CN108845584A - A kind of anti-unmanned plane retrospect burst gaseous contamination source method of wind based on LS-SVM control - Google Patents
A kind of anti-unmanned plane retrospect burst gaseous contamination source method of wind based on LS-SVM control Download PDFInfo
- Publication number
- CN108845584A CN108845584A CN201811035125.2A CN201811035125A CN108845584A CN 108845584 A CN108845584 A CN 108845584A CN 201811035125 A CN201811035125 A CN 201811035125A CN 108845584 A CN108845584 A CN 108845584A
- Authority
- CN
- China
- Prior art keywords
- point
- unmanned plane
- concentration
- highest
- control
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000011109 contamination Methods 0.000 title claims abstract description 20
- 238000012549 training Methods 0.000 claims description 9
- 238000009795 derivation Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 3
- 238000011161 development Methods 0.000 abstract description 2
- 230000000246 remedial effect Effects 0.000 abstract description 2
- 239000007789 gas Substances 0.000 description 28
- 238000005070 sampling Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 238000011835 investigation Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000013475 authorization Methods 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003331 infrared imaging Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 231100000331 toxic Toxicity 0.000 description 1
- 230000002588 toxic effect Effects 0.000 description 1
- 239000002341 toxic gas Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/08—Control of attitude, i.e. control of roll, pitch, or yaw
- G05D1/0808—Control of attitude, i.e. control of roll, pitch, or yaw specially adapted for aircraft
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a kind of methods in the anti-unmanned plane retrospect burst gaseous contamination source of wind based on LS-SVM control.The present invention is directed to overcome prior art Shortcomings, a kind of method of mobile flight retrospect pollution sources for tilting funnel track is proposed, inclination funnel Trajectory Tracking Control is carried out to unmanned plane using LS-SVM, and consider wind disturbing factor.The present invention is when tracing unknown pollution sources, due to consideration that gaseous contamination disturbs direct special relationship with air-dried, unmanned plane stops ten minutes after successfully tracing back to pollution sources and is taken pictures, sampled, flying quality is initialized later, circulation carries out pollution sources retrospect again, improves the accuracy positioned to pollution sources and anti-interference ability.The present invention can timely and effectively trace pollution sources, and to the evidence obtaining that timely sampled and taken pictures at pollution sources, convenient for environment supervision, the subsequent remedial efforts of personnel's development are administered, prevent pollution sources from expanding, while also the pollution fix duty for after provides strong evidence.
Description
Technical field
The invention belongs to automatically control track following technical field, and in particular to one kind is there are wind disturbance, nothing
The man-machine method that pollution sources are checked.
Background technique
After reform and opening-up, domestic large quantities of industrial enterprises are developed rapidly, and other polluting emissions fix duty problem has become
One of the environmental issue that many areas are primarily upon.
Traditional atmospheric monitoring method is mostly fixed point monitoring sampling, artificial sample etc., then the big destiny that sampling is obtained
It is believed that breath, which is transmitted to laboratory, carries out data analysis.It is sudden in view of gaseous contamination situation, it cannot predict its scene,
Therefore monitoring device is unlikely installed at pollution sources in advance, fixed point monitoring sampling obviously cannot acquire gaseous contamination source in time
Locate real-time, specific, accurate data cases.Likewise, artificial sample mode, it is contemplated that traffic is unfavorable, safety etc. at pollution sources
Unfavorable factor cannot equally accomplish real-time, specific, accurate monitoring when manually obtaining sample information at gaseous contamination source.No
The information that burst gaseous contamination area can be obtained in time, so that staff is difficult to obtain the accurate feelings of pollution in a short time
Condition, including pollution concrete type, pollution sources place etc., this, which has resulted in staff, to formulate in time suddenly accident
Emergency measure, cause a degree of pollution to expand.
Quadrotor drone is the technology quickly grown in recent years, and structure is relatively easy, and action is flexible, price
Rationally.It can overcome rough sledding caused by traffic, part landform, can also overcome the dangerous feelings such as toxic gas, gas burst
Condition quickly flies to pollution the area progress field investigation that happens suddenly, and carries out pollution sources retrospect, data sampling, the work such as evidence obtaining of taking pictures.It is right
Sudden gaseous contamination event is accomplished to monitor in real time, timely be handled, and can also provide effectively for subsequent disposal of pollutants fix duty
Evidence.
In existing research, there is the quadrotor drone controlling party of many reply gaseous contaminations, pollution sources retrospect
Method, but these methods remain unchanged in place of coming with some shortcomings, and need to carry out further R&D work.For example, Authorization Notice No. is
The patent of invention of CN107132313A, a kind of method and pollution sources Check System of unmanned plane investigation pollution sources, which describe
A kind of unmanned plane pollution sources investigation method of hexagon flight.It include that unmanned plane is one in horizontal plane flight path in its step
A regular hexagon tests six apex angle polluted gas concentration of hexagon, judges unmanned plane during flying side according to hexagon vertex concentration
To carry out pollution sources retrospect.But not the case where in this approach, not accounting for wind disturbance, and be at one in height
Position control unmanned plane, which vertically flies, carries out polluted gas Concentration Testing.
For example, Authorization Notice No. is the patent of invention of CN 106896145A, a kind of toxic and harmful gas unmanned plane detection system
System and detection method teach the polluted gas detection system and method for a kind of regulation detection starting point and terminal, this method
The data sampling at known pollution sources only is carried out using unmanned plane, still needs to carry out just to can determine that tool after data analysis
Body pollution source position.
Summary of the invention
The technical problem to be solved by the present invention is to：
A kind of method for proposing unmanned plane retrospect burst gaseous contamination source for overcoming wind disturbance.
The present invention uses following technical scheme to solve above-mentioned technical problem：
A method of the anti-unmanned plane retrospect burst gaseous contamination source of wind based on LS-SVM control, the method includes such as
Lower step：
(1) control unmanned plane flies into Polluted area；
(2) vertex A point, B point, D point, C point and the midpoint E of unmanned plane during flying track are determined, wherein A point, B point, D point, C point
In the same plane, the vertex of square is formed, so that distance AB=BC=DC=AD, midpoint E are handed in the square diagonal line
At crunode, record E point position, AB point distance and flight plane and horizontal plane angle theta, and will be at the beginning of at A point, B point, D point, C point
Beginning polluted gas concentration is disposed as zero, and record highest point concentration is zero；
(3) control unmanned plane flies according to inclination infundibulate flight path E → A → B → D → C → E, successively measures A point, B
Point, D point, C point pollution gas concentration are hovered at E point after unmanned plane completes primary inclination infundibulate flight；
(4) compare four vertex polluted gas concentration, determine polluted gas highest point, by the highest point concentration and record
Highest point concentration is compared, and remembers the highest point concentration if the highest point concentration that the highest point concentration is greater than or equal to record
Record is new highest point concentration and carries out step (5), carries out step if the highest point concentration is lower than the highest point concentration of record
(6)；
(5) with from E point to the direction of polluted gas concentration highest point for heading next time, flight AC length distance,
New E point is reached, new E point position is recorded, by by former vertex A point, B point, D point, C point translational length on this heading
AC determines new vertex A point, B point, D point, C point, repeats step (3) to (4)；
(6) make the E point of unmanned plane return recording, check whether θ is less than predetermined angle, if it is not, reducing flight plane and water
The angle theta of plane determines new vertex A point, B point, D point, C point according to the angle of AB point distance and flight plane and horizontal plane,
Repeat step (3) to (4)；If θ is less than predetermined angle, (7) are entered step；
(7) with from E point to polluted gas concentration highest point, for heading next time, flight AC length distance is reached new
E point, record new E point position, pass through by former vertex A point, B point, D point, C point on this heading translational length AC determine
New vertex A point, B point, D point, C point；
(8) control unmanned plane flies according to track E → A → B → D → C → E, successively measures A point, B point, D point, C point pollution
Gas concentration is hovered at E point after unmanned plane completes primary inclination infundibulate flight；
(9) compare four vertex polluted gas concentration, determine polluted gas highest point, by the highest point concentration and record
Highest point concentration is compared, and remembers the highest point concentration if the highest point concentration that the highest point concentration is greater than or equal to record
Record is new highest point concentration and carries out step (7), carries out step if the highest point concentration is lower than the highest point concentration of record
(10)；
(10) make the E point of unmanned plane return recording, check whether AB is less than preset length, if it is not, by AB Distance Shortened, root
New vertex A point, B point, D point, C point are determined according to the angle of AB point distance and flight plane and horizontal plane, repeat step (8) extremely
(9)；If AB is less than preset length, (11) are entered step；
(11) so that unmanned plane is hovered, take pictures and sample to pollution sources, pass the data information of acquisition back ground command center；
(12) θ and AB are redefined using unmanned plane hovering point as E point after the predetermined time, enters step (2)；
In all of above step, track following control is carried out to unmanned plane using least square method supporting vector machine LS-SVM
System.
Preferably, it is described use least square method supporting vector machine LS-SVM to unmanned plane carry out Trajectory Tracking Control include with
Lower step：
(2a) provides drive control power according to the motor on four vertex of cross, respectively in unmanned plane starting point and geometry
The heart defines inertial coodinate system and body coordinate system, and vector (x, y, z) indicates position coordinates of the unmanned plane in inertial coodinate system, to
AmountIt indicates the posture coordinate of unmanned plane in the body coordinate system, unmanned plane is established according to the kinetic model of unmanned plane
Six degree of freedom wind interference model；
(2b) defines Attitude Tracking errorPosition tracking error E(x,y,z)；
(2c) is solved by dynamical equation ek+1=f (ek,uk), k=1,2,3 ..., N, the minimum problems of limitationWherein
ekIndicate the posture and position tracking error between the actual path and desired trajectory at k moment, ukFor the control amount at k moment, Qf,
Q, R are constant, weightMappingC is constant, and ξ is mistake of the training data to SVM optimal hyperlane
Difference, LS-SVM optimal separating hyper plane are uk=wTL(ek)+ξk；
(2d) constructs Lagrangian to the minimum problems in (2c),
, to variable ek,eN+1,uk,w,ξk,λk,akSuccessively derivation, to solveWherein elFor training data, λkWith ak
It is Lagrange multiplier, solves training data elAfterwards, as the supporting vector data in control law；
(2e) uses RBF kernel functionDuring (2d) derivation,
Obtain ξ=ak/ c, ignores ξ, obtains optimal control law and is
Preferably, the predetermined time described in step (12) is ten minutes.
Preferably, predetermined angle described in step (6) is 3o.
Preferably, preset length described in step (10) is 3 meters.
The invention adopts the above technical scheme compared with prior art, has the following technical effects：
Can air-dry disturb in the case where, unknown pollution sources are timely and effectively traced, at pollution sources progress and
When sampling and take pictures evidence obtaining, convenient for environment supervision, administer the subsequent remedial efforts of personnel's development, prevent pollution sources from expanding, simultaneously
Also the pollution fix duty for after provides strong evidence.
Detailed description of the invention
Fig. 1 is the anti-unmanned plane pollution sources traceability system block diagram of wind.
Fig. 2 is unmanned plane tracking pollution sources funnel flight path figure.
Fig. 3 is the system block diagram based on tracking controller.
Specific embodiment
Technical solution of the present invention is described in further detail with reference to the accompanying drawing：
The invention proposes a kind of methods in the anti-unmanned plane retrospect burst gaseous contamination source of wind based on LS-SVM control.Nothing
Including ultrasonic wave module, high definition zoom camera, thermal infrared imaging module, gas detection module in man-machine, as shown in Figure 1.Wherein,
Unmanned plane allows unmanned plane to avoid aerial barrage object in flight course by ultrasonic wave module；High definition zoom camera is used for
Reply burst pollution on daytime situation acquires its geography information and collects evidence to taking pictures at pollution sources；Thermal infrared imaging module is used
In cope with night burst pollution the case where, unmanned plane can still carry out geographical information collection to it and photo is collected evidence；Gas inspection
Surveying module includes all kinds of gas sensors, for measuring the inflammable and explosive harmful gas concentration of contaminated areas.
It after unmanned plane flies into Polluted area, flies, and is flying according to the funnel shaped track for being angled θ with horizontal plane shape
4 grab samplings of row, judge next heading according to grab sampling concentration.Simultaneously using LS-SVM (least square support to
Amount machine) Trajectory Tracking Control is carried out to unmanned plane, thus achieve the purpose that pollution sources trace, the tool of one embodiment of the present of invention
Body step includes as follows：
(1) control unmanned plane flies into Polluted area；
(1a) substantially determines pollution direction, by the distribution of obstacles in ultrasonic wave module sensorcraft flight path,
Obstruction data information is sent to unmanned plane during flying data processing module.
(1b) flight visual simulation module analyzes unmanned plane during flying data and barrier data, and by processing result
UAV Flight Control System is returned to, so that unmanned function independently evades barrier.
(2) determine unmanned plane inclination infundibulate flight path E → A → B → D → C → E initial vertax A point, B point, D point,
C point and midpoint E, as shown in Fig. 2, wherein distance AB=BC=DC=AD, records initial AB point distance and flight plane and level
The initial angle theta in face, AB point initial distance can be 32 meters, and initial angle theta can be 45 degree, and will be at the beginning of at A point, B point, D point, C point
Beginning polluted gas concentration is disposed as zero；
(3) control unmanned plane flies according to inclination infundibulate track E → A → B → D → C → E, successively measures A point, B point, D
Point, C point pollution gas concentration hover at E point after unmanned plane completes primary inclination infundibulate flight；
(4) compare four vertex polluted gas concentration, determine polluted gas concentration highest point, record highest point concentration, it will
The highest point concentration is compared with last time inclination infundibulate top of the trajectory concentration, carries out step if this concentration is higher
(5), step (6) are carried out if last concentration is higher；
(5) with from E point to the direction of polluted gas concentration highest point for heading next time, flight AC length distance,
New E point is reached, step (3) to (4) are repeated；
(6) so that unmanned plane is returned to last time E point, check θ whether less than 3 °, if it is not, reduction flight plane and horizontal plane
Angle theta repeats step (3) to (4)；If θ is less than predetermined angle, (7) are entered step；
(7) using from E point to polluted gas concentration highest point as heading, flight AC length distance；
(8) control unmanned plane flies according to inclination infundibulate track E → A → B → D → C → E, successively measures A point, B point, D
Point, C point pollution gas concentration hover at E point after unmanned plane completes primary inclination infundibulate flight；
(9) compare four vertex polluted gas concentration, determine polluted gas concentration highest point, record highest point concentration, it will
The highest point concentration is compared with last time inclination infundibulate top of the trajectory concentration, carries out step if this concentration is higher
(10), step (11) are carried out if last concentration is higher；
(10) with from E point to the direction of polluted gas concentration highest point for heading next time, flight AC length distance,
New E point is reached, step (8) to (9) are repeated；
(11) so that unmanned plane is returned to last time E point, check AB whether less than 3 meters, if it is not, being original by AB Distance Shortened
Half repeats step (8) to (9)；If AB is less than preset length, (12) are entered step；
(12) so that unmanned plane is hovered, take pictures and sample to pollution sources, pass the data information of acquisition back ground command center；
(13) in view of gaseous contamination source will receive windage, θ and AB are redefined after 10 minutes, is entered step
(3)；
Wherein, in all of above step, using least square method supporting vector machine LS-SVM to unmanned plane carry out track with
Track control.
Preferably, it is described use least square method supporting vector machine LS-SVM to unmanned plane carry out Trajectory Tracking Control include with
Lower step：
(2a) provides drive control power according to the motor on four vertex of cross, respectively in unmanned plane starting point and geometry
The heart defines inertial coodinate system and body coordinate system, and vector (x, y, z) indicates position coordinates of the unmanned plane in inertial coodinate system, to
AmountIt indicates the posture coordinate of unmanned plane in the body coordinate system, unmanned plane is established according to the kinetic model of unmanned plane
Six degree of freedom wind interference model, Fig. 3 are the system block diagram of path tracking controller, and the track following of unmanned plane is by inner ring appearance
Two control closed loop compositions of state control and outer ring position control；
(2b) defines Attitude Tracking errorPosition tracking error E(x,y,z)；
(2c) can be summarised as solving the problems, such as Attitude Tracking and position tracking two, solve one by dynamical equation
ek+1=f (ek,uk), k=1,2,3 ..., N, the minimum problems of limitation
ekIndicate the posture and position tracking error between the actual path and desired trajectory at k moment, ukFor the control amount at k moment, Qf, Q, R are
The LS-SVM track following problem of constant, unmanned plane may be summarized to be, and solves one and is limited by solution one by dynamical equation ek+1=
f(ek,uk), k=1,2,3 ..., N, the minimum problems of limitation,
Wherein, weightMappingC is constant, and ξ is error of the training data to SVM optimal hyperlane,
LS-SVM optimal separating hyper plane is uk=wTL(ek)+ξk；
(2d) constructs Lagrangian to the minimum problems in (2c),
, to variable ek,eN+1,uk,w,ξk,λk, ak successively derivation, to solveWherein el is training data, λkWith ak
It is Lagrange multiplier, solves training data elAfterwards, as the supporting vector data in control law；
(2e) uses RBF kernel functionIn (2d) derivation process
In, available ξ=ak/ c, then can ignore ξ when the c of selection is sufficiently large, obtaining optimal control law is
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology art
Language and scientific term) there is meaning identical with the general understanding of those of ordinary skill in fields of the present invention.Should also
Understand, those terms such as defined in the general dictionary, which should be understood that, to be had and the meaning in the context of the prior art
The consistent meaning of justice, and unless defined as here, it will not be explained in an idealized or overly formal meaning.
Those skilled in the art can understand that the present invention can be related to for executing operation described herein
In one or more operations equipment.The equipment can specially design and manufacture for required purpose, or can also be with
Including the known device in general purpose computer, the general purpose computer activates or again with having the procedure selection being stored in it
Structure.Such computer program, which can be stored in equipment (for example, computer) readable medium or be stored in, is suitable for storage
E-command is simultaneously coupled in any kind of medium of bus respectively, and the computer-readable medium is including but not limited to any
The disk (including floppy disk, hard disk, CD, CD-ROM and magneto-optic disk) of type, random access memory (RAM), read-only memory (ROM),
Electrically programmable ROM, electrically erasable ROM (EPROM), electrically erasable ROM (EEPROM), flash memory, magnetic card or light card
Piece.Readable medium includes for by any mechanism of the readable form storage or transmission information of equipment (for example, computer).Example
Such as, readable medium includes random access memory (RAM), read-only memory (ROM), magnetic disk storage medium, optical storage medium, flash memory
Device, the signal (such as carrier wave, infrared signal, digital signal) propagated in the form of electricity, light, sound or other etc..
Those skilled in the art can understand that can realize these structure charts with computer program instructions
And/or the combination of each frame and these structure charts and/or the frame in block diagram and/or flow graph in block diagram and/or flow graph.It can be with
These computer program instructions are supplied to the processing of general purpose computer, special purpose computer or other programmable data processing methods
Device generates machine, creates to be performed instruction by the processor of computer or other programmable data processing methods
For realizing the method specified in the frame or multiple frames of structure chart and/or block diagram and/or flow graph.
Those skilled in the art can understand that the various operations crossed by discussion in the present invention, method, process
In step, measure, scheme can be replaced, changed, combined or be deleted.Further, there is in the present invention mistake by discussion
Various operations, method, other steps, measures, and schemes in process can also be replaced, change, reset, decomposing, combining or
It deletes.Further, it is in the prior art have in various operations, method disclosed in the present invention, process step, arrange
It applies, scheme may also be alternated, changed, rearranged, decomposed, combined or deleted.
Those skilled in the art do not depart from essence and spirit of the invention, can there are many deformation scheme realize the present invention,
The foregoing is merely preferably feasible embodiments of the invention, and not thereby limiting the scope of the invention, all with this
The variation of equivalent structure made by description of the invention and accompanying drawing content, is intended to be included within the scope of the present invention.
Claims (5)
1. a kind of anti-unmanned plane retrospect burst gaseous contamination source method of wind based on LS-SVM control, it is characterized in that the method packet
Include following steps：
(1) control unmanned plane flies into Polluted area；
(2) vertex A point, B point, D point, C point and the midpoint E of unmanned plane during flying track are determined, wherein A point, B point, D point, C point are same
In one plane, the vertex of square is formed, so that distance AB=BC=DC=AD, midpoint E are in the square diagonal line crosspoint
Place, record E point position, AB point distance and the plane and horizontal plane angle theta, and by initial contamination at A point, B point, D point, C point
Gas concentration is disposed as zero, and record highest point concentration is zero；
(3) control unmanned plane flies according to inclination infundibulate flight path E → A → B → D → C → E, successively measures A point, B point, D
Point, C point pollution gas concentration hover at E point after unmanned plane completes primary inclination infundibulate flight；
(4) compare four vertex polluted gas concentration, determine polluted gas highest point, by the highest of the highest point concentration and record
Point concentration is compared, and is by the highest point concentration records if the highest point concentration that the highest point concentration is greater than or equal to record
New highest point concentration simultaneously carries out step (5), carries out step (6) if the highest point concentration is lower than the highest point concentration of record；
(5) to be that heading, flight AC length distance reach next time from E point to the direction of polluted gas concentration highest point
New E point records new E point position, by the way that former vertex A point, B point, D point, C point translational length AC on this heading is true
Fixed new vertex A point, B point, D point, C point, repeat step (3) to (4)；
(6) make the E point of unmanned plane return recording, check whether θ is less than predetermined angle, if it is not, reducing flight plane and horizontal plane
Angle theta, new vertex A point, B point, D point, C point are determined according to the angle of AB point distance and flight plane and horizontal plane, repeat
Step (3) to (4)；If θ is less than predetermined angle, (7) are entered step；
(7) to be that heading, flight AC length distance reach new E next time from E point to polluted gas concentration highest point
Point records new E point position, by the way that by former vertex A point, B point, D point, C point, translational length AC is determined newly on this heading
Vertex A point, B point, D point, C point；
(8) control unmanned plane flies according to track E → A → B → D → C → E, successively measures A point, B point, D point, C point pollution gas
Concentration is hovered at E point after unmanned plane completes primary inclination infundibulate flight；
(9) compare four vertex polluted gas concentration, determine polluted gas highest point, by the highest of the highest point concentration and record
Point concentration is compared, and is by the highest point concentration records if the highest point concentration that the highest point concentration is greater than or equal to record
New highest point concentration simultaneously carries out step (7), carries out step (10) if the highest point concentration is lower than the highest point concentration of record；
(10) make the E point of unmanned plane return recording, check whether AB is less than preset length, if it is not, by AB Distance Shortened, according to AB
The angle of point distance and flight plane and horizontal plane determines new vertex A point, B point, D point, C point, repeats step (8) to (9)；If
AB is less than preset length, enters step (11)；
(11) so that unmanned plane is hovered, take pictures and sample to pollution sources, pass the data information of acquisition back ground command center；
(12) θ and AB are redefined using unmanned plane hovering point as E point after the predetermined time, enters step (2)；
In all of above step, Trajectory Tracking Control is carried out to unmanned plane using least square method supporting vector machine LS-SVM.
2. the anti-unmanned plane retrospect burst gaseous contamination source method of the wind according to claim 1 based on LS-SVM control,
It is characterized in that, it includes following step that the use least square method supporting vector machine LS-SVM, which carries out Trajectory Tracking Control to unmanned plane,
Suddenly：
(2a) provides drive control power according to the motor on four vertex of cross, fixed with unmanned plane starting point and geometric center respectively
Adopted inertial coodinate system and body coordinate system, vector (x, y, z) indicate position coordinates of the unmanned plane in inertial coodinate system, vectorIt indicates the posture coordinate of unmanned plane in the body coordinate system, unmanned plane six is established according to the kinetic model of unmanned plane
Freedom degree wind interference model；
(2b) defines Attitude Tracking errorPosition tracking error E(x,y,z)；
(2c) is solved by dynamical equation ek+1=f (ek,uk), k=1,2,3 ..., N, the minimum problems of limitationWhereinekIndicate the k moment actual path and desired trajectory between posture with
Position tracking error, ukFor the control amount at k moment, Qf, Q, R are constant, weightMappingC is normal
Number, ξ are error of the training data to SVM optimal hyperlane, and LS-SVM optimal separating hyper plane is uk=wTL(ek)+ξk；
(2d) constructs Lagrangian to the minimum problems in (2c),
, to variable ek,eN+1,uk,w,ξk,λk, ak successively derivation, to solveWherein el is training data, λkWith
akIt is Lagrange multiplier, solves training data elAfterwards, as the supporting vector data in control law；
(2e) uses RBF kernel functionDuring (2d) derivation, obtain
ξ=ak/ c, ignores ξ, obtains optimal control law and is
3. the anti-unmanned plane retrospect burst gaseous contamination source method of the wind according to claim 1 based on LS-SVM control,
It is characterized in that, the predetermined time described in step (12) is ten minutes.
4. the anti-unmanned plane retrospect burst gaseous contamination source method of the wind according to claim 1 based on LS-SVM control,
It is characterized in that, predetermined angle described in step (6) is 3 °.
5. the anti-unmanned plane retrospect burst gaseous contamination source method of the wind according to claim 1 based on LS-SVM control,
It is characterized in that, preset length described in step (10) is 3 meters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811035125.2A CN108845584B (en) | 2018-09-06 | 2018-09-06 | Wind-resistant unmanned aerial vehicle tracking burst gas pollution source method based on LS-SVM control |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811035125.2A CN108845584B (en) | 2018-09-06 | 2018-09-06 | Wind-resistant unmanned aerial vehicle tracking burst gas pollution source method based on LS-SVM control |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108845584A true CN108845584A (en) | 2018-11-20 |
| CN108845584B CN108845584B (en) | 2021-05-11 |
Family
ID=64189637
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811035125.2A Active CN108845584B (en) | 2018-09-06 | 2018-09-06 | Wind-resistant unmanned aerial vehicle tracking burst gas pollution source method based on LS-SVM control |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108845584B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112305163A (en) * | 2020-10-21 | 2021-02-02 | 西北工业大学 | Atmospheric pollution monitoring system based on fixed-wing unmanned aerial vehicle and data processing method |
| CN112526065A (en) * | 2020-11-19 | 2021-03-19 | 武汉云衡智能科技有限公司 | Unmanned aerial vehicle-based system and method for automatically positioning pollution source |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2471209C1 (en) * | 2011-07-29 | 2012-12-27 | Федеральное государственное бюджетное образовательное учреждение высшего профессионального образования "Санкт-Петербургский государственный горный университет" | Method of monitoring atmospheric air |
| CN103823028A (en) * | 2014-03-13 | 2014-05-28 | 山东省计算中心 | Stationary pollution source flue gas emission mobile monitoring system and method based on unmanned aerial vehicle |
| CN104656658A (en) * | 2015-01-19 | 2015-05-27 | 环境保护部卫星环境应用中心 | Atmospheric pollution discharge remote sensing monitoring method and atmospheric emission remote sensing monitoring system based on unmanned aerial vehicle |
| CN105158431A (en) * | 2015-09-22 | 2015-12-16 | 浙江大学 | Unmanned pollutant tracing system and method |
| CN105548476A (en) * | 2015-12-21 | 2016-05-04 | 新奥科技发展有限公司 | Gas leak detection method and detection system |
| CN106526074A (en) * | 2016-09-23 | 2017-03-22 | 天津大学 | Method for detecting direction of source of three dimensional odor loaded on unmanned rotorcraft |
| CN107132313A (en) * | 2017-05-08 | 2017-09-05 | 南京信息工程大学 | The method and pollution sources Check System of a kind of unmanned plane investigation pollution sources |
-
2018
- 2018-09-06 CN CN201811035125.2A patent/CN108845584B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2471209C1 (en) * | 2011-07-29 | 2012-12-27 | Федеральное государственное бюджетное образовательное учреждение высшего профессионального образования "Санкт-Петербургский государственный горный университет" | Method of monitoring atmospheric air |
| CN103823028A (en) * | 2014-03-13 | 2014-05-28 | 山东省计算中心 | Stationary pollution source flue gas emission mobile monitoring system and method based on unmanned aerial vehicle |
| CN104656658A (en) * | 2015-01-19 | 2015-05-27 | 环境保护部卫星环境应用中心 | Atmospheric pollution discharge remote sensing monitoring method and atmospheric emission remote sensing monitoring system based on unmanned aerial vehicle |
| CN105158431A (en) * | 2015-09-22 | 2015-12-16 | 浙江大学 | Unmanned pollutant tracing system and method |
| CN105548476A (en) * | 2015-12-21 | 2016-05-04 | 新奥科技发展有限公司 | Gas leak detection method and detection system |
| CN106526074A (en) * | 2016-09-23 | 2017-03-22 | 天津大学 | Method for detecting direction of source of three dimensional odor loaded on unmanned rotorcraft |
| CN107132313A (en) * | 2017-05-08 | 2017-09-05 | 南京信息工程大学 | The method and pollution sources Check System of a kind of unmanned plane investigation pollution sources |
Non-Patent Citations (4)
| Title |
|---|
| TAO HAN，ETC: "An effective approach to unmanned aerial vehicle navigation using visual topological map in outdoor and indoor environments", 《COMPUTER COMMUNICATIONS》 * |
| 刘毅男，等: "基于LS-SVM的非线性鲁棒自适应飞行控制器设计", 《系统工程与电子技术》 * |
| 李志强，等: "大气环境无人机监测方法研究", 《环境监测管理与技术》 * |
| 甘旭升，等: "基于鲁棒最小二乘支持向量机的气动参数拟合", 《计算机工程与应用》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112305163A (en) * | 2020-10-21 | 2021-02-02 | 西北工业大学 | Atmospheric pollution monitoring system based on fixed-wing unmanned aerial vehicle and data processing method |
| CN112305163B (en) * | 2020-10-21 | 2023-04-07 | 西北工业大学 | Atmospheric pollution monitoring system based on fixed-wing unmanned aerial vehicle and data processing method |
| CN112526065A (en) * | 2020-11-19 | 2021-03-19 | 武汉云衡智能科技有限公司 | Unmanned aerial vehicle-based system and method for automatically positioning pollution source |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108845584B (en) | 2021-05-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jordan et al. | State‐of‐the‐art technologies for UAV inspections | |
| CN106770930B (en) | A kind of method and system carrying out hazardous material detection using unmanned plane | |
| CN109780452A (en) | Gas based on laser telemetry technology leaks unmanned plane inspection retrieving concentration method | |
| CN207182103U (en) | For atmospheric environment on-line monitoring and the UAS of the controlled sampling of air | |
| CN112326686A (en) | Unmanned aerial vehicle intelligent cruise pavement disease detection method, unmanned aerial vehicle and detection system | |
| CN109633680A (en) | Four step closed loop atmosphere pollution traceability systems and method based on laser radar | |
| CN107976220A (en) | Based on Atmospheric components synchronization detecting system and method under fixed point different height | |
| CN109946564B (en) | Distribution network overhead line inspection data acquisition method and inspection system | |
| CN108845584A (en) | A kind of anti-unmanned plane retrospect burst gaseous contamination source method of wind based on LS-SVM control | |
| Mejias et al. | Forced landing technologies for unmanned aerial vehicles: towards safer operations | |
| CN205843666U (en) | A kind of depopulated helicopter three dimensional data collection and cruising inspection system | |
| CN109323694A (en) | A kind of indoor positioning and search and rescue system based on unmanned plane | |
| US5807113A (en) | Method and apparatus for training in the detection of nuclear, biological and chemical (NBC) contamination | |
| Pinney et al. | Drone path planning and object detection via QR codes; a surrogate case study for wind turbine inspection | |
| CN112987781A (en) | Unmanned aerial vehicle route generation method and device | |
| Anweiler et al. | Unmanned aerial vehicles for environmental monitoring with special reference to heat loss | |
| CN113449918B (en) | Emergency command aid decision-making method and system for sudden major pollution event | |
| Al Radi et al. | Video analysis of flare stacks with an autonomous low-cost aerial system | |
| CN213083501U (en) | Intelligent unmanned aerial vehicle environmental detection and fire investigation system | |
| Brown et al. | Visual & Inertial Datasets for an eVTOL Aircraft Approach and Landing Scenario | |
| CN109557571A (en) | A kind of Combustion Source intelligence method for tracing | |
| Bakirci | Efficient air pollution mapping in extensive regions with fully autonomous unmanned aerial vehicles: A numerical perspective | |
| Cook | Radiative contour mapping using UAS swarm | |
| CN116773745B (en) | Method and device for positioning pollutant gas emission source of industrial park and electronic equipment | |
| Lyu et al. | Research on UAV's Fixed-point Cruise Method Aiming at the Appearance Defects of Buildings |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |