CN110440886A - A kind of the seedling disk application rate dynamic metering device and metering method of seedling production line - Google Patents
A kind of the seedling disk application rate dynamic metering device and metering method of seedling production line Download PDFInfo
- Publication number
- CN110440886A CN110440886A CN201910590956.4A CN201910590956A CN110440886A CN 110440886 A CN110440886 A CN 110440886A CN 201910590956 A CN201910590956 A CN 201910590956A CN 110440886 A CN110440886 A CN 110440886A
- Authority
- CN
- China
- Prior art keywords
- weighing
- seedling
- seedling disk
- application rate
- 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
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01C—PLANTING; SOWING; FERTILISING
- A01C7/00—Sowing
- A01C7/20—Parts of seeders for conducting and depositing seed
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01G—HORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING
- A01G9/00—Cultivation in receptacles, forcing-frames or greenhouses; Edging for beds, lawn or the like
- A01G9/08—Devices for filling-up flower-pots or pots for seedlings; Devices for setting plants or seeds in pots
- A01G9/085—Devices for setting seeds in pots
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01G—WEIGHING
- G01G17/00—Apparatus for or methods of weighing material of special form or property
- G01G17/04—Apparatus for or methods of weighing material of special form or property for weighing fluids, e.g. gases, pastes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Soil Sciences (AREA)
- Environmental Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Sowing (AREA)
Abstract
The present invention discloses the seedling disk application rate dynamic metering device and metering method of a kind of seedling production line, including the control system for being set to several Weighing modules of seeding apparatus conveying direction and being connected with Weighing module, the weight of Weighing module support, driving, conveying and detection seedling disk in some position, the weight of several Weighing modules of conveying direction compares to obtain the seedling disk weight change of sowing front and back, control system combination seedling disk weight change, rotating speed of transmission shaft parameter and by establishing model, analysis obtains the accurate application rate of seedling production line.Compared with the prior art, technical solution of the present invention has many advantages, such as that dynamic weighing and weighing are precisely reliable, it can be achieved that seedling production line seedling disk application rate accurately dynamic measuring.
Description
Technical field
The present invention relates to rice growing technical field, in particular to the seedling disk application rate dynamic measuring of a kind of seedling production line
Device and metering method.
Background technique
In Rice Cropping production, application rate of different types of seed rice in seedling planting has different requirements.Positive reason
Under condition, conventional Rice needs dense planting, and hybrid paddy rice then needs this few thin planting, improves yield by the powerful tillering ability of hybrid paddy rice,
So the seedling planting of hybrid paddy rice is needed using Low seeding rate precise sowing technology.
Researchers at home and abroad have carried out certain research to Low seeding rate precise sowing technology at present, but to its true sowing
Amount carries out the rare report of research in terms of measuring with Real-time Feedback, therefore solves the triviality of traditional artificial detection application rate, real
The real time measure and feedback of existing production line application rate, research trends application rate metering device have realization Low seeding rate precise sowing
Significance.
In recent years, lot of domestic and international scholar for dynamic weighing system carry out it is a series of design and study and obtain centainly at
Fruit, such as Mao Jiandong etc. devise a kind of material metage system, establish weighing system dynamic using the thought of piece-wise linearization
ARMA mathematical model recognizes its parameter based on BP neural network;S.M.Maguire etc. devises a kind of for receiving
The dynamic weighing system of single rectangular bale packing weight is determined during obtaining and establishes physical model, passes through Chebyshev's low-pass filtering
Device determines the peak tensions of measurement sensor to obtain weighing value.The studies above personnel's weighing system has made intensive studies,
And establish the symmetrical weight values of correlation model and predicted, have many advantages, such as that weighing speed is fast, but due to no processing vibration well
Etc. factors influence, eventually lead to weighing precision and do not reach desirable.
In view of the above-mentioned problems, Shen little Qian etc. proposes a kind of method based on neural network prediction dynamic weighing final value,
That is genetic algorithm optimization on the basis of BP neural network exports AD value by dynamic line modeling forecasting system stable state, then
Object weight is obtained by the method for weighted moving average.Hao Xiaoxian etc. proposes to calculate based on small echo and the vehicle-mounted dynamic weighing of BP neural network
Method carries out noise filtering pretreatment to vehicle-mounted weighing-up wave first with wavelet transformation, then by vehicle velocity signal, acceleration
Vehicle-mounted weighing-up wave after signal and wavelet pretreatment obtains predicted value as BP neural network input layer building network model.On
It states researcher and digital processing mainly is carried out to weighing-up wave, the symmetrical weight values of model are established using BP algorithm and are predicted, weighing essence
Degree is high, but due to the complexity of algorithm height, causes the response speed of system low.
Therefore according to the requirement of hybrid paddy rice Low seeding rate precise sowing technology, to the application rate of seeder carry out dynamic weighing and
Real-time Feedback is very necessary, and the problem of current dynamic weighing is to solve contradiction between weighing speed and weighing precision, full
In the case of sufficient weighing precision requires, optimization related algorithm and reduction system response time become current technology urgently to be solved and ask
Topic.
Summary of the invention
The main object of the present invention is that a kind of seedling disk application rate for the seedling production line for proposing that homework precision is high, effect is good is dynamic
State metering device, the present invention also propose a kind of metering method of seedling disk application rate dynamic metering device using seedling production line,
Aim at seedling production line seedling disk application rate accurately dynamic measuring.
To achieve the above object, the seedling disk application rate dynamic metering device of a kind of seedling production line proposed by the present invention, packet
Include the control system for being set to several Weighing modules of seeding apparatus conveying direction and being connected with Weighing module, Weighing module
The weight of support, driving, conveying and detection seedling disk in some position, the weight comparison of several Weighing modules of conveying direction
The seedling disk weight change of sowing front and back is obtained, control system combination seedling disk weight change, rotating speed of transmission shaft parameter simultaneously pass through foundation
Model, analysis obtain the accurate application rate of seedling production line.
Preferably, the Weighing module include be set to seeding apparatus conveying direction front the first Weighing module and
Be set to second Weighing module at rear portion, the first Weighing module and the second Weighing module all have upper weighing support setting up and down and
Lower weighing support, lower weighing support front and rear sides are fixedly linked with support plate lower part respectively, and support plate top can adjust up and down with rack
It is connected, weighing sensor is equipped between lower weighing support and upper weighing support;Upper weighing support front and rear sides are solid with support frame lower part respectively
Fixed to be connected, the roller that several transmission seedling disks are equipped with above the support frame of two sides send disc mechanism to be connected.
Preferably, it includes the transmission shaft for conveying seedling disk that the roller, which send disc mechanism, if drive shaft circumference face is equipped with
Dry spaced rubber rollers;Two driven biographies are arranged in the top of first Weighing module and second Weighing module
Moving axis, the end of slave drive axis is not provided with sprocket wheel and end is connected by bearing with support frame as described above top, slave drive
The front of axis is equipped with driving transmission shaft, and driving the velocity of rotation of transmission shaft is n0。
Preferably, several intermediate propeller shafts for being used to cooperate transmission seedling disk are equipped between two slave drive axis,
The velocity of rotation n of intermediate propeller shaft1, the driving transmission shaft is socketed with head sprocket and driven sprocket simultaneously with side end to be connected,
Head sprocket is motor driven by chain, and driven sprocket is driven the sprocket wheel of intermediate propeller shaft end by horizontally disposed chain
It is dynamic, n1> n0, intermediate propeller shaft outer peripheral surface is cased with several spaced rubber rollers, the rubber rollers of the slave drive axis
The outer peripheral surface top of son is higher than the rubber rollers outer peripheral surface tip height of intermediate propeller shaft.
Preferably, the control system includes state monitoring module, data acquisition module and data processing module, state prison
It surveys module and data acquisition module is made of sensor and controller, sensor includes being connected with the rack and for detecting seedling
It the photoelectric sensor of disk delivery situation, the weighing sensor being set between the lower weighing support and the upper weighing support and sets
It is placed in rack and the Hall sensor for detecting rotating speed of transmission shaft, controller is then the STM32 single-chip microcontroller that is connected with sensor
Control circuit, data processing module include signal pre-processing module and neural net model establishing unit.
Preferably, collected " seedling disk weight " information is carried out noise reduction by wavelet transformation by the signal pre-processing module
Processing realizes that weighing actual signal separates and remove noise purpose with noise signal by the high and low frequency information in separation signal.
Preferably, the neural net model establishing unit is the BP neural network based on genetic algorithm optimization, BP neural network
The model of prediction is made of input layer, hidden layer and output layer, by pretreated " application rate " and " rotating speed of transmission shaft " information
As 2 neurons of mode input, 1 neuron of the application rate predicted value as output establishes BP neural network prediction mould
Type is optimized with threshold value by initial weight of the genetic algorithm to BP neural network, accelerates the convergence rate of model.
The present invention also proposes a kind of metering method of seedling disk application rate dynamic metering device using the seedling production line,
The following steps are included:
Step S1: the driving transmission shaft drives through sprocket wheel chain, so drive the roller send disc mechanism it is described in
Between transmission shaft rotate, through shop fixtures soil device complete paving soil seedling disk enter to be connected with first Weighing module be used for seedling disk
On two slave drive axis of support, by the seedling disk weight Q before the weighing sensor detection sowing of the first Weighing modulea;
Step S2: seedling disk continues to be passed through the seeding apparatus by driving and completed sowing, and enters to and claim with described second
Two slave drive axis for the support of seedling disk that molality block is connected detect sowing by the weighing sensor of the second Weighing module
Preceding seedling disk weight Qb;
Step S3: noise reduction pretreatment is carried out to seedling disk weight information by wavelet transformation, is calculated using data processing module
Seedling disk " application rate Q " out, wherein Q=Qb- Qa, the Hall sensor acquires " rotating speed of transmission shaft " information, last seedling disk simultaneously
Production line overall operation is completed into surface soil device is covered;
Step S4: by genetic algorithm optimization BP neural network structure, " application rate " and " rotating speed of transmission shaft " information is built
Vertical prediction model, obtains application rate predicted value and is shown in panel.
Preferably, in the step S3, noise reduction pretreatment is carried out to seedling disk weight information by wavelet transformation and is specifically included
Following steps:
S31: selection db4 wavelet basis function carries out wavelet decomposition to original seedling disk weighing-up wave, obtains original point of each size
Coefficient is solved, is shown through experimental study repeatedly best to 3 layers of wavelet decompositions denoising effect of weighing-up wave progress;
S32: one suitable threshold value of selection and threshold function table carry out threshold value quantizing processing to coefficient of wavelet decomposition, are greater than threshold
The coefficient of wavelet decomposition of value is weighing-up wave and is retained that the coefficient of wavelet decomposition less than threshold value is set for noise signal
Zero processing obtains estimation wavelet coefficient;
S33: wavelet decomposition out to out low frequency coefficient and the high frequency coefficient by threshold function table processing are subjected to small echo weight
Structure, the seedling disk weight signal after being denoised.
Preferably, the step of establishing prediction model include:
S41: selecting normalized function and goes back original function to input sample " application rate " and " rotating speed of transmission shaft " and output sample
This " application rate predicted value " is normalized, and avoids causing neural network forecast because inputoutput data order of magnitude difference is larger
Error is larger;
S42: initialization evolution number, population scale, crossover probability and mutation probability carry out real coding to population, and
Using the error between prediction data and expected data as fitness function;
S43: circulation is selected, is intersected, being made a variation, calculating fitness operation, until reaching evolution number, is obtained optimal
Initial weight and threshold value;
S44: obtained optimal initial weight and threshold value are constructed into BP neural network, sample set is divided into training set and survey
Examination collection is trained and tests to network, and the data renormalization of prediction is analyzed between prediction data and expected data
Error.
Technical solution of the present invention has the advantage that compared with the prior art
The weighing structure that the seedling disk application rate dynamic metering device of the seedling production line of technical solution of the present invention uses has
The advantages that stability is high, weighing support is horizontal adjustable and is suitable for complicated landform, the roller on Weighing module send disc mechanism to use
Driven works eliminate the influence because of system vibration to weighing-up wave, preferred high accuracy sensor and controller, have letter
Number acquisition and system response time is fast and the characteristics such as weighing precision is high.
Technical solution of the present invention pre-process and based on genetic algorithm to " seedling disk weight " information using wavelet transformation
BP neural network modeling realize the dynamic measuring of seedling production line seedling disk application rate, solve the cumbersome of traditional artificial weighing
Property, it is the important link that seedling production line realizes automation.
In addition the present invention also can be used for the seedling disk application rate metering of the seedling production line such as flowers, vegetables, and reliable performance has
Practical application value.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
The structure shown according to these attached drawings obtains other attached drawings.
Fig. 1 is the structural schematic diagram of seedling production line general assembly of the invention;
Fig. 2 is the schematic perspective view of the first weighing support of the invention;
Fig. 3 is the partial structure diagram of the first weighing support of the invention;
Fig. 4 is the seedling disk application rate dynamic metering device schematic diagram of seedling production line of the invention;
Fig. 5 is the work flow diagram of the seedling disk application rate dynamic metering device of seedling production line of the invention.
Drawing reference numeral explanation:
Label | Title | Label | Title |
1 | Motor | 5 | Hall sensor |
2 | Shop fixtures soil device | 6 | First weighing sensor |
3 | Roller send disc mechanism | 7 | First photoelectric sensor |
3-1 | Drive transmission shaft | 8 | Support member |
3-2 | Slave drive axis | 8-1 | Support frame |
3-3 | Intermediate propeller shaft | 8-2 | Support plate |
3-4 | Intermediate propeller shaft | 9 | Seeding apparatus |
3-5 | Slave drive axis | 10 | Second Weighing module |
3-6 | Sprocket wheel | 11 | Second weighing sensor |
4 | First Weighing module | 12 | Second photoelectric sensor |
4-1 | Upper weighing support | 13 | Cover surface soil device |
4-2 | Lower weighing support | 14 | Rack |
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 it is all its
His embodiment, shall fall within the protection scope of the present invention.
It is to be appreciated that if relating to directionality instruction (such as up, down, left, right, before and after ...) in the embodiment of the present invention,
Then directionality instruction be only used for explain under a certain particular pose (as shown in the picture) between each component relative 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 skill
The quantity of art feature." first " is defined as a result, the feature of " second " can explicitly or implicitly include at least one spy
Sign.It in addition, the technical solution between each embodiment can be combined with each other, but must be with those of ordinary skill in the art's energy
It is enough realize based on, will be understood that the knot of this technical solution when conflicting or cannot achieve when occurs in the combination of technical solution
Conjunction is not present, also not the present invention claims protection scope within.
The present invention proposes the seedling disk application rate dynamic metering device and metering method of a kind of seedling production line.
Referring to Figure 1 to Fig. 4, include in the seedling disk application rate dynamic metering device of the seedling production line of the embodiment of the present invention
The control system for being set to several Weighing modules of seeding apparatus conveying direction and being connected with Weighing module, Weighing module branch
Support, driving convey and detect seedling disk in the weight of some position, and the weight of several Weighing modules of conveying direction compares
To the seedling disk weight change of sowing front and back, control system combination seedling disk weight change, rotating speed of transmission shaft parameter and by establishing mould
Type, analysis obtain the accurate application rate of seedling production line.
Referring to Figure 1 to Fig. 3, two Weighing modules of the present embodiment include first be set to before seeding apparatus 9 is sowed
Weighing module 4 and it is set to the second Weighing module 10 of seeding apparatus 9 after planting, first Weighing module 4 of the present embodiment and the
Two Weighing modules 10 have identical structure, and specific structure includes the weighing support being connected with rack 14, and wherein weighing support includes upper title
Weight frame 4-1 and lower weighing support 4-2, the lower front and rear sides weighing support 4-2 are fixedly linked with the lower part support plate 8-2 respectively, and support plate
The top 8-2 is fixedly linked with rack 14, and is provided with the first title between the top lower weighing support 4-2 and the lower part upper weighing support 4-1
Sensor 6 is retransmitted, therefore lower weighing support 4-2 supports the upper bearing frame 4-2 on top by the first weighing sensor 6.It needs to illustrate
It is that upper weighing support 4-1 and rack 14 are disconnected relationship, so that upper weighing support 4-1 can support seedling disk and for detecting seedling
The weight change of disk, the front and rear sides of upper weighing support 4-1 are fixedly linked with the lower part support frame 8-1 of support member 8 respectively, two sides
The top support frame 8-1 send slave drive axis 3-2,3-5 of disc mechanism 3 to be connected with roller simultaneously, wherein roller send the packet of disc mechanism 3
Include slave drive axis 3-2, driving transmission shaft 3-1 and auxiliary for main driving horizontally disposed and for detecting seedling disk weight
Intermediate propeller shaft 3-3,3-4 of driving, wherein driving transmission shaft 3-1, slave drive axis 3-2 and intermediate propeller shaft 3-3,3-4
Outer peripheral surface be axially installed with several spaced rubber rollers, it should be noted that the end of slave drive axis 3-2 is simultaneously
It is not provided with sprocket wheel, and the both ends of intermediate propeller shaft 3-3,3-4 are respectively arranged with sprocket wheel 3-6.In the present embodiment with support frame 8-1
Connected roller send disc mechanism 3 to need support seedling disk, therefore the outer peripheral surface surface roughness with higher of rubber rollers, to keep away
Exempt from seedling disk transmission process to skid.The both ends of slave drive axis 3-2,3-5 are set to upper weighing support 4-1 by support frame 8-1
Top, although and slave drive axis 3-2,3-5 both ends pass through rack 14, the siding of organic frame 14 does not rotate directly
It is connected, therefore slave drive axis 3-2,3-5 can be effectively applied to weighing and conveying seedling disk on Weighing module.
In addition, two rollers on the present embodiment Weighing module send and are additionally provided with two intermediate propeller shaft 3- between disc mechanism 3
3,3-4, the outer peripheral surface of intermediate propeller shaft 3-3,3-4 are axially installed with several intermediate rubber rollers to cooperate roller to send disc mechanism
3 slave drive axis 3-2,3-5 transmits seedling disk, and the both ends of intermediate propeller shaft 3-3,3-4 are each passed through rack 14 and and rack
14 are rotatedly connected, in order to guarantee that two rollers of front and back send the top of the rubber rollers of slave drive axis 3-2,3-5 of disc mechanism 3
It will not be interfered by other rubber rollers in seedling disk weighing process, the roller of the present embodiment send the slave drive axis of disc mechanism 3
The outer peripheral surface top of the rubber rollers of 3-2,3-5 is higher than the rubber rollers outer peripheral surface tip height of intermediate propeller shaft 3-3,3-4.For
Guarantee that seedling disk is separated in weighing process with certain spacing, two transmission shaft 3-3,3-4 revolving speeds of the centre of the present embodiment
Faster compared with two sides rotating speed of transmission shaft.Two rollers of the present embodiment send the both ends slave drive axis 3-2,3-5 of disc mechanism 3 to be not provided with
Drive sprocket, and the end slave drive axis 3-2,3-5 does not contact with rack, and carrying seedling disk is only served in seedling disk transmission process
Effect, does not play active transmission, is passive transport.
Be equipped with the long hole being vertically arranged at the top of the support plate 8-2 of the present embodiment, thus adaptability adjust support plate 8-2
With the link position between rack 14, weighing support 4-1 and lower weighing support 4-2 is made to be in horizontality.
Fig. 2 to Fig. 4 is referred to, the control system of the present embodiment includes state monitoring module, data acquisition module and data
Processing module, wherein state monitoring module and data acquisition module are mainly made of sensor and controller, sensor include with
Rack 14 is connected and for detecting the conveying of seedling disk the first photoelectric sensor 7 and the second photoelectric sensor 12 of situation, setting in place
In between the top lower weighing support 4-2 and the lower part upper weighing support 4-1 the first weighing sensor 6 and the second weighing sensor 11 with
And it is set to rack 14 and the Hall sensor 5 for detecting rotating speed of transmission shaft, and the controller of the present embodiment is that STM32F4 is mono-
The control circuit of piece machine.
Specifically, it in the present embodiment, is set to the first weighing sensor 6 inside the first Weighing module 4 and is broadcast for measuring
Seedling disk weight Q before kinda, it is set to the second weighing sensor 11 inside the second Weighing module 10 and is used to measure seedling after planting
Disk weight Qb.First photoelectric sensor 7 and the second photoelectric sensor 12 of the present embodiment are respectively arranged in the side of rack and lean on
The rear of the traffic direction of nearly seedling disk and the information in place for being used to detect seedling disk.
In addition, the data processing module of the present embodiment includes signal pre-processing module and neural net model establishing unit, wherein
Collected " seedling disk weight " information is carried out noise reduction process by wavelet transformation by signal pre-processing module, by separation signal
High and low frequency information reach removal noise purpose, and neural network to realize the separation of weighing actual signal and noise signal
Modeling unit is a kind of BP neural network based on genetic algorithm optimization.The control system of the present embodiment adopts data acquisition module
The data of collection and actual weighing information establish BP neural network model, pass through genetic algorithm pair respectively as input and output
The initial weight of BP neural network is optimized with threshold value, further decreases the calculating error of BP neural network.
Referring to Figure 1 to Fig. 5, the work of the seedling disk application rate dynamic metering device of the seedling production line of the present embodiment is former
Reason:
The seedling disk application rate dynamic metering device of the seedling production line of the present embodiment at work, the first Weighing module 4 into
The motor 1 of row running, 4 lower part of the first Weighing module drives driving transmission shaft 3-1 to be rotated by sprocket wheel chain, accordingly
Ground, driving transmission shaft 3-1 operates intermediate propeller shaft 3-3,3-4 by horizontally disposed sprocket wheel chain, when seedling disk passes through shop fixtures
After native device 2 completes paving soil, then the first Weighing module 4 can be sequentially entered, and under the action of driving transmission shaft 3-1, completely
Into on slave drive axis 3-2, the 3-5 being connected with weighing support, the first photoelectric sensor 7 detects and is given to disk signal at this time,
First weighing sensor 6 of the first Weighing module 4 measures seedling disk weight Qa, then impetus of the seedling disk in the latter seedling disk
Under, the latter slave drive axis being connected with weighing support is left, is moved on into intermediate propeller shaft, it is complete by seeding apparatus 9
At after planting, seedling disk fully enters the second weighing support 10 of the second Weighing module 10, complete under the action of driving transmission shaft 3-1
Complete to enter on slave drive axis 3-2, the 3-5 being connected with weighing support, the second photoelectric sensor 12 detects and is given to disk letter at this time
Number, the second weighing sensor 11 of the second Weighing module 10 measures seedling disk weight Q at this timeb, then by wavelet transformation to seedling disk
Weight information carries out noise reduction pretreatment, calculates seedling disk " application rate Q " using data processing module, wherein Q=Qb- Qa, with this
Hall sensor 5 acquires " rotating speed of transmission shaft " information simultaneously, and last seedling disk is integrally made into the completion production line of surface soil device 13 is covered
Industry.
By input layer, hidden layer and output layer, totally 3 parts form the BP neural network prediction model of the present embodiment, pass through by
Pretreated " application rate Q " and " rotating speed of transmission shaft " information 2 neurons as input, application rate predicted value is as output
1 neuron, establish BP neural network prediction model.Since default precision of the node in hidden layer to BP neural network has very
Big influence, by constantly iterating to calculate it can be found that when node in hidden layer is 5, network structure is 2 × 5 × 1, instruction
Practicing error can reach model goal-selling precision, and training performance is best.
The learning process of BP neural network is the connection weight and threshold process that dynamic adjusts neuron, however BP algorithm exists
It, only will without considering the gradient direction before the moment by the gradient descent direction adjustment of the error at certain moment when adjusting weight
It will lead to search capability difference and easily fall into Local Minimum.Genetic algorithm can be used to global optimizing, first by the weight of BP network with
Threshold value is converted into the chromosome in hereditary space with binary coding, and generates initial population at random and carry out heredity, intersect, variation
Operation, screens individual according to certain fitness function, until neural metwork training is completed, optimum dyeing body is selected to make
For the weight of BP network.Sunken people's local minimum, fast convergence rate, search can be effectively avoided in BP algorithm based on genetic algorithm
Ability is strong, improves training speed.The result shows that the present embodiment technical solution is by introducing genetic algorithm optimization BP network knot
Structure, solving the problems, such as that BP network algorithm provides predicted value cannot be constant, and it is slow to compensate for system dynamic response to a certain extent
Defect, and compared to standard BP algorithm, precision improves 2%, has got good effect.Therefore the present invention is claimed using dynamic
The method of weight realizes the dynamic measuring of production line seedling disk application rate, and homework precision is high, effect is good, has application value.
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/it is used in it indirectly
He is included in scope of patent protection of the invention relevant technical field.
Claims (10)
1. a kind of seedling disk application rate dynamic metering device of seedling production line, which is characterized in that defeated including being set to seeding apparatus
The control system sending several Weighing modules in direction and being connected with Weighing module, Weighing module support, driving, conveying and
Seedling disk is detected in the weight of some position, the weight of several Weighing modules of conveying direction compares to obtain the seedling disk of sowing front and back
Weight change, control system combination seedling disk weight change, rotating speed of transmission shaft parameter and by establishing model, it is raw that analysis obtains seedling
The accurate application rate of producing line.
2. the seedling disk application rate dynamic metering device of seedling production line as described in claim 1, which is characterized in that the weighing
Module includes the second weighing mould for being set to the first Weighing module of seeding apparatus conveying direction front and being set to rear portion
Block, the first Weighing module and the second Weighing module all have upper weighing support and lower weighing support setting up and down, lower weighing support front and back
Two sides are fixedly linked with support plate lower part respectively, and support plate top can adjust up and down with rack to be connected, lower weighing support and upper weighing
Weighing sensor is equipped between frame;Upper weighing support front and rear sides are fixedly linked with support frame lower part respectively, on the support frame of two sides
The roller that side is equipped with several transmission seedling disks send disc mechanism to be connected.
3. the seedling disk application rate dynamic metering device of seedling production line as claimed in claim 2, which is characterized in that the roller
Sending disc mechanism includes the transmission shaft for conveying seedling disk, and drive shaft circumference face is equipped with several spaced rubber rollers;
Two slave drive axis are arranged in the top of first Weighing module and second Weighing module, and the end of slave drive axis is simultaneously
It being not provided with sprocket wheel and end is connected by bearing with support frame as described above top, the front of slave drive axis is equipped with driving transmission shaft,
The velocity of rotation for driving transmission shaft is n0。
4. the seedling disk application rate dynamic metering device of seedling production line as claimed in claim 3, which is characterized in that described in two
Several intermediate propeller shafts for being used to cooperate transmission seedling disk, the velocity of rotation n of intermediate propeller shaft are equipped between slave drive axis1,
The driving transmission shaft is connected with head sprocket and driven sprocket socket simultaneously with side end, and head sprocket is driven by chain by motor
Dynamic, driven sprocket is by horizontally disposed chain by the chain wheel drive of intermediate propeller shaft end, n1> n0, intermediate propeller shaft periphery
Surface cover has several spaced rubber rollers, and the outer peripheral surface top of the rubber rollers of the slave drive axis is higher than intermediate pass
The rubber rollers outer peripheral surface tip height of moving axis.
5. the seedling disk application rate dynamic metering device of seedling production line as claimed in claim 4, which is characterized in that the control
System includes state monitoring module, data acquisition module and data processing module, state monitoring module and data acquisition module by
Sensor and controller composition, sensor include the photoelectric sensing for being connected with the rack and be used to detect seedling disk delivery situation
Device, the weighing sensor being set between the lower weighing support and the upper weighing support and be set to rack and for detect pass
The Hall sensor of moving axis revolving speed, controller are then the control circuit of STM32 single-chip microcontroller of being connected with sensor, data processing module
Including signal pre-processing module and neural net model establishing unit.
6. the seedling disk application rate dynamic metering device of seedling production line as claimed in claim 5, which is characterized in that the signal
Collected " seedling disk weight " information is carried out noise reduction process by wavelet transformation by preprocessing module, passes through the height in separation signal
Low-frequency information realizes that weighing actual signal separates and remove noise purpose with noise signal.
7. the seedling disk application rate dynamic metering device of seedling production line as claimed in claim 6, which is characterized in that the nerve
Network modelling unit is the BP neural network based on genetic algorithm optimization, and the model of BP neural network prediction is by input layer, implicit
Layer and output layer composition, using pretreated " application rate " and " rotating speed of transmission shaft " information as 2 neurons of mode input,
1 neuron of the application rate predicted value as output, establishes BP neural network prediction model, by genetic algorithm to BP nerve net
The initial weight of network is optimized with threshold value, accelerates the convergence rate of model.
8. a kind of metering method of the seedling disk application rate dynamic metering device using seedling production line as claimed in claim 7,
It is characterized in that, comprising the following steps:
Step S1: the driving transmission shaft drives through sprocket wheel chain, and then the driving roller send the intermediate biography of disc mechanism
Moving axis rotation, the seedling disk for completing paving soil through shop fixtures soil device enter to the seedling disk that is used for being connected with first Weighing module and support
Two slave drive axis on, by the first Weighing module weighing sensor detection sowing before seedling disk weight Qa;
Step S2: seedling disk continues to be passed through the seeding apparatus by driving and completed sowing, and enters to and the second weighing mould
Two slave drive axis for the support of seedling disk that block is connected, before the weighing sensor detection sowing of the second Weighing module
Seedling disk weight Qb;
Step S3: noise reduction pretreatment is carried out to seedling disk weight information by wavelet transformation, calculates seedling using data processing module
Disk " application rate Q ", wherein Q=Qb- Qa, the Hall sensor acquires " rotating speed of transmission shaft " information simultaneously, and last seedling disk enters
It covers surface soil device and completes production line overall operation;
Step S4: by genetic algorithm optimization BP neural network structure, " application rate " and " rotating speed of transmission shaft " information are established pre-
Model is surveyed, application rate predicted value is obtained and is shown in panel.
9. metering method as claimed in claim 8, which is characterized in that in the step S3, by wavelet transformation to seedling disk weight
Measure information carry out noise reduction pretreatment specifically includes the following steps:
S31: selection db4 wavelet basis function carries out wavelet decomposition to original seedling disk weighing-up wave, obtains each size original decomposition system
Number shows best to 3 layers of wavelet decompositions denoising effect of weighing-up wave progress through experimental study repeatedly;
S32: one suitable threshold value of selection and threshold function table carry out threshold value quantizing processing to coefficient of wavelet decomposition, greater than threshold value
Coefficient of wavelet decomposition is weighing-up wave and is retained that the coefficient of wavelet decomposition less than threshold value carries out at zero setting for noise signal
Reason obtains estimation wavelet coefficient;
S33: wavelet decomposition out to out low frequency coefficient and the high frequency coefficient by threshold function table processing are subjected to wavelet reconstruction, obtained
Seedling disk weight signal after to denoising.
10. metering method as claimed in claim 8, which is characterized in that the step of establishing prediction model include:
S41:, which selecting normalized function, and goes back original function " broadcasts input sample " application rate " and " rotating speed of transmission shaft " and output sample
Kind amount predicted value " is normalized, and avoids causing neural network forecast error because inputoutput data order of magnitude difference is larger
It is larger;
S42: initialization evolution number, population scale, crossover probability and mutation probability carry out real coding to population, and will be pre-
Error between measured data and expected data is as fitness function;
S43: circulation, which selected, intersected, made a variation, calculates fitness operates, and until reaching evolution number, obtains optimal initial
Weight and threshold value;
S44: obtained optimal initial weight and threshold value are constructed into BP neural network, sample set is divided into training set and test set
Network is trained and is tested, and by the data renormalization of prediction, analyzes the error between prediction data and expected data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910590956.4A CN110440886B (en) | 2019-07-02 | 2019-07-02 | Dynamic metering device and metering method for seeding quantity of seedling trays of seedling raising production line |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910590956.4A CN110440886B (en) | 2019-07-02 | 2019-07-02 | Dynamic metering device and metering method for seeding quantity of seedling trays of seedling raising production line |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110440886A true CN110440886A (en) | 2019-11-12 |
CN110440886B CN110440886B (en) | 2021-03-26 |
Family
ID=68429405
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910590956.4A Active CN110440886B (en) | 2019-07-02 | 2019-07-02 | Dynamic metering device and metering method for seeding quantity of seedling trays of seedling raising production line |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110440886B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114342605A (en) * | 2021-12-14 | 2022-04-15 | 江苏大学 | Multi-information fusion rice and wheat seeder seeding rate estimation method and monitoring system |
CN116267326A (en) * | 2023-02-22 | 2023-06-23 | 华南农业大学 | Intelligent seedling tray seeding rate regulating and controlling device and method for rice seedling raising production line |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120316673A1 (en) * | 2011-06-10 | 2012-12-13 | Great Plains Manufacturing, Incorporated | Agricultural implement having hopper weighing system |
CN104041229A (en) * | 2014-06-06 | 2014-09-17 | 江苏大学 | Self-adaption inclined vibration seed disc mechanism and control method |
CN107091663A (en) * | 2017-07-03 | 2017-08-25 | 南京农业大学 | A kind of the real-time of combined seed and fertilizer drill broadcasts amount detecting device and detection method |
CN107367315A (en) * | 2017-08-29 | 2017-11-21 | 南京农业大学 | A kind of Weighing type broadcasts amount detecting device |
CN108323282A (en) * | 2018-02-10 | 2018-07-27 | 安徽农业大学 | A kind of grain and oil crop quantity-variation type seeding system based on adaptive Fuzzy PID Control |
CN207948098U (en) * | 2017-08-08 | 2018-10-12 | 华南农业大学 | A kind of high-efficient automatic rice industrial precise sowing seedling production line |
CN109060085A (en) * | 2018-08-27 | 2018-12-21 | 南京迈欧机械制造有限公司 | A kind of mostly package dynamic weighing method and meausring apparatus |
CN109429630A (en) * | 2018-12-12 | 2019-03-08 | 徐州超伟电子股份有限公司 | It is a kind of can be to the walking machine of ride-height and application rate early warning |
-
2019
- 2019-07-02 CN CN201910590956.4A patent/CN110440886B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120316673A1 (en) * | 2011-06-10 | 2012-12-13 | Great Plains Manufacturing, Incorporated | Agricultural implement having hopper weighing system |
CN104041229A (en) * | 2014-06-06 | 2014-09-17 | 江苏大学 | Self-adaption inclined vibration seed disc mechanism and control method |
CN107091663A (en) * | 2017-07-03 | 2017-08-25 | 南京农业大学 | A kind of the real-time of combined seed and fertilizer drill broadcasts amount detecting device and detection method |
CN207948098U (en) * | 2017-08-08 | 2018-10-12 | 华南农业大学 | A kind of high-efficient automatic rice industrial precise sowing seedling production line |
CN107367315A (en) * | 2017-08-29 | 2017-11-21 | 南京农业大学 | A kind of Weighing type broadcasts amount detecting device |
CN108323282A (en) * | 2018-02-10 | 2018-07-27 | 安徽农业大学 | A kind of grain and oil crop quantity-variation type seeding system based on adaptive Fuzzy PID Control |
CN109060085A (en) * | 2018-08-27 | 2018-12-21 | 南京迈欧机械制造有限公司 | A kind of mostly package dynamic weighing method and meausring apparatus |
CN109429630A (en) * | 2018-12-12 | 2019-03-08 | 徐州超伟电子股份有限公司 | It is a kind of can be to the walking machine of ride-height and application rate early warning |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114342605A (en) * | 2021-12-14 | 2022-04-15 | 江苏大学 | Multi-information fusion rice and wheat seeder seeding rate estimation method and monitoring system |
CN116267326A (en) * | 2023-02-22 | 2023-06-23 | 华南农业大学 | Intelligent seedling tray seeding rate regulating and controlling device and method for rice seedling raising production line |
CN116267326B (en) * | 2023-02-22 | 2024-05-28 | 华南农业大学 | Intelligent seedling tray seeding rate regulating and controlling device and method for rice seedling raising production line |
Also Published As
Publication number | Publication date |
---|---|
CN110440886B (en) | 2021-03-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104457936B (en) | Potted plant growing trend dynamic detection device and detection method thereof | |
CN109115776A (en) | A kind of Plug seedling growing way non-destructive monitoring method and device based on color and depth information | |
CN110440886A (en) | A kind of the seedling disk application rate dynamic metering device and metering method of seedling production line | |
CN107545890A (en) | A kind of sound event recognition method | |
CN100554969C (en) | The measuring method of turbulence condition low concentration sludge settlement rate and device | |
CN112418013A (en) | Complex working condition bearing fault diagnosis method based on meta-learning under small sample | |
CN111985494A (en) | Road disease detection and classification method based on lightweight vehicle-mounted terminal | |
CN105158186A (en) | Method for detecting black core of white radish based on hyperspectral image | |
CN102488518B (en) | Electroencephalogram detection method and device by utilizing fluctuation index and training for promotion | |
CN102750584B (en) | On-corncob corn niblet counting method | |
CN105170485A (en) | Kiwi fruit detecting and grading device | |
CN103270837A (en) | Variable seeding control system and method based on pressure sensor | |
CN112653991A (en) | WLAN indoor positioning method of TebNet neural network model based on deep learning | |
CN110471111A (en) | A kind of normal-moveout spectrum automatic pick method based on convolutional neural networks | |
CN104996181B (en) | A kind of cotton top-cutting machine and its control method of pinching | |
CN111881864A (en) | Wisdom farming crops growth full-period full-dynamic monitoring management system | |
CN108781657A (en) | A kind of Sowing machine for potatoes and its broadcast leakage detection method and detection device | |
CN106198885A (en) | A kind of Combine Harvester Grain water content on-line testing device and method | |
CN110531039A (en) | A kind of grain mildew detection method and device based on WiFi equipment | |
CN104730027B (en) | The method that puccinia striiformis uredospores germination rate is determined using near-infrared spectrum technique | |
CN110082106A (en) | A kind of Method for Bearing Fault Diagnosis of the depth measure study based on Yu norm | |
CN205032397U (en) | Kiwi fruit detects grading plant | |
CN117063714A (en) | Pepper harvester motion parameter control method based on point cloud image combination | |
CN116724755A (en) | Impulse type grain sensor output monitoring test bed system | |
CN114528773B (en) | Track traffic stray current waveform prediction system and method based on big data analysis |
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 |