CN116661474A - Cruise method, edge cluster, equipment and storage medium of automatic aircraft - Google Patents
Cruise method, edge cluster, equipment and storage medium of automatic aircraft Download PDFInfo
- Publication number
- CN116661474A CN116661474A CN202310747279.9A CN202310747279A CN116661474A CN 116661474 A CN116661474 A CN 116661474A CN 202310747279 A CN202310747279 A CN 202310747279A CN 116661474 A CN116661474 A CN 116661474A
- Authority
- CN
- China
- Prior art keywords
- data
- edge
- equipment
- resource
- image data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000003860 storage Methods 0.000 title claims abstract description 26
- 238000007689 inspection Methods 0.000 claims abstract description 81
- 238000013468 resource allocation Methods 0.000 claims abstract description 40
- 238000012545 processing Methods 0.000 claims abstract description 25
- 238000004458 analytical method Methods 0.000 claims abstract description 13
- 238000001514 detection method Methods 0.000 claims description 36
- 230000007547 defect Effects 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 22
- 230000008447 perception Effects 0.000 claims description 12
- 230000002787 reinforcement Effects 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 10
- 230000002068 genetic effect Effects 0.000 claims description 7
- 239000004973 liquid crystal related substance Substances 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 5
- 238000009529 body temperature measurement Methods 0.000 claims description 4
- 238000013500 data storage Methods 0.000 claims description 4
- 230000036544 posture Effects 0.000 claims description 4
- 230000008685 targeting Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 abstract description 9
- 238000004422 calculation algorithm Methods 0.000 description 22
- 239000003795 chemical substances by application Substances 0.000 description 8
- 238000004891 communication Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 239000011159 matrix material Substances 0.000 description 8
- 238000013527 convolutional neural network Methods 0.000 description 7
- 230000009471 action Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000003044 adaptive effect Effects 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 238000013519 translation Methods 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 230000007797 corrosion Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 235000005770 birds nest Nutrition 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 230000003749 cleanliness Effects 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000010076 replication Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000003466 welding Methods 0.000 description 1
- 235000005765 wild carrot Nutrition 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/08—Control of attitude, i.e. control of roll, pitch, or yaw
- G05D1/0808—Control of attitude, i.e. control of roll, pitch, or yaw specially adapted for aircraft
- G05D1/0816—Control of attitude, i.e. control of roll, pitch, or yaw specially adapted for aircraft to ensure stability
- G05D1/0825—Control of attitude, i.e. control of roll, pitch, or yaw specially adapted for aircraft to ensure stability using mathematical models
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
- G05D1/106—Change initiated in response to external conditions, e.g. avoidance of elevated terrain or of no-fly zones
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Aviation & Aerospace Engineering (AREA)
- Mathematical Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Physics (AREA)
- Mathematical Optimization (AREA)
- Algebra (AREA)
- Navigation (AREA)
Abstract
The invention discloses a cruising method, an edge cluster, equipment and a storage medium of an automatic aircraft, wherein the method comprises the following steps: the control center receives node resource data of the automaton nest, which are collected by each edge device; the control center generates an inspection task for an automaton nest in the edge cluster; the control center generates a resource allocation scheme for balancing loads for the inspection tasks according to the node resource data; the edge equipment executes the inspection task according to the resource allocation scheme so as to drive the automatic aircraft to acquire equipment sensing data when inspecting the power equipment of the transformer substation, and execute power business processing according to the equipment sensing data. By scheduling the resources in the edge cluster, the resource scheduling and utilization of different use scenes are met, the self-adaptability of the resource scheduling is improved, and the edge computing nodes can deploy the resources such as computation and storage into an automatic aircraft or an automatic machine nest, so that the real-time processing and analysis of data are realized, and the data transmission delay and network data are reduced.
Description
Technical Field
The invention relates to the technical field of power grids, in particular to a cruising method, an edge cluster, equipment and a storage medium of an automatic aircraft.
Background
The electric power facilities are deployed outdoors, particularly in the field with more complex terrains, so that an automaton nest is deployed in a transformer substation at present, an automatic aircraft is deployed in the automaton nest, the electric power facilities are inspected one by using the automatic aircraft, and unattended inspection of the transformer substation is realized.
The technical staff manually starts the inspection task or automatically starts the inspection task after the inspection task is scheduled, and after the automatic aircraft inspects the electric power facilities, the automaton nest uploads the data acquired during inspection to the cloud for processing.
However, the area covered by the automaton nest is large, the data volume acquired by the automatic aircraft is large, all data are directly uploaded to the cloud for processing, and the problems of transmission delay, cloud downtime and the like are possibly caused due to the influence of factors such as network bandwidth limitation, cloud resource shortage and the like, so that the overall efficiency is low.
Disclosure of Invention
The invention provides a cruising method, an edge cluster, equipment and a storage medium of an automatic aircraft, which are used for solving the problem of how to improve the efficiency of the inspection of an electric facility of the automatic aircraft.
According to an aspect of the present invention, there is provided a cruise method of an automatic aircraft, applied to an edge cluster, where the edge cluster includes a control center and a plurality of edge computing nodes, the edge computing nodes are automaton nests with edge devices in a substation, and the automaton nests are configured with the automatic aircraft, and the method includes:
the control center receives node resource data of the automaton nest, which are collected by each edge device;
the control center generates a patrol task for the automaton nest in the edge cluster;
the control center generates a resource allocation scheme for balancing loads for the inspection task according to the node resource data;
and the edge equipment executes the inspection task according to the resource allocation scheme so as to drive the automatic aircraft to acquire equipment perception data when inspecting the power equipment of the transformer substation, and execute power business processing according to the equipment perception data.
According to another aspect of the invention, an edge cluster is provided, wherein the edge cluster comprises a control center and a plurality of edge computing nodes, the edge computing nodes are automaton nests with edge equipment in a transformer substation, and automatic aircrafts are configured in the automaton nests;
The control center is used for receiving node resource data of the automaton nest, which are collected by each edge device;
the control center is further used for generating a patrol task for the automaton nest in the edge cluster;
the control center is further used for generating a resource allocation scheme for balancing loads for the inspection tasks according to the node resource data;
the edge equipment is used for executing the inspection task according to the resource allocation scheme so as to drive the automatic aircraft to acquire equipment perception data when inspecting the power equipment of the transformer substation, and execute power business processing according to the equipment perception data.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of cruising an automatic aircraft according to any of the embodiments of the present invention.
According to another aspect of the invention, a computer-readable storage medium is provided, which stores a computer program for causing a processor to execute the cruise method of an automatic aircraft according to any one of the embodiments of the invention.
In the embodiment, the edge cluster comprises a control center and a plurality of edge computing nodes, the edge computing nodes are automaton nests with edge devices in a transformer substation, automatic aircrafts are configured in the automaton nests, the plurality of automaton nests are used as the edge computing nodes for clustered deployment, so that the resource storage and data utilization rate are greatly improved, the high efficiency of the edge cluster is realized, and the control center receives node resource data of the automaton nests collected by each edge device; the control center generates an inspection task for an automaton nest in the edge cluster; the control center generates a resource allocation scheme for balancing loads for the inspection tasks according to the node resource data; the edge equipment executes the inspection task according to the resource allocation scheme so as to drive the automatic aircraft to acquire equipment sensing data when inspecting the power equipment of the transformer substation, and execute power business processing according to the equipment sensing data. By scheduling the resources in the edge cluster, the resource scheduling and utilization of different use scenes are met, the self-adaptability of the resource scheduling is improved, and the edge computing nodes can deploy the resources such as computation and storage into an automatic aircraft or an automatic machine nest, so that the real-time processing and analysis of data are realized, the data transmission delay and the network data volume are reduced, and the system operation efficiency and stability are improved.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method of cruising an automatic aircraft according to a first embodiment of the present invention;
fig. 2 is a schematic structural diagram of an edge cluster according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
Fig. 1 is a flowchart of a cruising method of an automatic aircraft, where the method may be applied to an edge cluster, where the edge cluster may be implemented in hardware and/or software, and includes a control center and a plurality of edge computing nodes, where the edge computing nodes are automaton nests with edge devices mounted in a substation, the automaton nests are configured with the automatic aircraft, and the automaton nests refer to a multifunctional electric platform capable of automatically providing power for the automatic aircraft, and take-off, landing, and other operations of the automatic aircraft are automatically completed through a ground control station or the automaton nest.
In general, the edge computing node is a computing device with relatively high computing power, which may be a computer, a server or an embedded device, and in addition, a Graphics Processor (GPU) or an embedded neural Network Processor (NPU) may be provided in the edge computing node according to different intelligent services.
In a specific implementation, a new edge device (such as a GPU (graphics processing unit), an NPU (non-point processing unit) and the like) is installed in the automaton nest, so that the computing capability of the automaton nest is enhanced, the automaton nest is used as an edge computing node to be accessed into an edge cluster, the edge computing node is accessed into a control center, logic for determining the edge computing node to control an automatic aircraft is redefined, the edge cluster is formed by the edge devices on the automaton nest in a plurality of substations, and computing, storage and network resources of the plurality of edge devices are combined, so that more efficient and extensible service is provided for automatic inspection of the automatic aircraft.
Furthermore, the edge computing node refers to a service platform constructed at the network edge side close to the user, provides storage, computing, network and other resources, and sinks part of key service applications to the access network edge so as to reduce the width and delay loss caused by network transmission and multistage forwarding. The edge computing node is located between the user and the cloud, and is closer to the user (data source) than the traditional cloud. Compared with a cloud end, the edge node has the characteristics of miniaturization, distribution and closer to users, massive data do not need to be uploaded to the cloud end for processing, the processing of the data at the network edge side is realized, the request response time is reduced, the network bandwidth is reduced, and meanwhile, the safety and the privacy of the data are guaranteed.
The edge computing node can realize algorithm function and model reasoning, is communicated with the controller of the elevator, and provides artificial intelligence (ArtificialIntelligence, AI) and complex computing capacity for the controller of the elevator; the edge calculation can be communicated with the cloud to realize the functions of algorithm function and model update, transfer the function call of the controller of the elevator and the like. Generally, the edge computing node may perform scheduling decision making, fault pre-diagnosis, and other functions.
Edge computing refers to providing near-end services on the side near the object or data source, using an open platform with integrated network, computing, storage, and application core capabilities. The application program is initiated at the edge side, and faster network service response is generated, so that the basic requirements of the industry in the aspects of real-time service, application intelligence, security, privacy protection and the like are met.
As shown in fig. 1, the method includes:
and step 101, the control center receives node resource data of the automaton nest, which are collected by each edge device.
In practical application, a monitoring component is arranged in each edge device to monitor the automaton nest in real time and collect node resource data thereof, namely, data representing the state of resources (such as a processor, a memory, a bandwidth and the like) of an edge computing node (especially the automaton nest).
Illustratively, the node resource data may include node resource utilization, node network information, node load information, and the like.
And uploading the node resource data to a control center in real time when each edge device acquires the node resource data of the automaton nest.
And 102, the control center generates a patrol task for the automaton nest in the edge cluster.
In this embodiment, the control center may generate a patrol task for the automaton nest in the edge cluster according to the requirement of the power service, and customize planning information such as a patrol object, a patrol route, and the like, so as to implement patrol of the power facility.
The automatic aircraft patrols and examines the electric power facilities, which means that the automatic aircraft can be provided with high-definition cameras, thermal infrared imagers, laser radars and other sensors, and the electric power facilities are perceived by the sensors of the automatic aircraft, so that periodic or unscheduled inspection and maintenance are realized, and the safe and efficient operation of the facilities is ensured.
Further, the primary inspection object of the automatic aircraft includes at least one of:
1. transmission line
The automatic aircraft can fly along the transmission line, check the conditions of equipment such as wires, insulators, towers and the like, find problems such as metal loosening, corrosion, breakage and the like, and potential threats to the line by trees, bird nests and the like.
2. Substation transformer
The automatic aircraft can patrol and examine main equipment in the transformer substation, such as a transformer, a circuit breaker, a disconnecting switch and the like, examine abnormal conditions of pollution, abrasion, leakage and the like on the surface of the equipment, and detect the temperature rise condition of the equipment through the thermal infrared imager to find potential faults.
3. Power transmission tower
The automatic aircraft can check the structural integrity of the power transmission tower and find problems such as metal corrosion, bolt loosening, welding cracking and the like of the tower.
4. Power distribution facility
The automatic aircraft can patrol facilities such as distribution lines, switching equipment, transformers and the like in cities and rural areas, and ensures the stability of power supply.
5. New energy power generation facility
The automatic aircraft is used for inspecting new energy power generation facilities such as a wind generating set, a solar photovoltaic panel and the like, and checking the cleanliness, the integrity and the running condition of equipment.
And 103, the control center generates a resource allocation scheme for balancing loads for the inspection task according to the node resource data.
The control center can process node resource data by utilizing technologies such as machine learning, deep learning and the like, establish a scheduling model of resources, dynamically adjust resource allocation of edge computing nodes, generate a balanced load resource allocation scheme for the routing inspection task, wherein the resource allocation scheme can comprise the identification of the edge computing nodes executing the routing inspection task, the time of the edge computing nodes executing the routing inspection task, the resource allocation information of the edge computing nodes executing the routing inspection task and the like, so that the load of each edge computing node in the edge cluster is balanced, and the performance optimization of the whole edge cluster is achieved.
In one embodiment of the present invention, step 103 may include the steps of:
step 1031, classifying the inspection tasks according to the complexity of the inspection tasks.
In this embodiment, the complexity of different inspection tasks may be marked in advance, so that the inspection tasks are classified according to the complexity of the inspection tasks, the difference in complexity between the inspection tasks is small in the same class, and the difference in complexity between the inspection tasks is large in different classes.
The complexity refers to resources required by an algorithm for executing the inspection task when the algorithm is written into an executable program, and the resources comprise time resources, memory resources and the like.
The problem of the same inspection task can be solved by different algorithms, and the quality of one algorithm influences the efficiency of the algorithm and even the program, so that the complexity analysis, particularly the time complexity and the space complexity, of the algorithm can be facilitated, and the selection of a proper algorithm and the improvement of the algorithm can be facilitated.
In one design, the categories include complex scenes, simple scenes, where the complex scenes have a complexity that is greater than the complexity of the simple scenes.
Illustratively, complex scenes include defect analysis, three-dimensional reconstruction, and simple scenes include data storage.
Step 1032, loading the resource scheduling model corresponding to the category.
Step 1033, inputting the node resource data into a resource scheduling model, and generating a balanced load resource allocation scheme for the patrol task.
In this embodiment, corresponding resource scheduling models may be constructed in advance according to characteristics of different types of inspection tasks, when scheduling resources, the resource scheduling models corresponding to the types of the resource scheduling models are loaded to a memory for operation, and node resource data is input into the resource scheduling models to generate a resource allocation scheme for balancing loads for the inspection tasks.
The correlation between the resources of the edge computing nodes and the complexity of the inspection tasks is high, and different resource scheduling models are matched with the complexity of the inspection tasks of corresponding categories, so that the scheduling of the resources can be optimized.
Illustratively, the resource scheduling model includes a reinforcement learning model (ReinforcementLearning, RL), a genetic model (GA), and a bayesian model (BayesianOptimization, BO).
The reinforcement learning model is used for describing and solving the problem that an Agent (Agent) achieves the maximization of return or achieves a specific target through a learning strategy in the interaction process with the environment.
If an Agent's certain behavior strategy results in a positive reward (signal enhancement) for the environment, the Agent's later trend to generate this behavior strategy will be enhanced. The goal of the Agent is to find the optimal strategy at each discrete state to maximize the desired discount rewards and.
Reinforcement learning refers to learning as a heuristic evaluation process, in which an Agent selects an action for an environment, the state of the environment changes after receiving the action, and a reinforcement signal (rewards or punishments) is generated and fed back to the Agent, and the Agent selects the next action according to the reinforcement signal and the current state of the environment, wherein the selection principle is that the probability of receiving positive reinforcement (rewards) is increased. The action selected affects not only the immediate enhancement value, but also the state at the moment in the environment and the final enhancement value.
The genetic model is a random global search optimization method, which simulates the phenomena of replication, crossover, mutation and the like in natural selection and genetics, and starts from any initial Population (Population), a group of individuals more suitable for the environment is generated through random selection, crossover and mutation operation, so that the group evolves to a better and better area in a search space, the generation of the generation is continuously propagated and evolved, and finally, the generation of the generation is converged to a group of individuals (indivisual) most suitable for the environment, thereby obtaining a high-quality solution of the problem.
The bayesian model is a method for guiding searching to find the minimum value or the maximum value of the objective function by using bayesian theorem, namely, when each iteration is performed, the history information (priori knowledge) observed before is utilized to perform the next optimization, namely, when the previous iteration is performed, the iteration result before the next iteration is firstly reviewed, the vicinity of the result which is too bad is not found, the best solution is found to the vicinity of the result which is as good as possible, so that the searching efficiency is greatly improved, namely, each trial and error is performed in the learning, and the optimal strategy is found according to the experiences in the next time.
If the classification of the inspection task is a complex scene such as defect analysis, three-dimensional reconstruction and the like, the node resource data can be input into the reinforcement learning model, and a resource allocation scheme with balanced load can be generated for the inspection task, so that when the scheduling decision is carried out on the complex scene, a more complex and fine scheduling strategy can be learned and optimized, and through continuous try, how to select proper behaviors according to the environment and the state thereof is learned, so that the maximization of accumulated return is expected.
If the type of the inspection task is a simple scene such as data storage, the node resource data can be input into a genetic model or a Bayesian model, a resource allocation scheme for balancing loads can be generated for the inspection task, and the operation space can be continuously optimized and searched, so that the optimization can be performed with the aim of reducing the use amount or cost of the resources of the edge computing node.
Of course, the complexity of the inspection task and the adaptive resource scheduling model thereof are merely examples, and when implementing the present embodiment, the complexity of other inspection tasks and the adaptive resource scheduling model thereof may be set according to actual situations, which is not limited in the present embodiment. In addition, besides the complexity of the inspection task and the adaptive resource scheduling model thereof, the skilled person can also adopt other complexity of the inspection task and the adaptive resource scheduling model thereof according to actual needs, which is not limited in this embodiment.
The control center, upon determining the resource allocation scheme, may inform the edge computing nodes (particularly edge devices in the automaton nest) performing the inspection tasks of the resource allocation scheme.
And 104, the edge equipment executes a patrol task according to the resource allocation scheme so as to drive the automatic aircraft to acquire equipment perception data when the automatic aircraft patrol the power equipment of the transformer substation, and execute power business processing according to the equipment perception data.
If the edge equipment receives a resource allocation scheme transmitted by the control center, a corresponding inspection task can be executed according to the specification of the resource allocation scheme, when the inspection task is executed, the automaton nest is informed to drive a corresponding automatic aircraft to acquire equipment sensing data of the power equipment of the transformer substation by the corresponding sensor in the inspection process, when the automatic aircraft returns to the automaton nest, the automaton nest receives the sensing data acquired by the automatic aircraft, and the edge equipment assists the automaton nest to execute power service processing according to the equipment sensing data.
In one embodiment of the present invention, where the device perceived data includes first image data, step 104 may include the steps of:
and 104-11, if the inspection task is defect analysis, driving the automatic aircraft to acquire first image data when inspecting the power equipment of the transformer substation.
If the inspection task is defect analysis, the automatic aircraft can be driven to call the camera to continuously collect first image data for the power equipment of the transformer substation in the process of inspecting the power equipment of the transformer substation.
Step 104-12, identifying a type of power device in the first image data.
In this embodiment, the image classification algorithm may be invoked to quickly distinguish the type of the electrical device, such as a transformer, a wire, a transformer, a lightning arrester, a disconnecting switch, and the like, and output the type of the electrical device to the next-layer algorithm.
Step 104-13, targeting a type of electrical device, performs object detection in the first image data.
In this embodiment, a target detection network based on deep learning may be constructed and trained for each type of power equipment in advance, when the type of power equipment is specified, a corresponding target detection network may be loaded, for each frame of first image data, the specified type of power equipment is set as a target for detection, the first image data is input into the target detection network to perform target detection, so as to obtain detection results, and in each detection result, the detection result may include an identifier of whether the type of power equipment exists in the first image data or an area where the type of power equipment exists in the first image data.
Further, the structure of the target detection network is not limited to the artificially designed neural network, but a neural network that can be optimized by a model quantization method, a neural network that is searched by a NAS (neural architecture search) method, or the like, which is not limited in this embodiment.
In a specific implementation, the object detection network may be divided into one-stage and two-stage.
two-stage belongs to the segment to segment, and means that the target detection operation is completed in two steps, wherein the first step is to use various convolutional neural networks as backbones of the target detection network, extract features from the original image data, perform rough classification (distinguishing foreground and background) and rough positioning (anchor) according to the features, and acquire candidate areas, and the second step is to classify the candidate areas (i.e. service objects) in a classification network of the target detection network.
Illustratively, the target detection operations of two-stage may include R-CNN (Region-CNN, region-based convolutional neural network), fastR-CNN (fast Region convolutional neural network), fasterR-CNN (faster Region convolutional neural network), R-FCN (Region-based convolutional neural network), and so forth.
The one-stage belongs to end-to-end, which means that the target detection operation is completed in one step, candidate areas are not searched independently, original image data is input into an integral network, and the generated detection result simultaneously contains the position and the category information of the service object.
Illustratively, the one-stage object detection operation may include SSD (SingleShotMultibox Detector, single step multi-frame detection), yolo (YouOyLookOne, unified real-time object detection), and so forth.
Generally, the two-stage has higher detection accuracy but slightly lower detection speed, and the one-stage has higher detection speed but slightly lower detection accuracy, so that a person skilled in the art can select one-stage or two-stage according to factors such as the resource of the edge computing node, the real-time requirement of defect detection, and the like, and the embodiment is not limited to this.
Step 104-14, if the type of power device is detected in the first image data, segmenting data characterizing the power device in the first image data as regional image data.
In this embodiment, if a specific type of power device is detected in the first image data, the data characterizing the type of power device may be completely segmented from the region selected by the target detection as completely as possible, and recorded as region image data, so as to reduce interference caused by the background.
And 104-15, performing infrared temperature measurement detection on the regional image data to detect defects of the power equipment.
For defect analysis, the characteristics of the power equipment on infrared temperature measurement can be effectively identified based on deep learning, key parameters are automatically and dynamically learned, a defect detection model based on deep learning is trained through a large number of samples, and the identification rate and the accuracy of defect detection are continuously improved.
At present, when the automaton nest is high-efficiency patrolled and examined, mass equipment patrolling and examining data can be generated, and defect marking is often carried out manually, so that the problems of low working efficiency, high requirements on professional skills, high experience dependence and the like are caused.
The inspection system of the automatic aircraft can be combined to rapidly display defects, feed back the current defect information to a user, rapidly and timely feed back the defect information to operation and maintenance after positioning the defects, reduce property loss, save human body cost, reduce the dependence degree of professional skills and industry experience, reduce operation threshold, lighten operation intensity, improve the detection rate of defect detection, reduce the defect false detection rate and the like.
In another embodiment of the present invention, where the device perceived data includes second image data, step 104 may include the steps of:
104-21, if the inspection task is three-dimensional reconstruction, driving the automatic aircraft to acquire second image data when inspecting the power equipment of the transformer substation, and recognizing the gesture of the automatic aircraft when acquiring the second image data.
If the inspection task is three-dimensional reconstruction, the automatic aircraft can be driven to call the camera to continuously acquire second image data for the power equipment of the transformer substation in the process of inspecting the power equipment of the transformer substation.
And, invoke a sensor such as an Inertial Measurement Unit (IMU) to continuously detect the attitude of the automatic aircraft, correlate the second image data with the attitude, or the high-quality second image data characterizes the tilting condition of the automatic aircraft, so that the attitude of the automatic aircraft can be directly calculated from the second image data.
And 104-22, extracting characteristic points on the scale space from the second image data in the multiple postures, and matching the characteristic points.
The second image data collected by the automatic aircraft under different poses expresses multiple views, so that feature points on the Scale space can be extracted from the second image data under different views through algorithms such as Scale-invariant feature transform (SIFT) and the like, and the feature points are matched.
Wherein, the SIFT algorithm maps (transforms) an image data into a local feature vector set; the feature vector has invariance to translation, scaling and rotation, and has certain invariance to illumination change, affine and projection transformation, and the essence of the SIFT algorithm can be classified into the problem of searching feature points (key points) on different scale spaces.
In general, the SIFT algorithm mainly includes three steps for object recognition:
1. extracting key points;
2. adding detailed information (local features) to the keypoints, so-called descriptors;
3. and (3) finding out a plurality of pairs of feature points matched with each other through pairwise comparison of the feature points (the key points attached with the feature vectors) of the two sides, so that the corresponding relation between scenes is established.
And 104-23, performing three-dimensional sparse reconstruction by using the successfully matched characteristic points to obtain first point cloud data.
In this embodiment, three-dimensional sparse reconstruction can be performed by using feature points successfully matched through algorithms such as SFM (structure motion) and the like, so as to obtain sparse first point cloud data.
The SFM algorithm is an algorithm for three-dimensional reconstruction based on various collected unordered pictures, and comprises the following steps:
1. Using a matched characteristic point basic matrix;
2. calculating an eigenvalue matrix by the basis matrix;
3. calculating the motion between two visual angles through the eigenvalue matrix to obtain a rotation matrix R and a translation matrix T;
4. and reconstructing all the characteristic points into first point cloud data according to the rotation matrix R and the translation matrix T by using an optical triangulation method.
And 104-24, performing three-dimensional dense reconstruction by using the first point cloud data to obtain second point cloud data.
In this embodiment, stereo matching may be performed by using the first point cloud data through an MVS (Multi-view stereo) algorithm or the like, so as to implement three-dimensional dense reconstruction, and obtain dense second point cloud data.
Step 104-25, inputting the second point cloud data into the octree to divide the third point cloud data.
In this embodiment, the octree is used to divide the massive second point cloud data to obtain third point cloud data, and the third point cloud data is stored, so that the efficiency of point cloud data management is improved.
Step 104-26, performing poisson reconstruction by using the third point cloud data to obtain a plurality of grids.
In this embodiment, the third point cloud data is used to construct and optimize the grid of the three-dimensional map model by using the poisson reconstruction algorithm, so as to improve the quality and effect of the three-dimensional map model.
Step 104-27, mapping textures of the second image data in the plurality of poses into a plurality of grids to reconstruct into a three-dimensional map model.
In this embodiment, the second image data and the third point cloud data under multiple view angles (postures) may be jointly optimized through a global optimal mapping algorithm to obtain a global optimal texture mapping model, so that the texture of the second image data is mapped into multiple grids, and the reconstructed three-dimensional map model is more real.
At present, the transformer substation is frequently newly increased in interval, and because updated information is not timely synchronized, when the automaton nest executes the inspection task, model updating of the transformer substation is easy to occur, and a route conflicts with the newly increased interval, so that the transformer substation is fried.
By reconstructing a real three-dimensional map model, the automatic aircraft can avoid obstacles such as intervals in time, and avoid the situation of frying, so that the operation safety of the automatic aircraft is improved.
In the embodiment, the edge cluster comprises a control center and a plurality of edge computing nodes, the edge computing nodes are automaton nests with edge devices in a transformer substation, automatic aircrafts are configured in the automaton nests, the plurality of automaton nests are used as the edge computing nodes for clustered deployment, so that the resource storage and data utilization rate are greatly improved, the high efficiency of the edge cluster is realized, and the control center receives node resource data of the automaton nests collected by each edge device; the control center generates an inspection task for an automaton nest in the edge cluster; the control center generates a resource allocation scheme for balancing loads for the inspection tasks according to the node resource data; the edge equipment executes the inspection task according to the resource allocation scheme so as to drive the automatic aircraft to acquire equipment sensing data when inspecting the power equipment of the transformer substation, and execute power business processing according to the equipment sensing data. By scheduling the resources in the edge cluster, the resource scheduling and utilization of different use scenes are met, the self-adaptability of the resource scheduling is improved, and the edge computing nodes can deploy the resources such as computation and storage into an automatic aircraft or an automatic machine nest, so that the real-time processing and analysis of data are realized, the data transmission delay and the network data volume are reduced, and the system operation efficiency and stability are improved.
Example two
Fig. 2 is a schematic structural diagram of an edge cluster according to a second embodiment of the present invention. As shown in fig. 2, the edge cluster includes a control center 210 and a plurality of edge computing nodes 220, where the edge computing nodes 220 are automaton nests 221 with edge devices in a substation, and the automaton nests 221 are configured with automatic aircrafts 222;
the control center 210 is configured to receive node resource data of the automaton nest collected by each edge device;
the control center 210 is further configured to generate a patrol task for the automaton nest in the edge cluster;
the control center 210 is further configured to generate a resource allocation scheme for balancing the load for the inspection task according to the node resource data;
the edge device 220 is configured to execute the inspection task according to the resource allocation scheme, so as to drive the automatic aircraft to collect device perception data when inspecting the power device of the substation, and execute power service processing according to the device perception data.
In one embodiment of the present invention, the control center 210 is further configured to:
classifying the inspection tasks according to the complexity of the inspection tasks;
Loading a resource scheduling model corresponding to the category;
and inputting the node resource data into the resource scheduling model, and generating a balanced load resource allocation scheme for the inspection task.
In one embodiment of the present invention, the resource scheduling model includes a reinforcement learning model, a genetic model, and a bayesian model, and the control center 210 is further configured to:
if the category is a complex scene, inputting the node resource data into the reinforcement learning model, and generating a resource allocation scheme of balanced load for the inspection task;
if the category is a simple scene, inputting the node resource data into the genetic model or the Bayesian model, and generating a resource allocation scheme with balanced load for the inspection task;
wherein the complexity of the complex scene is greater than the complexity of the simple scene.
Illustratively, the complex scene includes defect analysis, three-dimensional reconstruction, and the simple scene includes data storage.
In one embodiment of the present invention, the device-aware data comprises first image data, and the edge device 220 is further configured to:
if the inspection task is the defect analysis, driving the automatic aircraft to acquire first image data when inspecting the power equipment of the transformer substation;
Identifying a type of the power device in the first image data;
performing object detection in the first image data targeting the type of the power device;
if the type of the power equipment is detected in the first image data, segmenting data representing the power equipment in the first image data as regional image data;
and carrying out infrared temperature measurement detection on the regional image data so as to detect defects of the power equipment.
In one embodiment of the present invention, the device-aware data comprises second image data, and the edge device 220 is further configured to:
if the inspection task is three-dimensional reconstruction, driving the automatic aircraft to acquire second image data when inspecting the power equipment of the transformer substation, and recognizing the gesture of the automatic aircraft when acquiring the second image data;
extracting characteristic points on a scale space from the second image data in a plurality of postures, and matching the characteristic points;
performing three-dimensional sparse reconstruction by using the feature points successfully matched to obtain first point cloud data;
performing three-dimensional dense reconstruction by using the first point cloud data to obtain second point cloud data;
Inputting the second point cloud data into an octree to divide third point cloud data;
performing poisson reconstruction by using the third point cloud data to obtain a plurality of grids;
and mapping textures of the second image data in a plurality of the poses into a plurality of grids so as to reconstruct a three-dimensional map model.
Illustratively, the node resource data includes node resource utilization, node network information, node load information.
The edge cluster provided by the embodiment of the invention can execute the cruise method of the automatic aircraft provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the cruise method of the automatic aircraft.
Example III
Fig. 3 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 3, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM12 and the RAM13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the cruise method of an automatic aircraft.
In some embodiments, the method of cruising an automatic aircraft may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM12 and/or the communication unit 19. When the computer program is loaded into RAM13 and executed by processor 11, one or more steps of the above-described cruise method of an automatic aircraft may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the cruise method of the automatic aircraft in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
Example IV
Embodiments of the invention also provide a computer program product comprising a computer program which, when executed by a processor, implements a method of cruising an automatic aircraft as provided by any of the embodiments of the invention.
Computer program product in the implementation, the computer program code for carrying out operations of the present invention may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. The utility model provides a cruising method of automatic aircraft, characterized by is applied to edge cluster, including control center and a plurality of edge compute node in the edge cluster, edge compute node is the automation nest of carrying edge equipment in the transformer substation, dispose automatic aircraft in the automation nest, the method includes:
the control center receives node resource data of the automaton nest, which are collected by each edge device;
The control center generates a patrol task for the automaton nest in the edge cluster;
the control center generates a resource allocation scheme for balancing loads for the inspection task according to the node resource data;
and the edge equipment executes the inspection task according to the resource allocation scheme so as to drive the automatic aircraft to acquire equipment perception data when inspecting the power equipment of the transformer substation, and execute power business processing according to the equipment perception data.
2. The method of claim 1, wherein the control center generating a load-balancing resource allocation scheme for the inspection task based on the node resource data, comprises:
classifying the inspection tasks according to the complexity of the inspection tasks;
loading a resource scheduling model corresponding to the category;
and inputting the node resource data into the resource scheduling model, and generating a balanced load resource allocation scheme for the inspection task.
3. The method of claim 2, wherein the resource scheduling model includes a reinforcement learning model, a genetic model, and a bayesian model, wherein the inputting the node resource data into the resource scheduling model generates a load-balanced resource allocation scheme for the patrol task, comprising:
If the category is a complex scene, inputting the node resource data into the reinforcement learning model, and generating a resource allocation scheme of balanced load for the inspection task;
if the category is a simple scene, inputting the node resource data into the genetic model or the Bayesian model, and generating a resource allocation scheme with balanced load for the inspection task;
wherein the complexity of the complex scene is greater than the complexity of the simple scene.
4. A method according to claim 3, wherein the complex scene comprises defect analysis, three-dimensional reconstruction, and the simple scene comprises data storage.
5. The method of claim 4, wherein the device-aware data comprises first image data, wherein the edge device performs the inspection task according to the resource allocation scheme to drive the automatic aerial vehicle to collect device-aware data while inspecting the power devices of the substation, and wherein performing power business processes according to the device-aware data comprises:
if the inspection task is the defect analysis, driving the automatic aircraft to acquire first image data when inspecting the power equipment of the transformer substation;
Identifying a type of the power device in the first image data;
performing object detection in the first image data targeting the type of the power device;
if the type of the power equipment is detected in the first image data, segmenting data representing the power equipment in the first image data as regional image data;
and carrying out infrared temperature measurement detection on the regional image data so as to detect defects of the power equipment.
6. The method of claim 4, wherein the device-aware data comprises second image data, wherein the edge device performs the inspection task according to the resource allocation scheme to drive the automatic aerial vehicle to collect device-aware data while inspecting the power devices of the substation, and wherein performing power business processes according to the device-aware data comprises:
if the inspection task is three-dimensional reconstruction, driving the automatic aircraft to acquire second image data when inspecting the power equipment of the transformer substation, and recognizing the gesture of the automatic aircraft when acquiring the second image data;
extracting characteristic points on a scale space from the second image data in a plurality of postures, and matching the characteristic points;
Performing three-dimensional sparse reconstruction by using the feature points successfully matched to obtain first point cloud data;
performing three-dimensional dense reconstruction by using the first point cloud data to obtain second point cloud data;
inputting the second point cloud data into an octree to divide third point cloud data;
performing poisson reconstruction by using the third point cloud data to obtain a plurality of grids;
and mapping textures of the second image data in a plurality of the poses into a plurality of grids so as to reconstruct a three-dimensional map model.
7. The method of any of claims 1-6, wherein the node resource data comprises node resource utilization, node network information, node load information.
8. The edge cluster is characterized by comprising a control center and a plurality of edge computing nodes, wherein the edge computing nodes are automaton nests, wherein edge equipment is carried in a transformer substation, and automatic aircrafts are configured in the automaton nests;
the control center is used for receiving node resource data of the automaton nest, which are collected by each edge device;
the control center is further used for generating a patrol task for the automaton nest in the edge cluster;
The control center is further used for generating a resource allocation scheme for balancing loads for the inspection tasks according to the node resource data;
the edge equipment is used for executing the inspection task according to the resource allocation scheme so as to drive the automatic aircraft to acquire equipment perception data when inspecting the power equipment of the transformer substation, and execute power business processing according to the equipment perception data.
9. An electronic device, the electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of cruising an automatic aircraft according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that it stores a computer program for causing a processor to carry out the cruise method of an automatic aircraft according to any one of claims 1-7 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310747279.9A CN116661474A (en) | 2023-06-25 | 2023-06-25 | Cruise method, edge cluster, equipment and storage medium of automatic aircraft |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310747279.9A CN116661474A (en) | 2023-06-25 | 2023-06-25 | Cruise method, edge cluster, equipment and storage medium of automatic aircraft |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116661474A true CN116661474A (en) | 2023-08-29 |
Family
ID=87726122
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310747279.9A Pending CN116661474A (en) | 2023-06-25 | 2023-06-25 | Cruise method, edge cluster, equipment and storage medium of automatic aircraft |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116661474A (en) |
-
2023
- 2023-06-25 CN CN202310747279.9A patent/CN116661474A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111784685B (en) | Power transmission line defect image identification method based on cloud edge cooperative detection | |
| CN107742093B (en) | Real-time detection method, server and system for infrared image power equipment components | |
| CN112380952A (en) | Power equipment infrared image real-time detection and identification method based on artificial intelligence | |
| Sohn et al. | Automatic powerline scene classification and reconstruction using airborne lidar data | |
| CN113408087B (en) | Substation inspection method based on cloud side system and video intelligent analysis | |
| CN112367400B (en) | Intelligent inspection method and system for power internet of things with edge cloud coordination | |
| CN116824517B (en) | Substation operation and maintenance safety control system based on visualization | |
| CN110992307A (en) | Insulator positioning and identifying method and device based on YOLO | |
| CN113807450A (en) | Unmanned aerial vehicle power line patrol fault detection method based on ultrahigh resolution picture | |
| CN114897329A (en) | Power transmission line inspection method, device and system and storage medium | |
| CN113534832A (en) | Unmanned aerial vehicle inspection tracking distribution network line flying method based on edge calculation | |
| CN115019209A (en) | Method and system for detecting state of electric power tower based on deep learning | |
| Maduako et al. | Deep learning for component fault detection in electricity transmission lines | |
| Hao et al. | Detection of bird nests on power line patrol using single shot detector | |
| CN111027397A (en) | Method, system, medium and device for detecting comprehensive characteristic target in intelligent monitoring network | |
| CN113536944A (en) | Distribution line inspection data identification and analysis method based on image identification | |
| CN117197571A (en) | Photovoltaic module fault detection method and device, electronic equipment and storage medium | |
| Ying et al. | An improved defect detection method for substation equipment | |
| CN116661474A (en) | Cruise method, edge cluster, equipment and storage medium of automatic aircraft | |
| CN117197517A (en) | Insulator pollution classification method and device, electronic equipment and medium | |
| CN115329428A (en) | Method, device and equipment for determining fan arrangement mode and storage medium | |
| CN113393453A (en) | Method, apparatus, device, medium and product for detecting self-bursting insulators | |
| CN112683916A (en) | Method and device for identifying missing or mounting error of small hardware fittings of current collecting line tower | |
| Gu et al. | Object detection of overhead transmission lines based on improved YOLOv5s | |
| Jiang et al. | Research on Lightweight Method of Image Deep Learning Model for Power Equipment |
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 |