanned aerial vehicle inspection method, the unmanned aerial vehicle inspection equipment and the unmanned aerial vehicle inspection medium for the reservoir side slope defects, which realize unmanned aerial vehicle intelligent inspection for the reservoir side slope defects and improve the high efficiency of reservoir side slope monitoring. The invention provides an unmanned aerial vehicle inspection method for a reservoir bank slope defect, which comprises the following specific technical scheme: s1, acquiring defect point position data of a bank slope, dividing the defect point positions according to defect types, and numbering each defect point position; s2, inquiring and recording three-dimensional coordinates of each defect point in a pre-established three-dimensional live-action model of the bank side slope; S3, constructing a TSP model for the three-dimensional coordinate set of the defect points of the same class, and solving to obtain the shortest flight path covering all the defect points of the class; s4, converting the shortest flight path into an executable route of the unmanned aerial vehicle, downloading the executable route to a flight control system of the unmanned aerial vehicle, controlling the unmanned aerial vehicle to execute inspection on corresponding defect points according to the route, and collecting image data. Further, in step S1, the defect point location data is obtained by fusing the manual inspection record data and the unmanned aerial vehicle aerial image data. In step S1, the defect points are classified into cracking, breakage and falling of sprayed concrete, local breakage, blocking of drainage ditch and apparent water seepage and calcium precipitation. Further, the construction of the three-dimensional live-action model and the acquisition of the three-dimensional coordinates of each defect point are carried out by the following specific processes: S201, acquiring overall three-dimensional data of a target reservoir bank side slope; s202, constructing a three-dimensional live-action model of a reservoir bank slope according to the collected three-dimensional data; s203, marking the determined defect point positions in the three-dimensional live-action model; s204, inquiring and recording the coordinates of each numbered defect point of each class. Further, the defect point is taken as a necessary node, the unmanned plane take-off and landing point is taken as a starting node and a terminating node, the TSP model is constructed, the distance between the nodes is a three-dimensional Euclidean distance, and the objective function is the minimum total path length. Further, in the construction of the TSP model, if the number of the defect points is greater than the first threshold, the defect points are grouped according to the defect category, so that the number of each group of nodes is less than or equal to the first threshold, each group of independent TSP models is obtained, and each group of independent TSP models is solved to obtain a plurality of sub-air