CN117768626A - Patrol system based on digital twinning - Google Patents

Patrol system based on digital twinning Download PDF

Info

Publication number
CN117768626A
CN117768626A CN202410183785.4A CN202410183785A CN117768626A CN 117768626 A CN117768626 A CN 117768626A CN 202410183785 A CN202410183785 A CN 202410183785A CN 117768626 A CN117768626 A CN 117768626A
Authority
CN
China
Prior art keywords
inspection
image
module
similarity
digital
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
Application number
CN202410183785.4A
Other languages
Chinese (zh)
Inventor
冯继威
高伟明
李彦君
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nets Technology Group Co ltd
Original Assignee
Nets Technology Group Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nets Technology Group Co ltd filed Critical Nets Technology Group Co ltd
Priority to CN202410183785.4A priority Critical patent/CN117768626A/en
Publication of CN117768626A publication Critical patent/CN117768626A/en
Pending legal-status Critical Current

Links

Landscapes

  • Image Processing (AREA)

Abstract

The invention discloses a patrol system based on digital twinning, which is designed by the technical scheme that: the system comprises an inspection module, an analysis module and a digital twin platform; the inspection module is used for performing aerial inspection on different positions of the inspection site by using the unmanned aerial vehicle to obtain inspection images of the different positions of the inspection site; the analysis module is used for storing the inspection image and identifying whether the current inspection image is a repeated image or not, and eliminating the repeated image; the digital twin platform is used for inputting the inspection image, presetting the inspection path and presetting the scheme, constructing an inspection simulation scene to present the inspection process and outputting an inspection report.

Description

Patrol system based on digital twinning
Technical Field
The invention belongs to the field of inspection management, and particularly relates to an inspection system based on digital twinning.
Background
The digital twin technology can integrate a plurality of information technologies together, and the virtual mapping effect of physical entities is greatly improved by utilizing the virtual-real interaction technology, so that the existing digital twin technology is already an booster for the development of intellectualization, informatization and digitalization in various industries.
With the development of technology, in the field inspection, a digital twin technology is gradually used, the inspection data and the sensor state are simulated in real time, the inspection process is visually presented, the inspection process is monitored by a manager, the existing inspection system technology generally utilizes an unmanned aerial vehicle to carry out aerial photographing and data acquisition, the inspection data is input to construct a digital twin model of the inspection process for simulation, and then the inspection process is safely monitored or task arrangement is carried out; for the inspection data which needs to be input for constructing the digital twin model, a plurality of unmanned aerial vehicles are often used for cooperatively acquiring, and the plurality of unmanned aerial vehicles are used for inspecting and acquiring the same inspection data, for example, when two unmanned aerial vehicles which come and go meet, the same inspection data can be acquired, or the plurality of unmanned aerial vehicles are used for acquiring at the same position in a smaller time interval, so that a large amount of redundant data exists in the input inspection data, the subsequent analog data is huge, and the monitoring efficiency is influenced.
Disclosure of Invention
In view of the above-mentioned drawbacks of the prior art, the present invention proposes a digital twinning-based inspection system, and the technical scheme of the present invention includes:
the system comprises an inspection module, an analysis module and a digital twin platform;
the inspection module is used for performing aerial inspection on different positions of the inspection site by using the unmanned aerial vehicle to obtain inspection images of the different positions of the inspection site;
the analysis module is used for storing the inspection image and identifying whether the current inspection image is a repeated image or not, and eliminating the repeated image;
the digital twin platform is used for inputting inspection images, preset inspection paths and preset schemes, constructing an inspection simulation scene, presenting an inspection process and outputting inspection reports.
Preferably, the system further comprises a transmission module;
the transmission module is used for transmitting information among the inspection module, the analysis module and the digital twin platform through an aeroMACS wireless technology.
Preferably, the identifying whether the current inspection image is a repeated image includes:
and positioning the inspection image to output a position characteristic, calculating the similarity between the currently acquired inspection image and the stored image according to the position characteristic information, and identifying whether the current inspection image is a repeated image according to the similarity.
Preferably, the outputting the position feature by positioning the inspection image includes:
presetting a coordinate system, inputting the inspection image into a 3DPatMaxTool tool, selecting positions of a plurality of reference points of the inspection image in the preset coordinate system, and outputting position features of two-dimensional coordinates and/or three-dimensional coordinates of the plurality of reference points.
Preferably, the outputting the position features of the two-dimensional coordinates and/or the three-dimensional coordinates of the plurality of reference points includes:
the preset coordinate system for outputting the two-dimensional coordinates of the plurality of reference points is a two-dimensional coordinate system;
and the preset coordinate system for outputting the three-dimensional coordinates of the plurality of reference points is a three-dimensional coordinate system.
Preferably, the formula for calculating the similarity between the currently acquired inspection image and the stored image is as follows:
in the method, in the process of the invention,for similarity, n is the number of location features,as the ith position feature of the current inspection image,is the ith position feature of the stored inspection image.
Preferably, the identifying whether the current inspection image is a repeated image according to the similarity comprises:
setting a similarity threshold interval and a constraint time threshold, and judging that the current inspection image is a repeated image when the similarity of the images is in the similarity threshold interval and the difference between the acquisition time of the current inspection image and the acquisition time of the stored images is smaller than the constraint time threshold.
Preferably, the digital twin platform is further used for presenting a patrol process by constructing a patrol simulation scene, simulating simulation patrol of the unmanned aerial vehicle, optimizing a patrol path and sending a command for optimizing the patrol path to the patrol module.
Preferably, the digital twin platform comprises a security monitoring module;
the safety monitoring module is used for comprehensively judging according to the inspection report and against a preset scheme, judging whether potential safety hazards exist or not, recording the judging result, giving an alarm for the abnormal phenomenon and pushing the judging result to an administrator.
The beneficial effects are that: according to the invention, the unmanned aerial vehicle in the inspection module is utilized to collect inspection data, the analysis module is utilized to screen out repeated inspection data, finally, the digital twin platform is input for presenting the inspection process and outputting an inspection report, the digital twin technology is utilized to simulate the inspection data and the unmanned aerial vehicle, the inspection process is intuitively presented, the monitoring of a manager on the inspection process is enhanced, the problem that a large amount of redundant data exists in the inspection data before the digital twin platform is input is solved, and the simulation efficiency is improved.
Drawings
FIG. 1 is a schematic diagram of a system architecture according to a preferred embodiment of the present invention;
FIG. 2 is a first curve optimization schematic of a preferred embodiment of the present invention;
FIG. 3 is a second curve optimization schematic of a preferred embodiment of the present invention.
Detailed Description
The following examples of the present invention are described in detail, and are given by way of illustration of the present invention, but the scope of the present invention is not limited to the following examples.
The invention designs a patrol system based on digital twinning, as shown in fig. 1, the technical scheme specifically comprises:
the system comprises an inspection module, an analysis module and a digital twin platform;
the inspection module is used for performing aerial inspection on different positions of the inspection site by using the unmanned aerial vehicle to obtain inspection images of the different positions of the inspection site;
the analysis module is used for storing the inspection image and identifying whether the current inspection image is a repeated image or not, and eliminating the repeated image;
the digital twin platform is used for inputting an inspection image, a preset inspection path and a preset scheme, constructing an inspection simulation scene, presenting an inspection process and outputting an inspection report.
Specifically, the unmanned aerial vehicle is patrol along a straight line of a patrol path, and the uniform speed flying speed is 15 km/h; in addition, in the digital twin platform, the virtual scene is used as an important component of the digital twin platform to realize the mapping of the real inspection condition, and in order to realize the visual presentation of the virtual environment, the invention adopts Unity engine software to realize the scene construction, and comprises the steps of carrying out characteristic modeling on inspection process data, carrying out optimization improvement and light weight treatment on the model through 3dMax software, and finally carrying out rendering and material optimization on the model to improve the sense of realism of the inspection process model.
Preferably, the system further comprises a transmission module;
the transmission module is used for carrying out information transmission among the inspection module, the analysis module and the digital twin platform through an aeroMACS wireless technology.
Specifically, because AeroMACS has a lower time delay compared with 4G wireless technology, the time delay reaches between 0.5 ms and 20ms, and the time delay of 4G wireless technology generally reaches more than 20 ms; although the 5G time delay and the aeroMACS time delay are lower, the aeroMACS is a civil aviation special network, and the safety and the reliability are higher, so that the aeroMACS wireless technology is selected for transmission, the processing time of the digital twin scene platform is effectively improved, the twin scene is more attached to the field scene, and the accuracy of an emergency scheme and the real-time performance of prediction and early warning are improved.
Preferably, identifying whether the current inspection image is a duplicate image comprises:
and positioning the inspection image to output a position characteristic, calculating the similarity between the currently acquired inspection image and the stored image according to the position characteristic information, and identifying whether the current inspection image is a repeated image according to the similarity.
Preferably, the positioning operation for the inspection image outputs a position feature including:
and presetting a coordinate system, inputting the inspection image into a 3DPatMaxTool tool, selecting positions of a plurality of reference points of the inspection image in the preset coordinate system, and outputting the two-dimensional coordinates and/or the position characteristics of the three-dimensional coordinates of the plurality of reference points.
Preferably, outputting the position features of the two-dimensional coordinates and/or the three-dimensional coordinates of the plurality of reference points includes:
outputting a preset coordinate system of two-dimensional coordinates of a plurality of reference points as a two-dimensional coordinate system;
the preset coordinate system for outputting the three-dimensional coordinates of the plurality of reference points is a three-dimensional coordinate system.
Specifically, as the acquired image is a two-dimensional inspection image, when three-dimensional coordinates are required to be output, the two-dimensional image is converted into a three-dimensional point cloud image, and a coordinate system is reconstructed, so that different inspection requirements are met; the preset reference coordinate system can cover the whole inspection site by taking the unmanned aerial vehicle outgoing point as the preset coordinate system, and based on whether the image position characteristic information which can be selectively output by the inspection requirement manager is a two-dimensional or three-dimensional image, the invention can record four points of the upper left, the upper right, the lower left and the lower right of the image and respectively output the position characteristic information of the four points.
Preferably, a similarity formula of the currently acquired inspection image and the stored image is calculated as follows:
in the method, in the process of the invention,for similarity, n is the number of location features,as the ith position feature of the current inspection image,is the ith position feature of the stored inspection image.
Preferably, identifying whether the current inspection image is a duplicate image according to the similarity size includes:
setting a similarity threshold interval and a constraint time threshold, and judging that the current inspection image is a repeated image when the similarity of the images is in the similarity threshold interval and the difference between the acquisition time of the current inspection image and the acquisition time of the stored images is smaller than the constraint time threshold.
Specifically, the similarity between the current inspection image and the stored images is calculated by adopting the method, the current inspection image acquired in real time can be effectively identified and removed, redundant data is effectively reduced by removing repeated images, in addition, for an area needing to be inspected back and forth, when the advancing unmanned aerial vehicle and the reciprocating unmanned aerial vehicle acquire the same images, the image position features are inverted, so that when the similarity between the two images is calculated by using the traditional cosine function, the same images are generated and abnormal similarity is output, the similarity is calculated by adopting the formula, and when the situation occurs, half of the original similarity can still be output, or the image position features are partially inverted due to shaking of the unmanned aerial vehicle, the error of the formula can be reduced to the greatest extent, and the accuracy of the similarity between the images is improved.
Preferably, the digital twin platform is further used for presenting a patrol process by constructing a patrol simulation scene, simulating simulation patrol of the unmanned aerial vehicle, optimizing a patrol path and sending a command for optimizing the patrol path to the patrol module.
Specifically, when the inspection path is determined to be a repeated image, a rectangular coordinate area is built by taking the current unmanned aerial vehicle position as the center to be marked as a repeated area, the marked repeated area is reserved to a preset time, the preset time is used as an inspection area again, and the unmanned aerial vehicle inspection path is re-optimized based on the repeated area, and the method comprises the following steps:
s10: the initial inspection path of the unmanned aerial vehicle comprises a plurality of path points which are connected with the current unmanned aerial vehicle and the next path point;
s20: judging whether the connecting line breaks into the repeated area, when the connecting line breaks into the repeated area, rejecting the current next path point, sequentially connecting the unmanned plane, the break-in point, the repeated area end point and the break-out point to be used as new connecting lines, wherein the break-out point is used as a new next path point, otherwise, the original connecting line and the next path point are kept;
s30: the unmanned aerial vehicle carries out inspection operation along the connecting line to the next path point;
s40: steps S10-S30 are repeated until the last route point is reached.
Specifically, the steps re-optimize the inspection route of the unmanned aerial vehicle, avoid the repeated area to inspect the non-repeated area, additionally supplement other inspection data, enable the inspection result to be more complete, avoid generating more redundant inspection data, and improve the inspection operation efficiency of the unmanned aerial vehicle.
In addition, in step S20, the end points of the repeated area are one or two end points of the coordinate rectangular chart of the repeated area, and the end points of the coordinate rectangular chart of the path are used as the end points of the repeated area based on the shortest path between the break-in point and the break-out point according to the boundary of the coordinate rectangular chart connected between the break-in point and the break-out point;
step S20 further includes performing curve optimization on the new connection line, including:
as shown in fig. 2, when the number of the repeated area end points is two, the first curve optimization formula is as follows:
in the method, in the process of the invention,is a curve inspection route of two end points,andfor the break-in point and the break-out point,is the peak of a preset curve, t is an adjustment parameter,andis thatAndan approximate point of the two-dimensional space,andis thatAndapproximate points between;
as shown in fig. 3, when the end point of the repetition area is one, the second curve optimization formula is as follows:
in the method, in the process of the invention,a curve as one end pointThe line inspection route is adopted to carry out line inspection,andis thatAndapproximate points between;
specifically, as the new connecting line needs to avoid the repeated area, a plurality of deflection angles are usually generated, and the inspection angle of the unmanned aerial vehicle is suddenly changed, a plurality of inflection points in the inspection route are converted into curves, so that the unmanned aerial vehicle is prevented from rollover, overturning and other conditions in the optimized inspection route, the movement route is smoother, and the quality and effect of the inspection task are improved; in the first curve optimization formula, the repeated area end points comprise a first repeated area end point and a second repeated end point, a curve top point is arranged between the two end points, and a tangent line of the curve passes through the break-in point and the break-out point to form a curve inspection route, wherein in the process ofAndsetting two approximate pointsAnda half of the curve inspection route is formed inAndtwo approximate points are arranged betweenAndthe other half of the curve inspection route is formed, and the value range of the adjustment parameter t isThe method is used for adjusting the specific shape of the curve inspection route; in the second curve optimization formula, since there is only one repeated area end point, it is only necessary to construct a curve inspection route for the break-in point and the break-out point, and the curve inspection route will be usedAndand adjusting parameters to be as close to the end point of the repeated area as possible, and converting the linear inspection route into a curve inspection route.
In addition, the deflection angle can also be generated when the unmanned aerial vehicle passes through the break-in point and the break-out point, for example, a first control point is arranged at a position which does not reach the break-in point on the original path, a second control point is arranged at a position between the break-in point and an endpoint of an adjacent repeated area, a curve route is constructed by arranging two similar points between the first control point and the second control point, the curve route is adjusted as close to the break-in point as possible, the unmanned aerial vehicle is approximately passed through the break-in point, and otherwise, the second curve optimization processing is also performed before the unmanned aerial vehicle passes through the break-out point.
Preferably, the digital twin platform comprises a security monitoring module;
the safety monitoring module is used for comprehensively judging according to the inspection report and against a preset scheme, judging whether potential safety hazards exist or not, recording the judging result, giving an alarm for the abnormal phenomenon and pushing the judging result to an administrator.
The foregoing describes in detail preferred embodiments of the present invention. It should be understood that numerous modifications and variations can be made in accordance with the concepts of the invention without requiring creative effort by one of ordinary skill in the art. Therefore, all technical solutions which can be obtained by logic analysis, reasoning or limited experiments based on the prior art by a person skilled in the art according to the inventive concept shall be within the scope of protection defined by the claims.

Claims (8)

1. A digital twinning-based inspection system, comprising:
the system comprises an inspection module, an analysis module and a digital twin platform;
the inspection module is used for performing aerial inspection on different positions of the inspection site by using the unmanned aerial vehicle to obtain inspection images of the different positions of the inspection site;
the analysis module is used for storing the inspection image and identifying whether the current inspection image is a repeated image or not, and eliminating the repeated image;
the digital twin platform is used for inputting a patrol image, a preset patrol path and a preset scheme, constructing a patrol simulation scene, presenting a patrol process and outputting a patrol report;
the identifying whether the current inspection image is a repeated image comprises:
and positioning the inspection image to output a position characteristic, calculating the similarity between the currently acquired inspection image and the stored image according to the position characteristic information, and identifying whether the current inspection image is a repeated image according to the similarity.
2. A digital twinning-based inspection system according to claim 1, further comprising a transmission module;
the transmission module is used for transmitting information among the inspection module, the analysis module and the digital twin platform through an aeroMACS wireless technology.
3. The digital twinning-based inspection system of claim 1, wherein the locating the inspection image to output the location feature comprises:
presetting a coordinate system, inputting the inspection image into a 3DPatMaxTool tool, selecting positions of a plurality of reference points of the inspection image in the preset coordinate system, and outputting position features of two-dimensional coordinates and/or three-dimensional coordinates of the plurality of reference points.
4. A digital twinning-based inspection system in accordance with claim 3, wherein outputting the position characteristics of the two-dimensional coordinates and/or the three-dimensional coordinates of the plurality of reference points comprises:
the preset coordinate system for outputting the two-dimensional coordinates of the plurality of reference points is a two-dimensional coordinate system;
and the preset coordinate system for outputting the three-dimensional coordinates of the plurality of reference points is a three-dimensional coordinate system.
5. The digital twinning-based inspection system of claim 1, wherein the similarity formula for calculating the currently acquired inspection image and the stored image is as follows:
,
in the method, in the process of the invention,for similarity, n is the number of position features, +.>For the ith position feature of the current inspection image, -/-, for example>Is the ith position feature of the stored inspection image.
6. The digital twinning-based inspection system of claim 1, wherein the identifying whether the current inspection image is a duplicate image based on a similarity size comprises:
setting a similarity threshold interval and a constraint time threshold, and judging that the current inspection image is a repeated image when the similarity of the images is in the similarity threshold interval and the difference between the acquisition time of the current inspection image and the acquisition time of the stored images is smaller than the constraint time threshold.
7. The digital twin based inspection system according to claim 1, wherein the digital twin platform is further configured to present an inspection process by constructing an inspection simulation scene, simulate an inspection simulation of the unmanned aerial vehicle, optimize an inspection path, and send an optimized inspection path command to the inspection module.
8. A digital twinning-based inspection system in accordance with claim 1, wherein the digital twinning platform comprises a security monitoring module;
the safety monitoring module is used for comprehensively judging according to the inspection report and against a preset scheme, judging whether potential safety hazards exist or not, recording the judging result, giving an alarm for the abnormal phenomenon and pushing the judging result to an administrator.
CN202410183785.4A 2024-02-19 2024-02-19 Patrol system based on digital twinning Pending CN117768626A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410183785.4A CN117768626A (en) 2024-02-19 2024-02-19 Patrol system based on digital twinning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410183785.4A CN117768626A (en) 2024-02-19 2024-02-19 Patrol system based on digital twinning

Publications (1)

Publication Number Publication Date
CN117768626A true CN117768626A (en) 2024-03-26

Family

ID=90325992

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410183785.4A Pending CN117768626A (en) 2024-02-19 2024-02-19 Patrol system based on digital twinning

Country Status (1)

Country Link
CN (1) CN117768626A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220207217A1 (en) * 2020-12-31 2022-06-30 Electronics And Telecommunications Research Institute Method and system for real-time simulation using digital twin agent
CN115205712A (en) * 2022-04-07 2022-10-18 国网信息通信产业集团有限公司 Unmanned aerial vehicle inspection image quick duplicate checking method and system based on twin network
CN115935610A (en) * 2022-11-15 2023-04-07 国网浙江省电力有限公司湖州供电公司 Method and system for optimizing routing inspection strategy of unmanned aerial vehicle on overhead line
CN116231504A (en) * 2022-12-09 2023-06-06 华电新疆发电有限公司新能源分公司 Remote intelligent inspection method, device and system for booster station
CN117041311A (en) * 2023-09-12 2023-11-10 鑫达物管(北京)科技有限公司 Intelligent inspection method and device based on digital twinning

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220207217A1 (en) * 2020-12-31 2022-06-30 Electronics And Telecommunications Research Institute Method and system for real-time simulation using digital twin agent
CN115205712A (en) * 2022-04-07 2022-10-18 国网信息通信产业集团有限公司 Unmanned aerial vehicle inspection image quick duplicate checking method and system based on twin network
CN115935610A (en) * 2022-11-15 2023-04-07 国网浙江省电力有限公司湖州供电公司 Method and system for optimizing routing inspection strategy of unmanned aerial vehicle on overhead line
CN116231504A (en) * 2022-12-09 2023-06-06 华电新疆发电有限公司新能源分公司 Remote intelligent inspection method, device and system for booster station
CN117041311A (en) * 2023-09-12 2023-11-10 鑫达物管(北京)科技有限公司 Intelligent inspection method and device based on digital twinning

Similar Documents

Publication Publication Date Title
CN111832655B (en) Multi-scale three-dimensional target detection method based on characteristic pyramid network
US11922569B2 (en) Generating realistic point clouds
CN111409788B (en) Unmanned ship autonomous navigation capability testing method and system
KR20210078530A (en) Lane property detection method, device, electronic device and readable storage medium
CN102663921A (en) Multi-channel and multi-screen three dimensional immersion simulation system of ship steering and operation
CN114584571B (en) Space calculation technology-based digital twin synchronous communication method for power grid station
CN112528508B (en) Electromagnetic visualization method and device
CN114758337B (en) Semantic instance reconstruction method, device, equipment and medium
KR101405891B1 (en) Reality display system of air inteligence and method thereof
JP2022028870A (en) Lane detection method, apparatus, electronic device, storage medium, and vehicle
US20210209385A1 (en) Method and apparatus for recognizing wearing state of safety belt
CN117351521B (en) Digital twinning-based power transmission line bird detection method, system, medium and equipment
CN115082254A (en) Lean control digital twin system of transformer substation
CN115291515A (en) Automatic driving simulation test system and evaluation method based on digital twinning
CN112991537A (en) City scene reconstruction method and device, computer equipment and storage medium
CN113887318A (en) Embedded power violation detection method and system based on edge calculation
CN102521885B (en) Method for displaying monitoring data of power grid and device
CN111710041A (en) System based on multi-source heterogeneous data fusion display technology and environment simulation method
CN113673171B (en) Docking mechanism digital twin test system based on historical data driving and machine learning and operation method thereof
US11348261B2 (en) Method for processing three-dimensional point cloud data
CN117392328A (en) Three-dimensional live-action modeling method and system based on unmanned aerial vehicle cluster
CN117768626A (en) Patrol system based on digital twinning
CN111951404A (en) Ship control method, system, device and storage medium
CN116089261A (en) Ground verification system and method for helicopter low-altitude mission planning
CN115457411A (en) Unmanned inspection method and device for aviation oil pipeline and aviation oil safe operation and maintenance system

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