CN106444378B - Plant cultivating method and system based on Internet of Things big data analysis - Google Patents
Plant cultivating method and system based on Internet of Things big data analysis Download PDFInfo
- Publication number
- CN106444378B CN106444378B CN201610883950.2A CN201610883950A CN106444378B CN 106444378 B CN106444378 B CN 106444378B CN 201610883950 A CN201610883950 A CN 201610883950A CN 106444378 B CN106444378 B CN 106444378B
- Authority
- CN
- China
- Prior art keywords
- plant
- individual
- population
- layer
- dominant
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000007405 data analysis Methods 0.000 title claims abstract description 20
- 239000002689 soil Substances 0.000 claims abstract description 32
- 230000036541 health Effects 0.000 claims abstract description 21
- 238000013528 artificial neural network Methods 0.000 claims abstract description 19
- 239000003337 fertilizer Substances 0.000 claims abstract description 19
- 230000002262 irrigation Effects 0.000 claims abstract description 19
- 238000003973 irrigation Methods 0.000 claims abstract description 19
- 239000011159 matrix material Substances 0.000 claims abstract description 16
- 238000005286 illumination Methods 0.000 claims abstract description 13
- 230000002068 genetic effect Effects 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 8
- 230000012010 growth Effects 0.000 claims description 8
- 210000002569 neuron Anatomy 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 4
- 230000035772 mutation Effects 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 210000000349 chromosome Anatomy 0.000 claims description 2
- 230000007613 environmental effect Effects 0.000 claims 1
- 230000004720 fertilization Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- -1 dose Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008635 plant growth Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of plant cultivating method and system based on Internet of Things big data analysis, method therein includes: the type of herborization, soil moisture, soil pH value, intensity of illumination, environment temperature, ambient humidity, image, irrigation amount, dose, Fertilizer Type and constitutes influence factor matrix X, and is uploaded to server；Wherein, irrigation amount, dose and Fertilizer Type constitute decision variable；, using the complex nonlinear relationship between each influence factor matrix X of Elman neural network plant and plant health index, plant cultivation model is being obtained in server；Plant cultivation model is optimized using II algorithm of NSGA-, obtains one group of optimal solution of decision variable；Using this group of optimal solution of decision variable as the recommendation decision X of plant*It is shown by the terminal device that server is issued to user；User cultivates plant according to the recommendation decision that terminal device is shown.It can determine optimal plant cultivation scheme using the present invention, built better living environment for plant.
Description
Technical field
The present invention relates to plant intelligent cultivation fields, and in particular to a kind of plant cultivation based on Internet of Things big data analysis
Method and system.
Background technique
With the rapid development of the national economy, potted plant enters thousand as a kind of mode for increasing residence comfort
Ten thousand families.But since most plants owner lacks planting plants experience, make plant long term growth in the environment of inferior health.Another party
Face, since the interior space is limited, plant owner can require plant to have different dense degree according to own situation, avoid space unrestrained
Take.
Currently, the problem of urgent need to resolve is to establish a set of comprehensive plant cultivation model, and plant health index is fed back
To user, user can adjust in time to plant cultivation scheme.It influences between each factor of plant health degree often
The complexity of height and non-linear is embodied, using conventional prediction, there are certain difficulty for analysis method.
Summary of the invention
The present invention is existing to solve by providing a kind of plant cultivating method and system based on Internet of Things big data analysis
Because suitable growing environment can not be provided for plant during plant cultivation in technology, and causes plant growth situation to deviate and be expected
The problem of index.
To solve the above problems, the present invention is achieved by the following scheme:
On the one hand, the plant cultivating method provided by the invention based on Internet of Things big data analysis, comprising:
Step S1: the type of herborization, soil moisture, soil pH value, intensity of illumination, environment temperature, ambient humidity, figure
Picture, irrigation amount, dose, Fertilizer Type simultaneously constitute influence factor matrix X, and are uploaded to server；Wherein, irrigation amount, fertilising
Amount and Fertilizer Type constitute decision variable；
Step S2: referred to using each influence factor matrix X of Elman neural network plant with plant health in server
Complex nonlinear relationship between number obtains plant cultivation model；
Step S3: optimizing plant cultivation model using II algorithm of NSGA-, and one group for obtaining decision variable is optimal
Solution；
Step S4: using this group of optimal solution of decision variable as the recommendation decision X of plant*User is issued to by server
Terminal device shown；
Step S5: user cultivates plant according to the recommendation decision that terminal device is shown.
On the other hand, the plant cultivation system provided by the invention based on Internet of Things big data analysis, comprising:
Data acquisition unit, for the type of herborization, growth period, soil moisture, soil pH value, intensity of illumination,
Environment temperature, ambient humidity, image, irrigation amount, dose, Fertilizer Type simultaneously constitute influence factor matrix X, and are uploaded to service
Device；Wherein, irrigation amount, dose and the Fertilizer Type constitute decision variable；
Plant cultivation model foundation unit, in server utilize Elman neural network plant respectively influence because
Complex nonlinear relationship between prime matrix X and plant health index obtains plant cultivation model；
Decision variable optimal solution acquiring unit is obtained for being optimized using II algorithm of NSGA- to plant cultivation model
One group of optimal solution of decision variable, and using this group of optimal solution of decision variable as the recommendation decision X of plant*；
Recommend decision issuance unit, for passing through server for the recommendation decision X of plant*It is issued to the terminal device of user
It is shown.
Compared with prior art, the plant cultivating method and system provided by the invention based on Internet of Things big data analysis
Advantage is: utilizing Elman neural network plant cultivation model, recycles II algorithm optimization plant cultivation model of NSGA-, really
Irrigation amount, the dose, the optimal value of fertilization type of plant are determined, and immediate feedback allows user whenever and wherever possible can to user
Understand plant the present situation, realizes intelligent cultivation.
Detailed description of the invention
Fig. 1 is to be illustrated according to the process of the plant cultivating method based on Internet of Things big data analysis of the embodiment of the present invention
Figure；
Fig. 2 is the health index prediction result figure according to the embodiment of the present invention；
Fig. 3 is the health index prediction-error image according to the embodiment of the present invention；
Fig. 4 is the user interface schematic diagram according to the embodiment of the present invention.
Specific embodiment
Fig. 1 shows the process of the plant cultivating method according to an embodiment of the present invention based on Internet of Things big data analysis.
As shown in Figure 1, the plant cultivating method of the invention based on Internet of Things big data analysis, comprising:
Step S1: the type of herborization, growth period, soil moisture, soil pH value, intensity of illumination, environment temperature, ring
Border humidity, image, irrigation amount, dose, Fertilizer Type simultaneously constitute influence factor matrix X, and are uploaded to server；Wherein, it pours
Water, dose and Fertilizer Type constitute decision variable.
The health index y to plant is obtained by statistics1Influence maximum variable are as follows: floristics x1, growth period x2、
Soil moisture x3, soil pH value x4, intensity of illumination x5, environment temperature x6, ambient humidity x7, image x8, irrigation amount x9, dose
x10, Fertilizer Type x11, totally 11 variables；Wherein, soil moisture x3, soil pH value x4, intensity of illumination x5, environment temperature x6, environment
Humidity x7, image x8By corresponding sensor measurement data, floristics, growth period are build-in attribute, are inputted, are poured by user
Water, dose, Fertilizer Type are decision variable.
The environment temperature x of plant6It is acquired and is obtained by temperature sensor；The soil moisture x of plant3With ambient humidity x7It is logical
Humidity sensor acquisition is crossed to obtain；The intensity of illumination x of plant5It is acquired and is obtained by illuminance sensor；The soil pH value x of plant4
It is acquired and is obtained by soil pH meter；Using sample circuit respectively with temperature sensor, humidity sensor, illuminance sensor, soil
Earth pH meter is attached, and temperature sensor, humidity sensor, illuminance sensor, soil pH meter are distinguished collected ring
Border temperature, ambient humidity, soil moisture, intensity of illumination, P in soil H value are converted into digital signal.
Characteristic image of the plant at current time is acquired by camera to be obtained, and camera converts image information into number
Signal.
In the present invention, server is preferably Cloud Server.
Step S2: referred to using each influence factor matrix X of Elman neural network plant with plant health in server
Complex nonlinear relationship between number obtains plant cultivation model.
X is setk=[xk1,xk2,L,xkM] (k=1,2, L, S) be input vector, N be training sample number,
When for the g times iteration input layer M and hidden layer I it
Between weighted vector, WJP(g) be the g times iteration when hidden layer J and output layer P between weighted vector, WJCIt (g) is the g times iteration
When hidden layer J and accept layer C between weighted vector Yk(g)=[yk1(g),yk2(g),L,ykP(g)] (k=1,2, L, S) is g
The reality output of network, d when secondary iterationk=[dk1,dk2,L,dkP] (k=1,2, L, S) be desired output, the number of iterations g is
500。
It is being utilized between each influence factor matrix X of Elman neural network plant and plant health index in server
Complex nonlinear relationship, obtain plant cultivation model, comprising:
Step S21: initialization is assigned to W if the number of iterations g initial value is 0 respectivelyMI(0)、WJP(0)、WJC(0) one (0,1)
The random value in section；
Step S22: stochastic inputs sample Xk；
Step S23: to input sample Xk, the reality output Y of forward calculation Elman every layer of neuron of neural networkk(g)；
Step S24: according to desired output dkWith reality output Yk(g), error E (g) is calculated；
Step S25: error in judgement E (g) whether be less than preset error amount, if it is greater than or be equal to, enter step S26,
If it is less, entering step S29；
Step S26: judging whether the number of iterations g+1 is greater than maximum number of iterations, if it does, S29 is entered step, it is no
Then, S27 is entered step；
Step S27: to input sample XkThe partial gradient δ of retrospectively calculate Elman every layer of neuron of neural network；
Step S28: modified weight amount Δ W is calculated, and corrects weight；G=g+1 is enabled, go to step S23；
Wherein, Δ Wij=η δij, η is learning efficiency；Wij(g+1)=Wij(g)+ΔWij(g)；
Step S29: judge whether to complete the training of all samples；If so, completing modeling；If not, going to step
S22。
Elman neural network design in, the number of hidden nodes number be determine Elman neural network model quality pass
Difficult point in key and the design of Elman neural network, determines the number of nodes of hidden layer using trial and error procedure here.
In formula, p is hidden neuron number of nodes, and n is input layer number, and m is output layer neuron number, k 1-10
Between constant.The setting parameter of Elman neural network is as shown in table 2 below.
Parameter is arranged in table 2Elman neural network
| Objective function | Health index |
| The number of iterations | 500 |
| Hidden layer transmission function | Tansig |
| Output layer transmission function | Purelin |
| Node in hidden layer | 15 |
By the above process, it is as shown in Figures 2 and 3 that Elman neural network prediction effect can be obtained.The base of intelligent plant cultivation
Plinth is the foundation of model, and model accuracy directly affects output result.By analyzing Fig. 2 and 3 it is found that the pre- maximum survey of health index
Error is -3.5%, and model prediction accuracy is high, meets modeling demand.
Step S3: II algorithm of NSGA- (Non-dominated Sorting Genetic Algorithm- II, band are utilized
The genetic algorithm of the non-dominated ranking of elitism strategy) plant cultivation model is optimized, one group for obtaining decision variable is optimal
Solution.
One group of optimal solution of decision variable is obtained, that is, obtains the irrigation amount of plant, dose, one group of Fertilizer Type
Optimal value.
The step of being optimized using II algorithm of NSGA- to the plant cultivation model include:
Step S31: initialization system parameter；Wherein, the system parameter include population scale N, maximum genetic algebra G,
Crossover probability P and mutation probability Q.
Step S32: the new population Q that t generation is generatedtWith its parent population PtMerge composition population Rt, population RtSize
For 2N；If first generation population, then using first generation population as population Rt。
Step S33: to population RtNon-dominated ranking is carried out, a series of non-dominant collection Z is obtainedi, and calculate non-dominant collection Zi
In each individual crowding, generate new parent population Pt+1。
Detailed process is as follows by step S33:
Step S331: population R is judged using fitness functiontIn it is all individual between mutual dominance relation；Wherein,
D (i) .n indicates to dominate the individual amount of i-th of individual, the individual collections that D (i) .p expression is dominated by i-th of individual；If individual i
J is dominated, then individual j is put into D (i) .p set, the value of D (j) .n adds 1；It successively operates, obtains population RtIn all individual D
(i) information of .n and D (i) .p.
Step S332: by population RtIn all D (i) .n values be 0 individual, i.e., such individual not by other individual dominate,
It is put into the first layer of non-dominant layer, the individual that D (i) .n value is 1 is put into the second layer of non-dominant layer, is successively operated, until inciting somebody to action
The population RtIn until all individuals are put into different non-dominant layers；Individual in the same number of plies shares identical virtual fitness
Value, series is smaller, and virtual fitness value is lower, and individual is more excellent in the layer, by the number of plies of non-dominant layer by sequence from small to large
It is ranked up.
Step S333: since all individuals share same virtual fitness value in each layer, when needs select in same layer
When selecting more excellent individual, its crowding is calculated.
The crowding i of each pointdInitial value is set to 0；For each target, to the population RtNon-dominated ranking is carried out, is enabled
The population RtTwo individual crowdings on boundary be it is infinite, to the population RtMiddle other individuals carry out the meter of crowding
It calculates:
Wherein, idIndicate the crowding of i point,Indicate j-th of target function value of i+1 point,Indicate i-1 point
J-th of target function value.
Step S334: after being calculated by quick non-dominated ranking and crowding, population RtEach of individual i be owned by
Two attributes: the non-dominant sequence i that non-dominated ranking determinesrankWith crowding id.According to the two attributes, crowding can be defined
Comparison operator: individual i is compared with individual j, if non-dominant layer locating for individual i is better than non-dominant layer locating for individual j,
That is irank< jrank, alternatively, individual i and individual j have identical grade, and individual i is longer than the crowding distance of individual j, i.e. irank=
jrankAnd id> jd, then individual i wins.
Step S335: due to the individual and parent population P of progeny populationt+1Individual be included in population RtIn, then pass through
The later non-dominant collection Z of non-dominated ranking1In include individual be RtIn it is best, so first by non-dominant collection Z1It is put into parent
Population Pt+1；If parent population Pt+1Individual amount without departing from population scale N, then by the non-dominant collection Z of next stage2It is put into father
For population Pt+1, until by non-dominant collection Z3It is put into parent population Pt+1When, parent population Pt+1Individual amount exceed population scale
N, to non-dominant collection Z3In individual be compared using crowding comparison operator, { num (Z before taking3)-(num(Pt+1)-N) a
Individual makes parent population Pt+1Individual amount reach population scale N.
Step S34: to parent population Pt+1Intersected, the basic genetic that makes a variation operation obtains progeny population Qt+1。
To parent population Pt+1Carry out the process of crisscross inheritance operation are as follows:
By parent population Pt+1Interior all individuals mix into pair at random, to every a pair of of individual, generate a random number, if
The random number of certain a pair of of individual is less than crossover probability P, then exchanges this to the chromosome dyad between individual.
To parent population Pt+1Carry out the process of variation basic genetic operation are as follows:
To parent population Pt+1Each of individual, generate a random number, if some individual random number be less than variation
Probability Q, then changing the genic value on some or certain some locus of the individual is other genic values.
Step S35: genetic algebra adds 1, judges whether genetic algebra reaches maximum genetic algebra G, if so, output is current
Globally optimal solution；If not, the S32 that gos to step is computed repeatedly, it is until genetic algebra reaches maximum genetic algebra G
Only.
Step S4: using this group of optimal solution of decision variable as the recommendation decision X of plant*User is issued to by server
Terminal device shown.
The data of acquisition in various kinds of sensors every 2 hours are uploaded to server, and server connects data and passes through plant cultivation
Model provides irrigation amount, dose and the fertilization type that plant is currently recommended.
Step S5: user cultivates plant according to the recommendation decision that terminal device is shown.
User can open intelligent plant cultivation interface (as shown in Figure 4) on the terminal device, the interface display plant
Brief information, the brief information of plant include the image and current health index of plant, and the reason of plant can be arranged at interface in user
Think health index, ideal, issued by server and recommend irrigation amount, dose, Fertilizer Type, user can pass through mobile phone long-distance operating
Complete automatic watering function, fertilising.
The current health index of plant optimizes to obtain by being based on II algorithm of NSGA- to plant cultivation model, plant
Current health index is corresponding with one group of optimal solution of decision variable.
Plant cultivating method provided by the invention based on Internet of Things big data analysis, firstly, utilizing sensor, camera
Equal hardware herborization index parameter, plant image, irrigation amount, dose, Fertilizer Type then will be in collected data
It reaches server to be stored, Elman neural network influence factor matrix X and plant health index is utilized in server
Between complex nonlinear relationship, obtain plant cultivation model, plant cultivation model is optimized using II algorithm of NSGA-,
One group of optimal value of each decision variable is obtained, and is issued to PC the or APP terminal of user using this group of optimal solution as recommendation decision,
Finally, user can realize that remote auto is cultivated according to irrigation amount, dose, the fertilization type for recommending decision to determine plant.The party
Method can determine optimal plant cultivation scheme, build better living environment for plant.
It corresponds to the above method, the present invention also provides a kind of plant cultivation systems based on Internet of Things big data analysis.
Plant cultivation system provided by the invention based on Internet of Things big data analysis, comprising:
Data acquisition unit, for the type of herborization, growth period, soil moisture, soil pH value, intensity of illumination,
Environment temperature, ambient humidity, image, irrigation amount, dose, Fertilizer Type simultaneously constitute influence factor matrix X, and are uploaded to service
Device；Wherein, irrigation amount, dose and Fertilizer Type constitute decision variable.Data acquisition unit acquires the process of data with reference to upper
State step S1.
Plant cultivation model foundation unit, in server utilize Elman neural network plant respectively influence because
Complex nonlinear relationship between prime matrix X and plant health index obtains plant cultivation model.Plant cultivation model foundation list
Member establishes the detailed process of plant cultivation model with reference to above-mentioned steps S2.
Decision variable optimal solution acquiring unit is obtained for being optimized using II algorithm of NSGA- to plant cultivation model
One group of optimal solution of decision variable, and using this group of optimal solution of decision variable as the recommendation decision X of plant*.Decision variable is most
The detailed process that excellent solution acquiring unit obtains decision variable optimal solution refers to above-mentioned steps S3.
Recommend decision issuance unit, for passing through server for the recommendation decision X of plant*It is issued to the terminal device of user
It is shown.
The recommendation decision that user shows according to terminal device cultivates plant.
It should be pointed out that the above description is not a limitation of the present invention, the present invention is also not limited to the example above,
Variation, modification, addition or the replacement that those skilled in the art are made within the essential scope of the present invention, are also answered
It belongs to the scope of protection of the present invention.
Claims (6)
1. a kind of plant cultivating method based on Internet of Things big data analysis, which comprises the steps of:
Step S1: the type of herborization, growth period, soil moisture, soil pH value, intensity of illumination, environment temperature, environmental wet
Degree, image, irrigation amount, dose, Fertilizer Type simultaneously constitute influence factor matrix X, and are uploaded to server；Wherein, described to pour
Water, the dose and the Fertilizer Type constitute decision variable；
Step S2: referred to using each influence factor matrix X of Elman neural network plant with plant health in the server
Complex nonlinear relationship between number obtains plant cultivation model；Wherein, X in the plant cultivation modelkFor input vector, Xk
=[xk1,xk2,L,xkM], k=1,2, L, S, S are the number of training sample, WMI(g) input layer M and hidden layer I when being the g time iteration
Between weighted vector, WJP(g) be the g times iteration when hidden layer J and output layer P between weighted vector, WJC(g) repeatedly for the g times
For when hidden layer J and accept layer C between weighted vector, Yk(g) be the g times iteration when reality output, Yk(g)=[yk1(g),
yk2(g),L,ykP(g)], k=1,2, L, S, dkFor desired output, dk=[dk1,dk2,L,dkP], k=1,2, L, S；And
The step of establishing the plant cultivation model include:
Step S21: initialization is assigned to W if the number of iterations g initial value is 0 respectivelyMI(0)、WJP(0)、WJC(0) (0,1) section
Random value；
Step S22: stochastic inputs sample Xk；
Step S23: to input sample Xk, the reality output Y of every layer of neuron of Elman neural network described in forward calculationk(g)；
Step S24: according to desired output dkWith reality output Yk(g), error E (g) is calculated；
Step S25: error in judgement E (g) whether be less than preset error amount, if it is greater than or be equal to, enter step S26, if
It is less than, then enters step S29；
Step S26: judging whether the number of iterations g+1 is greater than maximum number of iterations, if it does, S29 is entered step, otherwise, into
Enter step S27；
Step S27: to input sample XkThe partial gradient δ of every layer of neuron of Elman neural network described in retrospectively calculate；
Step S28: modified weight amount Δ W is calculated, and corrects weight；G=g+1 is enabled, go to step S23；
Wherein, Δ Wij=η δij, η is learning efficiency；Wij(g+1)=Wij(g)+ΔWij(g)；
Step S29: judge whether to complete the training of all samples；If so, completing modeling；If not, the S22 that gos to step；
Step S3: optimizing the plant cultivation model using II algorithm of NSGA-, obtains one group of the decision variable most
Excellent solution；Wherein, the step of plant cultivation model being optimized using II algorithm of NSGA-, comprising:
Step S31: initialization system parameter；Wherein, the system parameter includes population scale N, maximum genetic algebra G, intersects
Probability P and mutation probability Q；
Step S32: the new population Q that t generation is generatedtWith its parent population PtMerge composition population Rt, population RtSize be 2N；
If first generation population, then using first generation population as the population Rt；
Step S33: to the population RtNon-dominated ranking is carried out, a series of non-dominant collection Z is obtainedi, and calculate described non-dominant
Collect ZiIn each individual crowding, generate new parent population Pt+1；
Step S34: to the parent population Pt+1Intersected, the basic genetic that makes a variation operation obtains progeny population Qt+1；
Step S35: genetic algebra adds 1, judges whether genetic algebra reaches the maximum genetic algebra G, if so, output is current
Globally optimal solution；If not, the S32 that gos to step is computed repeatedly, until genetic algebra reaches the maximum genetic algebra G
Until；
Step S4: using this group of optimal solution of the decision variable as the recommendation decision X of the plant*By under the server
The terminal device for being sent to user is shown；
Step S5: the user cultivates the plant according to the recommendation decision that the terminal device is shown.
2. the plant cultivating method according to claim 1 based on Internet of Things big data analysis, which is characterized in that step
S33 includes:
Step S331: the population R is judged using fitness functiontIn it is all individual between mutual dominance relation；Wherein, D
(i) .n indicates to dominate the individual amount of i-th of individual, and D (i) .p indicates the individual collections dominated by i-th of individual；If individual i
J is dominated, then individual j is put into D (i) .p set, the value of D (j) .n adds 1；It successively operates, obtains all individual D (i) .n and D
(i) information of .p；
Step S332: by the population RtIn all D (i) .n values be 0 individual, the first layer of non-dominant layer is put into, by described kind
Group RtIn all D (i) .n values be 1 individual be put into the second layer of non-dominant layer, until by the population RtIn all individuals be put into
Until different non-dominant layers, the number of plies of non-dominant layer is ranked up by sequence from small to large；
Step S333: it is directed to each target, to the population RtNon-dominated ranking is carried out, the population R is enabledtTwo of boundary
The crowding of body be it is infinite, to the population RtMiddle other individuals carry out the calculating of crowding:
Wherein, idIndicate the crowding of i point,Indicate j-th of target function value of i+1 point,Indicate j-th of i-1 point
Target function value；
Step S334: the non-dominant sequence i that non-dominated ranking is determinedrankWith crowding idAs the population RtIn per each and every one
Two attributes of body i, define crowding comparison operator: individual i is compared with individual j, if non-dominant layer locating for individual i
Better than non-dominant layer, i.e. i locating for individual jrank< jrank, or individual i and individual j have an identical grade, and individual i compare it is a
The crowding distance of body j is long, i.e. irank=jrankAnd id> jd, then individual i wins；
Step S335: by non-dominant collection Z1It is put into the parent population Pt+1；If the parent population Pt+1Individual amount do not surpass
The population scale N out, then by the non-dominant collection Z of next stage2It is put into the parent population Pt+1, until by non-dominant collection Z3It is put into
The parent population Pt+1When, the parent population Pt+1Individual amount exceed the population scale N, to the non-dominant collection Z3
In individual be compared using the crowding comparison operator, { num (Z before taking3)-(num(Pt+1)-N) individual, make institute
State parent population Pt+1Individual amount reach the population scale N.
3. the plant cultivating method according to claim 1 based on Internet of Things big data analysis, which is characterized in that described
Parent population Pt+1Carry out the process of crisscross inheritance operation are as follows:
By the parent population Pt+1Interior all individuals mix into pair at random, to every a pair of of individual, generate a random number, if
The random number of certain a pair of of individual is less than the crossover probability P, then exchanges this to the chromosome dyad between individual.
4. the plant cultivating method according to claim 1 based on Internet of Things big data analysis, which is characterized in that described
Parent population Pt+1Carry out the process of variation basic genetic operation are as follows:
To the parent population Pt+1Each of individual, generate a random number, if random number of some individual be less than it is described
Mutation probability Q, then changing the genic value on some or certain some locus of the individual is other genic values.
5. the plant cultivating method based on Internet of Things big data analysis described in any one of -4 according to claim 1, feature
It is,
The environment temperature of the plant is acquired using temperature sensor；
The ambient humidity and soil moisture of the plant are acquired using humidity sensor；
The intensity of illumination of the plant is acquired using illuminance sensor；
The P in soil H value of above-mentioned plant is acquired using P in soil H meter；
The plant is acquired in the feature at current time using camera, and converts image information into digital signal；And
Using sample circuit respectively with the temperature sensor, the humidity sensor, the illuminance sensor, the soil
PH meter is attached, and the temperature sensor, the humidity sensor, the illuminance sensor, the P in soil H are counted
Collected environment temperature, ambient humidity, soil moisture, intensity of illumination, P in soil H value are converted into digital signal respectively.
6. the system of the plant cultivating method according to any one of claims 1-5 based on Internet of Things big data analysis,
It is characterized in that,
Data acquisition unit, for the type of herborization, growth period, soil moisture, soil pH value, intensity of illumination, environment
Temperature, ambient humidity, image, irrigation amount, dose, Fertilizer Type simultaneously constitute influence factor matrix X, and are uploaded to server；
Wherein, the irrigation amount, the dose and the Fertilizer Type constitute decision variable；
Plant cultivation model foundation unit, in the server utilize Elman neural network plant respectively influence because
Complex nonlinear relationship between prime matrix X and plant health index obtains plant cultivation model；
Decision variable optimal solution acquiring unit is obtained for being optimized using II algorithm of NSGA- to the plant cultivation model
One group of optimal solution of the decision variable, and using this group of optimal solution of the decision variable as the recommendation decision of the plant
X*；
Recommend decision issuance unit, for by the server by the recommendation decision X of the plant*It is issued to the terminal of user
Equipment is shown.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610883950.2A CN106444378B (en) | 2016-10-10 | 2016-10-10 | Plant cultivating method and system based on Internet of Things big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610883950.2A CN106444378B (en) | 2016-10-10 | 2016-10-10 | Plant cultivating method and system based on Internet of Things big data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106444378A CN106444378A (en) | 2017-02-22 |
| CN106444378B true CN106444378B (en) | 2019-07-12 |
Family
ID=58173021
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610883950.2A Active CN106444378B (en) | 2016-10-10 | 2016-10-10 | Plant cultivating method and system based on Internet of Things big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106444378B (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI624799B (en) * | 2017-03-13 | 2018-05-21 | 中華大學 | Management system of mushroom intelligent cultivation with internet of things |
| CN107360775B (en) * | 2017-07-11 | 2018-09-28 | 中工武大设计研究有限公司 | A kind of the fertilising accuracy control method and its control system of water-fertilizer integral equipment |
| CN107766938A (en) * | 2017-09-25 | 2018-03-06 | 南京律智诚专利技术开发有限公司 | A kind of plant cover cultivation methods based on BP neural network |
| CN108074236B (en) * | 2017-12-27 | 2020-05-19 | Oppo广东移动通信有限公司 | Plant watering reminding method, device, equipment and storage medium |
| CN108633697A (en) * | 2018-05-15 | 2018-10-12 | 重庆科技学院 | A kind of foster culture method of the intelligent plant based on the daily data analysis of plant and cloud |
| CN108694444A (en) * | 2018-05-15 | 2018-10-23 | 重庆科技学院 | A kind of plant cultivating method based on intelligent data acquisition Yu cloud service technology |
| CN109147902A (en) * | 2018-07-19 | 2019-01-04 | 重庆科技学院 | A kind of user's sleep massage method and system based on Internet of Things big data analysis |
| CN109874477B (en) * | 2019-01-17 | 2021-01-26 | 北京农业智能装备技术研究中心 | Agricultural park fertilizer applicator hosting method and system |
| CN113627216B (en) * | 2020-05-07 | 2024-02-27 | 杭州睿琪软件有限公司 | Plant state evaluation method, system and computer readable storage medium |
| CN112099557A (en) * | 2020-09-24 | 2020-12-18 | 苏州七采蜂数据应用有限公司 | Internet-based household plant planting method and system |
| CN112488869B (en) * | 2020-12-03 | 2023-10-20 | 湖北添安农业科技有限公司 | Multi-factor management decision-making system suitable for agricultural production |
| CN112868435B (en) * | 2021-01-14 | 2022-07-05 | 同济大学 | NSGA-II-based blueberry greenhouse light and temperature coordination optimization method |
| CN113467238B (en) * | 2021-06-28 | 2023-03-21 | 燕山大学 | Watering control method for intelligent dry snow field |
| CN113570240B (en) * | 2021-07-27 | 2024-02-27 | 蒋俊伟 | Intelligent farm platform based on whole life cycle management of crops |
| CN116644575B (en) * | 2023-05-25 | 2024-03-26 | 淮阴工学院 | Intelligent design adjusting equipment for saline-alkali degree of wetland |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103646299A (en) * | 2013-12-19 | 2014-03-19 | 浙江省公众信息产业有限公司 | Neural network based crop prediction method and device |
| CN105334824A (en) * | 2015-11-06 | 2016-02-17 | 重庆科技学院 | Aluminum electrolysis production optimization method based on NSGA-II algorithm |
| CN105389452A (en) * | 2015-12-31 | 2016-03-09 | 西北农林科技大学 | Cucumber whole-course photosynthetic rate prediction model based on neural network, and establishment method |
| CN105588930A (en) * | 2015-12-17 | 2016-05-18 | 镇江市高等专科学校 | Method for measuring parameters of soil in greenhouse |
| CN105956715A (en) * | 2016-05-20 | 2016-09-21 | 北京邮电大学 | Soil moisture status prediction method and device |
-
2016
- 2016-10-10 CN CN201610883950.2A patent/CN106444378B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103646299A (en) * | 2013-12-19 | 2014-03-19 | 浙江省公众信息产业有限公司 | Neural network based crop prediction method and device |
| CN105334824A (en) * | 2015-11-06 | 2016-02-17 | 重庆科技学院 | Aluminum electrolysis production optimization method based on NSGA-II algorithm |
| CN105588930A (en) * | 2015-12-17 | 2016-05-18 | 镇江市高等专科学校 | Method for measuring parameters of soil in greenhouse |
| CN105389452A (en) * | 2015-12-31 | 2016-03-09 | 西北农林科技大学 | Cucumber whole-course photosynthetic rate prediction model based on neural network, and establishment method |
| CN105956715A (en) * | 2016-05-20 | 2016-09-21 | 北京邮电大学 | Soil moisture status prediction method and device |
Non-Patent Citations (1)
| Title |
|---|
| 非支配排序遗传算法的研究与应用;高媛;《中国优秀硕士学位论文全文数据库》;20061231;正文第3.4节 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106444378A (en) | 2017-02-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106444378B (en) | Plant cultivating method and system based on Internet of Things big data analysis | |
| CN106650212A (en) | Intelligent plant breeding method and system based on data analysis | |
| CN108694444A (en) | A kind of plant cultivating method based on intelligent data acquisition Yu cloud service technology | |
| CN108633697A (en) | A kind of foster culture method of the intelligent plant based on the daily data analysis of plant and cloud | |
| CN106482502B (en) | The intelligence drying long-range control method and system recommended based on cloud platform big data | |
| CN103823371B (en) | Agriculture Tree Precise Fertilization system and fertilizing method based on neural network model | |
| Visconti et al. | IoT-oriented software platform applied to sensors-based farming facility with smartphone farmer app | |
| CN106614273B (en) | Pet feeding method and system based on Internet of Things big data analysis | |
| CN106447117B (en) | Pet feeding method and system based on the daily data analysis of pet | |
| CN106472332A (en) | Pet feeding method and system based on dynamic intelligent algorithm | |
| CN106407711A (en) | Recommendation method and recommendation system of pet feeding based on cloud data | |
| CN107909149A (en) | A kind of Temperature in Greenhouse Forecasting Methodology based on Genetic BP Neutral Network | |
| CN107329511A (en) | Based on the vegetable aquaculture luminous environment high efficiency regulatory method and system between suitable root warm area | |
| CN109858180B (en) | Regional crop water consumption space pattern optimization design method | |
| CN115880433A (en) | Crop cultivation optimization method based on digital twinning | |
| CN117036088A (en) | Data acquisition and analysis method for identifying growth situation of greening plants by AI | |
| CN110069032A (en) | A kind of eggplant greenhouse intelligent checking system based on wavelet neural network | |
| CN115661547A (en) | Plant irrigation and maintenance method and system based on knowledge graph | |
| CN105913326B (en) | Constrain the Crop growing stage model Cultivar parameter optimization method of sex knowledge and the tactful Genetic Algorithm Fusion of elite individual | |
| CN117039852A (en) | Power prediction method, device, equipment and storage medium of wind-solar-water complementary power station | |
| Bazrafshan et al. | Evaluation and uncertainty assessment of wheat yield prediction by multilayer perceptron model with bayesian and copula bayesian approaches | |
| CN114723142A (en) | Multi-target land utilization simulation system and method based on non-dominated sorting genetic algorithm and FLUS model | |
| Li et al. | Prediction of grain yield in Henan Province based on grey BP neural network model | |
| Kumar et al. | IoT Enabled Crop Detection System using Soil Analysis | |
| CA2761682C (en) | Real-time process for targeting trait phenotyping of plant breeding experiments |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210113 Address after: Room 5-2, No.1-5, Tieshan Road, Biquan street, Bishan District, Chongqing 402760 Patentee after: Chongqing juce Intelligent Technology Research Institute Co.,Ltd. Address before: No. 20, East Road, University City, Chongqing, Shapingba District, Chongqing Patentee before: Chongqing University of Science & Technology |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20211217 Address after: 401320 22-2, unit 2, building 1, No. 18, Xinnong street, Banan District, Chongqing Patentee after: Chongqing Guangbo Technology Co.,Ltd. Address before: Room 5-2, No.1-5, Tieshan Road, Biquan street, Bishan District, Chongqing 402760 Patentee before: Chongqing juce Intelligent Technology Research Institute Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231019 Address after: No. B221, 2nd Floor, Building 39, Chongqing University of Science and Technology, No. 20 Daxue Cheng East Road, Huxi Street, High tech Zone, Shapingba District, Chongqing, 400000 Patentee after: Chongqing youshuo Technology Co.,Ltd. Address before: 401320 22-2, unit 2, building 1, No. 18, Xinnong street, Banan District, Chongqing Patentee before: Chongqing Guangbo Technology Co.,Ltd. |
|
| TR01 | Transfer of patent right |