CN111884333B - Unmanned inspection unmanned aerial vehicle cooperative work system and method thereof - Google Patents
Unmanned inspection unmanned aerial vehicle cooperative work system and method thereof Download PDFInfo
- Publication number
- CN111884333B CN111884333B CN202010618147.2A CN202010618147A CN111884333B CN 111884333 B CN111884333 B CN 111884333B CN 202010618147 A CN202010618147 A CN 202010618147A CN 111884333 B CN111884333 B CN 111884333B
- Authority
- CN
- China
- Prior art keywords
- aerial vehicle
- unmanned aerial
- inspection
- task
- server
- 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.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64C—AEROPLANES; HELICOPTERS
- B64C39/00—Aircraft not otherwise provided for
- B64C39/02—Aircraft not otherwise provided for characterised by special use
- B64C39/024—Aircraft not otherwise provided for characterised by special use of the remote controlled vehicle type, i.e. RPV
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02G—INSTALLATION OF ELECTRIC CABLES OR LINES, OR OF COMBINED OPTICAL AND ELECTRIC CABLES OR LINES
- H02G1/00—Methods or apparatus specially adapted for installing, maintaining, repairing or dismantling electric cables or lines
- H02G1/02—Methods or apparatus specially adapted for installing, maintaining, repairing or dismantling electric cables or lines for overhead lines or cables
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00006—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment
- H02J13/00022—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment using wireless data transmission
- H02J13/00026—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment using wireless data transmission involving a local wireless network, e.g. Wi-Fi, ZigBee or Bluetooth
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Computer Networks & Wireless Communication (AREA)
- Human Computer Interaction (AREA)
- Aviation & Aerospace Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a cooperative work system of an unmanned inspection unmanned aerial vehicle, which comprises an inspection unmanned aerial vehicle and a server side; the inspection unmanned aerial vehicle is used for acquiring inspection task data corresponding to the task control instruction and the emergency operation instruction according to the received task control instruction and the emergency operation instruction; and the server is used for carrying out deep learning identification analysis based on the received inspection task data, determining the operation grade corresponding to the identification analysis result according to the identification analysis result and the preset corresponding relationship between the task and the operation grade, and cooperatively finishing the intelligent inspection work. Also discloses a cooperative working method of the unmanned patrol unmanned aerial vehicle. The invention can realize the automation and the intellectualization of the working process of the unmanned aerial vehicle.
Description
Technical Field
The invention relates to the technical field of power grid inspection, in particular to an unmanned aerial vehicle cooperative work system and a method thereof for unattended inspection.
Background
In recent years, in order to improve the efficiency of patrolling and examining, power companies begin to adopt unmanned aerial vehicles to patrol and examine the power grid resource equipment, but to these patrol and examine unmanned aerial vehicles mostly need manual control, can't realize that unmanned aerial vehicle independently receives remote instruction, independently charges and independently accomplishes and patrol and examine the task.
The invention patent with publication number CN110298932A discloses an intelligent unmanned aerial vehicle inspection integrated control platform which comprises a sensing layer, a network layer, a platform layer and an application layer and can effectively perform closed-loop control on an inspection unmanned aerial vehicle. The application layer comprises an inspection image library, a talent knowledge library, a power grid resource library, an intelligent equipment library and an inspection functional module, and the inspection image is mainly used for realizing efficient inspection management, so that unmanned control and intelligent inspection of the unmanned aerial vehicle are not introduced. The invention patent with publication number CN110034816A discloses an intelligent management and control system for unmanned aerial vehicle inspection, which comprises a flight data recording device, an unmanned aerial vehicle data cloud and an intelligent management and control platform, and can carry out all-round management on an electric power inspection unmanned aerial vehicle. The intelligent management and control platform is used for acquiring flight data stored in the data cloud of the unmanned aerial vehicle, analyzing and calculating according to the flight data to form resources capable of being directly accessed, and the intelligent management and control platform is single in function and only used as a management and control platform of the unmanned aerial vehicle.
The future unmanned aerial vehicle technology will develop towards the unmanned and automatic direction of the whole work flow, and based on the prior art, a novel unmanned inspection unmanned aerial vehicle cooperative work system and a method thereof are urgently needed to solve the problems.
Disclosure of Invention
The invention aims to solve the technical problem of providing an unmanned inspection unmanned aerial vehicle cooperative work system and a method thereof, which can realize unmanned, automatic and intelligent work flow of the unmanned inspection unmanned aerial vehicle.
In order to solve the technical problems, the invention adopts a technical scheme that: the unmanned inspection unmanned aerial vehicle cooperative work system comprises an inspection unmanned aerial vehicle and a server side;
the inspection unmanned aerial vehicle is used for acquiring inspection task data corresponding to the task control instruction and the emergency operation instruction according to the received task control instruction and the emergency operation instruction;
the server is used for carrying out deep learning identification analysis based on the received routing inspection task data, determining the operation level corresponding to the identification analysis result according to the identification analysis result and the preset corresponding relation between the task and the operation level, and cooperatively finishing the intelligent routing inspection work.
In a preferred embodiment of the present invention, the server includes a cloud platform, a high-performance computing platform, and a terminal;
the terminal is used for sending a task control instruction and a first emergency operation instruction to the inspection unmanned aerial vehicle, receiving an optimized task scheme of a high-performance computing platform and a cloud platform, a second emergency operation instruction and a third emergency operation instruction, remotely controlling the intelligent inspection work of the inspection unmanned aerial vehicle, and simultaneously monitoring the real-time dynamic work of the inspection unmanned aerial vehicle;
the cloud platform is used for storing task control instructions between the terminal and the inspection unmanned aerial vehicle, and performing comparative analysis according to the actual flight to generate an optimized task scheme for the terminal to confirm; transmitting a third emergency operation instruction to the inspection unmanned aerial vehicle for obstacle avoidance; performing deep learning identification and large-scale flight data analysis on the image acquired by the inspection unmanned aerial vehicle, and storing data information between the high-performance computing platform and the inspection unmanned aerial vehicle;
the high-performance computing platform is used for inspecting an air park of the unmanned aerial vehicle, storing a task control command between the terminal and the inspection unmanned aerial vehicle, and performing comparative analysis according to the actual flight to generate an optimized task scheme for the terminal to confirm; the second emergency operation instruction is transmitted to the inspection unmanned aerial vehicle for obstacle avoidance; and the image identification and fault detection acquired by the inspection unmanned aerial vehicle and the analysis of flight perception data.
Further, the first emergency operation instruction is an intervention takeover instruction which is artificially used for correcting the deviation of the inspection unmanned aerial vehicle in the task execution process; the second emergency operation instruction is a safety obstacle avoidance instruction for autonomous control of the inspection unmanned aerial vehicle-high-performance computing platform-cloud platform system; the third emergency operation instruction is a secondary review instruction for identifying a suspected target or a fault.
In order to solve the technical problem, the invention adopts another technical scheme that: the cooperative work method of the unmanned inspection unmanned aerial vehicle comprises the following steps:
the inspection unmanned aerial vehicle receives a task control instruction and an emergency operation instruction sent by a server side, and acquires inspection task data corresponding to the task control instruction and the emergency operation instruction according to the instructions;
the service end carries out deep learning identification analysis on the received inspection task data, determines the operation level corresponding to the identification analysis result according to the identification analysis result and the preset corresponding relation between the task and the operation level, and completes intelligent inspection work cooperatively.
In a preferred embodiment of the present invention, the acquiring inspection task data corresponding to the task control instruction and the emergency operation instruction according to the task control instruction and the emergency operation instruction sent by the inspection unmanned aerial vehicle receiving server side includes:
the inspection unmanned aerial vehicle is used for taking off and inspecting after receiving the task control instruction sent by the server side; in the inspection process, the inspection unmanned aerial vehicle acquires inspection information;
the service end carries out deep learning identification analysis on the received routing inspection task data, determines an operation level corresponding to an identification analysis result according to the identification analysis result and a preset corresponding relation between the task and the operation level, and comprises the following steps:
when the server determines that the priority level of the preset task is set, operating the corresponding level of identification tasks on the inspection unmanned aerial vehicle and the server respectively according to the inspection information;
patrol and examine unmanned aerial vehicle and be in the server side determines not to be in when setting up the priority of presetting the task in the server side, then patrol and examine the degree of difficulty that unmanned aerial vehicle judged different tasks, according to the judged result, according to the priority of the different tasks of preset, the discernment task of corresponding rank is operated respectively on patrolling and examining unmanned aerial vehicle, server side.
Further, the priority level includes a simple level of identification tasks; when the server determines that the priority level of the preset task is set, the server respectively operates the corresponding level identification tasks on the inspection unmanned aerial vehicle and the server according to the inspection information, and the method comprises the following steps:
when the simple-level identification task is determined, the inspection unmanned aerial vehicle executes the task, and the inspection unmanned aerial vehicle returns to the home after the task is completed and sends generated data information to the server.
Further, the preferred level still includes the identification task of medium level, when the server determines that the priority of presetting the task has been set up, according to patrol and examine the information respectively patrolling and examining unmanned aerial vehicle, the identification task of service run corresponding rank on the end, include:
and when the recognition task of the medium level is determined, the server executes the recognition task of the medium level and transmits an execution result to the inspection unmanned aerial vehicle.
Furthermore, the patrol inspection information comprises images or/and pictures.
In a preferred embodiment of the present invention, the method further comprises: and the cooperation of information display is carried out between the inspection unmanned aerial vehicle and the server side.
Further, patrol and examine and carry out the cooperation that shows information between unmanned aerial vehicle and the server side, include:
according to information display set on the server, whether the server displays the flight data of the inspection unmanned aerial vehicle in real time or not is determined;
when the fact that the server side displays the flight data of the inspection unmanned aerial vehicle in real time is determined, and the server side is directly connected with a communication channel of the inspection unmanned aerial vehicle, the flight data of the inspection unmanned aerial vehicle is called;
and when the server side is determined not to display the flight data of the inspection unmanned aerial vehicle in real time and the server side is determined to store a historical data list, displaying the historical data list.
The beneficial effects of the invention are: according to the unmanned aerial vehicle remote control system, the cloud platform and the high-performance computing platform which are communicated with each other are arranged at the server side, the terminal and the inspection unmanned aerial vehicle which are communicated with each other are arranged on the terminal side, and the unmanned aerial vehicle, the cloud data platform, the high-performance computing platform and the multiple platforms of the terminal are in cross-platform cooperative work and management, and information intercommunication and mutual cooperation among the platforms are realized, so that the unmanned aerial vehicle remote control, automatic task deployment and intelligent inspection can be realized, and unmanned aerial vehicle full-flow operation, automation and intellectualization are really realized.
Drawings
FIG. 1 is a block diagram of the cooperative system of the unmanned inspection unmanned aerial vehicle according to the present invention;
fig. 2 is a flow chart of interaction of storage and transmission information in the cooperative working method of the unmanned patrol unmanned aerial vehicle;
fig. 3 is a flowchart of the interaction of the transmission control commands in the cooperative work method of the unmanned patrol unmanned aerial vehicle;
fig. 4 is a flow chart of the cooperation of the display information in the cooperative work method of the unmanned patrol unmanned aerial vehicle.
Detailed Description
The following detailed description of the preferred embodiments of the present invention, taken in conjunction with the accompanying drawings, will make the advantages and features of the invention easier to understand by those skilled in the art, and thus will clearly and clearly define the scope of the invention.
Referring to fig. 1, an embodiment of the present invention includes:
the utility model provides an unmanned aerial vehicle collaborative work system is patrolled and examined to unmanned on duty, mainly includes server side and terminal side, wherein can contain the terminal, patrol and examine unmanned aerial vehicle at the terminal side including the cloud platform, the high performance computing platform of intercommunications at the server side.
In the embodiment provided by the invention, the inspection unmanned aerial vehicle, the cloud platform, the high-performance computing platform and the terminal which are communicated with each other are taken as examples for detailed explanation.
The terminal is used for sending a task control instruction and a first emergency operation instruction to the inspection unmanned aerial vehicle, receiving an optimized task scheme of a high-performance computing platform and a cloud platform, a second emergency operation instruction and a third emergency operation instruction, remotely controlling the intelligent inspection work of the inspection unmanned aerial vehicle, and simultaneously monitoring the real-time dynamic work of the inspection unmanned aerial vehicle; the cloud platform is used for storing task control instructions between the terminal and the inspection unmanned aerial vehicle, and generating an optimized task scheme for the terminal to confirm according to comparative analysis of the actual flight; transmitting a third emergency operation instruction to the inspection unmanned aerial vehicle for obstacle avoidance; performing deep learning identification and large-scale flight data analysis on the image acquired by the inspection unmanned aerial vehicle, and storing data information between the high-performance computing platform and the inspection unmanned aerial vehicle; the high-performance computing platform is used for inspecting an air park of the unmanned aerial vehicle, storing a task control command between the terminal and the inspection unmanned aerial vehicle, and performing comparative analysis according to the actual flight to generate an optimized task scheme for the terminal to confirm; the second emergency operation instruction is transmitted to the inspection unmanned aerial vehicle for obstacle avoidance; and the image identification and fault detection acquired by the inspection unmanned aerial vehicle and the analysis of the flight sensing data are carried out. Preferably, the terminal can include remote controller, desktop terminal, panel computer, cell-phone terminal etc. and each terminal mainly is the edit task, looks over the task, sends the task, is the cooperation and patrols and examines the instrument that personnel carried out work and management, also is the interface and the entry of connecting unmanned aerial vehicle, cloud platform, high performance and calculating simultaneously.
The control commands are divided into two categories in nature, namely task control commands and emergency operation commands. The system comprises a terminal, a cloud platform and a high-performance platform, wherein the terminal is used for receiving a flight task command sent by the terminal and verifying and confirming the flight task command, the terminal (including a ground station terminal) can design a flight path, a photographing action and other task control commands by itself, and the commands can be directly sent to the inspection unmanned aerial vehicle for execution, can be stored in the cloud platform or the high-performance platform, and are sent to the unmanned aerial vehicle in a time-sharing manner according to a rule set by a program; the cloud platform and the high-performance platform store the task instructions, and generate an optimized task scheme according to comparison analysis of actual flight, big data analysis of historical flight tasks, priori knowledge and the like, and the terminal confirms the optimized task scheme.
The emergency operation instructions mainly comprise human intervention take-over instructions, machine-edge-cloud cooperative autonomous control safety obstacle avoidance instructions, secondary review instructions and the like, wherein the edges refer to a high-performance computing platform, the cloud refers to a cloud platform, the machine refers to a patrol unmanned aerial vehicle, the first emergency operation instructions are human intervention take-over instructions, the second emergency operation instructions are machine-edge-cloud cooperative autonomous control safety obstacle avoidance instructions, and the third emergency operation instructions are secondary review instructions. And sending emergency operation instructions of different levels to the inspection unmanned aerial vehicle according to different types of detection tasks of different service terminals.
(1) The manual intervention takeover instruction refers to that a person monitors deviation (which can be observed by naked eyes) of the unmanned aerial vehicle and does not take over emergently through a remote controller and other terminals in the process of executing a task.
(2) The machine-edge-cloud cooperative autonomous control safety obstacle avoidance instruction refers to that an unmanned aerial vehicle senses surrounding environment data (through a laser radar, a millimeter wave radar, binocular vision and the like), transmits the data to an onboard GPU (graphics processing unit) of the unmanned aerial vehicle through data transmission, 5G, 4G and the like, or a high-performance computing platform or a cloud platform, and the computing modules identify potential dangerous obstacles, generate an obstacle avoidance path emergency instruction and send the obstacle avoidance instruction to the inspection unmanned aerial vehicle for obstacle avoidance.
(3) The secondary rechecking instruction is mainly carried out according to target identification and fault detection based on deep learning, similar to the above parts, machine-edge-cloud cooperation, judgment is carried out according to the confidence level of image identification, a secondary rechecking path is generated for suspected targets or faults, and the secondary rechecking path is sent to the inspection unmanned aerial vehicle for execution.
For example, the control commands can be further divided into passive commands and active commands. The passive instruction refers to an emergency obstacle avoidance instruction or a secondary review instruction and the like which are sent when an obstacle avoidance program monitors that an obstacle needs to be avoided when a danger needs to be avoided or a secondary review action needs to be taken when a preset secondary review program monitors that the danger needs to be avoided, namely the emergency obstacle avoidance instruction or the secondary review instruction comprises a second emergency operation instruction and a third emergency operation instruction. The command can be a command sent from a cloud platform, a high-performance computing platform and an unmanned aerial vehicle GPU, and the priority level of the patrol unmanned aerial vehicle executing different server-side sending commands is the unmanned aerial vehicle GPU, the high-performance computing platform and the cloud platform in sequence. The unmanned aerial vehicle GPU mainly sends out obstacle avoidance instructions, and the high-performance computing platform and the cloud platform mainly send out secondary review instructions. Cloud platform, high performance computing platform, unmanned aerial vehicle GPU all are according to the discernment feedback of the data that perception equipment such as camera or laser radar on the unmanned aerial vehicle acquireed, if utilize binocular camera to detect the barrier, need directly send instructions such as slow down, stop or return to the navigation for unmanned aerial vehicle flight control this moment, if this instruction is that high performance computing platform or unmanned aerial vehicle GPU sent, then also need send the information of "carrying out this instruction" to the high in the clouds backup. The active instruction is an instruction which is manually set, can be set only from a terminal, and can be stored in a cloud platform or a high-performance computing platform, and the instruction can be a general task instruction, and can also comprise an instruction for manual emergency intervention, namely a task control instruction and a first emergency operation instruction. If the command is sent from the terminal, whether the state is modified or not needs to be detected before sending the command, and if the state is modified or newly generated, the command needs to be uploaded to a cloud platform for backup.
Further, the information stored between the cloud platform and the inspection unmanned aerial vehicle comprises flight data of the inspection unmanned aerial vehicle, inspection information acquired by the inspection unmanned aerial vehicle in an inspection process, interaction information between the machine-side-cloud and the inspection unmanned aerial vehicle, instruction information and automatically generated information, wherein the inspection information comprises image or/and picture information.
The inspection unmanned aerial vehicle, the cloud platform, the high-performance computing platform and the terminal transmit control instructions and data information in a wireless communication mode. Specifically, the inspection unmanned aerial vehicle and the cloud platform are transmitted through a 5G/4G or special communication tool; the cloud platform and the high-performance computing platform are transmitted through a 5G/4G or a special network; when the inspection unmanned aerial vehicle is located on the high-performance computing platform, namely, is in a nest, WIFI is adopted for transmission; when the inspection unmanned aerial vehicle is not on the high-performance computing platform, namely is away from the nest, 5G is adopted for transmission; and information transmission is carried out between the terminal and the patrol unmanned aerial vehicle, the cloud platform and the high-performance computing platform in wireless communication modes such as 5G/4G.
The method for inspecting the unmanned aerial vehicle cooperative work system based on the unattended operation comprises the following steps:
through storage and transmission information interaction, transmission control instruction interaction and the cooperation of display information between the inspection unmanned aerial vehicle, the cloud platform, the high-performance computing platform and the terminal, the inspection robot is remotely controlled, automatically charged, automatically deployed in tasks and intelligently inspected. For convenience of description, each platform in the drawings adopts corresponding english abbreviation: the patrol unmanned aerial vehicle is U1, the cloud platform is C1, the high-performance computing platform is P1, and the terminal is H1.
With reference to fig. 2, the specific steps of the interaction between the storage and the transmission information include:
s101: the inspection unmanned aerial vehicle receives the task instruction to take off and inspect;
s102: in the inspection process, the inspection unmanned aerial vehicle acquires image and picture information;
s103: judging whether priority levels of different tasks are preset through a terminal or not, wherein the identification tasks comprise target identification and fault detection identification, and the target identification comprises insulator sub-target detection, strain clamp detection, hardware/nut identification and the like; and fault detection and identification are carried out, such as insulator defect, tension clamp dislocation, bird nest and the like. The preset priority levels of different tasks comprise a simple identification task (Sm), a medium-difficulty identification task (Mm) and a complex-difficulty identification task (Dm). The difficulty of the task is determined by two factors, namely the size of the target, and the larger target is simpler to recognize like the recognition (Sm) of an insulator string; the smaller the target identification is, the more difficult, such as the identification (Mm) of tiny hardware fittings and the like; and secondly, target identification is simpler than fault detection, for example, fault detection of an insulator string is difficult (Mm), and fault detection difficulty is higher (Dm) due to the fact that a tiny hardware is lack and the like. Wherein the GPU (Ug) on the patrol unmanned aerial vehicle runs a simple recognition task (Sm); a recognition task (Mm) of moderate difficulty is run by a GPU (Pg) on a high-performance computing platform; the GPU (Cg) on the cloud platform runs a complex and difficult recognition task (Dm).
If the priority level of the preset task is set in the terminal, respectively operating recognition tasks of corresponding levels on the inspection unmanned aerial vehicle, the high-performance computing platform and the cloud platform according to the image and picture information collected in the step S102;
s104: if the priority level of the preset task is not set in the terminal, the inspection unmanned aerial vehicle automatically judges the difficulty level of different tasks, namely, the inspection unmanned aerial vehicle operates according to the default priority level;
s105: judging whether the task is a simple-level identification task, if so, directly executing the task by the inspection unmanned aerial vehicle, returning after the task is finished, and transmitting generated data information to the high-performance computing platform and the cloud platform for backup;
s106: if the recognition task is not the simple-level recognition task, judging whether the recognition task is the medium-level recognition task, if the recognition task is the medium-level recognition task, transmitting the inspection task to the high-performance computing platform through the inspection unmanned aerial vehicle for operation, and after the task is completed, transmitting generated data information to the cloud platform and the inspection unmanned aerial vehicle for backup;
s107: if the recognition task is not the medium-level recognition task, the inspection task is transmitted to the cloud platform through the inspection unmanned aerial vehicle to run, and after the task is completed, the generated data information is stored on the cloud platform and is transmitted to the inspection unmanned aerial vehicle and the high-performance computing platform to be backed up.
With reference to fig. 3, the interaction of the transmission control commands comprises the following steps:
s201: setting an unmanned aerial vehicle inspection flight task on the terminal, and sending the inspection flight task to the inspection unmanned aerial vehicle and the high-performance computing platform;
s202: the inspection unmanned aerial vehicle and the high-performance computing platform receive tasks, and the high-performance computing platform checks whether the inspection unmanned aerial vehicle meets normal takeoff conditions;
specifically, the high-performance computing platform OPENs the box lifting platform, releases the clamping, and is set to the "OPEN Ready to Fly" = true "state.
S203: if the patrol unmanned aerial vehicle does not meet the normal takeoff condition, the patrol unmanned aerial vehicle does not take off; if the patrol unmanned aerial vehicle meets the normal takeoff condition, normally taking off and executing according to the flight task;
s204: the inspection unmanned aerial vehicle acquires image and picture information in the inspection process, and distributes tasks to a cloud platform or a high-performance computing platform according to the preset priority levels of different tasks;
s205: whether the task is sent to the cloud platform or the high-performance computing platform is determined, and if not, the task is directly finished by the inspection unmanned aerial vehicle;
s206: if the identification result is sent to the cloud platform or the high-performance computing platform, the identification result of the cloud platform or the high-performance computing platform to the distribution task is sent to the inspection unmanned aerial vehicle;
s207: the inspection unmanned aerial vehicle autonomously judges whether the identification result needs to take action or not, and if so, the inspection unmanned aerial vehicle takes corresponding action; if not, continuing to carry out the normal flight inspection task.
With reference to fig. 4, the collaboration of display information includes the following steps:
s301: setting information display on the terminal, and observing whether the terminal displays the flight data of the inspection unmanned aerial vehicle in real time;
s302: if the flight data of the inspection unmanned aerial vehicle is displayed in real time, judging whether a communication channel directly connected with the inspection unmanned aerial vehicle exists at the terminal, and if so, directly connecting the inspection unmanned aerial vehicle for display; if not, judging whether a communication channel directly connected with the high-performance computing platform exists, if so, calling the flight data of the inspection unmanned aerial vehicle from the high-performance computing platform, and if not, calling the flight data of the inspection unmanned aerial vehicle from the cloud platform;
s303: if the flight data of the inspection unmanned aerial vehicle is not displayed in real time, displaying a historical data list;
s304: judging whether the historical data list is on the cloud platform or not, and if so, directly obtaining the historical data list to be displayed on the terminal; if not, judging whether the historical data list is on the high-performance computing platform;
s305: if the unmanned aerial vehicle is not on the high-performance computing platform, detecting whether the inspection unmanned aerial vehicle is in a working state, if so, displaying relevant information, and if not, displaying 'no relevant information'; if the historical data list is on the high-performance computing platform, judging whether a communication channel from the high-performance computing platform to the terminal exists or not, and if the communication channel exists, directly displaying the historical data list on the terminal through the high-performance computing platform; and if not, acquiring the historical data list from the cloud platform, transmitting the historical data list to the cloud platform through the high-performance computing platform, transmitting the historical data list to the terminal through the cloud platform, and indirectly displaying the historical data list on the terminal through the cloud platform.
According to the invention, through cross-platform cooperative work and management of the inspection unmanned aerial vehicle, the cloud data platform, the high-performance computing platform and the multiple platforms of the terminal, and information intercommunication and mutual cooperation among the platforms, the unmanned aerial vehicle can be remotely controlled, automatically deployed for tasks and intelligently inspected, and unmanned, automated and intelligent work flow of the unmanned aerial vehicle is really realized.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: although the present invention has been described in detail with reference to the above embodiments, it should be understood by those skilled in the art that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (8)
1. A cooperative work system of an unmanned inspection unmanned aerial vehicle is characterized by comprising an inspection unmanned aerial vehicle and a server side;
the inspection unmanned aerial vehicle is used for acquiring inspection task data corresponding to the task control instruction and the emergency operation instruction according to the received task control instruction and the emergency operation instruction;
the server is used for carrying out deep learning identification analysis based on the received inspection task data, determining an operation grade corresponding to an identification analysis result according to the identification analysis result and a preset corresponding relation between the task and the operation grade, and cooperatively finishing intelligent inspection work;
the server comprises a cloud platform, a high-performance computing platform and a terminal;
the terminal is used for sending a task control instruction and a first emergency operation instruction to the inspection unmanned aerial vehicle, receiving an optimized task scheme of a high-performance computing platform and a cloud platform, a second emergency operation instruction and a third emergency operation instruction, remotely controlling the intelligent inspection work of the inspection unmanned aerial vehicle, and simultaneously monitoring the real-time dynamic work of the inspection unmanned aerial vehicle;
the cloud platform is used for storing task control instructions between the terminal and the inspection unmanned aerial vehicle, and performing comparative analysis according to the actual flight to generate an optimized task scheme for the terminal to confirm; transmitting a third emergency operation instruction to the inspection unmanned aerial vehicle for obstacle avoidance; performing deep learning identification and large-scale flight data analysis on the image acquired by the inspection unmanned aerial vehicle, and storing data information between the high-performance computing platform and the inspection unmanned aerial vehicle;
the high-performance computing platform is used for inspecting an apron of the unmanned aerial vehicle, storing a task control instruction between the terminal and the inspection unmanned aerial vehicle, and performing comparative analysis according to the flight practice to generate an optimized task scheme for the terminal to confirm; the system is also used for transmitting a second emergency operation instruction to the inspection unmanned aerial vehicle for obstacle avoidance; and the image identification and fault detection acquired by the inspection unmanned aerial vehicle and the analysis of flight perception data.
2. The unmanned inspection unmanned aerial vehicle collaborative work system according to claim 1,
the first emergency operation instruction is an intervention takeover instruction which is artificially used for correcting the deviation of the inspection unmanned aerial vehicle in the task execution process;
the second emergency operation instruction is a safety obstacle avoidance instruction for autonomous control of the inspection unmanned aerial vehicle-high-performance computing platform-cloud platform system;
the third emergency operation instruction is a secondary review instruction for identifying a suspected target or a fault.
3. A cooperative working method of unmanned inspection unmanned aerial vehicle is characterized in that,
the inspection unmanned aerial vehicle receives a task control instruction and an emergency operation instruction sent by a server side, and acquires inspection task data corresponding to the task control instruction and the emergency operation instruction according to the instructions; the method comprises the following steps:
the inspection unmanned aerial vehicle is used for taking off and inspecting after receiving the task control instruction sent by the server; in the inspection process, the inspection unmanned aerial vehicle acquires inspection information;
the service end carries out deep learning identification analysis on the received inspection task data, determines the operation grade corresponding to the identification analysis result according to the identification analysis result and the preset corresponding relation between the task and the operation grade, and completes intelligent inspection work cooperatively, wherein the deep learning identification analysis comprises the following steps:
when the server determines that the priority level of the preset task is set, operating the corresponding level of identification tasks on the inspection unmanned aerial vehicle and the server respectively according to the inspection information;
patrol and examine unmanned aerial vehicle and be in the server side determines not to be in when setting up the priority of predetermineeing the task in the server side, then patrol and examine unmanned aerial vehicle and judge the degree of difficulty of different tasks by oneself, according to the judged result, according to the priority of the different tasks of presetting at the server side, the discernment task of corresponding rank is gone up to patrol and examine unmanned aerial vehicle, server side respectively.
4. The unmanned inspection tour unmanned aerial vehicle collaborative work method of claim 3, wherein the priority level includes a simple level of identification tasks; when the server determines that the priority level of the preset task is set, the server respectively operates the corresponding level identification tasks on the inspection unmanned aerial vehicle and the server according to the inspection information, and the method comprises the following steps:
when the simple-level identification task is determined, the inspection unmanned aerial vehicle executes the task, and the inspection unmanned aerial vehicle returns to the home after the task is completed and sends generated data information to the server.
5. The cooperative work method for the unmanned inspection unmanned aerial vehicle according to claim 3, wherein the priority levels further include identification tasks of medium levels, and when the server determines that the priority level of the preset task is set, the server respectively operates the identification tasks of corresponding levels on the inspection unmanned aerial vehicle and the server according to the inspection information, and the method comprises the following steps:
and when the identification task at the medium level is determined, the server executes the identification task at the medium level and transmits an execution result to the inspection unmanned aerial vehicle.
6. The cooperative work method for the unmanned inspection unmanned aerial vehicle according to any one of claims 3 to 5, wherein the inspection information comprises images and/or pictures.
7. The cooperative work method of the unmanned inspection tour unmanned aerial vehicle according to claim 3, further comprising: and the cooperation of information display is carried out between the inspection unmanned aerial vehicle and the server side.
8. The cooperative work method for the unmanned inspection unmanned aerial vehicle according to claim 7, wherein the cooperative display between the inspection unmanned aerial vehicle and the server comprises:
determining whether the server displays the flight data of the inspection unmanned aerial vehicle in real time or not according to information display arranged on the server;
when the fact that the server side displays the flight data of the inspection unmanned aerial vehicle in real time is determined, and the server side is directly connected with a communication channel of the inspection unmanned aerial vehicle, the flight data of the inspection unmanned aerial vehicle is called;
and when the server side is determined not to display the flight data of the inspection unmanned aerial vehicle in real time and the server side is determined to store a historical data list, displaying the historical data list.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010618147.2A CN111884333B (en) | 2020-06-30 | 2020-06-30 | Unmanned inspection unmanned aerial vehicle cooperative work system and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010618147.2A CN111884333B (en) | 2020-06-30 | 2020-06-30 | Unmanned inspection unmanned aerial vehicle cooperative work system and method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111884333A CN111884333A (en) | 2020-11-03 |
| CN111884333B true CN111884333B (en) | 2023-04-07 |
Family
ID=73158264
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010618147.2A Active CN111884333B (en) | 2020-06-30 | 2020-06-30 | Unmanned inspection unmanned aerial vehicle cooperative work system and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111884333B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112527013A (en) * | 2020-12-02 | 2021-03-19 | 广东电网有限责任公司 | Unmanned aerial vehicle group safety flight control system |
| CN112464859B (en) * | 2020-12-10 | 2024-05-21 | 交控科技股份有限公司 | Platform guidance system and method |
| CN114118819A (en) * | 2021-11-30 | 2022-03-01 | 蜂巢航宇科技（北京）有限公司 | Unmanned aerial vehicle inspection method and system based on cloud platform |
| CN114740901B (en) * | 2022-06-13 | 2022-08-19 | 深圳联和智慧科技有限公司 | Unmanned aerial vehicle cluster flight method and system and cloud platform |
| CN114911271B (en) * | 2022-06-23 | 2023-05-09 | 深圳市多翼创新科技有限公司 | Wide area distributed collaborative operation system and method based on cloud unmanned aerial vehicle |
| CN116050813B (en) * | 2023-03-31 | 2023-06-06 | 深圳市城市公共安全技术研究院有限公司 | Control method and equipment for photovoltaic operation and maintenance system and readable storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110991900A (en) * | 2019-12-05 | 2020-04-10 | 深圳中科创新实验室科技有限公司 | Inspection maintenance method |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8695764B2 (en) * | 2005-07-26 | 2014-04-15 | Goodrich Corporation | Aircraft shock strut having a fluid level monitor |
| WO2007093224A1 (en) * | 2006-02-16 | 2007-08-23 | Saab Ab | Decision making unit for autonomous platform |
| CN103823451B (en) * | 2014-03-07 | 2016-08-17 | 国家电网公司 | Unmanned plane power circuit polling centralized dispatching system and method based on GIS |
| CN107402580B (en) * | 2017-07-18 | 2021-01-29 | 国家电网公司 | Unmanned aerial vehicle-based power grid inspection automation method |
| CN107479571A (en) * | 2017-07-25 | 2017-12-15 | 中国电力科学研究院 | A kind of unmanned plane Power Line Inspection System and method based on four-dimensional information management space |
| CN108958286A (en) * | 2018-07-18 | 2018-12-07 | 福州大学 | Multi-rotor aerocraft Cloud Server network system and its control method |
-
2020
- 2020-06-30 CN CN202010618147.2A patent/CN111884333B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110991900A (en) * | 2019-12-05 | 2020-04-10 | 深圳中科创新实验室科技有限公司 | Inspection maintenance method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111884333A (en) | 2020-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111884333B (en) | Unmanned inspection unmanned aerial vehicle cooperative work system and method thereof | |
| CN111307823B (en) | System and method for detecting typical visual defects of power transformation equipment based on edge cloud cooperation | |
| CN110865917A (en) | AR technology-based electric power machine room inspection operation method, system and application | |
| CN109895116B (en) | Power pipe gallery track robot patrol inspection method and device | |
| CN112506214B (en) | Operation flow of unmanned aerial vehicle autonomous fan inspection system | |
| CN111244822B (en) | Fixed-wing unmanned aerial vehicle line patrol method, system and device in complex geographic environment | |
| CN115293508B (en) | Visual optical cable running state monitoring method and system | |
| WO2024093420A1 (en) | Patrol method and apparatus for cooperative operation of unmanned aerial vehicle and ground patrol robot | |
| CN115272888A (en) | Digital twin-based 5G + unmanned aerial vehicle power transmission line inspection method and system | |
| CN113093797A (en) | Unmanned aerial vehicle-based intelligent power transmission line inspection method and system | |
| CN113111714A (en) | Risk prevention and control system applied to power transmission field operation | |
| CN112123338A (en) | Transformer substation intelligent inspection robot system supporting deep learning acceleration | |
| CN109885091B (en) | Unmanned aerial vehicle autonomous flight control method and system | |
| CN110687394A (en) | Submarine cable fault automatic rapid positioning navigation device system | |
| CN114879679A (en) | Transformer substation inspection method and system | |
| CN112698662A (en) | Unmanned aerial vehicle substation equipment fine routing inspection remote control system and method | |
| CN210511074U (en) | Full-intelligent oil-gas pipeline inspection system based on unmanned aerial vehicle remote sensing and deep learning | |
| CN115457411B (en) | Unmanned inspection method and device for aviation oil pipeline and aviation oil safety operation and maintenance system | |
| CN115857536A (en) | Unmanned aerial vehicle intelligent inspection method, device, equipment and medium for workshop equipment | |
| Lin et al. | Realization of Intelligent-Inspection Functions of UAV in Transmission Grids Using Machine Learning | |
| CN114679569A (en) | Production line visual monitoring method and system based on three-dimensional modeling and storage medium | |
| CN114825616A (en) | AR first visual angle remote diagnosis method and device, storage medium and electronic device | |
| CN110989666A (en) | Unmanned aerial vehicle system for line inspection and control method thereof | |
| CN116935245B (en) | Long-distance communication power grid unmanned aerial vehicle inspection system and method | |
| CN112666980B (en) | Unmanned aerial vehicle cluster cooperation system, cooperation method and unmanned aerial vehicle cluster |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |