CN116027810A - Intelligent sea cable way inspection method and system based on unmanned aerial vehicle technology - Google Patents
Intelligent sea cable way inspection method and system based on unmanned aerial vehicle technology Download PDFInfo
- Publication number
- CN116027810A CN116027810A CN202310108897.9A CN202310108897A CN116027810A CN 116027810 A CN116027810 A CN 116027810A CN 202310108897 A CN202310108897 A CN 202310108897A CN 116027810 A CN116027810 A CN 116027810A
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- control parameter
- inspection
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention provides a marine cable line intelligent inspection method and system based on unmanned aerial vehicle technology, which relate to the technical field of intelligent inspection, and are used for acquiring the current position of a ship and the position of a marine cable protection area, acquiring a plurality of flight routes, optimizing the flight routes based on unmanned aerial vehicle information, acquiring the optimal flight routes, performing autonomous inspection, acquiring an inspection image through an image acquisition device, performing feature recognition on the inspection image, acquiring an image recognition result, and performing unmanned aerial vehicle control based on the image recognition result. The invention solves the technical problems that the traditional inspection method can only rely on an inspection ship to reach a submarine cable protection area for inspection of submarine cable lines, so that the treatment time efficiency is poor, the cost is high, and the personal safety risk exists, realizes the intelligent inspection of submarine cable lines based on unmanned plane technology, improves the efficiency of Gao Hailan operation and maintenance operation, reduces the operation cost, can avoid the risk of falling into water by offshore operators, and achieves the technical effect of improving the operation and maintenance level of submarine cables.
Description
Technical Field
The invention relates to the technical field of intelligent patrol, in particular to an intelligent patrol method and system for a submarine cable line based on an unmanned aerial vehicle technology.
Background
The submarine cable is an important component part of a cross-sea network power transmission system, and has important significance for guaranteeing regional power supply safety, reliability and flexibility. Submarine cables are protected by adding concrete cover plates, seabed flushing, stone throwing or rock piling and the like, but the submarine cables have exposure risks due to ocean currents, terrains and other changes. At this time, the sea cable is affected by external damage such as anchor breaking, drag breaking, offshore construction, port dredging, illegal fishery operation and the like of the sea ship, and the routing inspection of the sea cable is mainly carried out by personnel riding on the operation ship at present. The traditional operation method is to observe whether the behavior of the sea cable is damaged by external force such as ship anchoring, offshore construction, port dredging, illegal fishery operation and the like on the sea surface of the sea cable route by human eyes, but the traditional method has the problems of long time consumption, low operation efficiency, high cost, personnel falling into water and other personal safety risks.
Disclosure of Invention
The embodiment of the application provides a sea cable way intelligent inspection method and system based on unmanned aerial vehicle technology, which are used for performing sea cable way inspection by only relying on an inspection ship to reach a sea cable protection area for solving the technical problems of poor treatment time effect, high cost and personal safety risk in the traditional inspection method.
In view of the above problems, embodiments of the present application provide an intelligent inspection method and system for a submarine cable line based on unmanned aerial vehicle technology.
In a first aspect, an embodiment of the present application provides an intelligent inspection method for a submarine cable line based on unmanned aerial vehicle technology, where the method includes: acquiring the current position of a ship and the position of a submarine cable protection area, and acquiring a plurality of flight routes; optimizing the plurality of flight routes based on unmanned aerial vehicle information to obtain an optimal flight route; performing autonomous inspection based on the optimal flight route; in the autonomous inspection process, an inspection image is acquired through the image acquisition device; performing feature recognition on the inspection image to obtain an image recognition result; and controlling the unmanned aerial vehicle based on the image recognition result.
In a second aspect, an embodiment of the present application provides an intelligent inspection system for a submarine cable line based on unmanned aerial vehicle technology, the system includes: the system comprises a flying route acquisition module, a navigation module and a navigation module, wherein the flying route acquisition module is used for acquiring the current position of a ship and the position of a submarine cable protection area to acquire a plurality of flying routes; the optimal flight route acquisition module is used for optimizing the plurality of flight routes based on unmanned aerial vehicle information to obtain an optimal flight route; the autonomous patrol module is used for conducting autonomous patrol based on the optimal flight route; the inspection image acquisition module is used for acquiring an inspection image through the image acquisition device in an autonomous inspection process; the characteristic recognition module is used for carrying out characteristic recognition on the inspection image and obtaining an image recognition result; and the unmanned aerial vehicle control module is used for controlling the unmanned aerial vehicle based on the image recognition result.
One or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:
the embodiment of the application provides a sea cable way intelligent inspection method based on unmanned aerial vehicle technique relates to intelligent inspection technical field, acquires boats and ships current position to and sea cable protection zone position, obtains a plurality of flight routes, carries out optimizing to a plurality of flight routes based on unmanned aerial vehicle information, obtains optimum flight route, carries out independently to patrol and examine based on optimum flight route, and independently patrol and examine the in-process, acquire the image of patrolling and examining through image acquisition device, carry out feature recognition to the image of patrolling and examining, acquire image recognition result, carry out unmanned aerial vehicle's control based on image recognition result. The intelligent inspection method solves the technical problems that the traditional inspection method can only rely on an inspection ship to travel to a sea cable protection area for sea cable line inspection, so that the treatment time is poor, the cost is high, and the personal safety risk exists, realizes the intelligent inspection of the sea cable line based on the unmanned aerial vehicle technology, improves the efficiency of Gao Hailan operation and maintenance operation, reduces the operation cost, can avoid the risk of falling into water by offshore operators, and achieves the technical effect of improving the sea cable operation and maintenance level.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
Fig. 1 is a schematic flow chart of a submarine cable line intelligent inspection method based on unmanned aerial vehicle technology;
fig. 2 is a schematic diagram of a process of obtaining an optimal flight route in a submarine cable line intelligent patrol method based on unmanned aerial vehicle technology according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an intelligent inspection system for a submarine cable line based on unmanned aerial vehicle technology.
Reference numerals illustrate: the system comprises a flight route acquisition module 1, an optimal flight route acquisition module 2, an autonomous inspection module 3, an inspection image acquisition module 4, a feature identification module 5 and an unmanned aerial vehicle control module 6.
Detailed Description
According to the sea cable line intelligent inspection method based on the unmanned aerial vehicle technology, the technical problems that the traditional inspection method can only rely on an inspection ship to travel to a sea cable protection area to conduct sea cable line inspection, the treatment time is poor, the cost is high, and personal safety risks exist are solved.
Example 1
As shown in fig. 1, an embodiment of the present application provides an intelligent inspection method for a submarine cable line based on unmanned aerial vehicle technology, where the method is applied to an intelligent inspection system, and the intelligent inspection system is communicatively connected with an image acquisition device, and the method includes:
step S100: acquiring the current position of a ship and the position of a submarine cable protection area, and acquiring a plurality of flight routes;
specifically, the sea cable way intelligent inspection method based on unmanned aerial vehicle technology is applied to intelligent inspection system, intelligent inspection system and image acquisition device communication connection, image acquisition device is used for independently inspecting in-process and patrol and examine image acquisition.
The reference station is arranged on the take-off and landing ship, the reference station is used for continuously observing satellite navigation signals for a long time, and the communication facility transmits observation data to the ground fixed observation station of the data center in real time or at fixed time, and is used for positioning the starting position of the unmanned aerial vehicle before taking off, and simultaneously provides high-precision positioning capability for the unmanned aerial vehicle in the unmanned aerial vehicle return stage, so that the unmanned aerial vehicle can accurately land on the ship deck. The submarine cable protection area is the submarine cable pipeline protection area, generally, the coastal wide sea areas are 500 meters at the two sides of the submarine cable pipeline, the narrow sea areas such as a bay are 100 meters at the two sides of the submarine cable pipeline, and the submarine cable pipelines are 50 meters at the two sides of the submarine harbor area. And taking the current position of the ship as the center and taking the laying area of the submarine cable pipeline as the cruising range to obtain a plurality of flight routes.
Step S200: optimizing the plurality of flight routes based on unmanned aerial vehicle information to obtain an optimal flight route;
specifically, unmanned aerial vehicles are classified from flight platform configurations, and are classified into rotary-wing unmanned aerial vehicles, fixed-wing unmanned aerial vehicles, parachute-wing unmanned aerial vehicles, ornithopter unmanned aerial vehicles, unmanned airships, and the like. The rotor unmanned aerial vehicle can be divided into an unmanned helicopter platform, an unmanned multiaxial aircraft and an unmanned rotorcraft. Common unmanned multiaxial aircrafts, such as multi-rotor unmanned aerial vehicles, generate lift force by driving spiral prize rotation through a motor; when the fixed wing unmanned aerial vehicle flies, the power device generates forward pushing force or pulling force, and the lifting force is obtained by different air flow speeds passing through the upper surface and the lower surface of the wing. The navigation mark in the submarine cable protection area is abnormal or not, whether ship anchoring, offshore construction, port dredging, illegal fishery operation and the like exist or not, because the submarine cable protection area is long in navigation distance, a fixed-wing unmanned aerial vehicle, a composite-wing unmanned aerial vehicle and the like are generally selected according to the navigation content, the flight speed and the duration of the unmanned aerial vehicle are obtained according to the unmanned aerial vehicle type, the control parameters of the unmanned aerial vehicle are adjusted according to the flight speed and the duration, such as the maximum flight distance of the load guarantee of the unmanned aerial vehicle is closed, or all the load guarantee is started to acquire the maximum navigation information, the optimal control parameters are obtained according to the flight navigation through analog calculation, and the maximum distance which can be achieved is calculated according to the optimal control parameters, so that the optimal flight route is obtained.
Step S300: performing autonomous inspection based on the optimal flight route;
specifically, unmanned aerial vehicles selected according to the calculated optimal flight route control carry out sea cable route inspection operation, and the abnormal conditions of navigation marks in a sea cable protection area are mainly supervised. Although submarine cables are protected by adding concrete cover plates, seabed flushing, stone throwing or rock piling and the like, the submarine cables have exposure risks due to the changes of ocean currents, terrains and the like, and the submarine cables are affected by external damage such as anchor breaking of a marine ship, anchor towing, offshore construction, port dredging, illegal fishery operation and the like. The possible damage behavior of the submarine cable is monitored through unmanned aerial vehicle autonomous inspection.
Step S400: in the autonomous inspection process, an inspection image is acquired through the image acquisition device;
specifically, the image acquisition device is used for monitoring the inspection area, is usually a high-definition camera and a video camera, and on the one hand, the real-time image transmission is carried out on the inspection condition by carrying an image transmission system on the unmanned aerial vehicle, and the real-time condition of the sea cable routing sea surface is checked by a shore ground person. On the other hand, the inspection process can be photographed and recorded through the high-definition camera and the video camera, abnormal conditions are identified, corresponding measures are timely taken, and meanwhile, storage is carried out, so that later-stage consulting and calling are facilitated.
Step S500: performing feature recognition on the inspection image to obtain an image recognition result;
specifically, during image processing, given an input image, pixels in a small area in the input image are weighted and averaged to form each corresponding pixel in the output image, wherein a weight is defined by a function, the function is called a convolution kernel, the convolution kernel focuses on local features, namely, a standard feature is set, and the matching degree of the features is evaluated according to the numerical value of the convolution kernel of the local feature part. Before the convolution calculation of the convolution kernel is performed, the candidate region is used for replacing a sliding window in a traditional target detection algorithm to perform region selection, and a convolution neural network is used for extracting features of the candidate region. Firstly, a plurality of candidate areas are generated by using selective search on an image, the basic idea is that the image is divided into a plurality of subareas by means of over-segmentation, then two subareas with highest similarity are combined by using a greedy algorithm, the candidate areas are finally output, and then the generated candidate areas are scaled into squares with consistent sizes and sent to a convolutional neural network, so that an image recognition result is obtained.
Step S600: and controlling the unmanned aerial vehicle based on the image recognition result.
Specifically, the damage degree of abnormal behavior to the submarine cable is obtained according to the image recognition result, and when abnormal ship speed or anchoring, offshore construction, port dredging and illegal fishery operation of the ship are found, an emergency disposal process is started, and emergency personnel cooperate with law enforcement personnel to take the ship to go to a accident scene to develop emergency disposal of the accident ship; during the period of the second-loop sea cable sea area net cleaning, sea cable laying, sea cable flushing and burying and sea cable stone throwing, the second-loop construction ship and the construction operation are required to be guaranteed not to damage the first-loop sea cable, the unmanned plane can be used for carrying out real-time supervision on the construction ship by using the wireless line transmission, and emergency personnel can be immediately informed to carry out emergency treatment when the unmanned plane is found to break down in the first-loop sea cable area. The intelligent inspection method solves the technical problems that the traditional inspection method can only rely on an inspection ship to travel to a sea cable protection area for sea cable line inspection, so that the treatment time is poor, the cost is high, and the personal safety risk exists, realizes the intelligent inspection of the sea cable line based on the unmanned aerial vehicle technology, improves the efficiency of Gao Hailan operation and maintenance operation, reduces the operation cost, can avoid the risk of falling into water by offshore operators, and achieves the technical effect of improving the sea cable operation and maintenance level.
Further, as shown in fig. 2, step S200 of the present application further includes:
step S210: acquiring unmanned aerial vehicle information, and acquiring the flight speed and the endurance time of a target unmanned aerial vehicle based on the unmanned aerial vehicle information;
step S220: generating a plurality of control parameters based on the flying speed and the endurance time to form a control parameter set;
step S230: constraining a plurality of control parameters in the control parameter set based on the plurality of flight routes to obtain a qualified control parameter set conforming to constraint conditions;
step S240: and optimizing in the qualified control parameter set to obtain an optimal control parameter, and obtaining an optimal flight route according to the optimal control parameter.
Specifically, because sea cable protection district course is longer, generally select fixed wing unmanned aerial vehicle and compound wing unmanned aerial vehicle etc. according to the content of patrolling and examining, because battery technology restriction, many rotor unmanned aerial vehicle's flight time is generally 20 ~ 30min at present, and duration is shorter, and obviously many rotor unmanned aerial vehicle is not applicable to the long sea cable route of course and patrols, to oily fixed wing unmanned aerial vehicle and compound wing unmanned aerial vehicle, its duration can reach 1h and above, satisfies sea cable route long as characteristics. And acquiring a plurality of endurance times of the unmanned aerial vehicle when the load carried by the unmanned aerial vehicle is started and closed according to the maximum endurance time of the unmanned aerial vehicle, wherein if all the loads are closed and only carry out flight tasks, the endurance time is longest, the endurance of the starting photographing module is reduced, the endurance of the starting photographing return module is reduced to the lowest, and the on-off control of the plurality of loads is used as a control parameter to acquire a control parameter set.
And obtaining corresponding endurance time according to each control parameter, obtaining the maximum flight distance according to the endurance time and the flight speed, drawing a circle by taking the reference station as a circle center and the maximum flight distance as a radius, wherein the flight route covered by the circular area is a route which can be inspected, and optimizing among the obtained routes to obtain the optimal flight route.
Further, step S240 of the present application further includes:
step S241: randomly selecting a qualified control parameter from the qualified control parameter set to serve as a first qualified control parameter and serve as a current optimal control parameter;
step S242: acquiring a first control score of the first qualified control parameter;
step S243: randomly selecting a qualified control parameter from the qualified control parameter set again to serve as a second qualified control parameter;
step S244: obtaining a second control score for the second qualifying control parameter;
step S245: judging whether the second control score is larger than the first control score, if so, replacing the second qualified control parameter with an optimal control parameter;
step S246: if not, replacing the second qualified control parameter with the optimal control parameter according to the probability;
step S247: and continuing iterative optimization, and outputting the current optimal control parameters after the preset iterative times are reached to obtain the optimal control parameters.
Specifically, the unmanned aerial vehicle is subjected to navigation time calculation according to the first qualified control parameters, the simulated navigation time is obtained, the simulated navigation time and the load function are scored, the first control score is obtained, and the second control score is obtained in the same way. When the second control score is greater than the first control score, the second qualified control parameter is better than the first qualified control parameter, and the second qualified control parameter replaces the first qualified control parameter to serve as the current optimal control parameter. When the second control score is not greater than the first control score, replacing the first qualified control parameter with the second qualified control parameter according to the probability, and taking the second qualified control parameter as the current optimal control parameter, wherein the probability is obtained by the following formula:
wherein e is natural logarithm, K 2 Score for the second control, K 1 Scoring the first control, wherein C is an optimizing rate factor; c is in particular a constant decreasing with the progress of the optimization, preferably withThe constant of the index reduction of the optimizing process is larger at the initial stage of global optimizing, the second control score with smaller control score is accepted by the larger probability P as the current optimizing result, optimizing efficiency is improved, local optimizing is avoided, the qualified control parameter with smaller control score is accepted by the smaller probability as the current optimizing result at the later stage of optimizing, the accuracy of the later stage of optimizing is improved, the overall optimal adjustment parameter set is ensured to be obtained, the overall optimal control parameter is obtained through efficient and accurate optimizing, the specific size of C can be set according to the size of the adaptive parameter, so that P is close to 1 at the initial stage of optimizing, and P is close to 0 at the later stage of optimizing.
And repeating the optimizing step, sequentially calculating the following quantity from the previous quantity, wherein each iteration of the process is called an iteration, the result obtained by each iteration is used as the initial value of the next iteration to obtain the qualified control parameter corresponding to the highest control score, and outputting the current optimizing result after the preset iteration times are reached to obtain the optimal control parameter. The preset number of iterations may be set according to the number of adjustment parameter sets, illustratively 100.
Further, step S242 of the present application further includes:
step S2421: based on the first qualified control parameters, performing navigation time calculation on the unmanned aerial vehicle to obtain simulated navigation time;
step S2422: and evaluating based on the simulated navigation time to obtain the first control score.
Specifically, according to the first qualified control parameters, the unmanned aerial vehicle is subjected to navigation time calculation, simulated navigation time is obtained, corresponding load conditions are obtained, the simulated navigation time and the load functions are respectively scored, the longer the navigation time is, the higher the score is, the stronger the load functions are, the score is, the weighting is given to the navigation time score and the load function score, the final score is calculated, and the ratio of the navigation time score to the load function score is preferably 3:7, so that the inspection capability of the unmanned aerial vehicle is preferentially ensured. The final score is taken as a first control score.
Further, step S500 of the present application further includes:
step S510: partitioning the inspection image according to the edge information to obtain a first partitioning result;
step S520: obtaining a first convolution feature, wherein the first convolution feature is an abnormal behavior identification feature;
step S530: performing feature capturing on the first partition result according to the first convolution feature to obtain a first feature capturing result;
step S540: and obtaining the image recognition result according to the first characteristic capturing result.
Specifically, according to an image captured in real time, a region interval is set according to the edge of an object in the image, and the image is partitioned according to a region interval threshold. The method comprises the steps of obtaining a big data statistical result of abnormal behaviors of a submarine cable by using a first convolution feature as a convolution module for feature comparison, classifying the abnormal behaviors under the big data statistics, extracting features of different types of abnormal behaviors, obtaining a first feature according to the extracted results, performing feature matching on an image of a first partition result by using the first feature as the first convolution feature, judging the matching degree of a target position and the target feature according to the feature convolution results at different positions, and obtaining a calculation result of the feature matching degree, namely a first feature capturing result. A feature matching degree threshold is set, and when the feature matching degree threshold is met, the target position is indicated to be matched with the target feature, and the feature matching degree threshold is set to be 90% in an exemplary mode, and when the feature matching degree threshold is met, the corresponding abnormal behavior of the inspection image can be judged.
Further, step S600 of the present application includes:
step S610: acquiring abnormal behaviors according to the image recognition result;
step S620: performing grade evaluation on the abnormal behavior to obtain a grade evaluation result;
step S630: and controlling the unmanned aerial vehicle according to the grade evaluation result.
Specifically, the damage degree of the submarine cable is classified according to abnormal behaviors, and corresponding coping modes are set according to classification results, such as the second-pass submarine cable sea area net cleaning, submarine cable laying, submarine cable flushing and submarine cable stone throwing cannot cause direct damage to the submarine cable, but the construction process may be threatened, so that real-time supervision of a construction ship by using an unmanned plane is required, and the second-pass construction ship and the construction operation cannot damage the first-pass submarine cable are ensured; for large-area oil spill and oil-filled submarine cable fault damage of the accident ship, the oil spill condition needs to be tracked and shot for recording so as to rapidly judge and evaluate the oil spill condition, so that the damage is large and the damage level is high; for abnormal ship speed or anchoring, offshore construction, port dredging and illegal fishery operation, the damage to sea cables is the greatest, when the abnormal ship speed is found, an emergency disposal process is started, and emergency personnel cooperate with law enforcement personnel to take the ship to go to a trouble-causing site to carry out emergency disposal of the trouble-causing ship. The intelligent inspection of the submarine cable line based on the unmanned aerial vehicle technology is realized, the operation and maintenance operation efficiency of Gao Hailan is improved, the operation cost is reduced, the risk of the offshore operation personnel falling into water and the like can be avoided, and the technical effect of improving the submarine cable operation and maintenance level is achieved.
Example two
Based on the same inventive concept as the submarine cable line intelligent inspection method based on the unmanned aerial vehicle technology in the foregoing embodiment, as shown in fig. 3, the present application provides an submarine cable line intelligent inspection system based on the unmanned aerial vehicle technology, where the system includes:
the system comprises a flight route acquisition module 1, a navigation module 1 and a navigation module, wherein the flight route acquisition module 1 is used for acquiring the current position of a ship and the position of a submarine cable protection area to acquire a plurality of flight routes;
the optimal flight route acquisition module 2 is used for optimizing the plurality of flight routes based on unmanned aerial vehicle information to obtain an optimal flight route;
the autonomous patrol module 3 is used for performing autonomous patrol based on the optimal flight route;
the inspection image acquisition module 4 is used for acquiring an inspection image through the image acquisition device in an autonomous inspection process;
the characteristic recognition module 5 is used for carrying out characteristic recognition on the inspection image to acquire an image recognition result;
the unmanned aerial vehicle control module 6, unmanned aerial vehicle control module 6 is used for carrying out unmanned aerial vehicle's control based on the image recognition result.
Further, the system further comprises:
the unmanned aerial vehicle information acquisition module is used for acquiring unmanned aerial vehicle information and acquiring the flight speed and the endurance time of the target unmanned aerial vehicle based on the unmanned aerial vehicle information;
the control parameter set acquisition module is used for generating a plurality of control parameters based on the flying speed and the endurance time to form a control parameter set;
the control parameter set constraint module is used for constraining a plurality of control parameters in the control parameter set based on the plurality of flight routes to obtain a qualified control parameter set conforming to constraint conditions;
the optimal control parameter acquisition module is used for optimizing in the qualified control parameter set to obtain optimal control parameters, and obtaining an optimal flight route according to the optimal control parameters.
Further, the system further comprises:
the first qualified control parameter acquisition module is used for randomly selecting a qualified control parameter from the qualified control parameter set to serve as a first qualified control parameter and serve as a current optimal control parameter;
the first control score acquisition module is used for acquiring a first control score of the first qualified control parameter;
the second qualified control parameter acquisition module is used for randomly selecting a qualified control parameter again in the qualified control parameter set to serve as a second qualified control parameter;
a second control score acquisition module, configured to acquire a second control score of the second qualified control parameter;
the control score comparison module is used for judging whether the second control score is larger than the first control score or not, and if so, replacing the second qualified control parameter with an optimal control parameter;
the control parameter replacement module is used for replacing the second qualified control parameter with the optimal control parameter according to the probability if not;
and the iteration optimizing module is used for continuing iteration optimizing, and outputting the current optimal control parameters after the preset iteration times are reached to obtain the optimal control parameters.
Further, the system further comprises:
the navigation time calculation module is used for calculating the navigation time of the unmanned aerial vehicle based on the first qualified control parameter to obtain simulated navigation time;
and the navigation time evaluation module is used for evaluating based on the simulated navigation time and obtaining the first control score.
Further, the system further comprises:
the inspection image partitioning module is used for partitioning the inspection image according to the edge information to obtain a first partitioning result;
the first convolution feature acquisition module is used for acquiring a first convolution feature, wherein the first convolution feature is an abnormal behavior identification feature;
the feature capturing module is used for capturing the features of the first partition result according to the first convolution feature to obtain a first feature capturing result;
and the identification result acquisition module is used for acquiring the image identification result according to the first characteristic capturing result.
Further, the system further comprises:
the abnormal behavior acquisition module is used for acquiring abnormal behaviors according to the image recognition result;
the grade evaluation module is used for carrying out grade evaluation on the abnormal behaviors to obtain a grade evaluation result;
and the unmanned aerial vehicle intelligent control module is used for controlling the unmanned aerial vehicle according to the grade evaluation result.
Through the foregoing detailed description of the intelligent inspection method for the submarine cable line based on the unmanned aerial vehicle technology, those skilled in the art can clearly know the intelligent inspection method and system for the submarine cable line based on the unmanned aerial vehicle technology in the embodiment, and for the device disclosed in the embodiment, the description is relatively simple because the device corresponds to the method disclosed in the embodiment, and relevant places refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (7)
1. An intelligent inspection method for a submarine cable line based on unmanned aerial vehicle technology, which is applied to an intelligent inspection system, wherein the system is in communication connection with an image acquisition device and comprises the following steps:
acquiring the current position of a ship and the position of a submarine cable protection area, and acquiring a plurality of flight routes;
optimizing the plurality of flight routes based on unmanned aerial vehicle information to obtain an optimal flight route;
performing autonomous inspection based on the optimal flight route;
in the autonomous inspection process, an inspection image is acquired through the image acquisition device;
performing feature recognition on the inspection image to obtain an image recognition result;
and controlling the unmanned aerial vehicle based on the image recognition result.
2. The method of claim 2, wherein the optimizing the plurality of flight routes based on the drone information to obtain an optimal flight route comprises;
acquiring unmanned aerial vehicle information, and acquiring the flight speed and the endurance time of a target unmanned aerial vehicle based on the unmanned aerial vehicle information;
generating a plurality of control parameters based on the flying speed and the endurance time to form a control parameter set;
constraining a plurality of control parameters in the control parameter set based on the plurality of flight routes to obtain a qualified control parameter set conforming to constraint conditions;
and optimizing in the qualified control parameter set to obtain an optimal control parameter, and obtaining an optimal flight route according to the optimal control parameter.
3. The method of claim 2, wherein optimizing within the set of acceptable control parameters to obtain optimal control parameters comprises:
randomly selecting a qualified control parameter from the qualified control parameter set to serve as a first qualified control parameter and serve as a current optimal control parameter;
acquiring a first control score of the first qualified control parameter;
randomly selecting a qualified control parameter from the qualified control parameter set again to serve as a second qualified control parameter;
obtaining a second control score for the second qualifying control parameter;
judging whether the second control score is larger than the first control score, if so, replacing the second qualified control parameter with an optimal control parameter;
if not, replacing the second qualified control parameter with the optimal control parameter according to the probability;
and continuing iterative optimization, and outputting the current optimal control parameters after the preset iterative times are reached to obtain the optimal control parameters.
4. The method of claim 3, wherein the obtaining a first control score for the first qualifying control parameter comprises:
based on the first qualified control parameters, performing navigation time calculation on the unmanned aerial vehicle to obtain simulated navigation time;
and evaluating based on the simulated navigation time to obtain the first control score.
5. The method of claim 1, wherein performing feature recognition on the inspection image to obtain an image recognition result comprises:
partitioning the inspection image according to the edge information to obtain a first partitioning result;
obtaining a first convolution feature, wherein the first convolution feature is an abnormal behavior identification feature;
performing feature capturing on the first partition result according to the first convolution feature to obtain a first feature capturing result;
and obtaining the image recognition result according to the first characteristic capturing result.
6. The method of claim 1, wherein the controlling the drone based on the image recognition result comprises:
acquiring abnormal behaviors according to the image recognition result;
performing grade evaluation on the abnormal behavior to obtain a grade evaluation result;
and controlling the unmanned aerial vehicle according to the grade evaluation result.
7. Sea cable way intelligence system of patrolling and examining based on unmanned aerial vehicle technique, system and image acquisition device communication connection include:
the system comprises a flying route acquisition module, a navigation module and a navigation module, wherein the flying route acquisition module is used for acquiring the current position of a ship and the position of a submarine cable protection area to acquire a plurality of flying routes;
the optimal flight route acquisition module is used for optimizing the plurality of flight routes based on unmanned aerial vehicle information to obtain an optimal flight route;
the autonomous patrol module is used for conducting autonomous patrol based on the optimal flight route;
the inspection image acquisition module is used for acquiring an inspection image through the image acquisition device in an autonomous inspection process;
the characteristic recognition module is used for carrying out characteristic recognition on the inspection image and obtaining an image recognition result;
and the unmanned aerial vehicle control module is used for controlling the unmanned aerial vehicle based on the image recognition result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310108897.9A CN116027810A (en) | 2023-02-14 | 2023-02-14 | Intelligent sea cable way inspection method and system based on unmanned aerial vehicle technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310108897.9A CN116027810A (en) | 2023-02-14 | 2023-02-14 | Intelligent sea cable way inspection method and system based on unmanned aerial vehicle technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116027810A true CN116027810A (en) | 2023-04-28 |
Family
ID=86075935
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310108897.9A Pending CN116027810A (en) | 2023-02-14 | 2023-02-14 | Intelligent sea cable way inspection method and system based on unmanned aerial vehicle technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116027810A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116455463A (en) * | 2023-05-05 | 2023-07-18 | 众芯汉创（北京）科技有限公司 | Communication optical cable differential operation and maintenance system based on unmanned aerial vehicle |
| CN118732709A (en) * | 2024-09-04 | 2024-10-01 | 智洋创新科技股份有限公司 | Unmanned aerial vehicle group river channel intelligent tour inspection method, system and computer readable storage medium based on preset route and autonomous control |
-
2023
- 2023-02-14 CN CN202310108897.9A patent/CN116027810A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116455463A (en) * | 2023-05-05 | 2023-07-18 | 众芯汉创（北京）科技有限公司 | Communication optical cable differential operation and maintenance system based on unmanned aerial vehicle |
| CN116455463B (en) * | 2023-05-05 | 2024-06-04 | 众芯汉创（北京）科技有限公司 | Communication optical cable differential operation and maintenance system based on unmanned aerial vehicle |
| CN118732709A (en) * | 2024-09-04 | 2024-10-01 | 智洋创新科技股份有限公司 | Unmanned aerial vehicle group river channel intelligent tour inspection method, system and computer readable storage medium based on preset route and autonomous control |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110282143B (en) | Inspection method for offshore wind farm unmanned aerial vehicle | |
| US11814173B2 (en) | Systems and methods for unmanned aerial vehicles | |
| CN116027810A (en) | Intelligent sea cable way inspection method and system based on unmanned aerial vehicle technology | |
| CN110673628B (en) | Inspection method for oil-gas pipeline of composite wing unmanned aerial vehicle | |
| CN112669572B (en) | Unmanned ship system for intelligent inspection of river basin bank | |
| CN103778500A (en) | Water area management system | |
| CN112684806A (en) | Electric power inspection unmanned aerial vehicle system based on dual obstacle avoidance and intelligent identification | |
| US20220375351A1 (en) | Flight control systems, ground-based control centres, remotely piloted aircraft, and method | |
| CN211628088U (en) | Automatic unmanned aerial vehicle system of patrolling and examining in storehouse district | |
| KR20210007767A (en) | Autonomous navigation ship system for removing sea waste based on deep learning-vision recognition | |
| CN109835441A (en) | The automatic Pilot method and its system of water quality monitoring intelligence canoe | |
| CN116740833A (en) | Line inspection and card punching method based on unmanned aerial vehicle | |
| Santos et al. | Cooperative Unmanned Aerial and Surface Vehicles for Extended Coverage in Maritime Environments | |
| CN115326075A (en) | Path planning method for realizing wind field global automatic inspection based on unmanned aerial vehicle | |
| CN114021906A (en) | Unattended wind power generation operation and maintenance management method and system | |
| JP2023072588A (en) | Unmanned maintenance system and unmanned maintenance method | |
| CN113239747A (en) | Intelligent blowdown system of removing obstacles on water based on computer vision | |
| CN116363537B (en) | Method and system for identifying hidden danger of hanging objects outside transformer substation | |
| CN115421503A (en) | Unmanned aerial vehicle inspection system for bridge | |
| CN111323418A (en) | Sea surface oil stain monitoring system based on unmanned ship | |
| CN114655361B (en) | Intelligent buoy and offshore cruise unmanned aerial vehicle cluster control management system and method | |
| Messmer et al. | Evaluating UAV Path Planning Algorithms for Realistic Maritime Search and Rescue Missions | |
| JP2023072596A (en) | Unmanned inspection system and unmanned inspection method | |
| CN116659935B (en) | Intertidal zone surface sediment sampling method based on unmanned aerial vehicle platform | |
| Sun et al. | Research on the accurate fixed point algorithm for the landing of the UAV on the Arctic buoy |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |