CN109122633A - The accurate variable-rate spraying device of the plant protection drone of Decision of Neural Network and control method - Google Patents
The accurate variable-rate spraying device of the plant protection drone of Decision of Neural Network and control method Download PDFInfo
- Publication number
- CN109122633A CN109122633A CN201810660859.3A CN201810660859A CN109122633A CN 109122633 A CN109122633 A CN 109122633A CN 201810660859 A CN201810660859 A CN 201810660859A CN 109122633 A CN109122633 A CN 109122633A
- Authority
- CN
- China
- Prior art keywords
- controller
- neural network
- information
- spraying
- module
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 62
- 238000005507 spraying Methods 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 27
- 239000007921 spray Substances 0.000 claims abstract description 59
- 239000007788 liquid Substances 0.000 claims abstract description 41
- 230000006835 compression Effects 0.000 claims abstract description 11
- 238000007906 compression Methods 0.000 claims abstract description 11
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 11
- 239000003814 drug Substances 0.000 claims abstract description 5
- 241000196324 Embryophyta Species 0.000 claims description 84
- 241000607479 Yersinia pestis Species 0.000 claims description 45
- 201000010099 disease Diseases 0.000 claims description 34
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 34
- 238000012549 training Methods 0.000 claims description 31
- 210000002569 neuron Anatomy 0.000 claims description 19
- 238000009826 distribution Methods 0.000 claims description 18
- 230000007613 environmental effect Effects 0.000 claims description 17
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 claims description 15
- 230000010365 information processing Effects 0.000 claims description 15
- 230000002265 prevention Effects 0.000 claims description 15
- 239000012530 fluid Substances 0.000 claims description 13
- 230000003321 amplification Effects 0.000 claims description 12
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 12
- 241000238631 Hexapoda Species 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 239000003595 mist Substances 0.000 claims description 4
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 210000002364 input neuron Anatomy 0.000 claims description 3
- 238000009434 installation Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000012821 model calculation Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 210000004205 output neuron Anatomy 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 2
- 238000000465 moulding Methods 0.000 claims description 2
- 238000013500 data storage Methods 0.000 claims 1
- 238000001914 filtration Methods 0.000 claims 1
- 239000010914 pesticide waste Substances 0.000 abstract description 2
- 230000008021 deposition Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 210000005036 nerve Anatomy 0.000 description 2
- 238000002834 transmittance Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000008020 evaporation Effects 0.000 description 1
- 238000001704 evaporation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 239000010808 liquid waste Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01M—CATCHING, TRAPPING OR SCARING OF ANIMALS; APPARATUS FOR THE DESTRUCTION OF NOXIOUS ANIMALS OR NOXIOUS PLANTS
- A01M7/00—Special adaptations or arrangements of liquid-spraying apparatus for purposes covered by this subclass
- A01M7/0089—Regulating or controlling systems
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01M—CATCHING, TRAPPING OR SCARING OF ANIMALS; APPARATUS FOR THE DESTRUCTION OF NOXIOUS ANIMALS OR NOXIOUS PLANTS
- A01M7/00—Special adaptations or arrangements of liquid-spraying apparatus for purposes covered by this subclass
- A01M7/0025—Mechanical sprayers
- A01M7/0032—Pressure sprayers
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01M—CATCHING, TRAPPING OR SCARING OF ANIMALS; APPARATUS FOR THE DESTRUCTION OF NOXIOUS ANIMALS OR NOXIOUS PLANTS
- A01M7/00—Special adaptations or arrangements of liquid-spraying apparatus for purposes covered by this subclass
- A01M7/0082—Undercarriages, frames, mountings, couplings, tanks
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64D—EQUIPMENT FOR FITTING IN OR TO AIRCRAFT; FLIGHT SUITS; PARACHUTES; ARRANGEMENT OR MOUNTING OF POWER PLANTS OR PROPULSION TRANSMISSIONS IN AIRCRAFT
- B64D1/00—Dropping, ejecting, releasing, or receiving articles, liquids, or the like, in flight
- B64D1/16—Dropping or releasing powdered, liquid, or gaseous matter, e.g. for fire-fighting
- B64D1/18—Dropping or releasing powdered, liquid, or gaseous matter, e.g. for fire-fighting by spraying, e.g. insecticides
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Pest Control & Pesticides (AREA)
- Insects & Arthropods (AREA)
- Wood Science & Technology (AREA)
- Zoology (AREA)
- Environmental Sciences (AREA)
- Aviation & Aerospace Engineering (AREA)
- Mechanical Engineering (AREA)
- Catching Or Destruction (AREA)
Abstract
The present invention discloses a kind of accurate variable-rate spraying device of plant protection drone of Decision of Neural Network, horn end is connected with brshless DC motor and is connected with rotor blade, medicine-chest is connected by resistance to compression water pipe with spray head, and resistance to compression water pipe is connected with liquid pump, and spray head is by medicine liquid spray under the action of liquid pump；Positioning device is installed in the middle part of horn, be additionally provided with controller and miniature environment information acquisition device at the top of horn, controller also pass through Multichannel data acquisition device respectively with positioning device, miniature environment information acquisition device and be installed on the EO-1 hyperion camera of brshless DC motor bottom end and connect.The present invention also proposes a kind of control method of accurate variable-rate spraying device of the plant protection drone using Decision of Neural Network, compared with the prior art, it is administered on demand when the present invention comprehensively considers plant protection drone spraying operation on the various factors of spray amount influence and according to prescription values, the advantages that accurate adjustable spraying flow, effectively reduces pesticide waste and accurate variable rate spray and reaches best control efficiency.
Description
Technical field
The present invention relates to agricultural plant protection technical field, the in particular to accurate variables of the plant protection drone of Decision of Neural Network
Spraying device and control method.
Background technique
It is arranged when the plant protection drone of the prior art carries out operation by analyzing the pest and disease damage situation in entire operation plot
The pre- amount of spraying in practical flight operation, controls instantaneous flow according to unmanned plane during flying speed and height, to guarantee to spray
The uniformity of mist.
However the distribution situation in the same plot, disease pest and weed is each different, while plant protection drone is in spraying operation
When, due to being influenced by the factors such as operating environment and rotor wind field, so that there is evaporation, being attached to machine in the droplet sprayed
Body surface is drifted the air situations such as, in addition existing plant protection drone spray operation technical system it is not perfect and
The unmanned plane of ununified standard, different plant protection drone companies is different on structural parameters, joins in operating environment
In all identical situations such as number, flight parameter and prescription values, the plant protection drone spraying operation mist droplet deposition feelings of different model
Condition is also different, therefore the method for the prior art unmanned plane amount of spraying decision can no longer meet precision agriculture production requirement.
Summary of the invention
The main object of the present invention is to propose a kind of plant protection drone of the Decision of Neural Network of accurate adjustable spraying flow
Accurate variable-rate spraying device, the present invention also propose a kind of accurate variable rate spray dress of the plant protection drone using Decision of Neural Network
The control method set, it is intended to can be according to the severity of operating area disease pest and weed, flight parameter, plant protection drone specification
Parameter and environmental factor etc. are online precisely adjusted mist flow, are effectively reduced pesticide waste and accurate variable rate spray, are reached
Best control efficiency.
To achieve the above object, the accurate variable-rate spraying device of the plant protection drone of Decision of Neural Network proposed by the present invention,
Including several horns, the horn end is connected with brshless DC motor, the brshless DC motor top and rotor blade
It is connected, is connected with medicine-chest below the fuselage of the horn composition, the medicine-chest bottom is connected by resistance to compression water pipe with spray head, institute
It states resistance to compression water pipe and is connected with liquid pump, the spray head is mounted on the spray boom below fuselage；Several are installed in the middle part of the horn
Positioning device, the miniature environment information acquisition device that fuselage roof is equipped with controller and is used to collect environmental parameters, the control
Device processed also pass through Multichannel data acquisition device respectively with the positioning device, the miniature environment information acquisition device and installation
EO-1 hyperion camera in the brshless DC motor bottom end connects.
Preferably, fuselage roof is equipped with drive amplification module and connect respectively with the controller and the liquid pump.
Preferably, the liquid pump is led to the filter for being set to the medicine-chest bottom by pipeline.
Preferably, the resistance to compression water pipe is successively additionally provided with overflow valve, flow sensor and pressure along liquid medicine flow direction
Sensor is connect with the controller respectively.
Preferably, liquid level sensor and the institute for detecting medical fluid liquid level are equipped with inside the medicine-chest at the top of wall surface
State controller connection.
The present invention also proposes a kind of control method using the spraying device, comprising the following steps:
S1: being equipped on the crop image information in the EO-1 hyperion camera Collecting operation plot of the horn lower part, described
Positioning device obtains location information in real time and is equipped on the miniature environment information acquisition device acquisition field of fuselage roof
Environmental parameter, the EO-1 hyperion camera and the positioning device and the miniature environment information acquisition device will collect respectively
Data be transmitted to the controller；The flow sensor, the pressure sensor and the liquid level sensor will flow
Amount, pressure value and residual volume of solution Real-time Feedback to the controller；
S2: the controller by the Multichannel data acquisition device by collected data processing, in the controller
Information processing and decision-making module using the neural network module of training to information processings such as images and generate the space of pest and disease damage
Distribution map；
S3: the controller is according to processing result image and Crops Pests Control of Diseases Insects And Weeds Pests of Crops prevention and treatment expert module output is combined to spray
Dose value, generate target plot sprays operation prescription map, and the UAV Flight Control module combination operation prescription map is autonomous
Plan course line；
S4: the controller is to flight parameter, environmental parameter, plant protection drone real time information and the prescription being collected into
After the information processings such as value information, liquid level, flow and pressure, each decision content is carried out by trained neural network module
Operation simultaneously obtains the best amount of spraying；When having obtained the prescription map in operation plot before operation, the controller extracts present bit
Confidence breath is compared with prescription map, judges that unmanned plane is presently in position to obtain the information such as the prescription values of current location；
S5: the variable rate spray control module of the controller uses closed loop PID to the best amount of the spraying information received
Algorithm generates corresponding duty cycle pulse square wave, drives the liquid pump to work after drive amplification module amplification, while institute
Flow sensor, the pressure sensor Real-time Feedback actual flow, pressure value are stated, it is accurate to flow again by controller
It adjusts；Residual volume of solution in the liquid level sensor real-time monitoring medicine-chest, and residual volume of solution is fed back into flight control mould
Block makes operation of making a return voyage when medical fluid is lower than a certain setting value in time.
Preferably, the width of EO-1 hyperion camera Collecting operation plot described in the step S1 is 10 meters, the EO-1 hyperion
The length in camera Collecting operation plot is matched with plant protection drone flying speed, and the geography obtained in conjunction with the positioning device
Location information obtains operating area distributed intelligence figure；
Controller described in the step S2 carries out convolution fortune to Image Information Processing, using image information as input quantity
It calculates to filter garbage in image, then passes through the hidden layer of neural network module to pretreated image zooming-out color, shape
Shape, Texture eigenvalue export using operation and obtain operation plot disease pest and weed distribution map；
In the step S3 according in Different Crop growth cycle various disease pest and weed experience of prevention and treatment and a large amount of fields
Prevention and treatment experimental data establishes database, according to disease pest and weed space distribution situation is obtained after image recognition, by the crop disease pest
The output of prevention and control of weeds expert module sprays prescription values, and the distribution situation and the amount of spraying in conjunction with operation plot disease pest and weed generate
Operation plot prescription map, the prescription map obtained before operation, the flight control modules are autonomously generated most according to prescription map
Excellent sprays operation course line；
The amount of spraying information, the unmanned plane specification ginseng of Crops Pests Control of Diseases Insects And Weeds Pests of Crops prevention and treatment expert module output in the step S4
Number, flight parameter and environmental parameter are transmitted in the controller by the Multichannel data acquisition device；It is obtained before operation
When obtaining prescription map, prescription map is directed into the controller, during plant protection drone carries out plant protection operation, by current
Location information and the location information of prescription map compare, and determine plant protection drone with respect to prescription map position to obtain spray
Shi Liang.
Preferably, the neural network module of the step S4 is reverse transmittance nerve network module, the nerve net
Network includes input layer, hidden layer and output layer, and sample data needed for training neural network is the effective of a large amount of correlation tests
Test data, before training neural network, random initializtion weight and biasing, and the range of each weight is set in (- 1,1)
It is interior, set error function e, and set the maximum study number of training and computational accuracy value ε, the sample of selection as input quantity X,
And the corresponding desired output of sample is defined:
Number enters amount: X (k)=(x1(k), x2(k) ... xn(k))
Export desired value: Y
Calculating is output and input to each neuron of hidden layer respectively, wherein the input quantity of hidden layer:
In formula, wi(k) connection weight between each input neuron and hidden layer；biIt is inclined for the neuron of hidden layer
Set value；N is the number of input variable；
Hidden layer neuron output quantity:
In formula, wo(k) connection weight between output neuron and hidden layer；B is output layer neuron bias；
By the calculating of neural network multilayer hidden layer, output valve is obtained, and error is calculated according to the desired value of output quantity
Partial derivative δ of the function to output layer neurono(k), wherein global error are as follows:
The weight w of each layer neuron of hidden layer is adjusted in neural network training process according to cumulative errorsi(k), to subtract
Small global error, it may be assumed that
η in formula is learning rate；
Weight is adjusted according to the weighed value adjusting formula of each hidden neuron output layer, it may be assumed that
When previous cycle of training all variables are respectively less than some specified threshold value, neural network completes
The period is practised, learning process is completed according to the learning cycle of setting, the neural network module after deep learning training being capable of root
According to input information, a legitimate result is exported after model calculation.
Preferably, the step S5 by programming is established the satisfactory neural network module of training in controller
In, the information such as ambient temperature and humidity, wind speed and direction information, flight parameter and prescription values when operation by received operation
After treatment as the input quantity of neural network, an optimal amount of spraying is exported after neural network is run, it is embedded
System most preferably can will spray magnitude and be transmitted in Variable rate sprayer controller, the variable rate spray control module amount of spraying based on the received
Information generates the pulse square wave of corresponding duty ratio by amplification rear-guard hydrodynamic pump, at the same spray circuit flow sensor and
The flow velocity and pressure value of pressure sensor real-time measurement loading pipeline, and collocation Variable rate sprayer controller module is fed back, and combine
Deviation between actual flow velocity, actual pressure value and theoretical velocity, theoretical pressure value precisely adjusts spray process,
Liquid level sensor passes through dose situation in detection medicine-chest, when detecting medical fluid lower than setting value, flight control modules module hair
It makes a return voyage out instruction.
Technical solution of the present invention has the advantage that compared with the prior art
The accurate variable-rate spraying device of the plant protection drone of the Decision of Neural Network of technical solution of the present invention comprehensively considers plant protection
When unmanned plane spraying operation, a large amount of fields are collected in the influence of environmental factor, flight parameter, unmanned plane specifications parameter to medical fluid droplet
Between experimental data as training sample, one decision model of training passes through when actual job after input unmanned plane specifications parameter
Sensor real-time monitoring environmental factor, flight parameter and application prescription values, and using the information of acquisition as mode input amount,
Rapid computations obtain the best amount of spraying, and so that actual deposition is met prescription values requirement just to the liquid volume of crop surface, and can reach
To optimal control efficiency, therefore technical solution of the present invention can effectively reduce liquid waste, realize and precisely spray operation.
The plant protection drone of technical solution of the present invention is completed at the same time EO-1 hyperion and collects field Pest organism in plant protection operation
Evil distribution situation and the decision information for generating operation prescription map, and airborne various sensors being combined to collect quickly provide best
Spray is appropriate, and variable rate spray is instructed to operate.At the same time, for the operation prescription map before operation with regard to obtaining target plot, will locate
Square figure is imported into airborne embedded system, when plant protection drone flight, according to the location information that real-time locating module obtains,
Operation prescription map is interpreted and obtains prescription values, in conjunction with the decision information for combining airborne various sensors to collect, is quickly provided most
Good spray is appropriate, and variable rate spray is instructed to operate.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, below will to embodiment or
Attached drawing needed to be used in the description of the prior art is briefly described, it should be apparent that, the accompanying drawings in the following description is only
Some embodiments of the present invention, for those of ordinary skill in the art, without creative efforts, also
The structure that can be shown according to these attached drawings obtains other attached drawings.
Fig. 1 is the structural schematic diagram of the accurate variable-rate spraying device of plant protection drone of the present invention；
Fig. 2 is the system schematic of the accurate variable-rate spraying device of plant protection drone of the present invention；
Fig. 3 sprays operation prescription map for the accurate variable-rate spraying device of plant protection drone of the present invention；
Fig. 4 is information processing and the decision flow diagram of the accurate variable-rate spraying device of plant protection drone of the present invention；
Fig. 5 is the training flow chart of the accurate variable-rate spraying device neural network module of plant protection drone of the present invention.
Drawing reference numeral explanation:
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiment is only a part of the embodiments of the present invention, instead of all the embodiments.Base
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts all
Other embodiments shall fall within the protection scope of the present invention.
It is to be appreciated that if related in the embodiment of the present invention directionality instruction (such as upper and lower, left and right, it is preceding,
Afterwards ...), then directionality instruction is only used for explaining opposite between each component under a certain particular pose (as shown in the picture)
Positional relationship, motion conditions etc., if the particular pose changes, directionality instruction is also correspondingly changed correspondingly.
In addition, being somebody's turn to do " first ", " second " etc. if relating to the description of " first ", " second " etc. in the embodiment of the present invention
Description be used for description purposes only, be not understood to indicate or imply its relative importance or implicitly indicate indicated
The quantity of technical characteristic." first " is defined as a result, the feature of " second " can explicitly or implicitly include at least one
This feature.It in addition, the technical solution between each embodiment can be combined with each other, but must be with ordinary skill
Based on personnel can be realized, this technology will be understood that when the combination of technical solution appearance is conflicting or cannot achieve
The combination of scheme is not present, also not the present invention claims protection scope within.
The present invention proposes a kind of accurate variable-rate spraying device of the plant protection drone of Decision of Neural Network.
Referring to Figure 1, in the accurate variable rate spray dress of the plant protection drone of the Decision of Neural Network of technical solution of the present invention
It sets, including four horizontally disposed horns 17,17 end of horn is connected with brshless DC motor 18,18 top of brshless DC motor
It is connected with rotor blade 19, medicine-chest 8 is connected with below the fuselage being made of four horns 17,8 bottom of medicine-chest passes through resistance to compression water pipe
12 are connected with spray head 13, and resistance to compression water pipe 12 is connected with liquid pump 10, and spray head 13 is mounted on spray boom 14；Fuselage roof is equipped with control
Device 4 processed and miniature environment information acquisition device 3 for acquiring environmental factor data, wherein miniature environment information acquisition device 3 is used
The information such as environment temperature, humidity, wind speed and wind direction during Collecting operation.There are two positioning for installation in the middle part of horn 17
Device 1, wherein positioning device 1 uses real-time requiring method, can accurately provide the geographical location of plant protection drone,
The rank that its positioning accuracy can reach centimetre.Controller 4 by Multichannel data acquisition device 2 respectively with positioning device 1, miniature
It environment information acquisition device 3 and is installed on 18 bottom end of brshless DC motor and obtains the figure in operation plot and being continuously shot
As the EO-1 hyperion camera 6 of information connects.And positioning device 1, miniature environment information acquisition device 3 and EO-1 hyperion camera 6 will acquire
To location information, environmental parameter and image information be delivered to controller 4 to instruct to spray the reference of operation as subsequent
Information.
In addition, the fuselage of the accurate variable-rate spraying device of the plant protection drone of the Decision of Neural Network of technical solution of the present invention
It is connect respectively with controller 4 and liquid pump 10 equipped with drive amplification module 5, liquid pump 10 and the filter 9 for being set to 8 bottom of medicine-chest
Led to by pipeline, resistance to compression water pipe 12 is successively additionally provided with overflow valve 11, flow sensor 15 and pressure along liquid medicine flow direction
Sensor 16 is connect with controller 4 respectively, and the liquid for detecting medical fluid liquid level is in addition equipped at the top of 8 inside wall surface of medicine-chest
Level sensor 7 is connect with controller 4.
The accurate variable-rate spraying device of the plant protection drone of the Decision of Neural Network of technical solution of the present invention fills 1 by positioning
The position and precise positioning is carried out to it that real-time detection plant protection drone is flown, and 3 pairs of miniature environment information acquisition device plants
Protect the information such as the collected environment temperature of unmanned plane during flying process, humidity, wind speed and wind direction be sent in real time controller 4 into
Row analysis is handled to improve the precision of the sprinkling medical fluid of plant protection drone, and EO-1 hyperion camera 6 is shot for high definition to operating environment
Image is simultaneously sent to controller 4 and is analyzed and processed.Be set to the liquid pump 10 of the lower section of medicine-chest 8 by rotation by medical fluid from medicine-chest 8
Middle extraction flows to overflow valve 11 by filter 9, and medical fluid all the way therein can be connected by overflow valve 11 with medicine-chest 8
Channel be back in medicine-chest 8, and another way medical fluid can be led back by entering to after flow sensor 15, pressure sensor 16
Then Lu Zhong flows to spray head 13 by spray boom 14 respectively by multiple branched pipes and sprays still further below.Wherein by by flow
Sensor 15 and pressure sensor 16 are set on major loop, can effectively be accurately measured in this way to flow and pressure realization, and
And by measurement result Real-time Feedback into controller 4, at the same time, liquid level sensor 7 is mounted on inside medicine-chest 8, can be examined in real time
The surplus for surveying medical fluid, when liquid volume is lower than setting value, the flight control modules in controller 4 control plant protection drone into
Capable dosing of making a return voyage.
Fig. 2 to Fig. 5 is referred to, the controller of technical solution of the present invention uses embedded chip, by embedded chip
Interior setting functional module, including information processing and decision-making module, prescription map interpretation module, flight control modules, variable rate spray control
Molding block, Crops Pests Control of Diseases Insects And Weeds Pests of Crops prevent and treat expert module.
Specifically, the information processing of technical solution of the present invention and decision-making module can carry out the image information got
Processing, identifies the disease pest and weed in image and crop, and obtain the space distribution situation of disease pest and weed, then crop disease pest
Prevention and control of weeds expert module according to after image recognition crop and disease pest and weed distribution situation provide the application prescriptions of different zones
Value.Due to actually spraying in operation process, flight parameter, specifications parameter and the environmental factor of plant protection drone can be right
The amount of spraying generate it is certain influence, for the disease pest and weed control efficiency for enhancing target area, during spraying operation, information processing
And the prescription that decision-making module makes the environmental information received, flight parameter and Crops Pests Control of Diseases Insects And Weeds Pests of Crops prevention and treatment expert module
Input quantity of the specifications parameter of value and plant protection drone as neural network module, exports by neural network module operation
The best amount of spraying.
The training of the neural network module of the present embodiment using existing experimental data find out each influence factor and result it
Between complex relationship, wherein neural network module mainly includes that input layer, hidden layer, output layer are total to 3-tier architecture, training time-division
A large amount of image information, the amount of spraying decision factor and prescription values are not chosen as sample data, using sample data as input layer
The input quantity of each neuron, each hidden layer of neural network module calculate sample data feature, obtain the defeated of each hidden layer
It is worth out, and constantly training process parameter is optimized according to the error between desired value and real output value, when error is small
When given threshold, then training result is exported.
When obtaining prescription map before operation, prescription map is directed into controller, is believed when operation according to collected position
Breath judges that plant protection drone relative to prescription map position, and obtains the prescription values of current location.
Flight control modules can automatically control and keep the normal flight posture of plant protection drone, plant protection operation process
In, operating personnel sends enabled instruction to plant protection drone by hand-held earth station, and flight control modules are according to field Pest organism
Evil distribution situation plans course line automatically, when flight operation, flight control modules and information processing and decision-making module, variable rate spray
Control module is connected by bus, and flight control modules adjust flight attitude according to the actual conditions of operation.
In technical solution of the present invention, after variable rate spray control module receives the best amount of spraying information, program meeting is controlled
The pulse square wave signal of corresponding duty ratio is generated according to the error between actual flow value, pressure value and target value, is passed through
Drive amplification module is worked with amplifying rear-guard hydrodynamic pump, and is precisely controlled using closed-loop control realization to flow, thus
Achievable variable sprays operation.
Fig. 2 to Fig. 5 is referred to, technical solution of the present invention also proposes a kind of plant protection drone using Decision of Neural Network
The control method of accurate variable-rate spraying device, comprising the following steps:
Step S1: the crop image information in EO-1 hyperion camera Collecting operation plot, positioning device obtain location information in real time
And the environmental parameter in miniature environment information acquisition device acquisition field, EO-1 hyperion camera and positioning device and miniature environment are believed
Collected data are transmitted to controller respectively by breath collector；Flow sensor, pressure sensor and liquid level sensor will
Flow, pressure value and residual volume of solution Real-time Feedback are to controller；
Step S2: controller by Multichannel data acquisition device by collected data processing, at the information in controller
Reason and decision-making module to information processings such as images and generate the spatial distribution map of pest and disease damage using the neural network module of training；
Step S3: controller is according to processing result image and Crops Pests Control of Diseases Insects And Weeds Pests of Crops prevention and treatment expert module output is combined to spray
Dose value, generate target plot sprays operation prescription map, the UAV Flight Control module combination operation prescription map of controller
Contexture by self course line；
Step S4: controller is to flight parameter, environmental parameter, plant protection drone real time information and the prescription being collected into
After the information processings such as value information, liquid level, medicinal liquid flow and pressure, by trained neural network module to each decision content
It carries out operation and obtains the best amount of spraying；The prescription map in operation plot is obtained before operation, controller extracts current location
Information and prescription map compare, and judge that unmanned plane is presently in position to obtain the information such as the prescription values of current location；
Step S5: the variable rate spray control module of controller uses closed loop PID to the best amount of the spraying information received
Algorithm generates corresponding duty cycle pulse square wave, amplifies rear-guard hydrodynamic pump work, while flow sensing by drive amplification module
Residual volume of solution in device, pressure sensor and liquid level sensor Real-time Feedback actual flow, pressure value and medicine-chest, leads to again
It crosses controller and flow is precisely adjusted.
Preferably, the width in EO-1 hyperion camera Collecting operation plot is 10 meters in above-mentioned steps S1, the acquisition of EO-1 hyperion camera
The length in operation plot is matched with plant protection drone flying speed, and the geographical location information for combining positioning device to obtain obtains
The distributed intelligence figure of operating area；
Preferably, controller carries out convolution for image information as input quantity to Image Information Processing in above-mentioned steps S2
Operation to filter garbage in image, then by the hidden layer of neural network module to pretreated image zooming-out color,
Shape, Texture eigenvalue export the disease pest and weed distribution map for obtaining operation plot using operation；
Preferably, in above-mentioned steps S3 according in Different Crop growth cycle various disease pest and weed experience of prevention and treatment and
A large amount of field control experimental datas establish database, according to disease pest and weed space distribution situation is obtained after image recognition, by crop
Disease pest and weed prevention and treatment expert module output sprays prescription values, in conjunction with the distribution situation and the amount of spraying of operation plot disease pest and weed
Operation plot prescription map, the prescription map obtained before operation are generated, controller is autonomously generated optimal spray according to prescription map
Apply industry course line；
Preferably, the amount of the spraying information of the Crops Pests Control of Diseases Insects And Weeds Pests of Crops prevention and treatment expert module output in above-mentioned steps S4, unmanned plane
Specifications parameter, flight parameter and environmental parameter are transmitted in controller by Multichannel data acquisition device；At operation acquisition
When side's figure, prescription map is directed into controller, when plant protection drone carries out plant protection operation, passes through current location information and place
The location information of square figure compares, and determines plant protection drone with respect to prescription map position to obtain the amount of spraying.
Preferably, the neural network module of above-mentioned steps S4 is reverse transmittance nerve network module, neural network module packet
Input layer, hidden layer and output layer are included, the sample of training neural network module is the efficiency test number of a large amount of correlation tests
According to, before training neural network module, random initializtion weight and biasing, and to each weight setting in the range of (- 1,1),
Error function e is set, and sets the maximum study number of training and computational accuracy value ε, the sample of selection is and right as input quantity X
The corresponding desired output of sample is defined:
Number enters amount: X (k)=(x1(k), x2(k) ... xn(k))
Export desired value: Y
Calculating is output and input to each neuron of hidden layer respectively, wherein the input quantity of hidden layer:
In formula, wi(k) connection weight between each input neuron and hidden layer；biIt is inclined for the neuron of hidden layer
Set value；N is the number of input variable；
Hidden layer neuron output quantity:
In formula, wo(k) connection weight between output neuron and hidden layer；B is output layer neuron bias；
By the calculating of neural network module multilayer hidden layer, output valve is obtained, and is calculated according to the desired value of output quantity
Partial derivative δ of the error function to output layer neurono(k), wherein global error are as follows:
The weight w of each layer neuron of hidden layer is adjusted in neural network module training process according to cumulative errorsi(k), from
And reduce global error, it may be assumed that
η in formula is learning rate；
Weight is adjusted according to the weighed value adjusting formula of each hidden neuron output layer, it may be assumed that
When all variables of previous cycle of training are respectively less than some specified threshold value, neural network module completes one
A learning cycle completes learning process according to the learning cycle of setting, the artificial neural network mould after deep learning training
Block can export a legitimate result according to input information after model calculation.
Preferably, the controller of above-mentioned steps S5 establishes the satisfactory model of training by programming, passes through received work
The information such as ambient temperature and humidity, wind speed and direction information, flight parameter and prescription values when industry are used as neural network after treatment
The input quantity of module, exports an optimal amount of spraying after neural network module is run, and embedded system will can most preferably spray
It applies magnitude to be transmitted in Variable rate sprayer controller, the amount of spraying information generates accordingly variable rate spray control module based on the received
The pulse square wave of duty ratio is pumped by amplification rear-guard hydrodynamic, while spraying the flow sensor and pressure sensor reality in circuit
When measure loading pipeline flow velocity and pressure value, and feed back collocation Variable rate sprayer controller module, and combine actual flow velocity, reality
Deviation between border pressure value and theoretical velocity, theoretical pressure value precisely adjusts spray process, and liquid level sensor is logical
The dose situation for crossing detection medicine-chest, when detecting medical fluid lower than setting value, flight control modules module issues instruction of making a return voyage.
The above description is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all at this
Under the design of invention, using equivalent structure transformation made by description of the invention and accompanying drawing content, or directly/be used in indirectly
Other related technical areas are included in scope of patent protection of the invention.
Claims (9)
1. the accurate variable-rate spraying device of the plant protection drone of Decision of Neural Network, which is characterized in that described including several horns
Horn end is connected with brshless DC motor, and the brshless DC motor top is connected with rotor blade, the horn composition
Medicine-chest is connected with below fuselage, the medicine-chest bottom is connected by resistance to compression water pipe with spray head, and the resistance to compression water pipe is connected with liquid pump,
The spray head is mounted on the spray boom below fuselage；Several positioning devices, fuselage roof installation are installed in the middle part of the horn
The miniature environment information acquisition device for having controller and being used to collect environmental parameters, the controller are also adopted by multi-channel data
Storage respectively with the positioning device, the miniature environment information acquisition device and be installed on the brshless DC motor bottom end
The connection of EO-1 hyperion camera.
2. spraying device as described in claim 1, which is characterized in that fuselage roof be equipped with drive amplification module respectively with institute
Controller is stated to connect with the liquid pump.
3. spraying device as claimed in claim 2, which is characterized in that the liquid pump and the filtering for being set to the medicine-chest bottom
Device is led to by pipeline.
4. spraying device as claimed in claim 3, which is characterized in that the resistance to compression water pipe is successively also set along liquid medicine flow direction
There are overflow valve, flow sensor and pressure sensor to connect respectively with the controller.
5. spraying device as claimed in claim 4, which is characterized in that be equipped at the top of wall surface for detecting medicine inside the medicine-chest
The liquid level sensor of liquid liquid level is connect with the controller.
6. a kind of control method using spraying device as claimed in claim 5, which comprises the following steps:
S1: the crop image information in the EO-1 hyperion camera Collecting operation plot of the horn lower part, the positioning are equipped on
Device obtains location information in real time and is equipped on the environment in the miniature environment information acquisition device acquisition field of fuselage roof
Parameter, the EO-1 hyperion camera and the positioning device and the miniature environment information acquisition device are respectively by collected data
It is transmitted to the controller；The flow sensor, the pressure sensor and the liquid level sensor are by flow, pressure value
And residual volume of solution Real-time Feedback is to the controller；
S2: letter of the controller by the Multichannel data acquisition device by collected data processing, in the controller
Breath processing and decision-making module to information processings such as images and generate the spatial distribution of pest and disease damage using the neural network module of training
Figure；
S3: the controller is according to processing result image and Crops Pests Control of Diseases Insects And Weeds Pests of Crops prevention and treatment expert module output is combined to spray dose
Value, generate target plot sprays operation prescription map, the UAV Flight Control module combination operation prescription map contexture by self
Course line；
S4: the controller believes the flight parameter, environmental parameter, plant protection drone real time information and the prescription values that are collected into
After the information processings such as breath, liquid level, flow and pressure, operation is carried out simultaneously to each decision content by trained neural network module
Obtain the best amount of spraying；When having obtained the prescription map in operation plot before operation, the controller extracts current location information
It is compared with prescription map, judges that unmanned plane is presently in position to obtain the information such as the prescription values of current location；
S5: the variable rate spray control module of the controller produces the best amount of the spraying information received using closed loop pid algorithm
Raw corresponding duty cycle pulse square wave drives the liquid pump to work after drive amplification module amplification, while the flow
Sensor, the pressure sensor Real-time Feedback actual flow, pressure value, are precisely adjusted flow again by controller；Institute
Residual volume of solution in liquid level sensor real-time monitoring medicine-chest is stated, and residual volume of solution is fed back into flight control modules, works as medical fluid
When lower than a certain setting value, operation of making a return voyage is made in time.
7. control method as claimed in claim 6, which is characterized in that
The width of EO-1 hyperion camera Collecting operation plot described in the step S1 is 10 meters, the EO-1 hyperion camera Collecting operation
The length in plot is matched with plant protection drone flying speed, and is made in conjunction with the geographical location information that the positioning device obtains
Industry area distribution hum pattern；
Controller described in the step S2 carries out convolution algorithm to Image Information Processing, using image information as input quantity with mistake
Garbage in image is filtered, then passes through the hidden layer of neural network module to pretreated image zooming-out color, shape, texture
Etc. features, using operation export obtain operation plot disease pest and weed distribution map；
According to the various disease pest and weed experience of prevention and treatment and a large amount of field controls in Different Crop growth cycle in the step S3
Experimental data establishes database, according to disease pest and weed space distribution situation is obtained after image recognition, by the Crops Pests Control of Diseases Insects And Weeds Pests of Crops
Prevention and treatment expert module output sprays prescription values, and the distribution situation and the amount of spraying in conjunction with operation plot disease pest and weed are with generating operation
Block prescription map, the prescription map obtained before operation, the flight control modules are autonomously generated optimal spray according to prescription map
Apply industry course line；
The amount of the spraying information of Crops Pests Control of Diseases Insects And Weeds Pests of Crops prevention and treatment expert module output in the step S4, flies at unmanned plane specifications parameter
Row parameter and environmental parameter are transmitted in the controller by the Multichannel data acquisition device；Prescription is obtained before operation
When figure, prescription map is directed into the controller, during plant protection drone carries out plant protection operation, passes through current location information
It is compared with the location information of prescription map, determines plant protection drone with respect to prescription map position to obtain the amount of spraying.
8. control method as claimed in claim 6, which is characterized in that the neural network module of the step S4 is reversed
Propagation Neural Network module, the neural network include input layer, hidden layer and output layer, sample needed for training neural network
Notebook data is the efficiency test data of a large amount of correlation tests, before training neural network, random initializtion weight and biasing, and will
The range of each weight is set in (- 1,1), sets error function e, and sets the maximum study number of training and computational accuracy value ε,
The sample of selection is defined as input quantity X, and to the corresponding desired output of sample:
Number enters amount: X (k)=(x1(k), x2(k) ... xn(k))
Export desired value: Y
Calculating is output and input to each neuron of hidden layer respectively, wherein the input quantity of hidden layer:
In formula, wi(k) connection weight between each input neuron and hidden layer；biFor the neuron bias of hidden layer；
N is the number of input variable；
Hidden layer neuron output quantity:
In formula, wo(k) connection weight between output neuron and hidden layer；B is output layer neuron bias；
By the calculating of neural network multilayer hidden layer, output valve is obtained, and error function is calculated according to the desired value of output quantity
To the partial derivative δ of output layer neurono(k), wherein global error are as follows:
The weight w of each layer neuron of hidden layer is adjusted in neural network training process according to cumulative errorsi(k), to reduce the overall situation
Error, it may be assumed that
η in formula is learning rate；
Weight is adjusted according to the weighed value adjusting formula of each hidden neuron output layer, it may be assumed that
When all variables of previous cycle of training are respectively less than some specified threshold value, it is all that neural network completes a study
Phase completes learning process according to the learning cycle of setting, and the neural network module after deep learning training can be according to defeated
Enter information, a legitimate result is exported after model calculation.
9. control method as claimed in claim 6, which is characterized in that the step S5's is met the requirements training by programming
Neural network module establish in the controller, ambient temperature and humidity, wind speed and direction information when operation by received operation,
The information such as flight parameter and prescription values are used as the input quantity of neural network after treatment, export after neural network is run
One optimal amount of spraying, embedded system can be transmitted to most preferably magnitude is sprayed in Variable rate sprayer controller, variable rate spray control
The molding block pulse square wave that the amount of spraying information generates corresponding duty ratio based on the received sprays simultaneously by amplification rear-guard hydrodynamic pump
The flow sensor in circuit and the flow velocity and pressure value of pressure sensor real-time measurement loading pipeline are applied, and feeds back collocation variable spray
Mist controller module, and the deviation between combination actual flow velocity, actual pressure value and theoretical velocity, theoretical pressure value, to spraying
Process is precisely adjusted, and liquid level sensor is flown by dose situation in detection medicine-chest when detecting medical fluid lower than setting value
Row control module module issues instruction of making a return voyage.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810660859.3A CN109122633B (en) | 2018-06-25 | 2018-06-25 | Plant protection unmanned aerial vehicle accurate variable spraying device for neural network decision-making and control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810660859.3A CN109122633B (en) | 2018-06-25 | 2018-06-25 | Plant protection unmanned aerial vehicle accurate variable spraying device for neural network decision-making and control method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109122633A true CN109122633A (en) | 2019-01-04 |
| CN109122633B CN109122633B (en) | 2023-10-03 |
Family
ID=64802281
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810660859.3A Active CN109122633B (en) | 2018-06-25 | 2018-06-25 | Plant protection unmanned aerial vehicle accurate variable spraying device for neural network decision-making and control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109122633B (en) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109479862A (en) * | 2019-01-18 | 2019-03-19 | 吉林农业大学 | A kind of variable pesticide spraying system and its control method |
| CN109677612A (en) * | 2019-01-17 | 2019-04-26 | 昔阳县农业广播电视学校 | A kind of agricultural planting plant protection drone |
| CN110435892A (en) * | 2019-07-22 | 2019-11-12 | 北京中航智科技有限公司 | A kind of flusher and unmanned plane |
| CN110435893A (en) * | 2019-07-22 | 2019-11-12 | 北京中航智科技有限公司 | A kind of flusher and unmanned plane |
| CN110825118A (en) * | 2019-12-23 | 2020-02-21 | 河南大学 | Multi-unmanned aerial vehicle cooperative farmland spraying method based on deep learning algorithm |
| CN110979686A (en) * | 2019-10-31 | 2020-04-10 | 王国瑞 | Intelligent plant protection unmanned aerial vehicle and use method thereof |
| CN111077780A (en) * | 2019-12-23 | 2020-04-28 | 湖北理工学院 | Intelligent window adjusting method and device based on neural network |
| CN111280151A (en) * | 2020-02-06 | 2020-06-16 | 山东农业大学 | Variable pesticide application control method based on cotton growth period recognition |
| WO2020177506A1 (en) * | 2019-03-06 | 2020-09-10 | 广州极飞科技有限公司 | Pesticide spraying control method, apparatus, and device, and storage medium |
| CN111880558A (en) * | 2020-07-06 | 2020-11-03 | 广东技术师范大学 | Plant protection unmanned aerial vehicle obstacle avoidance spraying method and device, computer equipment and storage medium |
| EP3741214A1 (en) | 2019-05-20 | 2020-11-25 | BASF Agro Trademarks GmbH | Method for plantation treatment based on image recognition |
| CN112565726A (en) * | 2020-12-10 | 2021-03-26 | 广州极飞科技有限公司 | Method for determining job prescription chart, job control method and related device |
| WO2021105017A1 (en) * | 2019-11-25 | 2021-06-03 | Robert Bosch Gmbh | Method for processing plants in a field |
| CN112977828A (en) * | 2021-04-06 | 2021-06-18 | 中国农业科学院都市农业研究所 | Spraying method and device based on unmanned aerial vehicle, electronic equipment and medium |
| CN113247241A (en) * | 2021-06-29 | 2021-08-13 | 扬州大学 | Unmanned aerial vehicle target-aiming accurate pesticide applying system and pesticide applying method thereof |
| CN113460308A (en) * | 2021-07-30 | 2021-10-01 | 中国农业大学 | Unmanned aerial vehicle variable pesticide application control system and method |
| CN113826598A (en) * | 2021-09-10 | 2021-12-24 | 宁波权智科技有限公司 | Unmanned aerial vehicle pesticide spreading method and device based on neural network |
| CN113895631A (en) * | 2021-12-09 | 2022-01-07 | 山东理工职业学院 | Pesticide spraying control equipment, method and medium based on unmanned aerial vehicle |
| CN114445027A (en) * | 2021-12-27 | 2022-05-06 | 江西省交通工程集团有限公司 | Attendance frequency control method and system for spraying vehicle |
| US20220177132A1 (en) * | 2019-03-08 | 2022-06-09 | Toyo Seikan Co., Ltd. | Discharge System for Aircraft |
| CN115500334A (en) * | 2021-06-07 | 2022-12-23 | 中移(成都)信息通信科技有限公司 | Sprayer, plant disease and insect pest identification method and identification equipment |
| CN116050842A (en) * | 2023-02-01 | 2023-05-02 | 东华理工大学 | Dynamic control method and system for urban underground engineering construction safety risk |
| CN117153325A (en) * | 2023-10-30 | 2023-12-01 | 佛山科学技术学院 | Anticancer drug effectiveness evaluation method and system based on graph contrast learning |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103999841A (en) * | 2014-04-18 | 2014-08-27 | 浙江大学 | Automatic targeting and spraying system |
| CN105025262A (en) * | 2015-07-08 | 2015-11-04 | 常州华奥航空科技有限公司 | Large-area agricultural work unmanned plane |
| CN105173085A (en) * | 2015-09-18 | 2015-12-23 | 山东农业大学 | Automatic control system and method for variable pesticide spraying of unmanned aerial vehicle |
| CN106564599A (en) * | 2016-11-22 | 2017-04-19 | 江苏蒲公英无人机有限公司 | Plant protection method for unmanned aerial vehicle based on multispectral remote sensing |
| CN106857467A (en) * | 2017-03-06 | 2017-06-20 | 佳木斯大学 | A kind of brainpower insufflation agricultural chemicals machine and pesticide spraying control method |
| CN206573944U (en) * | 2016-12-21 | 2017-10-20 | 石河子大学 | The accurate pesticide spraying system of rotor wing unmanned aerial vehicle |
| CN108069027A (en) * | 2017-04-28 | 2018-05-25 | 深圳市九天创新科技有限责任公司 | The plant protection system and method for multispectral fixed-wing unmanned plane cooperation plant protection unmanned plane |
| CN108094379A (en) * | 2017-12-26 | 2018-06-01 | 燕山大学 | A kind of fog machine and its paths planning method for being used to perform agriculture automatic spraying task |
| CN208425428U (en) * | 2018-06-25 | 2019-01-25 | 华南农业大学 | The accurate variable-rate spraying device of plant protection drone |
-
2018
- 2018-06-25 CN CN201810660859.3A patent/CN109122633B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103999841A (en) * | 2014-04-18 | 2014-08-27 | 浙江大学 | Automatic targeting and spraying system |
| CN105025262A (en) * | 2015-07-08 | 2015-11-04 | 常州华奥航空科技有限公司 | Large-area agricultural work unmanned plane |
| CN105173085A (en) * | 2015-09-18 | 2015-12-23 | 山东农业大学 | Automatic control system and method for variable pesticide spraying of unmanned aerial vehicle |
| CN106564599A (en) * | 2016-11-22 | 2017-04-19 | 江苏蒲公英无人机有限公司 | Plant protection method for unmanned aerial vehicle based on multispectral remote sensing |
| CN206573944U (en) * | 2016-12-21 | 2017-10-20 | 石河子大学 | The accurate pesticide spraying system of rotor wing unmanned aerial vehicle |
| CN106857467A (en) * | 2017-03-06 | 2017-06-20 | 佳木斯大学 | A kind of brainpower insufflation agricultural chemicals machine and pesticide spraying control method |
| CN108069027A (en) * | 2017-04-28 | 2018-05-25 | 深圳市九天创新科技有限责任公司 | The plant protection system and method for multispectral fixed-wing unmanned plane cooperation plant protection unmanned plane |
| CN108094379A (en) * | 2017-12-26 | 2018-06-01 | 燕山大学 | A kind of fog machine and its paths planning method for being used to perform agriculture automatic spraying task |
| CN208425428U (en) * | 2018-06-25 | 2019-01-25 | 华南农业大学 | The accurate variable-rate spraying device of plant protection drone |
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109677612A (en) * | 2019-01-17 | 2019-04-26 | 昔阳县农业广播电视学校 | A kind of agricultural planting plant protection drone |
| CN109479862B (en) * | 2019-01-18 | 2023-04-07 | 吉林农业大学 | Variable pesticide spraying system and control method thereof |
| CN109479862A (en) * | 2019-01-18 | 2019-03-19 | 吉林农业大学 | A kind of variable pesticide spraying system and its control method |
| WO2020177506A1 (en) * | 2019-03-06 | 2020-09-10 | 广州极飞科技有限公司 | Pesticide spraying control method, apparatus, and device, and storage medium |
| US20220177132A1 (en) * | 2019-03-08 | 2022-06-09 | Toyo Seikan Co., Ltd. | Discharge System for Aircraft |
| EP3936431A4 (en) * | 2019-03-08 | 2022-11-02 | Toyo Seikan Co., Ltd. | Discharge system for flight vehicle |
| WO2020234296A1 (en) * | 2019-05-20 | 2020-11-26 | Basf Agro Trademarks Gmbh | Method for plantation treatment based on image recognition |
| EP3741214A1 (en) | 2019-05-20 | 2020-11-25 | BASF Agro Trademarks GmbH | Method for plantation treatment based on image recognition |
| CN110435893A (en) * | 2019-07-22 | 2019-11-12 | 北京中航智科技有限公司 | A kind of flusher and unmanned plane |
| CN110435892B (en) * | 2019-07-22 | 2022-03-11 | 北京中航智科技有限公司 | Sprinkler and unmanned aerial vehicle |
| CN110435892A (en) * | 2019-07-22 | 2019-11-12 | 北京中航智科技有限公司 | A kind of flusher and unmanned plane |
| CN110979686A (en) * | 2019-10-31 | 2020-04-10 | 王国瑞 | Intelligent plant protection unmanned aerial vehicle and use method thereof |
| WO2021105017A1 (en) * | 2019-11-25 | 2021-06-03 | Robert Bosch Gmbh | Method for processing plants in a field |
| CN111077780A (en) * | 2019-12-23 | 2020-04-28 | 湖北理工学院 | Intelligent window adjusting method and device based on neural network |
| CN110825118A (en) * | 2019-12-23 | 2020-02-21 | 河南大学 | Multi-unmanned aerial vehicle cooperative farmland spraying method based on deep learning algorithm |
| CN111280151A (en) * | 2020-02-06 | 2020-06-16 | 山东农业大学 | Variable pesticide application control method based on cotton growth period recognition |
| CN111880558A (en) * | 2020-07-06 | 2020-11-03 | 广东技术师范大学 | Plant protection unmanned aerial vehicle obstacle avoidance spraying method and device, computer equipment and storage medium |
| CN111880558B (en) * | 2020-07-06 | 2021-05-11 | 广东技术师范大学 | Plant protection unmanned aerial vehicle obstacle avoidance spraying method and device, computer equipment and storage medium |
| CN112565726A (en) * | 2020-12-10 | 2021-03-26 | 广州极飞科技有限公司 | Method for determining job prescription chart, job control method and related device |
| CN112977828A (en) * | 2021-04-06 | 2021-06-18 | 中国农业科学院都市农业研究所 | Spraying method and device based on unmanned aerial vehicle, electronic equipment and medium |
| CN115500334A (en) * | 2021-06-07 | 2022-12-23 | 中移(成都)信息通信科技有限公司 | Sprayer, plant disease and insect pest identification method and identification equipment |
| CN113247241A (en) * | 2021-06-29 | 2021-08-13 | 扬州大学 | Unmanned aerial vehicle target-aiming accurate pesticide applying system and pesticide applying method thereof |
| CN113460308A (en) * | 2021-07-30 | 2021-10-01 | 中国农业大学 | Unmanned aerial vehicle variable pesticide application control system and method |
| CN113826598A (en) * | 2021-09-10 | 2021-12-24 | 宁波权智科技有限公司 | Unmanned aerial vehicle pesticide spreading method and device based on neural network |
| CN113895631A (en) * | 2021-12-09 | 2022-01-07 | 山东理工职业学院 | Pesticide spraying control equipment, method and medium based on unmanned aerial vehicle |
| CN114445027A (en) * | 2021-12-27 | 2022-05-06 | 江西省交通工程集团有限公司 | Attendance frequency control method and system for spraying vehicle |
| CN116050842A (en) * | 2023-02-01 | 2023-05-02 | 东华理工大学 | Dynamic control method and system for urban underground engineering construction safety risk |
| CN116050842B (en) * | 2023-02-01 | 2023-08-04 | 东华理工大学 | Dynamic control method and system for urban underground engineering construction safety risk |
| CN117153325A (en) * | 2023-10-30 | 2023-12-01 | 佛山科学技术学院 | Anticancer drug effectiveness evaluation method and system based on graph contrast learning |
| CN117153325B (en) * | 2023-10-30 | 2024-01-30 | 佛山科学技术学院 | Anticancer drug effectiveness evaluation method and system based on graph contrast learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109122633B (en) | 2023-10-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109122633A (en) | The accurate variable-rate spraying device of the plant protection drone of Decision of Neural Network and control method | |
| Talaviya et al. | Implementation of artificial intelligence in agriculture for optimisation of irrigation and application of pesticides and herbicides | |
| CN111582055B (en) | Unmanned aerial vehicle aviation pesticide application route generation method and system | |
| CN108605923A (en) | Pesticide dispenser monitors and accurate volume control device and method | |
| CN103988824A (en) | Automatic targeting and spraying system based on binocular vision technology | |
| CN103999841A (en) | Automatic targeting and spraying system | |
| Seol et al. | Field evaluations of a deep learning-based intelligent spraying robot with flow control for pear orchards | |
| CN109003198A (en) | A kind of precision agriculture management platform and method based on big data technology | |
| CN108552149A (en) | A kind of unmanned plane fumicants spraying system and spraying method suitable for mountain and hill | |
| CN203860304U (en) | Automatic targeting and spraying system | |
| CN204104581U (en) | A kind of automatic target detection spraying system based on binocular vision technology | |
| CN106681400B (en) | A kind of variable spraying system suitable for unmanned plane | |
| JP2022537910A (en) | A Decision System for Crop Efficiency Product Application Using Remote Sensing Based on Soil Parameters | |
| JP2022526563A (en) | Method for crop treatment of agricultural land using variable spray rate | |
| CN113597874A (en) | Weeding robot and weeding path planning method, device and medium thereof | |
| Partel et al. | Smart Sprayer for Precision Weed Control Using Artificial Intelligence: Comparison of Deep Learning Frameworks. | |
| da Costa Lima et al. | Variable rate application of herbicides for weed management in pre-and postemergence | |
| WO2023082482A1 (en) | Variable spray control system based on annular pesticide application structure and plant canopy volume calculation method | |
| Roman et al. | Stereo vision controlled variable rate sprayer for specialty crops: Part II. Sprayer development and performance evaluation | |
| Patil et al. | Review on automatic variable-rate spraying systems based on orchard canopy characterization | |
| CN102968664A (en) | Mobile robot variable pesticide applying intelligent decision-making method and system | |
| Baltazar et al. | 2d lidar-based system for canopy sensing in smart spraying applications | |
| CN208425428U (en) | The accurate variable-rate spraying device of plant protection drone | |
| CN111288934B (en) | Target leaf area online calculation method based on mobile laser scanning | |
| CN116636518A (en) | Unmanned aerial vehicle pesticide application control method and 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |