A GNSS dam seepage pressure monitoring method and system based on Beidou positioning and image recognition

Abstract

The present application relates to the field of Beidou positioning and image recognition, and in particular to a GNSS dam seepage pressure monitoring method and system based on Beidou positioning and image recognition, the method comprising: obtaining images with continuous collection times corresponding to a plurality of surface monitoring points; obtaining the three-dimensional coordinates of each surface monitoring point determined by a Beidou positioning module; identifying seepage pressure information according to the image to obtain the seepage pressure level corresponding to the surface monitoring point; constructing a spatial distribution map of the dam seepage pressure level and determining the three-dimensional coordinates corresponding to the dangerous surface monitoring point according to the three-dimensional coordinates corresponding to each surface monitoring point and the seepage pressure level corresponding to each surface monitoring point; determining the inspection plan for the next inspection by the inspection drone according to the constructed spatial distribution map of the dam seepage pressure level and the three-dimensional coordinates corresponding to the dangerous surface monitoring point, so that the inspection drone conducts inspections in the next time period according to the inspection plan to realize monitoring of the dam seepage pressure.

Description

Technical Field

[0001] The present application relates to the field of Beidou positioning and image recognition, and in particular to a GNSS dam seepage pressure monitoring method and system based on Beidou positioning and image recognition. Background Art

[0002] As an important water conservancy engineering structure, the dam undertakes multiple functions such as reservoir regulation, flood control, and power generation. However, during the operation of the dam, due to the influence of various factors, such as changes in reservoir water levels, geological conditions, and climatic conditions, seepage may occur. Excessive or abnormal seepage may pose a direct threat to the structural safety of the dam, and even lead to serious consequences such as dam instability or dam failure.

[0003] Therefore, monitoring the seepage pressure of the dam and timely discovering and dealing with seepage problems have always been one of the important issues studied by relevant technical personnel. Summary of the invention

[0004] The purpose of this application is to provide a GNSS dam seepage pressure monitoring method and system based on Beidou positioning and image recognition, which can realize the monitoring of dam seepage pressure.

[0005] In a first aspect, a GNSS dam seepage pressure monitoring method based on Beidou positioning and image recognition is provided, which is applied to a monitoring system, wherein the monitoring system comprises: a Beidou positioning module, which is used to determine the three-dimensional coordinates of the dam monitoring point based on the received Beidou satellite signal; an inspection drone; and an electronic device for implementing the monitoring method that is communicatively connected to the Beidou positioning module and the inspection drone. The monitoring method comprises:

[0006] Obtaining images with continuous collection time corresponding to multiple surface monitoring points collected according to the current inspection plan and sent by the inspection drone;

[0007] Obtain the three-dimensional coordinates of each surface monitoring point determined by the Beidou positioning module;

[0008] For each surface monitoring point, the seepage pressure information is identified based on the continuous images to obtain the seepage pressure level corresponding to the surface monitoring point;

[0009] According to the three-dimensional coordinates corresponding to each surface monitoring point and the seepage pressure level corresponding to each surface monitoring point, a spatial distribution map of the seepage pressure level of the dam is constructed and the three-dimensional coordinates corresponding to the dangerous surface monitoring point are determined, wherein the dangerous surface monitoring point is a surface monitoring point whose seepage pressure level is greater than a preset threshold value;

[0010] According to the constructed spatial distribution map of the dam seepage pressure level and the three-dimensional coordinates corresponding to the dangerous surface monitoring points, the inspection plan of the next inspection by the inspection drone is determined so that the inspection drone can inspect in the next time period according to the inspection plan.

[0011] In an implementable solution, after determining the inspection plan of the next inspection by the inspection drone according to the constructed spatial distribution map of the dam seepage pressure level and the three-dimensional coordinates corresponding to the dangerous surface monitoring points, the method further includes:

[0012] According to the level difference between the seepage level of each surface monitoring point corresponding to the target time and the preset reference level, a level difference standard deviation for the target time is obtained, and according to the average value of the level difference standard deviations corresponding to each of the multiple acquisition times, a first standard deviation is obtained, and the target time is any time among the multiple acquisition times;

[0013] For each dangerous surface monitoring point, a standard deviation of the grade difference for the dangerous surface monitoring point is generated according to the grade differences corresponding to the multiple acquisition times, and the inspection cycle is adjusted according to the first standard deviation and the standard deviation of the grade difference corresponding to the dangerous surface monitoring point;

[0014] Based on the adjusted inspection cycle and the current inspection cycle corresponding to the inspection points in the inspection plan, the inspection cycle is determined so that the inspection drone determines the next time period based on the inspection cycle and performs inspection according to the inspection plan in the next time period.

[0015] In an implementable solution, the inspection plan for the next inspection by the inspection drone is determined based on the constructed spatial distribution map of the dam seepage pressure level and the three-dimensional coordinates corresponding to the dangerous surface monitoring points, including:

[0016] Analyze the spatial distribution map of the dam seepage pressure level to obtain the seepage pressure level information corresponding to each of the multiple areas of the dam, wherein the seepage pressure level information includes: average seepage pressure level and actual seepage pressure change data set;

[0017] Based on the average seepage level of each area, focus areas were obtained from multiple areas of the dam;

[0018] Time series analysis of actual seepage pressure change datasets in key focus areas was performed to obtain predicted long-term trends;

[0019] Important monitoring points in the key focus areas corresponding to the predicted long-term trend anomalies are used as supplementary danger points to update the danger surface monitoring points;

[0020] According to the updated three-dimensional coordinates of the dangerous surface monitoring points, the inspection plan for the next inspection by the inspection drone is planned.

[0021] In one possible approach, areas of concern are identified from multiple areas of the dam based on the average seepage level of each area, including:

[0022] The first priority area was selected from multiple areas of the dam based on the average seepage pressure level and actual seepage pressure change data set of each area;

[0023] For each area to be screened, the seepage pressure level is compared with the preset seepage pressure threshold to determine the first safety level; the safety adjustment level is determined according to the current rainfall and water level information; the area to be screened is the area other than the first key focus area among the multiple areas of the dam;

[0024] Screening out a second key focus area from all the areas to be screened according to the security level of each area to be screened, wherein the security level is determined according to the first security level and the security adjustment level;

[0025] The first key focus area and the second key focus area are used as key focus areas.

[0026] In one feasible solution, the inspection plan for the next inspection by the inspection drone is planned according to the updated three-dimensional coordinates of the dangerous surface monitoring points, including:

[0027] Determine the main route based on the updated three-dimensional coordinates of the dangerous surface monitoring points;

[0028] For each target dangerous surface monitoring point in the updated dangerous surface monitoring points, the flight altitude of the UAV is determined according to the elevation information of the target dangerous surface monitoring point, and the flight speed is determined according to the seepage pressure level of the target dangerous surface monitoring point. The higher the seepage pressure level, the lower the flight speed.

[0029] Generate the inspection plan for the next inspection of the inspection drone based on the flight altitude and speed of the main route and the target dangerous surface monitoring points.

[0030] In an implementable solution, the seepage pressure information is identified based on the continuous images to obtain the seepage pressure level corresponding to the surface monitoring point, including:

[0031] Using an image recognition model, the continuous images are subjected to abnormality type recognition to obtain the abnormality type and information corresponding to the abnormality type. When the abnormality type is a crack, the corresponding information is the crack size and crack shape; when the abnormality type is water seepage, the corresponding information is the water seepage area size and water seepage degree;

[0032] Determine a first value corresponding to the information corresponding to the abnormal type and a second value corresponding to the abnormal type;

[0033] Obtaining a third value according to the first value, the second value, and the corresponding weights;

[0034] According to the third value and the value ranges corresponding to the levels, the osmotic pressure level corresponding to the third value is matched.

[0035] In an implementable solution, after obtaining the three-dimensional coordinates of each surface monitoring point determined by the Beidou positioning module, the method further includes:

[0036] Determine the displacement value of each surface monitoring point according to the three-dimensional coordinates of each surface monitoring point;

[0037] Correspondingly, for each surface monitoring point, after identifying the seepage pressure information according to the continuous images and obtaining the seepage pressure level corresponding to the surface monitoring point, the method further includes:

[0038] For the surface monitoring points where displacement occurs, if the displacement value is higher than the preset maximum displacement threshold, the seepage pressure level is adjusted to the highest level; if the displacement value is less than the preset minimum displacement threshold, the seepage pressure level remains unchanged; otherwise, the level adjustment value is determined according to the displacement value, and the seepage pressure level is adjusted according to the level adjustment value.

[0039] In an implementable solution, determining the displacement value of each surface monitoring point according to the three-dimensional coordinates of each surface monitoring point includes:

[0040] Obtain the three-dimensional coordinates of the calibration point determined by the Beidou positioning module; determine the actual distance between the calibration point and each surface monitoring point based on the three-dimensional coordinates of the calibration point and the three-dimensional coordinates of each surface monitoring point, calculate the difference between the actual distance and the standard distance, and determine the displacement value of each surface monitoring point;

[0041] or,

[0042] The initial three-dimensional coordinates of each surface monitoring point are obtained, and the displacement value of each surface monitoring point is determined according to the initial three-dimensional coordinates of each surface monitoring point and the three-dimensional coordinates of each surface monitoring point.

[0043] In a second aspect, an electronic device is provided, the electronic device comprising:

[0044] one or more processors;

[0045] Memory;

[0046] One or more applications, wherein one or more applications are stored in a memory and configured to be executed by one or more processors, and one or more programs are configured to: perform operations corresponding to the method shown in any possible implementation of the first aspect.

[0047] In a third aspect, a computer-readable storage medium is provided, wherein the storage medium stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, at least one program, a code set or an instruction set is loaded and executed by a processor to implement a method as shown in any possible implementation of the first aspect.

[0048] According to a fourth aspect, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the method is implemented as shown in any possible implementation manner of the first aspect.

[0049] In summary, the present application includes at least one of the following beneficial technical effects:

[0050] 1. Through the inspection drone, the images of the surface detection points are collected periodically, and the seepage pressure information is identified to quickly obtain the seepage pressure level, and the seepage pressure level spatial distribution map is constructed, so that users can intuitively understand the seepage pressure situation. Through the constructed spatial distribution map of the dam seepage pressure level and the three-dimensional coordinates of the dangerous surface monitoring points, the next inspection plan is formulated. The drone inspection, image recognition and Beidou positioning technology are combined to realize the periodic monitoring of the dam;

[0051] 2. The standard deviation of the grade difference of the target time indicates the overall regional stability, and the standard deviation of the grade difference of the dangerous surface monitoring point indicates the stability of the point. The adjustable time of the cycle for a certain dangerous surface monitoring point is determined in combination with the overall stability and the stability of the dangerous surface monitoring point, that is, the adjusted inspection cycle. Then, a more reasonable inspection plan is formulated by comprehensively considering the adjusted inspection cycle of each inspection point in the inspection plan and the current inspection cycle. Based on the dynamically adjusted inspection cycle, the inspection drone can conduct inspections in the next period according to the optimized inspection plan, which can not only improve the efficiency and accuracy of the inspection, but also better meet the needs of dam safety management and ensure the safe and stable operation of the dam.

[0052] 3. The standard deviation of the grade difference at the target time indicates the overall regional stability, and the standard deviation of the grade difference at the dangerous surface monitoring point indicates the stability of the point. The overall stability and the stability of the dangerous surface monitoring point are combined to determine the adjustable time for a certain dangerous surface monitoring point, that is, the adjusted inspection cycle. Then, a more reasonable inspection plan is formulated by comprehensively considering the adjusted inspection cycle of each inspection point in the inspection plan and the current inspection cycle. Based on the dynamically adjusted inspection cycle, the inspection drone can conduct inspections in the next period according to the optimized inspection plan, which can not only improve the efficiency and accuracy of the inspection, but also better meet the needs of dam safety management and ensure the safe and stable operation of the dam. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is a structural schematic diagram of a GNSS dam seepage pressure monitoring system with Beidou positioning and image recognition provided in an embodiment of the present application;

[0054] Figure 2 It is a flow chart of a GNSS dam seepage pressure monitoring method using Beidou positioning and image recognition provided in an embodiment of the present application;

[0055] Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, those skilled in the art may make modifications to the present embodiment without any creative contribution as needed. However, as long as it is within the scope of the claims of the present application, it shall be protected by the patent law.

[0057] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0058] It should be noted that in the optional embodiments of the present application, the object information and other related data involved, when the embodiments in the present application are applied to specific products or technologies, need to obtain the permission or consent of the object, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. In other words, if the data related to the object is involved in the embodiments of the present application, it needs to be obtained through the authorization and consent of the object, the authorization and consent of the relevant departments, and in compliance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiments, the acquisition of all personal information needs to obtain the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained. The embodiments also need to be implemented with the authorization and consent of the object. In addition, the relevant data set in the monitoring scheme provided in the embodiments of the present application also complies with relevant regulations. The monitoring scheme provided by the embodiments of the present application assists in warning of abnormal seepage pressure and ensures the safety of the dam.

[0059] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0060] Please refer to Figure 1 , Figure 1 A GNSS (Global Navigation Satellite System) dam seepage pressure monitoring system based on Beidou positioning and image recognition provided in the embodiment of the present application includes:

[0061] Beidou positioning module 110, used to determine the three-dimensional coordinates of the dam monitoring point based on the received Beidou satellite signal;

[0062] Inspection drone 120, used to collect images with continuous collection time corresponding to each of a plurality of surface monitoring points according to the inspection plan;

[0063] An electronic device 130 is communicatively connected to the Beidou positioning module 110 and the inspection drone 120 and is used to implement a GNSS dam seepage pressure monitoring method based on Beidou positioning and image recognition.

[0064] Specifically, the electronic device 130 is used to: obtain continuous images of the collection time corresponding to multiple surface monitoring points collected according to the current inspection plan and sent by the inspection drone; obtain the three-dimensional coordinates of each surface monitoring point determined by the Beidou positioning module; for each surface monitoring point, identify the seepage pressure information according to the continuous images to obtain the seepage pressure level corresponding to the surface monitoring point; construct a spatial distribution map of the dam seepage pressure level and determine the three-dimensional coordinates corresponding to the dangerous surface monitoring point according to the three-dimensional coordinates corresponding to each surface monitoring point and the seepage pressure level corresponding to each surface monitoring point, wherein the dangerous surface monitoring point is a surface monitoring point whose seepage pressure level is greater than a preset threshold; determine the inspection plan of the next inspection by the inspection drone according to the constructed spatial distribution map of the dam seepage pressure level and the three-dimensional coordinates corresponding to the dangerous surface monitoring point, so that the inspection drone will inspect in the next time period according to the inspection plan.

[0065] In a possible implementation of the embodiment of the present application, the monitoring system may also include: a plurality of osmometers 140 set at the monitoring points of the dam body, which are used to collect the osmotic pressure data of the monitoring points and send the osmotic pressure data to the electronic device; the electronic device is also used to issue an alarm when the osmotic pressure data is greater than the preset osmotic pressure data threshold. The specific choice is whether to determine the relevant information of the osmotic pressure based on image recognition or to analyze the relevant information of the osmotic pressure based on the osmotic pressure meter data. The embodiment of the present application is no longer limited and can be set according to user needs.

[0066] Specifically, the present application provides a method, such as Figure 2 As shown, the method provided in the embodiment of the present application can be executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application. The method includes:

[0067] S101, obtaining images with continuous collection time corresponding to multiple surface monitoring points collected according to the current inspection plan and sent by the inspection drone;

[0068] S102, obtaining the three-dimensional coordinates of each surface monitoring point determined by the Beidou positioning module;

[0069] The inspection drone flies according to the current inspection plan and collects images that are continuous in time. Multiple surface monitoring points are pre-set on the dam, and each surface monitoring point is equipped with a Beidou positioning module. If it is the first inspection, the current inspection plan is the initial inspection plan, and the images collected by the inspection drone are images of all surface monitoring points; if it is not the first inspection, the current inspection plan is set based on the last inspection.

[0070] Three-dimensional coordinates include: longitude, latitude and elevation information.

[0071] S103, for each surface monitoring point, identifying the seepage pressure information according to the continuous images, and obtaining the seepage pressure level corresponding to the surface monitoring point;

[0072] Specifically, image recognition is performed on each surface monitoring point to obtain the permeability level. Before image recognition, the data can also be pre-processed, such as graying, denoising, contrast enhancement, etc.

[0073] S104, constructing a spatial distribution map of the dam's seepage pressure level and determining the three-dimensional coordinates corresponding to the dangerous surface monitoring points according to the three-dimensional coordinates corresponding to each surface monitoring point and the seepage pressure level corresponding to each surface monitoring point, wherein the dangerous surface monitoring points are surface monitoring points whose seepage pressure levels are greater than a preset threshold;

[0074] Specifically, a three-dimensional visualization tool such as GIS or an online platform is selected, and the three-dimensional coordinates and seepage pressure level data corresponding to each surface monitoring point are imported into the three-dimensional visualization tool. Different colors are set for different seepage pressure levels for easy distinction, and a spatial distribution map of the dam seepage pressure level is obtained.

[0075] S105. Determine the inspection plan for the next inspection by the inspection drone based on the constructed spatial distribution map of the dam seepage pressure level and the three-dimensional coordinates corresponding to the dangerous surface monitoring points, so that the inspection drone conducts inspections in the next time period according to the inspection plan.

[0076] It can be seen that in the embodiment of the present application, the inspection drone periodically collects images of the surface detection points and performs seepage pressure information identification to quickly obtain the seepage pressure level and construct a spatial distribution map of the seepage pressure level, so that users can intuitively understand the seepage pressure situation. The next inspection plan is formulated through the constructed spatial distribution map of the dam seepage pressure level and the three-dimensional coordinates of the dangerous surface monitoring points. The drone inspection, image recognition and Beidou positioning technology are combined to realize periodic monitoring of the dam.

[0077] A possible implementation of the embodiment of the present application, after determining the inspection plan of the next inspection of the inspection drone according to the constructed spatial distribution map of the dam seepage pressure level and the three-dimensional coordinates corresponding to the dangerous surface monitoring points, also includes: S106-S108 (not shown in the drawings), wherein:

[0078] S106, obtaining a standard deviation of the level difference for the target time according to the level difference between the seepage level of each surface monitoring point corresponding to the target time and the preset reference level, and calculating the average value of the level difference standard deviations corresponding to the multiple acquisition times to obtain a first standard deviation, where the target time is any one of the multiple acquisition times;

[0079] Specifically, any collection time is selected as the target time, and the difference between the seepage level of each surface monitoring point and the preset reference level is calculated, wherein the preset reference level can be set by the user based on experience, and it represents the level where there is no seepage. The preset reference level and the preset threshold value can be equal or different, and the embodiments of the present application will no longer limit this.

[0080] For example, the grade differences of all surface monitoring points include (x1, x2, x3, …, xn). Through the grade differences, the mean of the grade differences is calculated to be xp, and then the standard deviation of the grade differences is calculated to be Where n is the total number of surface monitoring points. The larger the standard deviation of the grade difference, the greater the degree of dispersion of the values, that is, the greater the difference between the values, and the greater the fluctuation; conversely, the smaller the standard deviation, the smaller the degree of dispersion of this group of values, that is, the smaller the difference between the values, and the smaller the fluctuation.

[0081] Through step S106, the standard deviation of the osmotic pressure difference at each time can be obtained, and then the first standard deviation can be calculated.

[0082] S107, for each dangerous surface monitoring point, generating a standard deviation of the grade difference for the dangerous surface monitoring point according to the grade differences corresponding to the multiple acquisition times, and determining to adjust the inspection cycle according to the first standard deviation and the grade difference standard deviation corresponding to the dangerous surface monitoring point;

[0083] For each hazardous surface monitoring point, the average grade difference is calculated through the grade differences corresponding to multiple acquisition times, and the standard deviation of the grade difference of the hazardous surface monitoring point is calculated through the grade differences corresponding to multiple acquisitions over time and the average grade difference.

[0084] When the degree of deviation of all surface monitoring points is small, that is, the first standard deviation is small, it indicates the stability of the overall area. However, the stability of the dangerous surface monitoring points also needs to be considered. Then, the stability is determined by the standard deviation of the grade difference of the dangerous surface monitoring points. The overall stability and the stability of the dangerous surface monitoring points are combined to jointly determine the adjustable time for a certain dangerous surface monitoring point, that is, to adjust the inspection cycle.

[0085] In an achievable scheme, a first sub-adjustment time corresponding to the first standard deviation is determined based on the first standard deviation and the first correspondence; a second sub-adjustment time corresponding to the level difference standard deviation corresponding to the dangerous surface monitoring point is determined based on the level difference standard deviation corresponding to the dangerous surface monitoring point and the second correspondence, wherein the first correspondence is a correspondence between multiple standard deviations and multiple first sub-adjustment times, and the second correspondence is a correspondence between multiple standard deviations and multiple second sub-adjustment times. The correspondence can be customized by the user and is no longer limited in the embodiments of the present application.

[0086] Through S107, the corresponding adjustment time lengths of all dangerous surface monitoring points can be obtained, that is, the inspection cycle is adjusted.

[0087] S108. Determine the inspection cycle based on the adjusted inspection cycle corresponding to the inspection point in the inspection plan and the current inspection cycle, so that the inspection drone determines the next time period based on the inspection cycle, and performs inspection according to the inspection plan in the next time period.

[0088] The inspection points include dangerous surface monitoring points and may also include designated surface monitoring points, which are not limited in the present embodiment and can be set by the user according to actual needs. For designated surface monitoring points, the inspection cycle is adjusted to 0 by default.

[0089] In a feasible solution, the highest adjusted inspection cycle can be used as the adjustment duration, or the average of the adjusted inspection cycles can be used as the adjustment duration, and the sum of the adjustment duration and the current inspection cycle can be used as the next inspection cycle, so that after the current inspection task is completed, the next inspection task can be performed after an interval inspection cycle.

[0090] It can be seen that in the embodiment of the present application, the standard deviation of the level difference of the target time represents the stability of the overall area, and the standard deviation of the level difference of the dangerous surface monitoring point represents the stability of the point. The overall stability and the stability of the dangerous surface monitoring point are combined to jointly determine the adjustable time of the cycle for a certain dangerous surface monitoring point, that is, to adjust the inspection cycle. Then, considering the adjusted inspection cycle of each inspection point in the inspection plan and the current inspection cycle, a more reasonable inspection plan is formulated. Based on the dynamically adjusted inspection cycle, the inspection drone can conduct inspections in the next time period according to the optimized inspection plan, which can not only improve the efficiency and accuracy of the inspection, but also better meet the needs of dam safety management and ensure the safe and stable operation of the dam.

[0091] In a possible implementation example, S105 determines the inspection plan for the next inspection of the inspection drone according to the constructed spatial distribution map of the dam seepage pressure level and the three-dimensional coordinates corresponding to the dangerous surface monitoring points, including: S1051-S1055 (not shown in the drawings), wherein:

[0092] S1051. Analyze the spatial distribution map of the dam seepage pressure level to obtain the seepage pressure level information corresponding to multiple areas of the dam, the seepage pressure level information including: average seepage pressure level and actual seepage pressure change data set;

[0093] The dam was divided into regions in advance, each of which included several monitoring points; then, the surface monitoring points were divided into regions based on the obtained spatial distribution map of the dam seepage pressure level, so as to obtain the relevant information of the surface monitoring points corresponding to each region, and then the average seepage pressure level was calculated based on the relevant information of the surface monitoring points in the region. Among them, the actual seepage pressure change data set includes the average seepage pressure level at different times.

[0094] S1052. Based on the average seepage level of each area, focus areas are obtained from multiple areas of the dam;

[0095] In one possible approach, areas where the average osmotic pressure level is greater than a preset average osmotic pressure level are taken as key focus areas, wherein the preset average osmotic pressure level can be set by the user based on experience, and its size is close to a preset threshold, preferably, smaller than the preset threshold.

[0096] In another possible embodiment, S1052 includes:

[0097] According to the average seepage pressure level and the actual seepage pressure change data set of each area, the first key focus area is screened out from multiple areas of the dam; wherein, based on the average seepage pressure level at each moment in the actual seepage pressure change data set, the standard deviation is determined to determine the degree of discreteness, and based on the standard deviation and average seepage pressure level corresponding to each area, the area with a large standard deviation and / or a large average seepage pressure level is selected as the first key focus area.

[0098] For each area to be screened, the seepage pressure level is compared with the preset seepage pressure threshold to determine the first safety level; the safety adjustment level is determined according to the current rainfall and water level information; the area to be screened is the area other than the first key focus area in the multiple areas of the dam; for areas other than the key focus area, there may also be areas with certain risks implicitly. Then, in the embodiment of the present application, the safety of the area is analyzed to screen out additional areas that need to be focused on. Among them, the preset seepage pressure threshold is less than the preset threshold, and there is a preset correspondence between the level difference and the safety level, the rainfall and the adjustment level, and the water level and the adjustment level. Then, according to the correspondence between the rainfall and the adjustment level, the water level and the adjustment level, and the current rainfall and water level information, the safety adjustment level is determined, and the first safety level is determined according to the correspondence between the level difference and the safety level. By summing the first safety level and the safety adjustment level, the safety level corresponding to each area to be screened is obtained.

[0099] According to the security level of each area to be screened, a second key focus area is screened out from all the areas to be screened, and the security level is determined according to the first security level and the security adjustment level; the first key focus area and the second key focus area are used as key focus areas. Among them, the areas to be screened with low security levels are used as supplements to obtain key focus areas.

[0100] S1053. Perform time series analysis on the actual osmotic pressure change data set in the key focus areas to obtain predicted long-term trends;

[0101] The actual seepage pressure change data set of the key focus area is fitted to obtain the trend change curve, which is used to predict the change trend in the future preset time period, where the preset time period is at least the current inspection cycle. If the change trend is increasing, it means that the predicted long-term trend is abnormal, there is danger, and it needs to be monitored. Otherwise, it means that the current state of the area is relatively stable.

[0102] S1054, using important monitoring points in the key focus area corresponding to the predicted long-term trend anomaly as supplementary danger points to update the danger surface monitoring points;

[0103] S1055. Plan the next inspection plan of the inspection drone based on the updated three-dimensional coordinates of the dangerous surface monitoring points.

[0104] It can be seen that in the embodiment of the present application, by analyzing the spatial distribution map of the dam's seepage pressure level, the seepage pressure level information of each area of ​​the dam can be obtained, and then, combined with the average seepage pressure level, a screening is performed to obtain the key focus area, and the development trend of the key focus area is predicted. In case of abnormality, the dangerous surface monitoring points are supplemented as supplementary dangerous points, which can make the determined dangerous surface monitoring points more comprehensive and accurate.

[0105] In a possible embodiment, S1055 plans the inspection plan of the next inspection of the inspection drone based on the updated three-dimensional coordinates of the dangerous surface monitoring points, including: determining the main route based on the updated three-dimensional coordinates of the dangerous surface monitoring points; for each target dangerous surface monitoring point among the updated dangerous surface monitoring points, determining the flight altitude of the drone based on the elevation information of the target dangerous surface monitoring point, and determining the flight speed based on the seepage pressure level of the target dangerous surface monitoring point, the higher the seepage pressure level, the lower the flight speed; generating the inspection plan of the next inspection of the inspection drone based on the main route and the flight altitude and flight speed of the target dangerous surface monitoring point.

[0106] The drone's flight altitude can be a fixed altitude above the dangerous surface monitoring point. If there are obstructions around the dangerous surface monitoring point, the drone's flight altitude can be lowered and the shooting angle can be adjusted according to the obstruction situation, so as to obtain a complete image of the dangerous surface monitoring point. The higher the permeability level, the higher the probability that the dangerous surface monitoring point may be dangerous. Therefore, the flight speed can be reduced to reduce the impact of the shaking of the fuselage when taking photos, making the photos clearer.

[0107] It can be seen that in the embodiment of the present application, a corresponding flight altitude and flight speed are set for each inspection point, and the generated inspection plan can optimize the inspection efficiency of the drone to the greatest extent. The drone can fly along the main route at an appropriate speed while ensuring safety, and adjust the flight speed according to the seepage pressure level of different dangerous points, thereby achieving optimal utilization of resources.

[0108] In a possible embodiment, S103, the permeability information is identified according to continuous images to obtain the permeability level corresponding to the surface monitoring point, including: method one and method two; method one is to obtain the permeability level based on image recognition, and method two is to determine the permeability level based on the permeability value collected by the permeability device.

[0109] In some cases, installing sensors directly on the dam may be limited or impractical. In this case, image recognition technology, as a non-contact monitoring method, can avoid interference with the dam structure while monitoring the seepage pressure. Method 1 can be selected to identify the seepage pressure level. It should be noted that the seepage pressure can also be determined through joint analysis of method 1 and method 2 to improve the accuracy of monitoring.

[0110] Method 1:

[0111] Using the image recognition model, the abnormality type of continuous images is identified to obtain the abnormality type and the corresponding information of the abnormality type. When the abnormality type is crack, the corresponding information is the crack size and crack shape. When the abnormality type is water seepage, the corresponding information is the water seepage area size and water seepage degree.

[0112] Determine a first value corresponding to the information corresponding to the abnormal type and a second value corresponding to the abnormal type;

[0113] Obtaining a third value according to the first value, the second value, and the corresponding weights;

[0114] According to the third value and the value ranges corresponding to the levels, the osmotic pressure level corresponding to the third value is matched.

[0115] Specifically, the training process of the image recognition model includes: obtaining training images and corresponding labels, identifying the initial model based on the training images to obtain recognition results, determining the loss value according to the recognition results and the corresponding labels, iterating the training model through the loss value until the loss value reaches a preset loss value threshold, and obtaining the image recognition model.

[0116] Corresponding second values ​​are pre-set for different abnormality types, so that after the abnormality type is determined, the corresponding second value is obtained according to the determined abnormality type.

[0117] For cracks, different size ranges and shapes are preset with corresponding sub-values, so that after determining the actual crack size and crack shape of the crack, two sub-values ​​are obtained, and the first value is obtained based on the two sub-values. The two sub-values ​​can be directly summed, or combined with weighted summation, and users can customize the settings.

[0118] For water seepage, the water seepage degree may be the flow rate of the water seepage, specifically the water flow rate estimated by relevant characteristics of the water flow, such as water surface texture, wave pattern, etc. The electronic device pre-stores sub-values ​​corresponding to different water seepage degrees and water seepage areas, so that after determining the actual water seepage degree and the size of the water seepage area, two sub-values ​​can be obtained, and the first value is obtained based on the two sub-values. The two sub-values ​​can be directly summed, or combined with weighted summation, and the user can customize the setting.

[0119] It can be seen that the model can quickly determine the type of anomaly and related information, and then perform weighted calculations based on the type of anomaly and related information to more accurately determine the permeability level.

[0120] In a possible implementation, after obtaining the three-dimensional coordinates of each surface monitoring point determined by the Beidou positioning module, the method further includes:

[0121] Determine the displacement value of each surface monitoring point according to the three-dimensional coordinates of each surface monitoring point;

[0122] Correspondingly, for each surface monitoring point, after the seepage pressure information is identified based on the continuous images and the seepage pressure level corresponding to the surface monitoring point is obtained, the following steps are also included:

[0123] For the surface monitoring points where displacement occurs, if the displacement value is higher than the preset maximum displacement threshold, the seepage pressure level is adjusted to the highest level; if the displacement value is less than the preset minimum displacement threshold, the seepage pressure level remains unchanged; otherwise, the level adjustment value is determined according to the displacement value, and the seepage pressure level is adjusted according to the level adjustment value.

[0124] Specifically, according to the three-dimensional coordinates of each surface monitoring point, the displacement value of each surface monitoring point is determined, including:

[0125] Obtain the three-dimensional coordinates of the calibration point determined by the Beidou positioning module; determine the actual distance between the calibration point and each surface monitoring point based on the three-dimensional coordinates of the calibration point and the three-dimensional coordinates of each surface monitoring point, calculate the difference between the actual distance and the standard distance, and determine the displacement value of each surface monitoring point;

[0126] or,

[0127] The initial three-dimensional coordinates of each surface monitoring point are obtained, and the displacement value of each surface monitoring point is determined according to the initial three-dimensional coordinates of each surface monitoring point and the three-dimensional coordinates of each surface monitoring point.

[0128] If the displacement value exceeds the limit, it means that the dam has a large deformation degree at this point, so no matter how large the seepage pressure level is, it is adjusted to the highest level to focus on it. If there is a certain displacement value, but the displacement value is very low, the level remains unchanged. If it is between the minimum displacement threshold and the maximum displacement threshold, it means that there is a certain degree of position. The larger the displacement, the more dangerous the point. Therefore, according to the preset displacement adjustment information, match the level adjustment value corresponding to the displacement value and adjust the level.

[0129] It can be seen that in the embodiment of the present application, by calculating the displacement value of the surface monitoring point, the slight deformation of the dam surface can be discovered in time. When the displacement value is higher than the preset maximum displacement threshold, the seepage pressure level is adjusted to the highest level, which can quickly trigger the safety warning mechanism; according to the different ranges of the displacement value, the seepage pressure level is finely adjusted. When the displacement value is lower than the minimum displacement threshold, the seepage pressure level is kept unchanged, which avoids unnecessary adjustments and maintains the stability and accuracy of the seepage pressure level. When the displacement value is between the two thresholds, the level adjustment value is determined according to the displacement value, and the seepage pressure level is adjusted accordingly, which can more accurately reflect the actual safety status of the dam; by combining the monitoring technology of three-dimensional coordinates and displacement values, the automatic adjustment of the seepage pressure level of the dam is realized.

[0130] An electronic device is provided in an embodiment of the present application, such as Figure 3 As shown, Figure 3 The electronic device 130 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 130 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 130 does not constitute a limitation on the embodiments of the present application.

[0131] Processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0132] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0133] The memory 303 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to this.

[0134] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0135] Among them, electronic devices include but are not limited to: mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0136] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.

[0137] An embodiment of the present application provides a computer program product, including a computer program, which implements the corresponding contents of the aforementioned method embodiment when the computer program is executed by a processor.

[0138] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0139] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A GNSS dam seepage pressure monitoring method based on Beidou positioning and image recognition, characterized in that: Applied to a monitoring system, the monitoring system includes: a Beidou positioning module, which is used to determine the three-dimensional coordinates of the dam monitoring point based on the received Beidou satellite signal; an inspection drone; and an electronic device that is communicatively connected to the Beidou positioning module and the inspection drone and is used to implement a monitoring method, the monitoring method including: Obtaining images with continuous collection time corresponding to multiple surface monitoring points collected according to the current inspection plan and sent by the inspection drone; Obtain the three-dimensional coordinates of each surface monitoring point determined by the Beidou positioning module; For each surface monitoring point, the seepage pressure information is identified based on the continuous images to obtain the seepage pressure level corresponding to the surface monitoring point; According to the three-dimensional coordinates corresponding to each surface monitoring point and the seepage pressure level corresponding to each surface monitoring point, a spatial distribution map of the seepage pressure level of the dam is constructed and the three-dimensional coordinates corresponding to the dangerous surface monitoring point are determined, wherein the dangerous surface monitoring point is a surface monitoring point whose seepage pressure level is greater than a preset threshold value; According to the constructed spatial distribution map of the dam seepage pressure level and the three-dimensional coordinates corresponding to the dangerous surface monitoring points, the inspection plan of the next inspection by the inspection drone is determined, so that the inspection drone conducts inspections in the next time period according to the inspection plan; According to the level difference between the seepage level of each surface monitoring point corresponding to the target time and the preset reference level, a level difference standard deviation for the target time is obtained, and the average value of the level difference standard deviations corresponding to each of the multiple acquisition times is calculated to obtain a first standard deviation, wherein the target time is any time among the multiple acquisition times; For each dangerous surface monitoring point, a standard deviation of the grade difference for the dangerous surface monitoring point is generated according to the grade differences corresponding to the multiple acquisition times, and the inspection cycle is adjusted according to the first standard deviation and the standard deviation of the grade difference corresponding to the dangerous surface monitoring point; Based on the adjusted inspection cycle and the current inspection cycle corresponding to the inspection points in the inspection plan, the inspection cycle is determined so that the inspection drone determines the next time period based on the inspection cycle and performs inspection according to the inspection plan in the next time period.

2. The GNSS dam seepage pressure monitoring method based on Beidou positioning and image recognition according to claim 1 is characterized in that: The method of determining the inspection plan of the next inspection by the inspection drone based on the constructed spatial distribution map of the dam seepage pressure level and the three-dimensional coordinates corresponding to the dangerous surface monitoring points includes: Analyze the spatial distribution map of the dam seepage pressure level to obtain the seepage pressure level information corresponding to each of the multiple areas of the dam, wherein the seepage pressure level information includes: average seepage pressure level and actual seepage pressure change data set; Based on the average seepage level of each area, focus areas were obtained from multiple areas of the dam; Time series analysis of actual seepage pressure change datasets in key focus areas was performed to obtain predicted long-term trends; Important monitoring points in the key focus areas corresponding to the predicted long-term trend anomalies are used as supplementary danger points to update the danger surface monitoring points; According to the updated three-dimensional coordinates of the dangerous surface monitoring points, the inspection plan for the next inspection by the inspection drone is planned.

3. The GNSS dam seepage pressure monitoring method based on Beidou positioning and image recognition according to claim 2 is characterized in that: Based on the average seepage level of each area, areas of focus were identified from multiple areas of the dam, including: The first priority area was selected from multiple areas of the dam based on the average seepage pressure level and actual seepage pressure change data set of each area; For each area to be screened, the seepage pressure level is compared with the preset seepage pressure threshold to determine the first safety level; the safety adjustment level is determined according to the current rainfall and water level information; the area to be screened is the area other than the first key focus area among the multiple areas of the dam; Screening out a second key focus area from all the areas to be screened according to the security level of each area to be screened, wherein the security level is determined according to the first security level and the security adjustment level; The first key focus area and the second key focus area are used as key focus areas.

4. The GNSS dam seepage pressure monitoring method based on Beidou positioning and image recognition according to claim 2 is characterized in that: According to the updated three-dimensional coordinates of the dangerous surface monitoring points, the inspection plan for the next inspection by the inspection drone is planned, including: Determine the main route based on the updated three-dimensional coordinates of the dangerous surface monitoring points; For each target dangerous surface monitoring point in the updated dangerous surface monitoring points, the flight altitude of the UAV is determined according to the elevation information of the target dangerous surface monitoring point, and the flight speed is determined according to the seepage pressure level of the target dangerous surface monitoring point. The higher the seepage pressure level, the lower the flight speed. Generate the inspection plan for the next inspection of the inspection drone based on the flight altitude and speed of the main route and the target dangerous surface monitoring points.

5. The GNSS dam seepage pressure monitoring method based on Beidou positioning and image recognition according to claim 1 is characterized in that: According to the continuous images, the seepage pressure information is identified to obtain the seepage pressure level corresponding to the surface monitoring point, including: Using an image recognition model, the continuous images are subjected to abnormality type recognition to obtain the abnormality type and information corresponding to the abnormality type. When the abnormality type is a crack, the corresponding information is the crack size and crack shape; when the abnormality type is water seepage, the corresponding information is the water seepage area size and water seepage degree; Determine a first value corresponding to the information corresponding to the abnormal type and a second value corresponding to the abnormal type; Obtaining a third value according to the first value, the second value, and the corresponding weights; According to the third value and the value ranges corresponding to the levels, the osmotic pressure level corresponding to the third value is matched.

6. The GNSS dam seepage pressure monitoring method based on Beidou positioning and image recognition according to claim 1 is characterized in that: After obtaining the three-dimensional coordinates of each surface monitoring point determined by the Beidou positioning module, the method further includes: Determine the displacement value of each surface monitoring point according to the three-dimensional coordinates of each surface monitoring point; Correspondingly, for each surface monitoring point, after identifying the seepage pressure information according to the continuous images and obtaining the seepage pressure level corresponding to the surface monitoring point, the method further includes: For the surface monitoring points where displacement occurs, if the displacement value is higher than the preset maximum displacement threshold, the seepage pressure level is adjusted to the highest level; if the displacement value is less than the preset minimum displacement threshold, the seepage pressure level remains unchanged; otherwise, the level adjustment value is determined according to the displacement value, and the seepage pressure level is adjusted according to the level adjustment value.

7. The GNSS dam seepage pressure monitoring method based on Beidou positioning and image recognition according to claim 6 is characterized in that: Determining the displacement value of each surface monitoring point according to the three-dimensional coordinates of each surface monitoring point includes: Obtain the three-dimensional coordinates of the calibration point determined by the Beidou positioning module; determine the actual distance between the calibration point and each surface monitoring point based on the three-dimensional coordinates of the calibration point and the three-dimensional coordinates of each surface monitoring point, calculate the difference between the actual distance and the standard distance, and determine the displacement value of each surface monitoring point; or, The initial three-dimensional coordinates of each surface monitoring point are obtained, and the displacement value of each surface monitoring point is determined according to the initial three-dimensional coordinates of each surface monitoring point and the three-dimensional coordinates of each surface monitoring point.

8. An electronic device, characterized in that: include: one or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to: execute the steps of the GNSS dam seepage pressure monitoring method based on Beidou positioning and image recognition according to any one of claims 1 to 7.

9. A GNSS dam seepage pressure monitoring system based on Beidou positioning and image recognition, characterized in that: include: Beidou positioning module, used to determine the three-dimensional coordinates of the dam monitoring point based on the received Beidou satellite signals; Inspection drones are used to collect images with continuous collection time corresponding to multiple surface monitoring points according to the inspection plan; An electronic device that is communicatively connected to a Beidou positioning module and an inspection drone and is used to implement a GNSS dam seepage pressure monitoring method based on Beidou positioning and image recognition as claimed in any one of claims 1 to 7.

Images