CN114092537A - Automatic inspection method and device for electric unmanned aerial vehicle of transformer substation - Google Patents
Automatic inspection method and device for electric unmanned aerial vehicle of transformer substation Download PDFInfo
- Publication number
- CN114092537A CN114092537A CN202111112945.9A CN202111112945A CN114092537A CN 114092537 A CN114092537 A CN 114092537A CN 202111112945 A CN202111112945 A CN 202111112945A CN 114092537 A CN114092537 A CN 114092537A
- Authority
- CN
- China
- Prior art keywords
- aerial vehicle
- unmanned aerial
- transformer substation
- point cloud
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/521—Depth or shape recovery from laser ranging, e.g. using interferometry; from the projection of structured light
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Bioinformatics & Computational Biology (AREA)
- Electromagnetism (AREA)
- Optics & Photonics (AREA)
- Traffic Control Systems (AREA)
- Navigation (AREA)
Abstract
The invention discloses an automatic inspection method and device for a substation electric unmanned aerial vehicle, wherein the method comprises the steps of utilizing a laser radar to collect point cloud data of a substation; acquiring images in the transformer substation by using an image acquisition device; completing three-dimensional reconstruction of an unknown environment by the unmanned aerial vehicle based on the acquired point cloud data, the images in the transformer substation and the real-time position information of the unmanned aerial vehicle; and planning a route based on a three-dimensional reconstruction result, and controlling the electric unmanned aerial vehicle of the transformer substation to automatically patrol. The unmanned aerial vehicle automatic inspection system realizes the full-automatic inspection of the unmanned aerial vehicle of the transformer substation without human participation, reduces the operation difficulty of field personnel, frees operation and maintenance personnel from heavy and tedious conventional inspection work, improves the efficiency of integral operation, and improves the automation and intelligence level of the operation and maintenance of the transformer substation.
Description
Technical Field
The invention belongs to the field of intelligent inspection of transformer substations, and particularly relates to an automatic inspection method and device for a transformer substation electric unmanned aerial vehicle.
Background
In an electric power system, inspection tour, maintenance and management of substation equipment and timely discovery of equipment problems are one of the main tasks of substation operation and maintenance. The defects, hidden dangers, abnormal operation states and the like of the power equipment directly influence the safe operation of the power equipment, the reliable power supply of a power grid and the production and operation activities of industrial, agricultural and commercial users, even bring serious economic loss, are not beneficial to social harmony and stability, and as a power transformation operation and maintenance worker, the inspection quality of the equipment must be paid attention to. The method can find the problems of the equipment in time and improve the power supply reliability and the service level, and becomes an important means for improving the service level of power supply enterprises. Therefore, the transformer substation needs to continuously enhance the construction of the inspection operation capability, and create more economic benefits and social benefits for power users. In the unmanned aerial vehicle inspection application of the transformer substation, which is widely developed at present, the unmanned aerial vehicle needs manual operation of professionals, so that the inspection universality of the unmanned aerial vehicle is greatly reduced; moreover, because the flyer is limited by the body, spirit and physical strength are difficult to concentrate for a long time, and when the unmanned aerial vehicle is controlled to fly in a transformer substation environment with a complex environment, safety accidents such as explosion and the like easily occur.
The daily inspection visual angle of the existing manual or robot is generally observed from the lower part of equipment to the upper part, and inspection dead angles exist at the high part and the upper part of the equipment; in the unmanned aerial vehicle inspection application of the transformer substation, which is widely developed at present, the unmanned aerial vehicle needs manual operation of professionals, so that the inspection universality of the unmanned aerial vehicle is greatly reduced; moreover, since the flyer is limited by the body, the spirit and physical strength are difficult to concentrate for a long time, and when the unmanned aerial vehicle is controlled to fly in a transformer substation environment with a complex environment, safety accidents such as machine explosion and the like are easy to occur; the existing unmanned aerial vehicle inspection path is taught by inspection personnel, the debugging workload is very huge, the quality of route point setting and inspection acquisition pictures is related to the skill level of a flyer, and a safety path for global check flight is not formed in the flight path design and the flight process; most of the existing inspection methods have the function of manually planning the route, but the problems that the route planning is not standard, a combined complementary mechanism is not established with other inspection systems (inspection robots and manual work) and the like still exist, the inspection effect of the unmanned aerial vehicle inspection is weakened, and the inspection advantage of the unmanned aerial vehicle cannot be brought into full play.
Disclosure of Invention
Aiming at the problems, the invention provides the automatic inspection method and the automatic inspection device for the electric unmanned aerial vehicle of the transformer substation, which realize the full-autonomous inspection of the unmanned aerial vehicle of the transformer substation without human participation, reduce the operation difficulty of field personnel, liberate operation and maintenance personnel from heavy and tedious conventional inspection work, improve the efficiency of integral operation and improve the automation and intelligence level of operation and maintenance of the transformer substation.
In order to achieve the technical purpose and achieve the technical effects, the invention is realized by the following technical scheme:
in a first aspect, the invention provides an automatic inspection method for a substation electric unmanned aerial vehicle, which comprises the following steps:
carrying out point cloud data acquisition on the transformer substation by using a laser radar;
acquiring images in the transformer substation by using an image acquisition device;
completing three-dimensional reconstruction of an unknown environment by the unmanned aerial vehicle based on the acquired point cloud data, the images in the transformer substation and the real-time position information of the unmanned aerial vehicle;
and planning a route based on a three-dimensional reconstruction result, and controlling the electric unmanned aerial vehicle of the transformer substation to automatically patrol.
Optionally, the point cloud data acquisition of the transformer substation by using the laser radar specifically includes the following steps:
according to the structure of the unmanned aerial vehicle, calculating the coordinates of the installation positions of the RTK, the GPS, the image collector and the laser radar on the unmanned aerial vehicle by adopting an ICP algorithm based on geometrical characteristics, and acquiring the parameters of the installation positions at the coordinate positions;
respectively carrying out single-point positioning on the RTK, the GPS, the image collector and the laser radar according to the acquired installation position parameters to generate respective independent coordinate systems;
selecting an unmanned aerial vehicle origin as a coordinate system origin, calculating space position coordinates of RTK, GPS, an image collector and a laser radar according to the installation position coordinates, deducing a transformation relation between each independent coordinate system and the unmanned aerial vehicle origin, establishing an object-image relation model, and deducing a calculation formula between object-image point coordinates and external camera orientation elements and a ground coordinate calculation formula of laser point cloud;
in the normal flight process of the unmanned aerial vehicle, the GPS and the RTK record the flight track of the unmanned aerial vehicle in real time, and meanwhile, the image collector and the laser radar acquire image and point cloud data in a transformer substation by utilizing a space automatic scanning technology.
Optionally, the three-dimensional reconstruction of the unknown environment comprises the following steps:
the method comprises the steps that a positioning module is used for receiving point cloud data output by a laser radar in real time, the positioning module comprises a GPS and an RTK, the real-time positioning of the unmanned aerial vehicle in an unknown environment is completed through a specific algorithm by combining with the flight track of the unmanned aerial vehicle, and the output of the positioning module is a three-dimensional laser radar odometer, namely the pose change of the current time relative to the original pose;
performing coloring and adding model textures by using point cloud data output by a laser radar, performing image registration by combining images in the transformer substation, and splicing all the point cloud data by using a coordinate matrix through point cloud splicing to completely reflect the point cloud characteristics of a scanned object;
the method comprises the steps of generating radar point cloud information by fusing point cloud data output by an image collector and a laser radar, combining position information obtained by real-time positioning of the unmanned aerial vehicle, and constructing the point cloud data fused by the radar point cloud information and a sensor by utilizing a calculation formula between object image point coordinates and external camera orientation elements and a ground coordinate calculation formula of the laser point cloud, so as to realize three-dimensional reconstruction of the unmanned aerial vehicle on an unknown environment.
Optionally, the positioning module is used to receive point cloud data output by the laser radar in real time, and the unmanned aerial vehicle is positioned in an unknown environment in real time through a specific algorithm by combining with a flight trajectory of the unmanned aerial vehicle, and the method further includes the following steps:
the unmanned aerial vehicle is identified and early warned according to the danger possibly encountered by the obtained current flight pose, an unmanned aerial vehicle control locking strategy is adopted, and predetermined strategies such as return on the original way, take-off prohibition and landing on the spot are executed, so that the safety of the unmanned aerial vehicle is ensured.
Optionally, the performing route planning based on the result of the three-dimensional reconstruction specifically includes the following steps:
building substation field knowledge by using the point cloud data after three-dimensional reconstruction, and building a formula based on first-order logic;
mapping the identified targets into the examples of the transformer substation field body through an image target automatic identification algorithm, wherein the spatial position relation between the image targets corresponds to the object association attributes among the examples in the field body;
utilizing the identified target mapping to carry out image preprocessing, converting the image into a characteristic vector, selecting a CNN convolutional neural network to carry out characteristic identification and extraction on the characteristic vector of the identified target, and then training an optimal decision tree by constructing a depth algorithm for classification;
mapping the extracted target features to an object attribute association relation between field ontology instances, testing the image by using a decision binary tree, and performing logical reasoning according to the constructed field knowledge so as to perform retrieval;
the method includes the steps that a full-coverage type flight band design method is adopted, an obtained optimal decision tree and a retrieval result are combined, initial polygonal flight band design is achieved, then routing inspection areas are divided based on the initial polygonal flight band, under the condition that the full area can be covered, routing calculation is conducted on the routing inspection areas one by one in the areas, and accurate routing design of a transformer substation scene is achieved.
Optionally, the planning a route based on the result of the three-dimensional reconstruction further includes:
and automatically inspecting the electric unmanned aerial vehicle of the transformer substation, displaying and presenting the result in the one-stop data visualization development platform, and checking whether the result meets the inspection requirement of the transformer substation after the result is finished.
In a second aspect, the invention provides an automatic inspection device for a substation electric unmanned aerial vehicle, which comprises: RTK, GPS, pattern collector and laser radar;
the laser radar is used for carrying out point cloud data acquisition on the transformer substation;
the image collector is used for obtaining images in the transformer substation;
completing three-dimensional reconstruction of an unknown environment by the unmanned aerial vehicle based on the acquired point cloud data, the images in the transformer substation and the real-time position information of the unmanned aerial vehicle; the real-time position information of the unmanned aerial vehicle is obtained by calculating based on output information of an RTK and a GPS;
and planning a route based on a three-dimensional reconstruction result, and controlling the electric unmanned aerial vehicle of the transformer substation to automatically patrol.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides an automatic inspection method and device for a substation electric unmanned aerial vehicle, which are used for realizing full-autonomous inspection of the substation unmanned aerial vehicle without human participation, reducing the operation difficulty of field personnel, liberating operation and maintenance personnel from heavy and tedious conventional inspection work, improving the efficiency of integral operation and improving the automation and intelligentization level of operation and maintenance of a substation.
Drawings
In order that the present disclosure may be more readily and clearly understood, reference is now made to the following detailed description of the present disclosure taken in conjunction with the accompanying drawings, in which:
fig. 1 is a block diagram of an automatic inspection method for a substation electric unmanned aerial vehicle.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the scope of the invention.
The following detailed description of the principles of the invention is provided in connection with the accompanying drawings.
Example 1
The embodiment of the invention provides an automatic inspection method for a substation electric unmanned aerial vehicle, which realizes the full-autonomous inspection of the substation unmanned aerial vehicle without human participation, and as shown in figure 1, the method comprises the following steps:
step 1: according to the body structure of the power patrol unmanned aerial vehicle, calculating the installation position coordinates of a sensor (comprising an RTK (real-time carrier phase difference), a GPS (global positioning system), an image collector (digital camera) and a laser radar) on the unmanned aerial vehicle by adopting an ICP algorithm based on geometrical characteristics, and acquiring the installation position parameters at the coordinate position;
step 2: according to the acquired installation position parameters, performing single-point positioning on each sensor respectively to generate independent coordinate systems;
and step 3: selecting an unmanned aerial vehicle origin as a coordinate system origin, calculating space position coordinates of each sensor according to the installation position coordinates, deducing a transformation relation between the independent coordinate system and the unmanned aerial vehicle origin in the step 2, establishing an object image relation model, and deducing a calculation formula between object image point coordinates and camera exterior orientation elements and a ground coordinate calculation formula of laser point cloud;
and 4, step 4: in the normal flight process of the unmanned aerial vehicle, the GPS and the RTK record the flight track of the unmanned aerial vehicle in real time, and the image collector and the laser radar acquire images and three-dimensional laser radar point cloud data in a transformer substation by utilizing a space automatic scanning technology;
and 5: the positioning module receives laser radar information in real time, the positioning module comprises a GPS and an RTK, the real-time positioning of the unmanned aerial vehicle in an unknown environment is completed through a specific algorithm by combining the flight track of the unmanned aerial vehicle, the input of the positioning module is the three-dimensional laser radar point cloud original data acquired in the step 4, and the output of the positioning module is a three-dimensional laser radar odometer, namely the pose change of the current time relative to the original pose;
step 6: performing coloring and adding model textures by using the three-dimensional laser radar point cloud data, performing image registration by combining the images in the transformer substation acquired in the step 4, splicing all the point cloud data by using a coordinate matrix through point cloud splicing, completely embodying the point cloud characteristics of a scanning object, and deleting noise and redundant point cloud data in a preprocessing stage;
and 7: radar point cloud information with rich textures and higher spatial precision is generated by fusing vision sensor and laser radar original point cloud data, the position information obtained by real-time positioning of the unmanned aerial vehicle in the step 5 is combined, the radar point cloud information and the sensor fused point cloud data are constructed by using two calculation formulas deduced in the step 3, three-dimensional reconstruction of an unknown environment by the unmanned aerial vehicle is realized, and the three-dimensional reconstruction is presented in a one-stop data visualization development platform;
and 8: building substation field knowledge including examples, attribute association and the like by using the point cloud data generated after the three-dimensional reconstruction in the step 7, building a formula based on first-order logic, mapping the identified targets into the examples of the substation field body through an image target automatic identification algorithm, wherein the spatial position relationship between the image targets corresponds to the object association attributes among the examples in the field body, and the space position relationship is used for automatically identifying the digital objects of the electric unmanned aerial vehicle substation;
and step 9: utilizing the target mapping identified in the step 8, firstly carrying out image preprocessing, converting the image into a characteristic vector, selecting a CNN convolutional neural network to carry out characteristic identification and extraction on the characteristic vector of the identified target, and then training an optimal decision tree by constructing a depth algorithm for classification;
step 10: mapping the target features extracted in the step 9 to an object attribute association relation between field ontology instances, testing the image by using a decision binary tree, and performing logical reasoning according to the constructed field knowledge so as to perform retrieval;
step 11: adopting a full-coverage type flight band design method, combining the optimal decision tree obtained in the step 9 and the retrieval result obtained in the step 10 to realize initial polygonal flight band design, then dividing a routing inspection area based on the initial polygonal flight band, and calculating routes one by one in areas under the condition of ensuring that the full area can be covered, so as to realize the accurate route design of a transformer substation scene;
step 12: on the basis of the accurately designed air route, identifying and early warning the danger possibly encountered by the unmanned aerial vehicle according to the current flight pose obtained in the step 5, adopting an unmanned aerial vehicle control locking strategy, and executing a preset strategy such as original return, prohibited take-off and on-site landing to ensure the safety of the unmanned aerial vehicle;
step 13: and (4) deploying an unmanned aerial vehicle at the transformer substation, automatically inspecting the electric unmanned aerial vehicle of the transformer substation according to the air route designed in the step 11, displaying and presenting the result in a one-stop data visualization development platform, checking whether the result meets the inspection requirement of the transformer substation after the result is finished, skipping to the step 4 if the result does not meet the inspection requirement, and finishing inspection if the inspection requirement is met.
In a specific implementation manner of the embodiment of the present invention, the spatial auto-scanning technology refers to: updating the position of the unmanned aerial vehicle by utilizing the surrounding environment, namely acquiring accurate odometer information by extracting the characteristics of the environment and combining an airflow interference resistant scene data acquisition technology and a strong light interference resistant scene data acquisition technology, performing new observation and determining the position information of the unmanned aerial vehicle when the unmanned aerial vehicle moves around, accumulating and superposing the sensor information by means of the accurate odometer information, acquiring original point cloud data, and helping to build a subsequent image;
in a specific implementation manner of the embodiment of the invention, the anti-airflow interference scene data acquisition technology adopts a multi-level wavelet scale decomposition method to perform image denoising on the basis of performing edge contour detection and pixel information fusion processing on an acquired laser radar scanning image, so as to improve the imaging definition of original point cloud data;
in a specific implementation manner of the embodiment of the present invention, the scene data acquisition technology resisting strong light interference calculates spatial three-dimensional coordinates of feature points in a designated area and projections of the feature points on different sub-eye images through spatial geometric association and stereoscopic vision of a plurality of sub-eyes (i.e., a plurality of sensors), and when a certain sub-eye or a part of sub-eyes are strongly interfered by illumination or a background, focuses attention on the designated area for feature extraction through feature extraction results of other sub-eyes and a current viewing angle, so as to improve the imaging definition of original point cloud data;
in a specific implementation manner of the embodiment of the invention, the laser point cloud data preprocessing method utilizes a three-dimensional laser scanner to scan point cloud coloring and add model texture of an object, performs image registration, and splices all point cloud data by a coordinate matrix through point cloud splicing to completely embody point cloud characteristics of the scanned object. Noise and redundant point cloud data are deleted in the preprocessing stage: the obvious in-vitro points can be manually selected and deleted, and the unobvious in-vitro points are screened and deleted by point cloud post-processing software;
in a specific implementation manner of the embodiment of the invention, the substation digital object automatic identification comprises the steps of firstly constructing substation field knowledge and a formula based on first-order logic, mapping an identified target to an example of a substation field body through an image target automatic identification algorithm, wherein a spatial position relation between image targets corresponds to an object association attribute between the examples in the field body, then identifying a specified specific target from visual data of the image, carrying out image preprocessing, converting the image into a feature vector, selecting a CNN convolutional neural network to extract the target to be identified as a feature, obtaining image features by a full link layer, training an optimal (near) decision tree through a construction algorithm to classify the image features, mapping the image features to an object attribute association relation between the examples of the field body after identifying the features of the target, obtaining a binary tree to test the image, digging out and carrying out logical reasoning according to the constructed domain knowledge to obtain a retrieval result;
in a specific implementation manner of the embodiment of the invention, the point cloud feature identification and extraction processing adopts a CNN convolutional neural network method, firstly, single-layer neurons are built layer by layer, a single-layer network is trained each time, weights among other layers except the topmost layer are changed into bidirectional weights, so that the topmost layer is still a single-layer neural network, and other layers are changed into a graph model, then, a wake-sleep algorithm is used for adjusting all weights, so that the cognition and the generation are consistent, the generated topmost layer can recover bottom nodes as much as possible, and the feature extraction is facilitated.
In a specific implementation manner of the embodiment of the invention, the full-coverage type flight band design method is characterized in that a basic mathematical model of unmanned aerial vehicle flight path planning is calculated through three-dimensional reconstructed substation point cloud data, unmanned aerial vehicle body structure and physical characteristics, routing inspection target characteristics and the like, the shortest path problem that the mathematical model meets constraint conditions between two points in a substation space is solved by using an A-x algorithm, and the optimal fitness in all the finally generated shortest paths is selected as the optimal solution of the algorithm by using a genetic algorithm;
in a specific implementation manner of the embodiment of the invention, the unmanned aerial vehicle control locking strategy adopted by the autonomous inspection control of the unmanned aerial vehicle comprises an unmanned aerial vehicle airspace locking strategy, a near-earth locking strategy, a dangerous weather locking strategy and a flight conflict early warning strategy, and on the basis of analyzing the flight path of the unmanned aerial vehicle, the unmanned aerial vehicle is identified and early warned according to the danger possibly encountered by the current flight situation;
in a specific implementation manner of the embodiment of the invention, the one-stop data visualization development platform is adapted to various data sources on the cloud and the cloud, provides abundant and various 2D and 3D visualization components, adopts a dragging type free layout, integrates relevant information of a transformer substation into a data visualization platform with extremely high universality and expansibility through the visualization components, position information visualization, a graphical editing interface and support of various data sources, and rapidly customizes and applies a large data screen.
In conclusion, the invention collects point cloud data of the transformer substation through the laser radar and establishes the high-precision three-dimensional model, so that the route planning function is performed in the established transformer substation three-dimensional model in a more intuitive way, the times of route planning personnel going to the site are reduced, and the efficiency is improved; the spatial position, the shooting distance and the shooting angle of the unmanned aerial vehicle during patrol are more accurately specified by the air route planning based on the three-dimensional model, and the standard of each patrol operation is ensured. According to the method, on the premise that the flight safety of the unmanned aerial vehicle substation is fully guaranteed, the reliability and the practicability of inspection equipment are improved, special inspection such as equipment (building) inspection, infrared temperature measurement, severe weather and dangerous environment inspection is carried out by carrying, hidden dangers and defects such as corrosion, looseness and falling of equipment at high positions such as a substation framework, a lightning rod and a bus are mainly discovered, an equipment inspection system combining intelligent robot (high-definition video) inspection, unmanned aerial vehicle inspection, manual inspection and professional live-line detection is built, the workload of operation and maintenance personnel is reduced, the risk of climbing inspection is reduced, and the inspection quality and the benefit of the equipment are further improved.
Example 2
The embodiment of the invention provides an automatic inspection device for a substation electric unmanned aerial vehicle, which comprises: RTK, GPS, pattern collector and laser radar;
the laser radar is used for carrying out point cloud data acquisition on the transformer substation;
the image collector is used for obtaining images in the transformer substation;
completing three-dimensional reconstruction of an unknown environment by the unmanned aerial vehicle based on the acquired point cloud data, the images in the transformer substation and the real-time position information of the unmanned aerial vehicle; the real-time position information of the unmanned aerial vehicle is obtained by calculating based on output information of an RTK and a GPS;
and planning a route based on a three-dimensional reconstruction result, and controlling the electric unmanned aerial vehicle of the transformer substation to automatically patrol.
The rest of the process was the same as in example 1.
The foregoing shows and describes the general principles and broad features of the present invention and advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (7)
1. The automatic inspection method for the electric unmanned aerial vehicle of the transformer substation is characterized by comprising the following steps of:
carrying out point cloud data acquisition on the transformer substation by using a laser radar;
acquiring images in the transformer substation by using an image acquisition device;
completing three-dimensional reconstruction of an unknown environment by the unmanned aerial vehicle based on the acquired point cloud data, the images in the transformer substation and the real-time position information of the unmanned aerial vehicle;
and planning a route based on a three-dimensional reconstruction result, and controlling the electric unmanned aerial vehicle of the transformer substation to automatically patrol.
2. The automatic inspection method for the electric unmanned aerial vehicle of the transformer substation according to claim 1, wherein point cloud data of the transformer substation is acquired by using a laser radar, and an image in the transformer substation is acquired by using an image acquisition device, and the method specifically comprises the following steps:
according to the structure of the unmanned aerial vehicle, calculating the coordinates of the installation positions of the RTK, the GPS, the image collector and the laser radar on the unmanned aerial vehicle by adopting an ICP algorithm based on geometrical characteristics, and acquiring the parameters of the installation positions at the coordinate positions;
respectively carrying out single-point positioning on the RTK, the GPS, the image collector and the laser radar according to the acquired installation position parameters to generate respective independent coordinate systems;
selecting an unmanned aerial vehicle origin as a coordinate system origin, calculating space position coordinates of RTK, GPS, an image collector and a laser radar according to the installation position coordinates, deducing a transformation relation between each independent coordinate system and the unmanned aerial vehicle origin, establishing an object-image relation model, and deducing a calculation formula between object-image point coordinates and external camera orientation elements and a ground coordinate calculation formula of laser point cloud;
in the normal flight process of the unmanned aerial vehicle, the GPS and the RTK record the flight track of the unmanned aerial vehicle in real time, and meanwhile, the image collector and the laser radar acquire image and point cloud data in a transformer substation by utilizing a space automatic scanning technology.
3. The automatic inspection method for the substation electric unmanned aerial vehicle according to claim 2, characterized in that: the three-dimensional reconstruction of the unknown environment comprises the following steps:
the method comprises the steps that a positioning module is used for receiving point cloud data output by a laser radar in real time, the positioning module comprises a GPS and an RTK, the real-time positioning of the unmanned aerial vehicle in an unknown environment is completed through a specific algorithm by combining with the flight track of the unmanned aerial vehicle, and the output of the positioning module is a three-dimensional laser radar odometer, namely the pose change of the current time relative to the original pose;
performing coloring and adding model textures by using point cloud data output by a laser radar, performing image registration by combining images in the transformer substation, and splicing all the point cloud data by using a coordinate matrix through point cloud splicing to completely reflect the point cloud characteristics of a scanned object;
the method comprises the steps of generating radar point cloud information by fusing point cloud data output by an image collector and a laser radar, combining position information obtained by real-time positioning of the unmanned aerial vehicle, and constructing the point cloud data fused by the radar point cloud information and a sensor by utilizing a calculation formula between object image point coordinates and external camera orientation elements and a ground coordinate calculation formula of the laser point cloud, so as to realize three-dimensional reconstruction of the unmanned aerial vehicle on an unknown environment.
4. The automatic inspection method for the electric unmanned aerial vehicle of the transformer substation according to claim 3, wherein the positioning module is used for receiving point cloud data output by the laser radar in real time, the flying track of the unmanned aerial vehicle is combined, the real-time positioning of the unmanned aerial vehicle in an unknown environment is completed through a specific algorithm, and the method further comprises the following steps:
the unmanned aerial vehicle is identified and early warned according to the danger possibly encountered by the obtained current flight pose, an unmanned aerial vehicle control locking strategy is adopted, and predetermined strategies such as return on the original way, take-off prohibition and landing on the spot are executed, so that the safety of the unmanned aerial vehicle is ensured.
5. The automatic inspection method for the substation electric unmanned aerial vehicle according to claim 3, wherein the air route planning is performed based on the three-dimensional reconstruction result, and the method specifically comprises the following steps:
building substation field knowledge by using the point cloud data after three-dimensional reconstruction, and building a formula based on first-order logic;
mapping the identified targets into the examples of the transformer substation field body through an image target automatic identification algorithm, wherein the spatial position relation between the image targets corresponds to the object association attributes among the examples in the field body;
utilizing the identified target mapping to carry out image preprocessing, converting the image into a characteristic vector, selecting a CNN convolutional neural network to carry out characteristic identification and extraction on the characteristic vector of the identified target, and then training an optimal decision tree by constructing a depth algorithm for classification;
mapping the extracted target features to an object attribute association relation between field ontology instances, testing the image by using a decision binary tree, and performing logical reasoning according to the constructed field knowledge so as to perform retrieval;
the method includes the steps that a full-coverage type flight band design method is adopted, an obtained optimal decision tree and a retrieval result are combined, initial polygonal flight band design is achieved, then routing inspection areas are divided based on the initial polygonal flight band, under the condition that the full area can be covered, routing calculation is conducted on the routing inspection areas one by one in the areas, and accurate routing design of a transformer substation scene is achieved.
6. The automatic inspection method for the substation electric unmanned aerial vehicle according to claim 1, characterized in that: and planning a route based on the three-dimensional reconstruction result, wherein the method further comprises the following steps:
and automatically inspecting the electric unmanned aerial vehicle of the transformer substation, displaying and presenting the result in the one-stop data visualization development platform, and checking whether the result meets the inspection requirement of the transformer substation after the result is finished.
7. The utility model provides an automatic inspection device of electric unmanned aerial vehicle of transformer substation, its characterized in that includes: RTK, GPS, pattern collector and laser radar;
the laser radar is used for carrying out point cloud data acquisition on the transformer substation;
the image collector is used for obtaining images in the transformer substation;
completing three-dimensional reconstruction of an unknown environment by the unmanned aerial vehicle based on the acquired point cloud data, the images in the transformer substation and the real-time position information of the unmanned aerial vehicle; the real-time position information of the unmanned aerial vehicle is obtained by calculating based on output information of an RTK and a GPS;
and planning a route based on a three-dimensional reconstruction result, and controlling the electric unmanned aerial vehicle of the transformer substation to automatically patrol.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111112945.9A CN114092537A (en) | 2021-09-23 | 2021-09-23 | Automatic inspection method and device for electric unmanned aerial vehicle of transformer substation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111112945.9A CN114092537A (en) | 2021-09-23 | 2021-09-23 | Automatic inspection method and device for electric unmanned aerial vehicle of transformer substation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114092537A true CN114092537A (en) | 2022-02-25 |
Family
ID=80296168
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111112945.9A Pending CN114092537A (en) | 2021-09-23 | 2021-09-23 | Automatic inspection method and device for electric unmanned aerial vehicle of transformer substation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114092537A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114781674A (en) * | 2022-06-16 | 2022-07-22 | 深圳市信润富联数字科技有限公司 | Method and device for positioning faults of wind power equipment, storage medium and electronic equipment |
| CN114779679A (en) * | 2022-03-23 | 2022-07-22 | 北京英智数联科技有限公司 | Augmented reality inspection system and method |
| CN114967756A (en) * | 2022-07-07 | 2022-08-30 | 华能盐城大丰新能源发电有限责任公司 | Auxiliary landing method, system and device for offshore wind turbine inspection unmanned aerial vehicle and storage medium |
| CN115562348A (en) * | 2022-11-03 | 2023-01-03 | 国网福建省电力有限公司漳州供电公司 | Unmanned aerial vehicle image technology method based on transformer substation |
| CN115597659A (en) * | 2022-09-21 | 2023-01-13 | 山东锐翊电力工程有限公司（Cn） | Intelligent safety management and control method for transformer substation |
| CN115861849A (en) * | 2022-10-12 | 2023-03-28 | 国网山东省电力公司滨州市沾化区供电公司 | Steel-cast tower climbing protection method and system |
| CN116090838A (en) * | 2023-04-07 | 2023-05-09 | 协筑科技(厦门)有限公司 | Automatic building site system of patrolling and examining based on camera |
| CN116543322A (en) * | 2023-05-17 | 2023-08-04 | 深圳市保臻社区服务科技有限公司 | Intelligent property routing inspection method based on community potential safety hazards |
| CN117499439A (en) * | 2023-11-14 | 2024-02-02 | 北京理工大学前沿技术研究院 | Inspection data processing system and method based on industrial Internet of things |
| CN117557931A (en) * | 2024-01-11 | 2024-02-13 | 速度科技股份有限公司 | Planning method for meter optimal inspection point based on three-dimensional scene |
-
2021
- 2021-09-23 CN CN202111112945.9A patent/CN114092537A/en active Pending
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114779679A (en) * | 2022-03-23 | 2022-07-22 | 北京英智数联科技有限公司 | Augmented reality inspection system and method |
| CN114781674B (en) * | 2022-06-16 | 2022-09-16 | 深圳市信润富联数字科技有限公司 | Method and device for positioning faults of wind power equipment, storage medium and electronic equipment |
| CN114781674A (en) * | 2022-06-16 | 2022-07-22 | 深圳市信润富联数字科技有限公司 | Method and device for positioning faults of wind power equipment, storage medium and electronic equipment |
| CN114967756A (en) * | 2022-07-07 | 2022-08-30 | 华能盐城大丰新能源发电有限责任公司 | Auxiliary landing method, system and device for offshore wind turbine inspection unmanned aerial vehicle and storage medium |
| CN114967756B (en) * | 2022-07-07 | 2024-05-24 | 华能盐城大丰新能源发电有限责任公司 | Auxiliary landing method, system, device and storage medium for unmanned aerial vehicle for marine fan inspection |
| CN115597659B (en) * | 2022-09-21 | 2023-04-14 | 山东锐翊电力工程有限公司 | Intelligent safety management and control method for transformer substation |
| CN115597659A (en) * | 2022-09-21 | 2023-01-13 | 山东锐翊电力工程有限公司（Cn） | Intelligent safety management and control method for transformer substation |
| CN115861849A (en) * | 2022-10-12 | 2023-03-28 | 国网山东省电力公司滨州市沾化区供电公司 | Steel-cast tower climbing protection method and system |
| CN115562348A (en) * | 2022-11-03 | 2023-01-03 | 国网福建省电力有限公司漳州供电公司 | Unmanned aerial vehicle image technology method based on transformer substation |
| CN116090838A (en) * | 2023-04-07 | 2023-05-09 | 协筑科技(厦门)有限公司 | Automatic building site system of patrolling and examining based on camera |
| CN116090838B (en) * | 2023-04-07 | 2023-06-09 | 协筑科技(厦门)有限公司 | Automatic building site system of patrolling and examining based on camera |
| CN116543322A (en) * | 2023-05-17 | 2023-08-04 | 深圳市保臻社区服务科技有限公司 | Intelligent property routing inspection method based on community potential safety hazards |
| CN117499439A (en) * | 2023-11-14 | 2024-02-02 | 北京理工大学前沿技术研究院 | Inspection data processing system and method based on industrial Internet of things |
| CN117557931A (en) * | 2024-01-11 | 2024-02-13 | 速度科技股份有限公司 | Planning method for meter optimal inspection point based on three-dimensional scene |
| CN117557931B (en) * | 2024-01-11 | 2024-04-02 | 速度科技股份有限公司 | Planning method for meter optimal inspection point based on three-dimensional scene |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114092537A (en) | Automatic inspection method and device for electric unmanned aerial vehicle of transformer substation | |
| US11869192B2 (en) | System and method for vegetation modeling using satellite imagery and/or aerial imagery | |
| Jiang et al. | UAV-based 3D reconstruction for hoist site mapping and layout planning in petrochemical construction | |
| Xu et al. | Power line-guided automatic electric transmission line inspection system | |
| CN111597666B (en) | Method for applying BIM to transformer substation construction process | |
| CN110866887A (en) | Target situation fusion sensing method and system based on multiple sensors | |
| CN111537515A (en) | Iron tower bolt defect display method and system based on three-dimensional live-action model | |
| CN112923904B (en) | Geological disaster hidden danger detection method for multi-unmanned aerial vehicle collaborative photogrammetry | |
| CN114240868A (en) | Unmanned aerial vehicle-based inspection analysis system and method | |
| CN110189405B (en) | Live-action three-dimensional modeling method considering building density | |
| WO2024040566A1 (en) | Transformer substation intelligent inspection system and method based on image recognition | |
| CN114898234B (en) | Unmanned aerial vehicle power grid inspection three-dimensional imaging method carrying laser radar thermal imaging technology | |
| CN104091168A (en) | Power line automatic extraction and positioning method based on unmanned aerial vehicle image | |
| CN112650218A (en) | Transformer substation inspection route planning method and device based on collision detection | |
| CN114841944B (en) | Tailing dam surface deformation inspection method based on rail-mounted robot | |
| CN111578861A (en) | Power distribution network tree obstacle detection method and system | |
| Kim et al. | As-is geometric data collection and 3D visualization through the collaboration between UAV and UGV | |
| CN116310891A (en) | Cloud-edge cooperative transmission line defect intelligent detection system and method | |
| CN115909092A (en) | Light-weight power transmission channel hidden danger distance measuring method and hidden danger early warning device | |
| CN117406789A (en) | Automatic planning method for multi-unmanned aerial vehicle bridge support inspection route based on image analysis | |
| Tan et al. | An adaptive crack inspection method for building surface based on BIM, UAV and edge computing | |
| CN113111714A (en) | Risk prevention and control system applied to power transmission field operation | |
| Wang et al. | Target detection for construction machinery based on deep learning and multisource data fusion | |
| Huang et al. | Research and design of space-sky-ground integrated transmission line inspection platform based on artificial intelligence | |
| Ding et al. | Electric power line patrol operation based on vision and laser SLAM fusion perception |
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 |