CN117647993A - Unmanned aerial vehicle inspection method based on electric power inspection scene - Google Patents
Unmanned aerial vehicle inspection method based on electric power inspection scene Download PDFInfo
- Publication number
- CN117647993A CN117647993A CN202311602426.XA CN202311602426A CN117647993A CN 117647993 A CN117647993 A CN 117647993A CN 202311602426 A CN202311602426 A CN 202311602426A CN 117647993 A CN117647993 A CN 117647993A
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- inspection
- data
- electric power
- 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
- 238000007689 inspection Methods 0.000 title claims abstract description 97
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000012545 processing Methods 0.000 claims abstract description 10
- 238000005516 engineering process Methods 0.000 claims description 30
- 238000004891 communication Methods 0.000 claims description 20
- 230000006870 function Effects 0.000 claims description 19
- 230000000007 visual effect Effects 0.000 claims description 19
- 230000005540 biological transmission Effects 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 14
- 238000001914 filtration Methods 0.000 claims description 10
- 239000002245 particle Substances 0.000 claims description 9
- 238000013135 deep learning Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000013500 data storage Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 3
- 238000011084 recovery Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 238000005457 optimization Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 6
- 238000013144 data compression Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000008030 elimination Effects 0.000 description 5
- 238000003379 elimination reaction Methods 0.000 description 5
- 230000001965 increasing effect Effects 0.000 description 4
- 238000012805 post-processing Methods 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 230000002708 enhancing effect Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000008054 signal transmission Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 241000209527 Arum Species 0.000 description 1
- 235000006481 Colocasia esculenta Nutrition 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005562 fading Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
Landscapes
- Navigation (AREA)
Abstract
The invention discloses an unmanned aerial vehicle inspection method based on an electric power inspection scene, which belongs to the technical field of unmanned aerial vehicle electric power inspection, and comprises the steps of adopting an unmanned aerial vehicle and an inspection sensor to acquire electric power equipment information in real time; real-time image processing; and planning the inspection path. By adopting the unmanned aerial vehicle inspection method based on the electric power inspection scene, the problems that in the current stage, the intelligent inspection in a plurality of transformer substations is needed to be manually participated in inspection, the accurate positioning of an inspection system is affected, the electric power inspection cannot provide accurate unmanned aerial vehicle inspection service in different scenes, the adaptability is poor, the unmanned aerial vehicle cannot quickly find target equipment, enough data cannot be acquired in a short time, and the electric power inspection task cannot be quickly completed are solved.
Description
Technical Field
The invention relates to the technical field of unmanned aerial vehicle power inspection, in particular to an unmanned aerial vehicle inspection method based on a power inspection scene.
Background
Along with the continuous iterative upgrade of Chinese economic digital transformation and unmanned aerial vehicle technology, unmanned aerial vehicle operation based on precise positioning technologies such as GNSS (global navigation positioning system), radar, inertial navigation, mapping and the like is required to ensure the normal operation of the industry in various fields such as electric power, energy, geology, agriculture and forestry, communication and the like. The invention provides an unmanned aerial vehicle inspection method based on an electric power inspection scene, which is characterized in that a latest digital technology is generally used for actively collecting data and feeding back to a server, and then each component, working condition, environmental data and the like are dynamically presented in real time through a three-dimensional platform, so that the fastest and accurate data are provided for decision-making personnel as an inspection support, a special network accurate positioning broadcast system is an important component of an electric power system, and special channel transmission safety, centimeter and positioning services are provided for power transmission, power transformation, power distribution and the like of the electric power system, so that the unmanned aerial vehicle inspection method is a core technology for guaranteeing safe and stable operation of each system of the electric power system.
At present, a plurality of intelligent inspection in transformer substations need to be manually participated in inspection, the accurate positioning of an inspection system is influenced, moreover, the power inspection cannot provide accurate unmanned aerial vehicle inspection service under different scenes, the adaptability is poor, the unmanned aerial vehicle cannot quickly find target equipment, cannot acquire enough data in a short time, and cannot quickly complete the power inspection task.
Disclosure of Invention
The invention aims to provide an unmanned aerial vehicle inspection method based on a power inspection scene, so as to solve the technical problems mentioned in the background.
In order to achieve the above purpose, the invention provides an unmanned aerial vehicle inspection method based on an electric power inspection scene, comprising the following steps:
s1, acquiring images of a power line and power equipment in real time by adopting an unmanned aerial vehicle and a patrol sensor;
s2, carrying out real-time processing on the image acquired in the step S1;
s3, planning a routing inspection path, and determining the routing inspection path of the unmanned aerial vehicle by adopting dynamic planning, kalman filtering and particle filtering algorithms.
Preferably, the objective function of the three-dimensional path planning of the unmanned aerial vehicle is that
Comprehensively considering the limit of the shortest path cost, the minimum threat cost, the flight height cost and the flight corner cost related to the flight path Xi of the unmanned aerial vehicle, the multi-objective function based on multi-factor constraint is constructed as follows: wherein the first objective function F1 is the shortest path cost, the second objective function F2 is the sum of the threat cost F1, the flying height cost F3 and the flying corner cost flying F4, and is specifically defined as follows:
f1(Xi)＝F1(Xi)
f2(Xi)＝F1(Xi)+F3(Xi)+F4(Xi)。
preferably, the unmanned aerial vehicle comprises a visual odometer and inertial navigation, wherein the visual odometer comprises a sensor device, a control system, a map and navigation;
a sensor device, a visual odometer using a plurality of sensors to collect data while the unmanned aerial vehicle is traveling, including global positioning system GPS and lidar;
the control system comprises a computer and a controller, processes data collected by the unmanned aerial vehicle sensor, and controls the direction and speed of the unmanned aerial vehicle;
and the map and navigation are used for determining the running direction and the running path of the unmanned aerial vehicle.
Preferably, the step S2 specifically includes:
(1) training a real-time power line and power equipment image on the basis of a data acquisition system by using a deep learning target detection algorithm on a power inspection scene image data set so as to learn the position characteristics of the unmanned aerial vehicle in different scenes;
(2) based on a data storage system, a distributed database system is adopted to realize the storage, backup and recovery of data;
(3) based on a data processing system, adopting a computer vision and machine learning technology to process and analyze the inspection data to generate an inspection report;
(4) based on the data display system, the patrol data are displayed to the user in a visual mode by adopting a map and report form;
(5) based on a wireless transmission system, the data transmission between the unmanned aerial vehicle and the ground control center is realized by adopting a wireless communication technology.
Preferably, the wireless communication techniques include selecting an appropriate communication protocol, enhancing signal coverage, interference cancellation techniques, and data compression and optimization;
selecting an appropriate communication protocol: according to the task and performance requirements of the unmanned aerial vehicle, a proper communication protocol is selected, the Mavlink communication allows the unmanned aerial vehicle to perform two-way communication with a transformer substation, the transformer substation sends instructions and control information to the unmanned aerial vehicle, the unmanned aerial vehicle sends telemetry and other state information to the transformer substation, and the protocols have different performances and advantages under different environments;
enhanced signal coverage: by increasing the number of base stations, increasing the base station power and using higher gain transmitters;
the interference elimination technology can be utilized in the task process of the unmanned aerial vehicle;
data compression and optimization: during the unmanned aerial vehicle's mission, sensor data may be compressed and optimized.
Preferably, in the step S3, the unmanned aerial vehicle quickly finds the target device in the inspection process, acquires data, completes the power inspection task, and establishes a state transition table by using a dynamic programming algorithm, wherein a row represents the current position of the unmanned aerial vehicle, and a column represents the state between different devices; one device is selected in a given list of devices, and if the state of the device is the same as the current state of the unmanned aerial vehicle, the device is selected, otherwise, other devices are selected.
Preferably, in order to improve the inspection efficiency, the unmanned aerial vehicle needs to quickly identify the target device and acquire the state thereof, in order to acquire enough data in a given time interval, a kalman filter algorithm may be used to reduce over-sampling of sensor data, the kalman filter may estimate the state of the target device according to the motion state of the unmanned aerial vehicle and the sensor data, and then the unmanned aerial vehicle may select a suitable device for inspection according to the estimated state of the target device.
Preferably, in the inspection process, the unmanned aerial vehicle is subjected to random factors including wind speed and wind direction, in order to improve the reliability and stability of inspection, a particle filter algorithm is used to reduce the influence of the uncertain factors, the future position of the unmanned aerial vehicle is estimated by the particle filter according to the state of the unmanned aerial vehicle and sensor data, and then the unmanned aerial vehicle can select a proper device for inspection according to the estimated future position.
Therefore, the unmanned aerial vehicle inspection method based on the electric power inspection scene has the following beneficial effects:
(1) The method comprises the steps of adopting an advanced visual navigation technology, including a visual odometer and inertial navigation, realizing autonomous flight of the unmanned aerial vehicle, wherein the visual odometer further comprises a sensor device, a control system, a map and navigation, calculating the acceleration of an object by measuring the moment of inertia of the object by utilizing the inertial navigation, determining the motion state of the object, upgrading the navigation precision, the anti-interference capability and the Doppler effect resistance of the inertial navigation technology, and adopting two positioning modes to realize real-time accurate positioning of the unmanned aerial vehicle;
(2) The wireless communication technology is adopted to realize the data transmission between the unmanned aerial vehicle and the ground control center and the real-time and remote data transmission between the inspection system and the ground command center, and comprises the steps of selecting proper communication protocols, enhancing signal coverage, interference elimination technology and data compression and optimization, so that the unmanned aerial vehicle power inspection system is suitable for substations in plain, hills and mountains;
(3) The Kalman filtering algorithm is used for reducing the over sampling of the sensor data, so that enough data can be acquired within a given time interval, and the inspection efficiency is improved.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
FIG. 1 is a schematic diagram of the present invention;
FIG. 2 is a navigation view of the unmanned aerial vehicle of the present invention;
FIG. 3 is a diagram of a flight trajectory of the unmanned aerial vehicle of the present invention;
FIG. 4 is a schematic diagram of a wireless communication technique according to the present invention;
FIG. 5 is a schematic diagram of a distributed database of the present invention;
FIG. 6 is a schematic diagram of a data processing system of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention.
Example 1
Referring to fig. 1-6, an unmanned aerial vehicle inspection method based on a power inspection scene includes the steps:
s1, unmanned aerial vehicle inspection system based on vision
(1) Unmanned aerial vehicle: advanced visual navigation technology is adopted, including visual odometer and inertial navigation, realize unmanned aerial vehicle's autonomous flight, unmanned aerial vehicle adopts the M300RTK of great ARUM, unmanned aerial vehicle can adapt to complicated topography to can be in real time to the image and the data of wire pole and electric wire junction be returned, the high accuracy model also can be obtained in the mountain area, support real-time three-dimensional reconstruction, efficient, the field application that the practicality is strong of being convenient for.
Target function for three-dimensional path planning of unmanned aerial vehicle
Comprehensively considering the limit of the shortest path cost, the minimum threat cost, the flying height cost and the flying corner cost related to the flight path Xi of the unmanned aerial vehicle, the multi-objective function construction based on multi-factor constraint is as follows: wherein the first objective function F1 is the shortest path cost, the second objective function F2 is the sum of the threat cost F1, the flying height cost F3 and the flying corner cost flying F4, and is specifically defined as follows:
f1(Xi)＝F1(Xi)
f2(Xi)＝F1(Xi)+F3(Xi)+F4(Xi)；
determining a cost function, wherein the cost function tightly links an algorithm with actual physical problems, for unmanned aerial vehicle track planning, the cost function is a standard for evaluating the track quality, the smaller the cost value is, the better the track is indicated, otherwise, the worse the track is indicated, each factor affecting the track performance needs to be comprehensively considered for determining the cost function, each index is quantized and calculated, the cost function for three-dimensional track planning generally comprises track length cost, threat cost and altitude cost, and the cost is expressed as:
J＝W1L+W2T+W3H
W1+W2+W3＝1
wherein J is the total cost of the track, L is the length cost of the track, which is also called the fuel cost, T is the threat cost, H is the altitude cost, W1, W2 and W3 are the corresponding weight coefficients, the values of which are set according to the task needs, and the altitude cost is not required to be considered in the two-dimensional track planning.
The flight path of the unmanned aerial vehicle is shown in figure 3, a and a mountain area; b. hills; c. plain; x, flying height; y, flight path; z, vertical axis.
The visual odometer comprises a sensor device, a control system, a map and navigation;
a. sensor device: the visual odometer typically uses a plurality of sensors to collect data while the drone is traveling, including GPS and lidar, which can capture real-time environmental information around the drone and fuse it with the drone's navigation data to determine the direction and path of travel of the drone. b. And (3) a control system: the control system of the visual odometer generally comprises a computer and a controller for processing data collected by the unmanned aerial vehicle sensor and controlling the direction and speed of the unmanned aerial vehicle, and the control system generally adopts a high-precision control system to ensure the navigation precision and stability of the unmanned aerial vehicle. c. Map and navigation: the visual odometer also has map and navigation functions for assisting the drone in determining its direction and path of travel, which generally include functions of real-time navigation, path planning and various map displays.
Inertial navigation the acceleration of an object is calculated by measuring the moment of inertia of the object so as to determine the motion state of the object, and the inertial navigation technology is upgraded in terms of navigation precision, anti-interference capability and anti-Doppler effect and comprises the following steps: a. by improving the performance and sensitivity of the sensor, the sensor is selected with consideration of improving the technical parameters of the sensor, such as sampling rate, signal-to-noise ratio and randomness resistance, and in addition, by improving the sensor structure, such as improving the size of the sensor or adopting a novel sensor device, the performance of the sensor can be improved; b. reducing external interference by selecting a sensor with higher anti-interference capability and adopting an anti-interference algorithm; c. by using spectral estimation, adaptive filtering techniques, and data fusion techniques, for example, by estimating the Doppler shift of a received target and using an adaptive filter to cancel the effect of the Doppler shift, the Doppler effect resistance can be improved.
(2) Inspection sensor: the high-precision power inspection sensor comprises a laser radar and a thermal infrared imager and is used for acquiring power line and power equipment images in real time.
S2, high-precision positioning system
And a Global Positioning System (GPS) and Inertial Navigation (INS) are adopted to realize real-time accurate positioning of the unmanned aerial vehicle.
S3, real-time image processing
(1) And a data acquisition system: the inspection sensor of the laser radar and the thermal infrared imager is adopted to collect images of the power line and the power equipment in real time, and a deep learning target detection algorithm is used to train on a large number of image datasets of the power inspection scene so as to learn possible position features of the unmanned aerial vehicle in different scenes.
(2) A data storage system: and a distributed database system is adopted to realize the storage, backup and recovery of data.
(3) A data processing system: the inspection data is processed and analyzed by adopting a computer vision and machine learning technology, and the data processing system comprises: a. data quality: firstly, cleaning, de-duplication and preprocessing data to ensure the quality and reliability of the data; b. feature extraction: the original data needs to be converted and transformed so that the computer vision algorithm can better process and identify the data, and advanced feature extraction algorithms such as a deep learning algorithm are adopted; c. model selection: depending on the characteristics of the data and the complexity of the problem, suitable models are selected, such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), d, model evaluation: the model is evaluated and optimized by adopting common evaluation indexes such as accuracy, recall and F1 value; e. model optimization: if the performance of the model is not satisfactory, it needs to be optimized, including adjusting the architecture and super parameters of the model to improve the performance and effect of the model.
(4) And (3) a data display system: and displaying the patrol data to a user in a visual mode by adopting a map and report form.
(5) A wireless communication system: and the wireless communication technology is adopted to realize the data transmission between the unmanned aerial vehicle and the ground control center, and the real-time and remote data transmission between the inspection system and the ground command center.
Wireless communication techniques include selecting appropriate communication protocols, enhancing signal coverage, interference cancellation techniques, and data compression and optimization;
a. selecting an appropriate communication protocol: according to the task and performance requirements of the unmanned aerial vehicle, a proper communication protocol is selected, the Mavlink communication allows the unmanned aerial vehicle to perform two-way communication with a transformer substation, the transformer substation sends instructions and control information to the unmanned aerial vehicle, the unmanned aerial vehicle sends telemetry and other state information to the transformer substation, and the protocols have different performances and advantages under different environments, b, the signal coverage range is enhanced: through increasing the quantity of base stations, improving the power of the base stations and using the mode of the emitter with higher gain, the signal coverage of the unmanned aerial vehicle is enhanced, the signal quality and the stability are improved, and c, the interference elimination technology is as follows: in the task process of the unmanned aerial vehicle, the quality and stability of signals can be improved by utilizing interference elimination technologies such as self-adaptive ultra-bandwidth and self-adaptive multipath fading inhibition, and d, data compression and optimization: in the unmanned aerial vehicle's task process, can compress and optimize sensor data, reduce data volume and transmission delay, improve signal transmission's efficiency.
S4, routing inspection path planning
Dynamic planning, kalman filtering and particle filtering algorithms are used for determining an efficient path of unmanned aerial vehicle inspection and ensuring the high efficiency and accuracy of the inspection process.
In the dynamic programming, in the process of polling, the unmanned aerial vehicle needs to quickly find target equipment, data is acquired according to the heavy degree of the polling task so as to complete the power polling task, a dynamic programming algorithm can be used, firstly, a state transition table is established, wherein a row represents the current position of the unmanned aerial vehicle, a column represents the state among different equipment, then, one equipment is selected in a given equipment list, if the state of the equipment is the same as the current state of the unmanned aerial vehicle, the equipment is selected, and otherwise, other equipment is selected.
In order to improve the inspection efficiency, the unmanned aerial vehicle needs to quickly identify the target device and acquire the state thereof, in order to acquire enough data in a given time interval, a kalman filter algorithm can be used to reduce the over-sampling of sensor data, the kalman filter can estimate the state of the target device according to the motion state of the unmanned aerial vehicle and the sensor data, and then the unmanned aerial vehicle can select a proper device for inspection according to the estimated state of the target device.
Particle filtering in the course of patrolling and examining, unmanned aerial vehicle probably receives the influence of some random factors, for example wind speed and wind direction, in order to improve reliability and the stability of patrolling and examining, can use particle filtering algorithm to reduce the influence of these uncertain factors, particle filter can estimate unmanned aerial vehicle's future position according to unmanned aerial vehicle's state and sensor data, then, unmanned aerial vehicle can select suitable equipment to patrol and examine according to estimated future position.
S5, technical implementation
(1) Technical training: technical training is carried out on team members participating in technical implementation, so that the team members can be ensured to be skilled in learning the technology;
(2) and (3) technical verification: technical verification is carried out in an actual application environment, and feasibility and effectiveness of a technical scheme are ensured;
(3) and (3) technical optimization: according to the problems in the practical application process, the technical proposal is optimized, the technical effect is improved,
(4) safety construction standard: a. the standby electric quantity of the unmanned aerial vehicle is determined to be more than 80%, so that the complete completion of one-time inspection can be ensured, and the unmanned aerial vehicle cannot fall in the middle; b. during inspection, except for a person controlling the unmanned aerial vehicle, a transformer substation or a power transmission high tower background control person needs to be on duty; c. weather requirements: the maximum wind resistance of the unmanned aerial vehicle is 12m/s, and in thunder weather, the unmanned aerial vehicle and related equipment can possibly draw a mine, and for self safety, stopping flying is recommended; d. person identification: whether unmanned aerial vehicles qualify; e. if the unmanned aerial vehicle falls to the power transmission line to cause the short circuit of the power line, a corresponding accident plan is required.
Example 2
As shown in the figure, unlike the first embodiment, the unmanned aerial vehicle inspection method based on the power inspection scene in the present embodiment includes the following steps:
s1, generating a path
Unmanned aerial vehicle: advanced visual navigation technology is adopted;
s2, high-precision positioning system
PPK (dynamic post-processing technology), PPP (precision single point positioning technology) and RTK (carrier phase difference technology) are adopted;
s3, positioning inspection
(1) PPK (dynamic post-processing technique) is used: the PPK technology adopts a mode of post-processing of observed data, and a real-time data transmission path is not required to be established between a reference station and a mobile station, so that the reference station and the mobile station are not limited by signal transmission distance during observation, and the PPK technology has the advantages of large positioning radius, high positioning precision, simplicity in operation and relatively mature technology;
(2) PPP (precision single point positioning technique): a method for high-precision single-point positioning using carrier phase observations, high-precision satellite ephemeris and satellite clock bias provided by IGS organization;
(3) RTK (carrier phase difference technique): the principle of the differential positioning technology is that a receiver of a reference station and a receiver of a mobile station continuously receive satellite signals, and the space coordinates of the receiver are calculated through inter-station observation value differential elimination, so that high-precision positioning is completed.
PPK (dynamic post-processing technology) is a post-calculation, so that a user cannot obtain real-time coordinate data, cannot see the accuracy of observation in real time, and needs to maintain good observation conditions during observation.
The planar position precision of the point position obtained by PPP according to the observation value of one day can reach 1-3cm and the elevation precision is 2-4cm at present, but the static base station needs to be erected for a long time, the environment requirement for erecting the base station is higher, only the known point position can be obtained, the point position can not be moved, and the previous steps need to be repeated after the change occurs.
The RTK technology adopts a service mode based on an observation domain (OSR), and because satellites seen by different areas are different, the 'observation value' of the satellites is different, and the actual position of a user needs to be relied on, and when the number of users is increased, a larger service pressure can be generated.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention and not for limiting it, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that: the technical scheme of the invention can be modified or replaced by the same, and the modified technical scheme cannot deviate from the spirit and scope of the technical scheme of the invention.
Claims (7)
1. The unmanned aerial vehicle inspection method based on the electric power inspection scene is characterized by comprising the following steps:
s1, acquiring images of a power line and power equipment in real time by adopting an unmanned aerial vehicle and a patrol sensor;
s2, carrying out real-time processing on the image acquired in the step S1;
s3, planning a routing inspection path, and determining the routing inspection path of the unmanned aerial vehicle by adopting dynamic planning, kalman filtering and particle filtering algorithms.
2. The unmanned aerial vehicle inspection method based on the power inspection scene of claim 1, wherein the objective function of the unmanned aerial vehicle three-dimensional path planning is
Comprehensively considering the limit of the shortest path cost, the minimum threat cost, the flight height cost and the flight corner cost related to the flight path Xi of the unmanned aerial vehicle, the multi-objective function based on multi-factor constraint is constructed as follows: wherein the first objective function F1 is the shortest path cost, the second objective function F2 is the sum of the threat cost F1, the flying height cost F3 and the flying corner cost flying F4, and is specifically defined as follows:
f1(Xi)＝F1(Xi)
f2(Xi)＝F1(Xi)+F3(Xi)+F4(Xi)。
3. the unmanned aerial vehicle inspection method based on the power inspection scene as claimed in claim 1, wherein the unmanned aerial vehicle inspection method is characterized in that: the unmanned aerial vehicle comprises a visual odometer and inertial navigation, wherein the visual odometer comprises a sensor device, a control system, a map and navigation;
a sensor device, a visual odometer using a plurality of sensors to collect data while the unmanned aerial vehicle is traveling, including global positioning system GPS and lidar;
the control system comprises a computer and a controller, processes data collected by the unmanned aerial vehicle sensor, and controls the direction and speed of the unmanned aerial vehicle;
and the map and navigation are used for determining the running direction and the running path of the unmanned aerial vehicle.
4. The unmanned aerial vehicle inspection method based on the power inspection scene of claim 1, wherein the step S2 specifically comprises:
(1) based on a data acquisition system, training on an electric power inspection scene image data set by using a deep learning target detection algorithm for acquiring images of an electric power circuit and electric power equipment in real time so as to learn the position characteristics of the unmanned aerial vehicle in different scenes;
(2) based on a data storage system, a distributed database system is adopted to realize the storage, backup and recovery of data;
(3) based on a data processing system, adopting a computer vision and machine learning technology to process and analyze the inspection data to generate an inspection report;
(4) based on the data display system, the patrol data are displayed to the user in a visual mode by adopting a map and report form;
(5) based on a wireless transmission system, the data transmission between the unmanned aerial vehicle and the ground control center is realized by adopting a wireless communication technology.
5. The unmanned aerial vehicle inspection method based on the power inspection scene as claimed in claim 1, wherein the unmanned aerial vehicle inspection method is characterized in that: in the step S3, in the process of inspection, the unmanned aerial vehicle quickly finds out the target equipment, acquires data, completes the electric power inspection task, and establishes a state transition table by using a dynamic programming algorithm, wherein the row represents the current position of the unmanned aerial vehicle, and the column represents the state among different equipment; one device is selected in a given list of devices, and if the state of the device is the same as the current state of the unmanned aerial vehicle, the device is selected, otherwise, other devices are selected.
6. The unmanned aerial vehicle inspection method based on the power inspection scene as claimed in claim 1, wherein the unmanned aerial vehicle inspection method is characterized in that: the Kalman filter estimates the state of the target equipment according to the motion state of the unmanned aerial vehicle and the sensor data, and the unmanned aerial vehicle selects proper equipment for inspection according to the estimated state of the target equipment.
7. The unmanned aerial vehicle inspection method based on the power inspection scene as claimed in claim 1, wherein the unmanned aerial vehicle inspection method is characterized in that: the particle filter estimates the future position of the unmanned aerial vehicle according to the motion state of the unmanned aerial vehicle and the sensor data, and the unmanned aerial vehicle selects proper equipment for inspection according to the estimated future position.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311602426.XA CN117647993A (en) | 2023-11-28 | 2023-11-28 | Unmanned aerial vehicle inspection method based on electric power inspection scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311602426.XA CN117647993A (en) | 2023-11-28 | 2023-11-28 | Unmanned aerial vehicle inspection method based on electric power inspection scene |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117647993A true CN117647993A (en) | 2024-03-05 |
Family
ID=90044456
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311602426.XA Pending CN117647993A (en) | 2023-11-28 | 2023-11-28 | Unmanned aerial vehicle inspection method based on electric power inspection scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117647993A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118068853A (en) * | 2024-04-24 | 2024-05-24 | 辽宁高比科技有限公司 | Autonomous flight inspection method for indoor substation GIS room unmanned aerial vehicle |
-
2023
- 2023-11-28 CN CN202311602426.XA patent/CN117647993A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118068853A (en) * | 2024-04-24 | 2024-05-24 | 辽宁高比科技有限公司 | Autonomous flight inspection method for indoor substation GIS room unmanned aerial vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9784836B2 (en) | System for monitoring power lines | |
| EP2743788B1 (en) | Aerial forest inventory system | |
| KR101839599B1 (en) | Road facility surveying system using drone | |
| CN106682592B (en) | Image automatic identification system and method based on neural network method | |
| CN105182997A (en) | Electromagnetic-simulation-based evaluation method for unmanned plane planning route | |
| CN113075938B (en) | Remote intelligent inspection system and method for power transmission line | |
| CN111026150A (en) | System and method for pre-warning geological disasters of power transmission line by using unmanned aerial vehicle | |
| CN105184776A (en) | Target tracking method | |
| CN117647993A (en) | Unmanned aerial vehicle inspection method based on electric power inspection scene | |
| CN109085573A (en) | Vehicle-mounted unmanned aerial vehicle managing and control system and method | |
| CN109781635B (en) | Distributed remote sensing satellite system | |
| CN103852077A (en) | Automatic anti-cheating judgment method for unmanned aerial vehicle positioning information in link failure process | |
| CN203480030U (en) | Unmanned aerial vehicle positioning system based on mobile phone base station signal | |
| CN113075686B (en) | Cable trench intelligent inspection robot graph building method based on multi-sensor fusion | |
| CN113077561A (en) | Intelligent inspection system for unmanned aerial vehicle | |
| CN110647170A (en) | Navigation mark inspection device and method based on unmanned aerial vehicle | |
| CN206649347U (en) | A kind of application deployment system based on unmanned vehicle | |
| CN117269989A (en) | GNSS spoofing detection method and system based on ins assistance | |
| CN103777196A (en) | Ground target distance single station measurement method based on geographic information and measurement system thereof | |
| CN114719881B (en) | Path-free navigation algorithm and system applying satellite positioning | |
| WO2022138182A1 (en) | Artificial satellite and ground system | |
| WO2022138181A1 (en) | Terrestrial system and image processing method for same | |
| CN115406439A (en) | Vehicle positioning method, system, device and nonvolatile storage medium | |
| Yang | Research on key technologies of UAV navigation and positioning system | |
| CN114371726A (en) | Unmanned aerial vehicle air-ground integrated detection positioning method, device, system and 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 |