Water conservancy facility patrol early warning method and system based on unmanned aerial vehicle

The panoramic image of the embankment is obtained through the drone system and the molecular area is divided, and outliers are analyzed. The problem of inaccurate inspection and detection of embankment in the existing technology is solved, and the efficiency and comprehensiveness of embankment instability assessment is achieved, timely early warning is achieved, and the improvement of the improvement of Elevation safety and maintenance efficiency.

CN119048942AActive Publication Date: 2024-11-29SHENZHEN LIANHE SMART TECH CO LTD

Patent Information

Application Number
CN202411248487.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-06
Publication Date
2024-11-29
Estimated Expiration
2044-09-06

AI Technical Summary

Technical Problem

In the prior art, the inspection and inspection of dams is limited to a single area, which leads to the inaccurate and comprehensiveness of the assessment, and it is impossible to detect abnormalities in other areas of the dam in a timely manner.

Method used

Adopt a drone-based water conservancy facility patrol and early warning system, communicate with the drone through the control center, obtain panoramic images of the embankment and divide molecular areas, determine detection points, obtain detection images, analyze outliers, evaluate instability, and give users Issue an alarm message.

Benefits of technology

The accuracy and comprehensiveness of the dam patrol efficiency and unstable value evaluation are improved, timely and comprehensive early warning is achieved, abnormal sub-regions are quickly positioned, and the efficiency of dam safety and maintenance is improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119048942A_ABST
    Figure CN119048942A_ABST
Patent Text Reader

Abstract

The invention discloses a water conservancy facility patrol early warning method and system based on an unmanned aerial vehicle, and belongs to the technical field of water conservancy facility detection. The shooting detection point of each sub-region ensures that the unmanned aerial vehicle covers the corresponding sub-region under the condition that the number of all detection images corresponding to the unmanned aerial vehicle after the unmanned aerial vehicle completes shooting in the corresponding sub-region is minimum and the detection images are not lower than the preset definition, so that the patrol efficiency of the unmanned aerial vehicle is improved, and the unstable value of the target dam is comprehensively evaluated according to the abnormal value of each sub-region. And meanwhile, early warning is carried out according to the abnormal values of the different sub-regions and the unstable value of the target dam, early warning is carried out comprehensively and timely, the abnormal sub-regions are quickly positioned, and the safety maintenance efficiency of the dam is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of hydraulic facility detection technology, and in particular to a hydraulic facility inspection and early warning method and system based on an unmanned aerial vehicle. Background Art

[0002] A dam is an important water conservancy facility used to control water flow, prevent floods and store water, so it is very important to inspect and test the dam. However, in the existing inspection and early warning methods or systems, most of them detect a certain area of ​​the dam, and the stability assessment is limited to a single area, which makes the stability assessment inaccurate and incomplete, and thus makes it impossible to detect abnormalities in other areas of the dam in a timely manner. Summary of the invention

[0003] In order to solve the technical problems existing in the prior art, the present invention provides a water conservancy facility inspection and early warning system based on a drone, comprising a control center and a drone equipped with a camera device, wherein the control center is in communication connection with the drone, and the control center comprises: a first image acquisition module, a region division module, a detection point determination module, a second image acquisition module, an abnormality analysis module, an instability assessment module and an alarm module; The first image acquisition module is used to acquire a panoramic image of the target dam taken by the drone; The region division module is used to divide the target dam into sub-regions according to the panoramic image of the dam; The detection point determination module is used to determine the shooting detection points of the drone in each sub-area of ​​the target dam. The shooting detection points of each sub-area ensure that all the corresponding detection images of the drone after the corresponding sub-area is shot are covered with the minimum number and the detection image is not less than the preset clarity. The second image acquisition module is used to acquire the corresponding detection images taken by the drone at each shooting detection point; The abnormality analysis module is used to identify and analyze abnormal values ​​of each sub-region according to each detection image; The instability assessment module is used to assess the instability value BW of the target dam according to the abnormal values ​​of each sub-area; The alarm module is used to send alarm information to the user according to the abnormal values ​​of each sub-area and the instability value of the target dam.

[0004] Furthermore, the sub-areas of the target dam include a dam foundation area, a dam body area and a slope area; and the detection image includes a dam foundation area image, a dam body area image and a slope area image.

[0005] Furthermore, the abnormality analysis module includes: a dam foundation abnormality analysis module, a dam body abnormality analysis module and a slope abnormality analysis module; The dam body abnormality analysis module is used to analyze the complete crack information of the dam body area according to the dam body area image, and calculate the dam body abnormality value BT according to the complete crack information; The dam foundation abnormality analysis module is used to analyze the settlement and depression information of the dam foundation area according to the dam foundation area image, and calculate the dam foundation abnormality value BJ according to the settlement and depression information; The slope anomaly analysis module is used to analyze the surface spalling information of the slope area according to the slope area image, and calculate the slope anomaly value BP according to the surface spalling information.

[0006] Further, the complete crack information of the dam body area is analyzed according to the dam body area image, and the dam body abnormality value BT is calculated according to the complete crack information, specifically: The edge detection algorithm is used to extract the suspected crack contours in the dam area image; Identifying real cracks from the suspected crack contours by using a pre-trained first deep learning model; According to the shooting detection points of the dam area, the images of each dam area are spliced ​​to obtain a complete dam area image; According to the endpoint position of the real crack, find the real crack that can be connected with the endpoint of the current real crack in the complete dam area image, and perform continuous splicing to obtain the corresponding complete crack; According to the endpoint position of the complete crack, determine whether the corresponding complete crack passes through the important area of ​​the dam body, and record the number N1 of complete cracks passing through the important area of ​​the dam body; Obtain the total number of pixels G of the complete dam area image and the number of pixels g occupied by each complete crack in the complete dam area image. If g / G is greater than or equal to a first preset threshold, the corresponding complete crack is determined to be a severe crack, and the number of severe cracks N2 is counted; Calculate the abnormal value BT of the dam body, BT=k1*N1+k2*N2, where k1 represents the first preset coefficient and k2 represents the second preset coefficient.

[0007] Furthermore, according to the endpoint position of the real crack, a real crack that can be connected to the endpoint of the current real crack is found in the complete dam area image, and continuous splicing is performed to obtain the corresponding complete crack, specifically: In the complete dam area image, a real crack whose end point coincides with the end point of the current real crack, or a real crack whose end point is in the current real crack area, is found and spliced ​​with the current real crack to form a temporary complete crack; Then find a real crack whose endpoint position coincides with the endpoint position of the current temporary complete crack, or a real crack whose endpoint position is in the current real crack area, and then splice it to form a new temporary complete crack. Repeat this step until no real crack whose endpoint position coincides with the endpoint position of the new temporary complete crack and no real crack whose endpoint position is in the new temporary complete crack area can be found, and the latest temporary complete crack is a complete crack.

[0008] Furthermore, the settlement depression information of the dam foundation area is analyzed according to the dam foundation area image, and the dam foundation abnormal value is calculated according to the settlement depression information. Specifically, the settlement depression area is identified from the dam foundation area image through a pre-trained second deep learning model, and the total number N3 of the settlement depression areas in all the dam foundation area images and the number of pixels N4 occupied by each settlement depression area in the corresponding dam foundation area image are counted; Calculate the dam foundation abnormal value BJ, BJ=k3*N3+k4*N4, where k3 represents the third preset coefficient and k4 represents the fourth preset coefficient.

[0009] Furthermore, the surface spalling information of the slope area is analyzed according to the slope area image, and the slope anomaly value is calculated according to the surface spalling information. Specifically, the surface spalling area is identified from the slope area image through a pre-trained third deep learning model, and the total number N5 of surface spalling areas in all slope area images and the number N6 of pixels occupied by each subsidence depression area in the corresponding dam foundation area image are counted; Calculate the dam foundation abnormal value BP, BP=k5*N5+k6*N6, where k5 represents the fifth preset coefficient and k6 represents the sixth preset coefficient.

[0010] Furthermore, the instability assessment module assesses the instability value BW of the target dam according to the abnormal values ​​of each sub-area, specifically: BW=r1*BT+r2*BJ+r3*BP, where BW represents an unstable value, r1 represents a first preset weight, r2 represents a second preset weight, and r3 represents a third preset weight.

[0011] Furthermore, the alarm module sends alarm information to the user according to the abnormal values ​​of each sub-area and the instability value of the target dam, specifically: If the dam body abnormal value is greater than a first preset abnormal threshold, a dam body abnormality warning message is issued to the user; If the dam foundation abnormality value is greater than a second preset abnormality threshold, a dam foundation abnormality alarm message is sent to the user; If the slope abnormality value is greater than a third preset abnormality threshold, a slope abnormality warning message is issued to the user; If the instability value of the target dam is greater than a preset comprehensive threshold, a dam instability warning message is sent to the user.

[0012] The present invention also provides a water conservancy facility inspection and early warning method based on an unmanned aerial vehicle, comprising the following steps: Obtain a panoramic image of the target dam by using a drone equipped with a camera; The sub-areas of the target dam are divided through the panoramic image of the dam, including the dam foundation area, the dam body area and the slope area; Analyze the shooting detection points of each sub-area; Acquire the corresponding detection images taken by the drone at each shooting detection point, wherein the detection images are divided into dam foundation area images, dam body area images and slope area images; According to each detection image, analyze the abnormal value of each sub-region; The instability value of the target dam is evaluated based on the outliers of each sub-area; Warning information is issued to users based on the abnormal values ​​of each sub-area and the instability value of the target dam.

[0013] Compared with the prior art, the present invention has the following beneficial effects: After dividing the target dam into sub-areas, the shooting and detection points of the UAV are determined. The shooting and detection points of each sub-area ensure that after the UAV completes the shooting of the corresponding sub-area, all the corresponding detection images cover the corresponding sub-area with the minimum number and the detection image not less than the preset clarity, thereby improving the efficiency of UAV inspections. The instability value of the target dam is comprehensively evaluated based on the abnormal values ​​of each sub-area, thereby improving the accuracy and comprehensiveness of the evaluation of the instability value of the dam. At the same time, early warnings are issued based on the abnormal values ​​of different sub-areas and the instability values ​​of the target dam. Early warnings are issued comprehensively and timely, abnormal sub-areas are quickly located, and the efficiency of dam safety maintenance is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention. In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0015] Figure 1 It is a structural block diagram of the water conservancy facility inspection and early warning system based on unmanned aerial vehicle of the present invention; Figure 2 It is a structural block diagram of the control center of the water conservancy facility inspection and early warning system based on unmanned aerial vehicles of the present invention; Figure 3 It is a structural block diagram of an abnormal analysis module of a water conservancy facility inspection and early warning system based on an unmanned aerial vehicle of the present invention; Figure 4 It is a flow chart of the water conservancy facility inspection and early warning method based on unmanned aerial vehicle of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0018] In addition, the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention. See also Figure 1 As shown, the water conservancy facility inspection and early warning system based on drone provided by the present invention includes a control center and a drone equipped with a camera device, and the control center is communicatively connected with the drone.

[0019] See also Figure 2 As shown, the control center includes: a first image acquisition module, a region division module, a detection point determination module, a second image acquisition module, an abnormality analysis module, an instability assessment module and an alarm module, and a central processing unit that is communicatively connected to the above modules.

[0020] The first image acquisition module is used to acquire a panoramic image of the target dam taken by the drone.

[0021] The area division module is used to divide the target dam into sub-areas according to the panoramic image of the dam, specifically including the dam foundation area, the dam body area and the slope area.

[0022] The detection point determination module is used to determine the shooting detection points of the drone in each sub-area of ​​the target dam. The shooting detection points of each sub-area ensure that after the drone completes shooting in the corresponding sub-area, all corresponding detection images cover the corresponding sub-area with the minimum number and the detection image not less than the preset clarity.

[0023] The second image acquisition module is used to acquire the corresponding detection images taken by the UAV at each shooting detection point, and the detection images are divided into dam foundation area images, dam body area images and slope area images.

[0024] The abnormality analysis module is used to identify and analyze the abnormal values ​​of each sub-region based on each detection image.

[0025] The instability assessment module is used to assess the instability value of the target dam based on the outliers of each sub-area.

[0026] The alarm module is used to send alarm information to users based on the abnormal values ​​of each sub-area and the unstable value of the target dam.

[0027] The area division module divides the target dam into sub-areas according to the panoramic image of the dam, and specifically can divide the sub-areas of the panoramic image of the dam manually, or identify and divide through a database, and the database pre-stores the location data of the sub-areas of the target dam.

[0028] See also Figure 3 As shown, the abnormality analysis module includes: a dam foundation abnormality analysis module, a dam body abnormality analysis module and a slope abnormality analysis module.

[0029] The dam body abnormality analysis module is used to analyze the complete crack information of the dam body area according to the dam body area image, and calculate the dam body abnormality value according to the complete crack information, specifically: The edge detection algorithm is used to extract the suspected crack contours in the dam area image; Identifying real cracks from the suspected crack contours by using a pre-trained first deep learning model; According to the shooting detection points of the dam area, the images of each dam area are spliced ​​to obtain a complete dam area image; According to the endpoint position of the real crack, find the real crack that can be connected with the endpoint of the current real crack in the complete dam area image, and perform continuous splicing to obtain the corresponding complete crack; According to the endpoint position of the complete crack, determine whether the corresponding complete crack passes through the important area of ​​the dam body, and record the number N1 of complete cracks passing through the important area of ​​the dam body; Obtain the total number of pixels G of the complete dam area image and the number of pixels g occupied by each complete crack in the complete dam area image. If g / G is greater than or equal to a first preset threshold, the corresponding complete crack is determined to be a severe crack, and the number of severe cracks N2 is counted; Calculate the abnormal value BT of the dam body, BT=k1*N1+k2*N2, where k1 represents the first preset coefficient and k2 represents the second preset coefficient.

[0030] The edge detection algorithm may select the Canny edge detection algorithm. The Canny edge detection algorithm usually converts a color image into a grayscale image because the Canny algorithm is designed based on a single-channel grayscale image. In order to reduce the noise in the image and maintain the integrity of the edge, a Gaussian filter is used to smooth the grayscale image. The Gaussian filter is a low-pass filter that can effectively remove high-frequency noise in the image. Subsequently, a gradient operator (the Sobel operator is selected) is used to calculate the gradient size and direction of each pixel on the Gaussian-smoothed image. In order to eliminate false responses generated in the gradient calculation, the gradient direction of each pixel is checked. If the gradient intensity of the pixel is not the local maximum along the gradient direction, the gradient value of the pixel is suppressed. Strong edge points are detected by a high threshold and weak edge points are detected by a low threshold. When the edges are connected, each weak edge point is checked to see if it is adjacent to any strong edge point. If so, the weak edge point is retained. Therefore, the Canny algorithm can ensure the continuity and integrity of the edge points, thereby generating a clear and continuous edge contour.

[0031] The first deep learning model can select a U-Net model or a convolutional neural network model, and be trained using a large number of dam crack images as a training set.

[0032] According to the shooting detection points of the dam body area, the dam body area images are spliced ​​to obtain a complete dam body area image. For example, in the dam body area, the shooting detection point A is adjacent to the shooting detection point B, and point A is on the right side of point B. Then the dam body area image A corresponding to the shooting detection point A and the dam body area image B corresponding to the shooting detection point B can be spliced, and the dam body area image A is spliced ​​on the right side of the dam body area image B.

[0033] According to the endpoint position of the real crack, find the real crack that can be connected with the endpoint of the current real crack in the complete dam area image, and perform continuous splicing to obtain the corresponding complete crack, specifically: In the complete dam area image, a real crack whose end point coincides with the end point of the current real crack, or a real crack whose end point is in the current real crack area, is found and spliced ​​with the current real crack to form a temporary complete crack; Then find a real crack whose endpoint position coincides with the endpoint position of the current temporary complete crack, or a real crack whose endpoint position is in the current real crack area, and then splice it to form a new temporary complete crack. Repeat this step until no real crack whose endpoint position coincides with the endpoint position of the new temporary complete crack and no real crack whose endpoint position is in the new temporary complete crack area can be found, and the latest temporary complete crack is a complete crack.

[0034] The important areas of the dam body are pre-divided by the staff according to the dam body structure of the target dam.

[0035] The dam foundation abnormality analysis module is used to analyze the settlement information of the dam foundation area according to the dam foundation area image, and calculate the dam foundation abnormality value according to the settlement information, specifically identifying the settlement area from the dam foundation area image through the pre-trained second deep learning model, and counting the total number N3 of settlement areas in all dam foundation area images and the number N4 of pixels occupied by each settlement area in the corresponding dam foundation area image; Calculate the dam foundation abnormal value BJ, BJ=k3*N3+k4*N4, where k3 represents the third preset coefficient and k4 represents the fourth preset coefficient.

[0036] The second deep learning model can select a U-Net model or a convolutional neural network model, and be trained using a large number of dam foundation settlement depression images as a training set.

[0037] The slope anomaly analysis module is used to analyze the surface spalling information of the slope area according to the slope area image, and calculate the slope anomaly value according to the surface spalling information, specifically identifying the surface spalling area from the slope area image through a pre-trained third deep learning model, and counting the total number N5 of surface spalling areas in all slope area images and the number N6 of pixels occupied by each subsidence depression area in the corresponding dam foundation area image; Calculate the dam foundation abnormal value BP, BP=k5*N5+k6*N6, where k5 represents the fifth preset coefficient and k6 represents the sixth preset coefficient.

[0038] The third deep learning model can select a U-Net model or a convolutional neural network model, and be trained with a large number of slope surface spalling images as training sets.

[0039] The instability assessment module assesses the instability value of the target dam according to the abnormal values ​​of each sub-area, specifically: BW=r1*BT+r2*BJ+r3*BP, where BW represents an unstable value, r1 represents a first preset weight, r2 represents a second preset weight, and r3 represents a third preset weight. In this embodiment, r1+r2+r3=1.

[0040] The alarm module sends alarm information to the user according to the abnormal values ​​of each sub-area and the instability value of the target dam, specifically: If the dam body abnormal value is greater than a first preset abnormal threshold, a dam body abnormality warning message is issued to the user; If the dam foundation abnormality value is greater than a second preset abnormality threshold, a dam foundation abnormality alarm message is sent to the user; If the slope abnormality value is greater than a third preset abnormality threshold, a slope abnormality warning message is issued to the user; If the instability value of the target dam is greater than a preset comprehensive threshold, a dam instability warning message is sent to the user.

[0041] In another embodiment, the first image acquisition module is further used to acquire second facility images taken by the drone, wherein the second facility images include levee images, revetment images, and sluice gate images.

[0042] The second facility image is acquired by the UAV after acquiring the dam foundation area image, the dam body area image and the slope area image according to the shooting detection points.

[0043] The levee image is an image of the levee area that affects the stability of the target levee, and the levee area that affects the stability of the target levee is divided manually or identified and divided through the database; the bank protection image is an image of the bank protection area that affects the stability of the target levee, and the bank protection area that affects the stability of the target levee is divided manually or identified and divided through the database.

[0044] The database pre-stores the position data of the dike area that affects the stability of the target dike and the position data of the bank protection area that affects the stability of the target dike.

[0045] The abnormality analysis module also includes a dike abnormality analysis module, a revetment abnormality analysis module, a sluice abnormality analysis module and a pump station abnormality analysis module.

[0046] a dike anomaly analysis module, used for analyzing dike crack information of the dike according to the dike image, and calculating a dike anomaly value DF according to the dike crack information, specifically identifying dike cracks from the dike image through a pre-trained fourth deep learning model, and counting the total number N7 of dike cracks and the number N8 of pixels occupied by the dike cracks in the dike image; DF=k7*N7+k8*N8, wherein k7 represents the seventh preset coefficient, and k8 represents the eighth preset coefficient; The fourth deep learning model can select a U-Net model or a convolutional neural network model, and be trained using a large number of embankment crack images as a training set.

[0047] A revetment anomaly analysis module is used to analyze the revetment crack information of the revetment according to the revetment image, and calculate the revetment anomaly value HA according to the revetment crack information, specifically identifying the revetment cracks from the revetment image through a pre-trained fifth deep learning model, and counting the total number N9 of the revetment cracks and the number N10 of pixels occupied by the revetment cracks in the revetment image; HA=k9*N9+k10*N10, wherein k9 represents the ninth preset coefficient and k10 represents the tenth preset coefficient; The fifth deep learning model can select a U-Net model or a convolutional neural network model, and be trained using a large number of bank crack images as a training set.

[0048] A sluice anomaly analysis module, used for analyzing sluice crack information and sluice corrosion information of the sluice according to the sluice image, and calculating a sluice anomaly value SZ according to the sluice crack information and the sluice corrosion information, specifically identifying sluice cracks from the sluice image through a pre-trained sixth deep learning model, counting the total number N11 of sluice cracks and the number N12 of pixels occupied by sluice cracks in the sluice image, identifying sluice corrosion areas from the sluice image through a pre-trained seventh deep learning model, and counting the number N13 of pixels occupied by the sluice corrosion areas in the sluice image; SZ=k11*N11+k12*N12+k13*N13, wherein k11 represents the eleventh preset coefficient, k12 represents the twelfth preset coefficient, and k13 represents the thirteenth preset coefficient; The sixth deep learning model can select a U-Net model or a convolutional neural network model, and be trained with a large number of sluice crack images as a training set. The seventh deep learning model can select a U-Net model or a convolutional neural network model, and be trained with a large number of sluice corrosion images as a training set.

[0049] The instability assessment module also assesses the instability value of the target dam based on the embankment outliers, revetment outliers, sluice outliers and outliers of each sub-area, specifically: BW=r1*BT+r2*BJ+r3*BP+r4*DF+r5*HA+r6*SZ, wherein r4 represents the fourth preset weight, r5 represents the fifth preset weight, and r6 represents the sixth preset weight. In this embodiment, r1+r2+r3+r4+r5+r6=1.

[0050] The alarm module also sends alarm information to the user based on the abnormal values ​​of the dike, the revetment and the sluice, specifically: If the levee abnormal value is greater than a fourth preset abnormal threshold, a levee abnormality warning message is issued to the user; If the bank protection abnormal value is greater than a fifth preset abnormal threshold, a bank protection abnormality warning message is issued to the user; If the water gate abnormal value is greater than the sixth preset abnormal threshold, a water gate abnormality alarm message is sent to the user.

[0051] Embodiment 2 See also Figure 4 As shown, the present invention also provides a water conservancy facility inspection and early warning method based on an unmanned aerial vehicle, which specifically includes the following steps: S1. Obtaining a panoramic image of the target dam by using a drone equipped with a shooting device; S2, dividing the sub-areas of the target dam through the panoramic image of the dam, including the dam foundation area, the dam body area and the slope area; S3, analyzing the shooting detection points of each sub-area; S4, obtaining the corresponding detection images taken by the drone at each shooting detection point, wherein the detection images are divided into dam foundation area images, dam body area images and slope area images; S5. Analyze the abnormal value of each sub-region according to each detection image; S6, evaluating the instability value of the target dam according to the outliers of each sub-area; S7. Sending warning information to the user according to the abnormal values ​​of each sub-area and the instability value of the target dam.

[0052] For step S3, the shooting detection points of each sub-area ensure that after the drone completes shooting of the corresponding sub-area, all corresponding detection images cover the corresponding sub-area with the minimum number and the detection image not less than the preset clarity.

[0053] Regarding step S5, the analysis of the abnormal values ​​of each sub-area includes analyzing the abnormal values ​​of the dam foundation, the abnormal values ​​of the dam body and the abnormal values ​​of the slope.

[0054] T1. Analyze the abnormal values ​​of the dam body, including the following steps: T2, using edge detection algorithm to extract the suspected crack contours in the dam area image; T3, identifying real cracks from the suspected crack contours by using a pre-trained first deep learning model; T4. Based on the shooting detection points of the dam area, the images of the dam area are spliced ​​to obtain a complete dam area image; T5. According to the endpoint position of the real crack, find the real crack that can be connected with the endpoint of the current real crack in the complete dam area image, and perform continuous splicing to obtain the corresponding complete crack; T6. Determine whether the corresponding complete crack passes through the important area of ​​the dam body according to the endpoint position of the complete crack, and record the number N1 of complete cracks passing through the important area of ​​the dam body; T7, obtaining the total number of pixels G of the complete dam area image and the number of pixels g occupied by each complete crack in the complete dam area image, if g / G is greater than or equal to a first preset threshold, determining that the corresponding complete crack is a severe crack, and counting the number of severe cracks N2; T8. Calculate the abnormal value BT of the dam body, BT=k1*N1+k2*N2, wherein k1 represents the first preset coefficient and k2 represents the second preset coefficient.

[0055] The first deep learning model can select a U-Net model or a convolutional neural network model, and be trained using a large number of dam crack images as a training set.

[0056] For step T5, according to the endpoint position of the real crack, find the real crack that can be connected with the endpoint of the current real crack in the complete dam area image, and perform continuous splicing to obtain the corresponding complete crack, specifically: In the complete dam area image, a real crack whose end point coincides with the end point of the current real crack, or a real crack whose end point is in the current real crack area, is found and spliced ​​with the current real crack to form a temporary complete crack; Then find a real crack whose endpoint position coincides with the endpoint position of the current temporary complete crack, or a real crack whose endpoint position is in the current real crack area, and then splice it to form a new temporary complete crack. Repeat this step until no real crack whose endpoint position coincides with the endpoint position of the new temporary complete crack and no real crack whose endpoint position is in the new temporary complete crack area can be found, and the latest temporary complete crack is a complete crack.

[0057] The important areas of the dam body are pre-divided by the staff according to the dam body structure of the target dam.

[0058] Analyzing the abnormal values ​​of the dam foundation includes the following steps: Using a pre-trained second deep learning model, the subsidence area is identified from the dam foundation area image, and the total number N3 of the subsidence areas in all the dam foundation area images and the number N4 of pixels occupied by each subsidence area in the corresponding dam foundation area image are counted; Calculate the dam foundation abnormal value BJ, BJ=k3*N3+k4*N4, where k3 represents the third preset coefficient and k4 represents the fourth preset coefficient.

[0059] The second deep learning model can select a U-Net model or a convolutional neural network model, and be trained using a large number of dam foundation settlement depression images as a training set.

[0060] Analyzing slope anomalies includes the following steps: The surface spalling area is identified from the slope area image by using the pre-trained third deep learning model, and the total number N5 of surface spalling areas in all slope area images and the number N6 of pixels occupied by each subsidence depression area in the corresponding dam base area image are counted; Calculate the dam foundation abnormal value BP, BP=k5*N5+k6*N6, where k5 represents the fifth preset coefficient and k6 represents the sixth preset coefficient.

[0061] The third deep learning model can select a U-Net model or a convolutional neural network model, and be trained with a large number of slope surface spalling images as training sets.

[0062] For step S6, the instability value of the target dam is evaluated according to the abnormal values ​​of each sub-area, specifically: BW=r1*BT+r2*BJ+r3*BP, where BW represents an unstable value, r1 represents a first preset weight, r2 represents a second preset weight, and r3 represents a third preset weight.

[0063] For step S7, a warning message is issued to the user according to the abnormal values ​​of each sub-area and the instability value of the target dam, specifically: If the dam body abnormal value is greater than a first preset abnormal threshold, a dam body abnormality warning message is issued to the user; If the dam foundation abnormality value is greater than a second preset abnormality threshold, a dam foundation abnormality alarm message is sent to the user; If the slope abnormality value is greater than a third preset abnormality threshold, a slope abnormality warning message is issued to the user; If the instability value of the target dam is greater than a preset comprehensive threshold, a dam instability warning message is sent to the user.

[0064] Embodiment 3 The present invention also provides an electronic device, comprising: a processor, a sending device, an input device, an output device and a memory, the memory is used to store computer program code, the computer program code includes computer instructions, when the processor executes the computer instructions, the electronic device executes a method as any one of the possible implementation methods described above.

[0065] Embodiment 4 The present invention also provides a computer-readable storage medium, in which a computer program is stored. The computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes a method as described in any possible implementation manner.

[0066] The beneficial effects of the present invention are: After dividing the target dam into sub-areas, the shooting detection points of the drone are determined. The shooting detection points of each sub-area ensure that all the corresponding detection images of the drone after the corresponding sub-area is completed cover the corresponding sub-area with the minimum number and the detection image is not less than the preset clarity, which improves the efficiency of drone inspections. The instability value of the target dam is comprehensively evaluated according to the abnormal values ​​of each sub-area, which improves the accuracy and comprehensiveness of the evaluation of the instability value of the dam. At the same time, early warnings are issued according to the abnormal values ​​of different sub-areas and the instability values ​​of the target dam. Early warnings are issued comprehensively and timely, abnormal sub-areas are quickly located, and the efficiency of dam safety maintenance is improved. In the description of the specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0067] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A water conservancy facility inspection and early warning system based on drones, comprising a control center and a drone equipped with a camera, wherein the control center is in communication connection with the drone, and is characterized in that: The control center includes: a first image acquisition module, a region division module, a detection point determination module, a second image acquisition module, an abnormality analysis module, an instability assessment module and an alarm module; The first image acquisition module is used to acquire a panoramic image of the target dam taken by the drone; The region division module is used to divide the target dam into sub-regions according to the panoramic image of the dam; The detection point determination module is used to determine the shooting detection points of the drone in each sub-area of ​​the target dam. The shooting detection points of each sub-area ensure that all the corresponding detection images of the drone after the corresponding sub-area is shot are covered with the minimum number and the detection image is not less than the preset clarity. The second image acquisition module is used to acquire the corresponding detection images taken by the drone at each shooting detection point; The abnormality analysis module is used to identify and analyze abnormal values ​​of each sub-region according to each detection image; The instability assessment module is used to assess the instability value BW of the target dam according to the abnormal values ​​of each sub-area; The alarm module is used to send alarm information to the user according to the abnormal values ​​of each sub-area and the instability value of the target dam.

2. The water conservancy facility inspection and early warning system based on drone according to claim 1 is characterized in that: The sub-areas of the target dam include a dam foundation area, a dam body area and a slope area; the detection image includes a dam foundation area image, a dam body area image and a slope area image.

3. The water conservancy facility inspection and early warning system based on drone according to claim 2 is characterized in that: The abnormality analysis module includes: a dam foundation abnormality analysis module, a dam body abnormality analysis module and a slope abnormality analysis module; The dam body abnormality analysis module is used to analyze the complete crack information of the dam body area according to the dam body area image, and calculate the dam body abnormality value BT according to the complete crack information; The dam foundation abnormality analysis module is used to analyze the settlement and depression information of the dam foundation area according to the dam foundation area image, and calculate the dam foundation abnormality value BJ according to the settlement and depression information; The slope anomaly analysis module is used to analyze the surface spalling information of the slope area according to the slope area image, and calculate the slope anomaly value BP according to the surface spalling information.

4. The water conservancy facility inspection and early warning system based on drone according to claim 3 is characterized in that: The complete crack information of the dam area is analyzed according to the dam area image, and the dam body abnormal value BT is calculated according to the complete crack information, specifically: The edge detection algorithm is used to extract the suspected crack contours in the dam area image; Identifying real cracks from the suspected crack contours by using a pre-trained first deep learning model; According to the shooting detection points of the dam area, the images of each dam area are spliced ​​to obtain a complete dam area image; According to the endpoint position of the real crack, find the real crack that can be connected with the endpoint of the current real crack in the complete dam area image, and perform continuous splicing to obtain the corresponding complete crack; According to the endpoint position of the complete crack, determine whether the corresponding complete crack passes through the important area of ​​the dam body, and record the number N1 of complete cracks passing through the important area of ​​the dam body; Obtain the total number of pixels G of the complete dam area image and the number of pixels g occupied by each complete crack in the complete dam area image. If g / G is greater than or equal to a first preset threshold, the corresponding complete crack is determined to be a severe crack, and the number of severe cracks N2 is counted; Calculate the abnormal value BT of the dam body, BT=k1*N1+k2*N2, where k1 represents the first preset coefficient and k2 represents the second preset coefficient.

5. The water conservancy facility inspection and early warning system based on drone according to claim 4 is characterized in that: According to the endpoint position of the real crack, a real crack that can be connected to the endpoint of the current real crack is found in the complete dam area image, and continuous splicing is performed to obtain the corresponding complete crack, specifically: In the complete dam area image, a real crack whose end point coincides with the end point of the current real crack, or a real crack whose end point is in the current real crack area, is found and spliced ​​with the current real crack to form a temporary complete crack; Then find a real crack whose endpoint position coincides with the endpoint position of the current temporary complete crack, or a real crack whose endpoint position is in the current real crack area, and then splice it to form a new temporary complete crack. Repeat this step until no real crack whose endpoint position coincides with the endpoint position of the new temporary complete crack and no real crack whose endpoint position is in the new temporary complete crack area can be found, and the latest temporary complete crack is a complete crack.

6. The water conservancy facility inspection and early warning system based on drone according to claim 3 is characterized in that: The subsidence information of the dam foundation area is analyzed according to the dam foundation area image, and the dam foundation abnormal value is calculated according to the subsidence information, specifically, the subsidence area is identified from the dam foundation area image through a pre-trained second deep learning model, and the total number N3 of subsidence areas in all dam foundation area images and the number N4 of pixels occupied by each subsidence area in the corresponding dam foundation area image are counted; Calculate the dam foundation abnormal value BJ, BJ=k3*N3+k4*N4, where k3 represents the third preset coefficient and k4 represents the fourth preset coefficient.

7. The water conservancy facility inspection and early warning system based on drone according to claim 3 is characterized in that: The analyzing the surface spalling information of the slope area according to the slope area image, and calculating the slope anomaly value according to the surface spalling information, specifically identifying the surface spalling area from the slope area image through a pre-trained third deep learning model, and counting the total number N5 of surface spalling areas in all slope area images and the number N6 of pixels occupied by each subsidence depression area in the corresponding dam foundation area image; Calculate the dam foundation abnormal value BP, BP=k5*N5+k6*N6, where k5 represents the fifth preset coefficient and k6 represents the sixth preset coefficient.

8. The water conservancy facility inspection and early warning system based on drone according to claim 3 is characterized in that: The instability assessment module assesses the instability value BW of the target dam according to the abnormal values ​​of each sub-area, specifically: BW=r1*BT+r2*BJ+r3*BP, where BW represents an unstable value, r1 represents a first preset weight, r2 represents a second preset weight, and r3 represents a third preset weight.

9. The water conservancy facility inspection and early warning system based on drone according to claim 3 is characterized in that: The alarm module sends alarm information to the user according to the abnormal values ​​of each sub-area and the instability value of the target dam, specifically: If the dam body abnormal value is greater than a first preset abnormal threshold, a dam body abnormality warning message is issued to the user; If the dam foundation abnormality value is greater than a second preset abnormality threshold, a dam foundation abnormality alarm message is sent to the user; If the slope abnormality value is greater than a third preset abnormality threshold, a slope abnormality warning message is issued to the user; If the instability value of the target dam is greater than a preset comprehensive threshold, a dam instability warning message is sent to the user.

10. A water conservancy facility inspection and early warning method based on an unmanned aerial vehicle, applied to the water conservancy facility inspection and early warning system based on an unmanned aerial vehicle according to any one of claims 1 to 9, characterized in that: The following steps are involved: Obtain a panoramic image of the target dam by using a drone equipped with a camera; The sub-areas of the target dam are divided through the panoramic image of the dam, including the dam foundation area, the dam body area and the slope area; Analyze the shooting detection points of each sub-area; Acquire the corresponding detection images taken by the drone at each shooting detection point, wherein the detection images are divided into dam foundation area images, dam body area images and slope area images; According to each detection image, analyze the abnormal value of each sub-region; The instability value of the target dam is evaluated based on the outliers of each sub-area; Warning information is issued to users based on the abnormal values ​​of each sub-area and the instability value of the target dam.

Citation Information

Patent Citations

  • An empty foundation detection method and a device for abnormal condition of a dam body

    CN109409406A

  • Shale reservoir refracturing stress-fracture redirection simulation method and system

    CN114266204A

  • Quantitative characterization method for shale oil horizontal well volume fracturing fracture volume

    CN116128083A

  • Urban river big data monitoring liquid level alarm system and method

    CN116202590A

  • Water conservancy facility patrol early warning method, system and equipment based on unmanned aerial vehicle and medium

    CN116310904A

Cited By

  • Dam detection method and system based on unmanned aerial vehicle

    CN120084285A