CN110533547A - Fruits and vegetables water-fertilizer conditioning method and device and computer readable storage medium - Google Patents
Fruits and vegetables water-fertilizer conditioning method and device and computer readable storage medium Download PDFInfo
- Publication number
- CN110533547A CN110533547A CN201910925554.5A CN201910925554A CN110533547A CN 110533547 A CN110533547 A CN 110533547A CN 201910925554 A CN201910925554 A CN 201910925554A CN 110533547 A CN110533547 A CN 110533547A
- Authority
- CN
- China
- Prior art keywords
- fruits
- vegetables
- water
- fertilizer
- parameter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Mining
Abstract
The present invention relates to agricultural irrigation technologies, more particularly to fruits and vegetables water-fertilizer conditioning method, fruits and vegetables water-fertilizer conditioning device and computer readable storage medium.The fruits and vegetables water-fertilizer conditioning method include: obtain fruits and vegetables real-time phenotypic parameter data, with identify fruits and vegetables current growth period and current growth period under current upgrowth situation;According to the default phenotypic parameter data of fruits and vegetables, the default upgrowth situation under current growth period is identified, and compare with current upgrowth situation;According to comparing result, determines the liquid manure degree of lacking of fruits and vegetables and determine water and fertilizer irrigation scheme;According to the current water and fertilizer irrigation mode of water and fertilizer irrigation project setting, until stopping water and fertilizer irrigation operation when meeting default environmental parameter condition.The present invention, which at least can be realized, can carry out dynamic adjustment to irrigation volume and dose in real time according to fruits and vegetables phenotype and growing environment.
Description
Technical field
The present invention relates to agricultural irrigation technologies, more particularly to fruits and vegetables water-fertilizer conditioning method and device and computer
Readable storage medium storing program for executing.
Background technique
With the development of agricultural modernization, Irrigation and fertilization system is developing industrialized agriculture, water-saving agriculture and ecological agriculture etc.
The importance of aspect becomes increasingly conspicuous.Generally according to empirically determined irrigation volume during Cotton Varieties by Small Farming Households fruits and vegetables, often result in " high
Put into low output " status, lead to water resource and fertilizer serious waste deep fertilizer leaching loss and environmental pollution.
Currently, there are many research about fruits and vegetables fertigation, but focus primarily upon using fruits and vegetables yield and quality as target
It is most to be still based on crop empirical model in water and fertilizer coupling research, i.e., liquid manure formula is empirically provided, while monitoring liquid manure and production
The relationship of amount.But the prior art lacks the influence to growing environment factor dynamic change to irrigation capacity of crops and dose
Consider, existing water-fertilizer conditioning technology liquid manure utilization efficiency is low, and economic benefit cannot achieve maximization.
Summary of the invention
In view of the deficiencies in the prior art, the purpose of the present invention is to provide fruits and vegetables water-fertilizer conditioning method and device with
And corresponding computer readable storage medium, at least realize can according to fruits and vegetables phenotype and growing environment in real time to irrigation volume and
Dose carries out dynamic adjustment.
According to an aspect of the invention, there is provided a kind of fruits and vegetables water-fertilizer conditioning method, comprising: obtain the real-time table of fruits and vegetables
Shape parameter data, with identify fruits and vegetables current growth period and the current growth period under current upgrowth situation;According to fruits and vegetables
Default phenotypic parameter data, identify the default upgrowth situation under the current growth period, and with the current upgrowth situation
It compares;According to comparing result, determines the liquid manure degree of lacking of fruits and vegetables and determine water and fertilizer irrigation scheme;It is filled according to the liquid manure
The current water and fertilizer irrigation mode of project setting is irrigate, until stopping water and fertilizer irrigation operation when meeting default environmental parameter condition.
According to an embodiment of the invention, the fruits and vegetables water-fertilizer conditioning method further comprises: obtaining the real-time phenotype ginseng of fruits and vegetables
Number data, to obtain the Morphologic Parameters and physiologic parameters of fruits and vegetables;And the current of fruits and vegetables is identified based on deep approach of learning
Current upgrowth situation under growth period and the current growth period.
According to an embodiment of the invention, the Morphologic Parameters for obtaining fruits and vegetables include the plant height parameter for obtaining fruits and vegetables, stem diameter
One or more of parameter, hat width parameter and fruit image;And the physiologic parameters for obtaining fruits and vegetables include obtaining fruits and vegetables
One or more of chlorophyll parameter, photosynthetic parameter, water stress parameter and leaf water content parameter.
According to an embodiment of the invention, determining that the liquid manure degree of lacking of fruits and vegetables includes that the liquid manure degree of lacking of determining fruits and vegetables is
Any one of water shortage, fertilizer deficiency or water shortage and fertilizer deficiency;And the growth period includes germination period, Seedling Stage, florescence and knot
Either phase in fruiting period.
According to an embodiment of the invention, the fruits and vegetables water-fertilizer conditioning method further comprises: the growth ring obtained according to history
The growing environment gain of parameter environmental parameter predicted value that border parameter and current real-time monitoring obtain;By the environmental parameter predicted value
It is compared with environmental parameter a reference value;If the environmental parameter predicted value is consistent with the environmental parameter a reference value, stop
Only water and fertilizer irrigation operates.
According to an embodiment of the invention, the growing environment supplemental characteristic include air themperature, air humidity, atmospheric pressure,
One or more of wind direction, wind speed, illuminance, gas concentration lwevel numerical value.
According to another aspect of the present invention, a kind of fruits and vegetables water-fertilizer conditioning device is provided, comprising: fruits and vegetables phenotypic parameter obtains
Module, for obtaining the real-time phenotypic parameter data of fruits and vegetables, to identify the current growth period and the current growth period of fruits and vegetables
Under current upgrowth situation;Processing module identifies the current growth period for the default phenotypic parameter data according to fruits and vegetables
Under default upgrowth situation and compared with the current upgrowth situation and according to comparing result determine fruits and vegetables liquid manure lack
Mistake situation simultaneously determines water and fertilizer irrigation scheme;Water-fertilizer conditioning module, for the liquid manure current according to the water and fertilizer irrigation project setting
Irrigation method, until stopping water and fertilizer irrigation operation when meeting default environmental parameter condition.
According to an embodiment of the invention, the fruits and vegetables water-fertilizer conditioning device further include: environmental parameter obtains module, is used for basis
The growing environment gain of parameter environmental parameter predicted value that the growing environment parameter and current real-time monitoring that history obtains obtain;Its
In, the processing module is also used to for the environmental parameter predicted value being compared with environmental parameter a reference value;And if institute
It is consistent with the environmental parameter a reference value to state environmental parameter predicted value, then controls the water-fertilizer conditioning module and stops water and fertilizer irrigation behaviour
Make.
According to another aspect of the invention, a kind of fruits and vegetables water-fertilizer conditioning device is provided, comprising: memory, for storing
Program;And processor, for executing described program, described program is at least for realizing as above any fruits and vegetables liquid manure tune
Each step of prosecutor method.
In accordance with a further aspect of the present invention, a kind of computer readable storage medium is provided, computer program is stored with,
When the computer program is executed by processor, each step of as above any fruits and vegetables water-fertilizer conditioning method is realized.
The beneficial effects of the present invention are:
It is available in fruits and vegetables water-fertilizer conditioning method provided by the invention and device and computer readable storage medium
The real-time phenotypic parameter data of fruits and vegetables, to identify the current growth period of fruits and vegetables and deserve the current growth shape under preceding growth period
Condition;Further, the default upgrowth situation under current growth period is compared with current upgrowth situation;Then, according to comparison
As a result it can determine the liquid manure degree of lacking of fruits and vegetables and determine water and fertilizer irrigation scheme;It is finally current according to water and fertilizer irrigation project setting
Water and fertilizer irrigation mode, until stopping water and fertilizer irrigation operation when meeting default environmental parameter condition.It is possible thereby to significantly see
Out, the present invention, which can be realized, can carry out dynamic adjustment to irrigation volume and dose in real time according to fruits and vegetables phenotype and growing environment.
Thus while effectively save liquid manure resource, in order to which fruits and vegetables can quickly and efficiently growth and development.
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 the present invention
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 is the flow chart of fruits and vegetables water-fertilizer conditioning method according to an embodiment of the present invention.
Fig. 2 is the schematic block diagram of fruits and vegetables water-fertilizer conditioning method according to an embodiment of the present invention.
Fig. 3 is the flow chart according to an embodiment of the present invention based on ResNet50 convolutional neural networks.
Fig. 4 is the greenhouse variable prediction model flow according to an embodiment of the present invention based on LSTM neural network model
Figure.
Fig. 5 is the greenhouse variable prediction model frame according to an embodiment of the present invention based on LSTM neural network model
Figure.
Fig. 6 is the internal cell structure figure of LSTM cellular layer according to an embodiment of the present invention.
Fig. 7 is the structural schematic diagram of fruits and vegetables water-fertilizer conditioning device according to an embodiment of the present invention.
Fig. 8 is the structural schematic diagram of fruits and vegetables phenotypic parameter acquisition device according to an embodiment of the present invention.
Fig. 9 is electronic devices structure schematic diagram according to an embodiment of the present invention.
Appended drawing reference:
101,102,103,104: each step;200: block diagram;301,302,303: each step;401,402,403,
404,405: each step;700: fruits and vegetables water-fertilizer conditioning device;701: fruits and vegetables phenotypic parameter obtains module;702: processing module;
703: water-fertilizer conditioning module;704: environmental parameter obtains module;801: crossbeam;802: vertical beam;803: height adjuster;804: sliding
Rail;805: pulley;806: image acquisition device;807: hollow out bracket;901: processor;902: communication interface;903: memory;
904: communication bus.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiments of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
Member's every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that unless otherwise clearly defined and limited, term " installation ", " phase
Even ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or be integrally connected;It can
To be mechanical connection, it is also possible to be electrically connected;It can be directly connected, can also can be indirectly connected through an intermediary
Connection inside two elements.For the ordinary skill in the art, above-mentioned term can be understood at this with concrete condition
Concrete meaning in invention.
In addition, in the description of the present invention, unless otherwise indicated, " multiple ", " more ", " multiple groups " be meant that two or
Two or more, " several ", " several ", " several groups " are meant that one or more.
As shown in Figures 1 to 9, the embodiment provides fruits and vegetables water-fertilizer conditioning methods and fruits and vegetables water-fertilizer conditioning to fill
It sets and corresponding computer readable storage medium.Below with reference to each attached drawing, the embodiment of the present invention is retouched in detail
It states.
As shown in Figure 1, according to one embodiment of present invention, which may comprise steps of:
At step 101, the real-time phenotypic parameter data of fruits and vegetables are obtained, to identify current growth period of fruits and vegetables and described
Current upgrowth situation under current growth period.
Then, it at step 102, according to the default phenotypic parameter data of fruits and vegetables, identifies default under current growth period
Upgrowth situation, and compared with current upgrowth situation.
Next, at step 103, according to the comparison between above-described default upgrowth situation and current upgrowth situation
As a result, determining the liquid manure degree of lacking of fruits and vegetables and determining water and fertilizer irrigation scheme.
Then, at step 104, according to the current water and fertilizer irrigation mode of water and fertilizer irrigation project setting, until meeting default
When environmental parameter condition, stop water and fertilizer irrigation operation.
By method provided by the invention above it is apparent that the present invention can be realized can according to fruits and vegetables phenotype and
Growing environment carries out dynamic adjustment to irrigation volume and dose in real time.Thus while effectively save liquid manure resource, in order to
Fruits and vegetables can quickly and efficiently growth and development.
Further, in one embodiment of the invention, procedure described above 101 may be embodied as obtaining fruit first
The real-time phenotypic parameter data of vegetable, to obtain the Morphologic Parameters and physiologic parameters of fruits and vegetables;And known based on deep approach of learning
It Chu not current upgrowth situation under the current growth period and current growth period of fruits and vegetables.In one embodiment, the shape of fruits and vegetables is obtained
State parameter may include one or more in the plant height parameter for obtaining fruits and vegetables, stem diameter parameter, hat width parameter and fruit image
It is a;And the physiologic parameters for obtaining fruits and vegetables include obtain the chlorophyll parameters of fruits and vegetables, photosynthetic parameter, water stress parameter and
One or more of leaf water content parameter.It should be understood, of course, that above-described each parameter is only optional reality of the invention
Example is applied, other any parameters appropriate obtain can also be using in the present invention.In addition, about above-described deep approach of learning
It will be further described in more detail referring to embodiment.
In one embodiment of the invention, determine that the liquid manure degree of lacking of fruits and vegetables may further include as described above
The liquid manure degree of lacking for determining fruits and vegetables is any one of water shortage, fertilizer deficiency or water shortage and fertilizer deficiency.And growth period as described above
Including the either phase in germination period, Seedling Stage, florescence and fruiting period.In other words, in step 101 as described above,
To identify that fruits and vegetables current growth period is which in germination period, Seedling Stage, florescence and the fruiting period in stage first, so
Default upgrowth situation under can transferring at this stage in a step 102 afterwards.In addition, the liquid manure degree of lacking of fruits and vegetables refers to
When being judged as water shortage, then moisture is required supplementation with;When being judged as fertilizer deficiency, then fertilizer is required supplementation with;When being judged as water shortage and lack
It when fertile, then needs to keep the skin wet simultaneously and fertilizer, thus can determine subsequent water and fertilizer irrigation scheme.
Further, in one embodiment of the invention, step 104 as described above can be implemented are as follows: firstly, according to
The growing environment gain of parameter environmental parameter predicted value that the growing environment parameter and current real-time monitoring that history obtains obtain.So
Afterwards, environmental parameter predicted value is compared with environmental parameter a reference value.If environmental parameter predicted value and environmental parameter benchmark
Value is consistent, then stops water and fertilizer irrigation operation;If inconsistent, continue previously corresponding water and fertilizer irrigation operation.
In above-described each embodiment, above-mentioned growing environment supplemental characteristic may include air themperature, air
One or more of humidity, atmospheric pressure, wind direction, wind speed, illuminance, gas concentration lwevel numerical value.In one embodiment, warm
The acquisition of room environmental parameter can be realized by sensor.However, it is to be understood that above-described parameters data and
Its acquisition modes is only illustrative, and can be adjusted according to particular condition in use, the present invention is not limited thereto.
On the other hand, as shown in fig. 7, in one embodiment of the invention, additionally providing a kind of fruits and vegetables water-fertilizer conditioning dress
700 are set, which may include that fruits and vegetables phenotypic parameter obtains module 701, processing module 702 and liquid manure
Regulate and control module 703.Specifically, fruits and vegetables phenotypic parameter, which obtains module 701, can be used for obtaining the real-time phenotypic parameter data of fruits and vegetables,
With identify fruits and vegetables current growth period and current growth period under current upgrowth situation.Processing module 702 can be used for basis
The default phenotypic parameter data of fruits and vegetables identify the default upgrowth situation under current growth period and carry out pair with current upgrowth situation
It determines the liquid manure degree of lacking of fruits and vegetables than and according to comparing result and determines water and fertilizer irrigation scheme.Water-fertilizer conditioning module 703 can
By in a manner of according to the current water and fertilizer irrigation of water and fertilizer irrigation project setting, until stopping when meeting default environmental parameter condition
Water and fertilizer irrigation operation.Further, which can also include that environmental parameter obtains module 704.The ring
The growth ring that the growing environment parameter and current real-time monitoring that border parameter acquisition module 704 can be used for being obtained according to history obtain
Border gain of parameter environmental parameter predicted value.In specifically used, processing module 702 can join environmental parameter predicted value and environment
Number a reference value is compared.And if environmental parameter predicted value is consistent with environmental parameter a reference value, control water-fertilizer conditioning mould
Block 703 stops water and fertilizer irrigation operation.
It in one embodiment, can be with for the water-fertilizer conditioning module for realizing greenhouse liquid manure intelligent control
Equipment is controlled including Main Control Tank and liquid manure amount.
Specifically, in the present embodiment, Main Control Tank can be used for being sent out according to target irrigation scheme to liquid manure amount control equipment
Corresponding control instruction is sent, Main Control Tank connects liquid manure amount and controls equipment.
On the other hand, liquid manure amount control equipment can be used for executing the corresponding control instruction of Main Control Tank transmission, for temperature
Room fruits and vegetables carry out water-fertilizer integral irrigation control.Wherein, liquid manure amount control equipment can be equipped with solenoid valve, for use as control liquid manure
The switch that integration is irrigated.
In addition, the embodiments of the present invention also provide another fruits and vegetables water-fertilizer conditioning device, the fruits and vegetables water-fertilizer conditioning device
Including the memory for storing program and the processor for executing above procedure, wherein the program at least for realizing
Each step of fruits and vegetables water-fertilizer conditioning method as described above.Also, the present invention also provides a kind of computer-readable storage mediums
Matter, the computer-readable recording medium storage have computer program, and when the computer program is executed by processor, can be with
Realize each step of fruits and vegetables water-fertilizer conditioning method as described above.
More detailed embodiment of the invention is described below with reference to attached drawing.In the following description, made with tomato
It is described for illustrative fruits and vegetables;It should be understood, however, that various embodiments below and associated description are only signals
Property, any restriction is not constituted to the present invention, and fruits and vegetables are also possible to any other form, it is not limited to tomato.
In other words, the present invention can apply in the water-fertilizer conditioning application of various fruits and vegetables.
Real-time greenhouse tomato phenotypic parameter number is obtained first when carrying out water-fertilizer conditioning to tomato according to one embodiment
According to, and identify based on deep learning method growth period and the upgrowth situation of current tomato, in conjunction with kind under best liquid manure state
Eggplant phenotypic parameter data (that is, default phenotypic parameter data) compare and analyze.Then, according to tomato phenotypic parameter data difference
Value, determines liquid manure degree of lacking, and decision liquid manure target protocol, starts to carry out intelligence to fertigation mode by control instruction
It can regulation.Then, by environmental parameter predicted value and environmental parameter a reference value comparative analysis, for stopping to fertigation
Only, which obtained based on LSTM neural network model.
It can thus be seen that in present example, needing first to obtain tomato phenotypic data, passing through deep learning
Model identifies tomato phenotype, is compared therewith according to the tomato phenotypic parameter data got under best liquid manure state
Analysis, then according to the two tomato phenotypic parameter data difference, determines liquid manure degree of lacking with this.
In one embodiment of the invention, Fig. 2 is the signal of fruits and vegetables water-fertilizer conditioning method according to an embodiment of the present invention
Property block diagram 200.As shown in Fig. 2, needing to obtain real-time greenhouse tomato phenotypic parameter data first, which includes form
Learn parameter and physiologic parameters.Further, Morphologic Parameters include: plant height, stem diameter, hat width, fruit;And physiologic parameters
It include: chlorophyll, photosynthetic rate, water stress, leaf water content.It is then based on deep learning method and identifies current tomato
Growth period and upgrowth situation.In embodiment as described above, growth period includes germination period, Seedling Stage, florescence and fruiting period
Four growth phases.Next, being compared and analyzed in conjunction with the tomato phenotypic parameter data under best liquid manure state, Jin Ergen
Liquid manure degree of lacking is determined with this according to the two tomato phenotypic parameter data difference.Liquid manure degree of lacking includes water shortage, fertilizer deficiency, lacks
Water fertilizer deficiency.Then, decision goes out liquid manure target protocol after obtaining liquid manure degree of lacking according to judging result, is started by control instruction
Intelligent control is carried out to fertigation mode.
In embodiment as described above, deep learning method is carried out using ResNet50 convolutional neural networks.
Specifically, Fig. 3 is the flow chart provided in an embodiment of the present invention based on ResNet50 convolutional neural networks.Such as Fig. 3
It is shown, data prediction is carried out first at step 301, comprising to the training dataset and survey for obtaining tomato phenotypic parameter data
Examination data set carries out pretreatment and data enhancing, to have the function that EDS extended data set and enhancing data characteristics.Then, in step
Model training is carried out at 302, and comprising carrying out weight initialization, feature extraction is carried out to raw to training dataset using convolutional layer
At characteristic pattern, obtain output valve to transmitting before carrying out by pond layer and full articulamentum, then find out output valve and target value it
Between error carry out back transfer, according to errors carry out right value update, finally obtain trained disaggregated model.It connects down
Come, image recognition is carried out at step 303, includes the tomato phenotypic parameter number using the disaggregated model trained to unknown classification
Output valve is obtained according to being predicted, to identify to growth period belonging to tomato and upgrowth situation.
49 convolutional layers and 1 full articulamentum are contained in embodiment described above, in ResNet50.According to
ResNet model structure, 49 convolutional layers are divided into 5 groups, and the size of convolution kernel is respectively 7x7,1x1,3x3, for input
Image carries out feature extraction, and the activation primitive of convolutional layer is linear R eLU activation primitive, uses the maximum pond layer of 1 3x3
With the average pond layer of 1 7x7;Occur over-fitting in order to prevent, has been eventually adding Dropout layers and complete in convolutional layer
Articulamentum.Dropout layers of effect is the feature quantity for reducing middle layer, reduces data redundancy and increase the orthogonal of every layer data
Property.Characteristic pattern is mapped to one-dimensional vector, the ability to express of enhancing network output feature by the convolution kernel of 1x1 by full articulamentum.
It is noted that disaggregated model classifies to image using softmax classifier.
On the other hand, in the example of the present invention, environmental parameter predicted value is obtained according to based on LSTM neural network model
Out.Specifically, as shown in figure 4, Fig. 4 is that the greenhouse according to an embodiment of the present invention based on LSTM neural network model becomes
Measure prediction model flow chart.
Firstly, carrying out historical data acquisition and pretreatment at step 401, wherein pretreatment may include following steps:
The data for not collecting or lacking are concentrated to reject data.Then, at step 402, proportionally divide after handling data
For training data and test data.Then at step 403, LSTM neural network model is constructed.Next, at step 404,
Using training dataset to the training of LSTM neural network model.Then at step 405, according to the LSTM nerve net for completing training
Network model prediction greenhouse.
Further, using Min Max Scaler by between all data normalizations to 0~1, formula is as follows:
Wherein, X* indicates the data after normalization, XmaxIndicate the maximum value of data, XminIndicate the minimum value of data.
It should be pointed out that in the example of the present invention, as described above based on the greenhouse ring of LSTM neural network model
Border variable prediction model includes an input layer, a LSTM cellular layer, an output layer.
Further, as shown in figure 5, Fig. 5 is the greenhouse according to an embodiment of the present invention based on LSTM neural network model
Environmental variance prediction model block diagram.Wherein, hidden layer is made of several LSTM cellular layers, and output layer includes network training layer,
Neural network forecast is that the method predicted by iteration predicts the LSTM network trained.
Then as shown in fig. 6, in an embodiment of the present invention, Fig. 6 is LSTM cellular layer according to an embodiment of the present invention
Internal cell structure figure.It includes forgeing door ft, tri- input gate it, out gate ot thresholdings;0 indicates to forbid all information logical
It crosses, 1 indicates that all information is allowed to pass through.The propagated forward function of LSTM recursion cycle neural network is made of these three thresholdings.
Wherein, the propagated forward function of LSTM recursion cycle neural network are as follows:
i<t>=σ (Wxix<t>+Whih<t-1>+Wcic<t-1>+bi);
f<t>=σ (Wxfx<t>+Whfh<t-1>+Wcfc<t-1>+bf);
c<t>=ftc<t-1>+ittanh(Wxcx<t>+Whch<t-1>+bc);
o<t>=σ (Wxox<t>+Whoh<t-1>+Wcoc<t>+bo);
h<t>=o<t>tanh(c<t>);
Wherein, i<t>Indicate input gate, f<t>It indicates to forget door, c<t>T moment is indicated by input gate and forgets behind the door thin
Born of the same parents' location mode, o<t>Indicate cell factory state, the h of t moment out gate<t>Indicate all output shapes of t moment LSTM unit
State;W indicates weight matrix;B indicates bias term;Sigmoid indicate activation primitive, effect be by variable mappings to section [0,
1] in.
In present example, training dataset as described above includes following step to the training of LSTM neural network model
It is rapid:
The output valve of LSTM cell is calculated according to forward calculation method formula;
The error term of each LSTM cell is calculated on time and network level both direction;Including temporally and network layer
2 backpropagation directions of grade;
Following root-mean-square error RMSE is used as error calculation formula to update model parameter;
Wherein: L (m-L) is the total sample number of training;PiFor predicted value;YiFor true value.According to corresponding error term, meter
Calculate the gradient of each weight.In addition, the optimization algorithm based on gradient is selected to update weight, updated using Adam gradient descent algorithm
Weight and biasing in LSTM model keep network losses minimum.
Referring now to Fig. 8, in one embodiment of the invention, Fig. 8 shows fruits and vegetables phenotype according to an embodiment of the present invention
The structural schematic diagram of parameter obtaining device.The fruits and vegetables phenotypic parameter acquisition device may include crossbeam 801, vertical beam 802, height tune
Save device 803, sliding rail 804, pulley 805, image acquisition device 806 and hollow out bracket 807.
Specifically as shown in figure 8, fruits and vegetables phenotypic parameter acquisition device includes the vertical beam 802 of the high settings such as two, vertical beam 802
Lower section connection hollow out bracket 807 to be placed on ground.Wherein, height adjuster and sliding platform are equipped on vertical beam 802.
Sliding platform can be made of sliding rail 804 and pulley 805.Further, crossbeam 801, In is connected between two vertical beams 802
Sliding platform also is provided on crossbeam 801.Image acquisition device 806 is fixed on sliding platform.When using image acquisition device 806,
It is placed in target crop between two vertical beams 802, crossbeam 801 is made to be located at the surface of target crop.In one embodiment, scheme
As collector 806 can be spherical visible light near-infrared camera.
It should be noted that the fruits and vegetables phenotypic parameter acquisition device in Fig. 8 is only schematic diagram, it is specifically laid out sum number
Amount can be configured according to actual needs.
It is of the invention in actual use, start to take pictures when image acquisition device 806 is moved to predeterminated position.Pass through
Sliding platform controls the movement of camera, and single camera can shoot all information of a growth belt, avoid every plant of tomato
A corresponding camera results in waste of resources.Meanwhile piecemeal can be carried out to planting area, it is arranged one in advance for each block area
If position, when camera is often moved to a predeterminated position, all once shot, taking pictures interior includes tomato phenotypic data.
From the above description, it can be seen that the embodiment of the invention provides fruits and vegetables water-fertilizer conditioning device, by obtaining fruits and vegetables phenotype
Data differentiate liquid manure degree of lacking.By calling water-fertilizer conditioning module decision to go out corresponding fertilizer irrigation scheme, control is issued
The corresponding liquid manure solenoid valve of instruction unpack.It is predicted in conjunction with growing environment to determine whether reaching liquid manure requirement, and then control water
The switch of fertilizer regulation module solenoid valve, realizes the intelligent control to greenhouse liquid manure with this.Perfect liquid manure model of the invention as a result,
Time lag, improve the utility rate of water of water and fertilizer irrigation.
In one embodiment of the invention, Fig. 9 is electronic devices structure schematic diagram according to an embodiment of the present invention.Such as figure
Shown in 9, which may include processor 901, communication interface 902, memory 903 and communication bus 904.Its
In, processor 901, communication interface 902, memory 903 complete mutual communication by communication bus 904.
In addition, the logical order in above-mentioned memory 903 can be realized and be made by way of SFU software functional unit
It is independent product when selling or using, can store in a computer readable storage medium.Based on this understanding,
Technical solution of the present invention can be embodied in the form of software products, which is stored in storage medium
In, including some instructions are used so that computer equipment (can be personal computer, server or network equipment etc.) executes
All or part of the steps of the method according to each embodiment of the present invention.And storage medium above-mentioned include: USB flash disk, mobile hard disk, only
Read memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk
Or the various media that can store program code such as CD.
Embodiments described above is only illustrative, wherein the unit as illustrated by the separation member can be or
Person, which may not be, to be physically separated, and component shown as a unit may or may not be physical unit
With in one place, or may be distributed over multiple network units.Portion therein can be selected according to the actual needs
Point or whole module achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creative labor
In the case where, it can it understands and implements.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features;
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (10)
1. a kind of fruits and vegetables water-fertilizer conditioning method characterized by comprising
Obtain fruits and vegetables real-time phenotypic parameter data, with identify fruits and vegetables current growth period and the current growth period under work as
Preceding upgrowth situation;
According to the default phenotypic parameter data of fruits and vegetables, identify the default upgrowth situation under the current growth period, and with it is described
Current upgrowth situation compares;
According to comparing result, determines the liquid manure degree of lacking of fruits and vegetables and determine water and fertilizer irrigation scheme;
According to the current water and fertilizer irrigation mode of the water and fertilizer irrigation project setting, until stopping when meeting default environmental parameter condition
Only water and fertilizer irrigation operates.
2. fruits and vegetables water-fertilizer conditioning method according to claim 1, which is characterized in that further comprise:
The real-time phenotypic parameter data of fruits and vegetables are obtained, to obtain the Morphologic Parameters and physiologic parameters of fruits and vegetables;And
Current upgrowth situation under the current growth period and the current growth period of identifying fruits and vegetables based on deep approach of learning.
3. fruits and vegetables water-fertilizer conditioning method according to claim 2, which is characterized in that the Morphologic Parameters for obtaining fruits and vegetables include
Obtain one or more of plant height parameter, stem diameter parameter, hat width parameter and the fruit image of fruits and vegetables;And obtain fruits and vegetables
Physiologic parameters include chlorophyll parameter, photosynthetic parameter, water stress parameter and the leaf water content parameter for obtaining fruits and vegetables
One or more of.
4. fruits and vegetables water-fertilizer conditioning method according to claim 1, which is characterized in that determine the liquid manure degree of lacking packet of fruits and vegetables
The liquid manure degree of lacking for including determining fruits and vegetables is any one of water shortage, fertilizer deficiency or water shortage and fertilizer deficiency;And the growth period packet
Include the either phase in germination period, Seedling Stage, florescence and fruiting period.
5. fruits and vegetables water-fertilizer conditioning method according to claim 1, which is characterized in that further comprise:
The growing environment parameter obtained according to history and the growing environment gain of parameter environmental parameter that current real-time monitoring obtains are pre-
Measured value;
The environmental parameter predicted value is compared with environmental parameter a reference value;
If the environmental parameter predicted value is consistent with the environmental parameter a reference value, stop water and fertilizer irrigation operation.
6. fruits and vegetables water-fertilizer conditioning method according to claim 5, which is characterized in that the growing environment supplemental characteristic includes
One or more of air themperature, air humidity, atmospheric pressure, wind direction, wind speed, illuminance, gas concentration lwevel numerical value.
7. a kind of fruits and vegetables water-fertilizer conditioning device characterized by comprising
Fruits and vegetables phenotypic parameter obtains module, for obtaining the real-time phenotypic parameter data of fruits and vegetables, works as previous existence with identify fruits and vegetables
Current upgrowth situation under the long-term and current growth period;
Processing module identifies the default growth under the current growth period for the default phenotypic parameter data according to fruits and vegetables
Situation and liquid manure degree of lacking and the determination that fruits and vegetables are compared and determined according to comparing result with the current upgrowth situation
Water and fertilizer irrigation scheme;
Water-fertilizer conditioning module, for the water and fertilizer irrigation mode current according to the water and fertilizer irrigation project setting, until meeting default
When environmental parameter condition, stop water and fertilizer irrigation operation.
8. fruits and vegetables water-fertilizer conditioning device according to claim 7, which is characterized in that further include:
Environmental parameter obtains module, the growth ring that the growing environment parameter and current real-time monitoring for being obtained according to history obtain
Border gain of parameter environmental parameter predicted value;
Wherein, the processing module is also used to for the environmental parameter predicted value being compared with environmental parameter a reference value;And
If the environmental parameter predicted value is consistent with the environmental parameter a reference value, controls the water-fertilizer conditioning module and stop liquid manure
Irrigate operation.
9. a kind of fruits and vegetables water-fertilizer conditioning device characterized by comprising
Memory, for storing program;And
Processor, for executing described program, described program is at least for realizing according to claim 1 to described in any one of 6
Fruits and vegetables water-fertilizer conditioning method each step.
10. a kind of computer readable storage medium, is stored with computer program, which is characterized in that the computer program is located
When managing device execution, each step of fruits and vegetables water-fertilizer conditioning method according to any one of claim 1 to 6 is realized.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910925554.5A CN110533547A (en) | 2019-09-27 | 2019-09-27 | Fruits and vegetables water-fertilizer conditioning method and device and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910925554.5A CN110533547A (en) | 2019-09-27 | 2019-09-27 | Fruits and vegetables water-fertilizer conditioning method and device and computer readable storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110533547A true CN110533547A (en) | 2019-12-03 |
Family
ID=68670997
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910925554.5A Pending CN110533547A (en) | 2019-09-27 | 2019-09-27 | Fruits and vegetables water-fertilizer conditioning method and device and computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110533547A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111078732A (en) * | 2019-12-31 | 2020-04-28 | 新疆农业科学院园艺作物研究所 | Method for identifying almond variety |
CN111108879A (en) * | 2020-01-03 | 2020-05-08 | 华维节水科技集团股份有限公司 | Solanaceous fruit water and fertilizer and environment management method based on expert decision system |
CN114821253A (en) * | 2022-03-18 | 2022-07-29 | 北京国垦节水科技有限公司 | Method and system for regulating and controlling applicability of water and fertilizer spraying and drip irrigation integrated system |
CN117114374A (en) * | 2023-10-25 | 2023-11-24 | 四川省商投信息技术有限责任公司 | Intelligent agricultural irrigation management system based on weather prediction |
CN117236519A (en) * | 2023-11-10 | 2023-12-15 | 中化现代农业有限公司 | Water and fertilizer regulation and control method and device, electronic equipment and storage medium |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170038749A1 (en) * | 2015-08-05 | 2017-02-09 | Iteris, Inc. | Customized land surface modeling for irrigation decision support in a crop and agronomic advisory service in precision agriculture |
CN107087539A (en) * | 2017-05-27 | 2017-08-25 | 苟瀚文 | A kind of fruits and vegetables Intelligent irrigation system based on Internet of Things |
CN107896949A (en) * | 2017-11-20 | 2018-04-13 | 深圳春沐源控股有限公司 | A kind of water and fertilizer irrigation autocontrol method and system |
CN107944596A (en) * | 2017-10-20 | 2018-04-20 | 上海交通大学 | A kind of muskmelon growth management expert system based on Internet of Things |
CN108074236A (en) * | 2017-12-27 | 2018-05-25 | 广东欧珀移动通信有限公司 | Irrigating plant based reminding method, device, equipment and storage medium |
CN108207592A (en) * | 2018-02-13 | 2018-06-29 | 海东市福强农业科技有限公司 | Irrigation method and system based on water-fertilizer integral |
CN108510102A (en) * | 2018-02-07 | 2018-09-07 | 青岛农业大学 | A kind of water-fertilizer integral control method of irrigation using big data calculative strategy |
CN109673480A (en) * | 2019-02-22 | 2019-04-26 | 福州阿里他巴信息科技有限公司 | Intelligent water and fertilizer integrated sprinkling irrigation system and control method |
CN110214506A (en) * | 2019-06-26 | 2019-09-10 | 北京农业智能装备技术研究中心 | Liquid manure management-control method and system |
-
2019
- 2019-09-27 CN CN201910925554.5A patent/CN110533547A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170038749A1 (en) * | 2015-08-05 | 2017-02-09 | Iteris, Inc. | Customized land surface modeling for irrigation decision support in a crop and agronomic advisory service in precision agriculture |
CN107087539A (en) * | 2017-05-27 | 2017-08-25 | 苟瀚文 | A kind of fruits and vegetables Intelligent irrigation system based on Internet of Things |
CN107944596A (en) * | 2017-10-20 | 2018-04-20 | 上海交通大学 | A kind of muskmelon growth management expert system based on Internet of Things |
CN107896949A (en) * | 2017-11-20 | 2018-04-13 | 深圳春沐源控股有限公司 | A kind of water and fertilizer irrigation autocontrol method and system |
CN108074236A (en) * | 2017-12-27 | 2018-05-25 | 广东欧珀移动通信有限公司 | Irrigating plant based reminding method, device, equipment and storage medium |
CN108510102A (en) * | 2018-02-07 | 2018-09-07 | 青岛农业大学 | A kind of water-fertilizer integral control method of irrigation using big data calculative strategy |
CN108207592A (en) * | 2018-02-13 | 2018-06-29 | 海东市福强农业科技有限公司 | Irrigation method and system based on water-fertilizer integral |
CN109673480A (en) * | 2019-02-22 | 2019-04-26 | 福州阿里他巴信息科技有限公司 | Intelligent water and fertilizer integrated sprinkling irrigation system and control method |
CN110214506A (en) * | 2019-06-26 | 2019-09-10 | 北京农业智能装备技术研究中心 | Liquid manure management-control method and system |
Non-Patent Citations (2)
Title |
---|
张雪飞;彭凯;王建春;宋治文;王艳;梁新书;钱春阳;李鹏;: "设施蔬菜水肥一体化智能灌溉控制系统的设计及试验", 山西农业科学 * |
江新兰;杨邦杰;高万林;晏清洪;: "基于两线解码技术的水肥一体化云灌溉系统研究", 农业机械学报 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111078732A (en) * | 2019-12-31 | 2020-04-28 | 新疆农业科学院园艺作物研究所 | Method for identifying almond variety |
CN111108879A (en) * | 2020-01-03 | 2020-05-08 | 华维节水科技集团股份有限公司 | Solanaceous fruit water and fertilizer and environment management method based on expert decision system |
CN114821253A (en) * | 2022-03-18 | 2022-07-29 | 北京国垦节水科技有限公司 | Method and system for regulating and controlling applicability of water and fertilizer spraying and drip irrigation integrated system |
CN117114374A (en) * | 2023-10-25 | 2023-11-24 | 四川省商投信息技术有限责任公司 | Intelligent agricultural irrigation management system based on weather prediction |
CN117114374B (en) * | 2023-10-25 | 2024-02-06 | 四川省商投信息技术有限责任公司 | Intelligent agricultural irrigation management system based on weather prediction |
CN117236519A (en) * | 2023-11-10 | 2023-12-15 | 中化现代农业有限公司 | Water and fertilizer regulation and control method and device, electronic equipment and storage medium |
CN117236519B (en) * | 2023-11-10 | 2024-04-09 | 中化现代农业有限公司 | Water and fertilizer regulation and control method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110533547A (en) | Fruits and vegetables water-fertilizer conditioning method and device and computer readable storage medium | |
WO2022253057A1 (en) | Intelligent moisture precise irrigation control system and method for fruit and vegetable cultivation in solar greenhouse | |
US20220075344A1 (en) | A method of finding a target environment suitable for growth of a plant variety | |
CN111008733B (en) | Crop growth control method and system | |
CN109978234A (en) | Soil moisture content prediction, irrigation decision method and apparatus | |
CN109242201A (en) | A kind of method, apparatus and computer readable storage medium for predicting crop yield | |
CN108614601B (en) | Facility light environment regulation and control method fused with random forest algorithm | |
CN102789579A (en) | Identification method for stressed state of water fertilizer of greenhouse crop on basis of computer vision technology | |
CN112800665A (en) | Plant growth self-feedback learning cultivation method based on artificial intelligence | |
CN110119169A (en) | A kind of tomato greenhouse temperature intelligent early warning system based on minimum vector machine | |
US20220248616A1 (en) | Irrigation control with deep reinforcement learning and smart scheduling | |
CN108510102A (en) | A kind of water-fertilizer integral control method of irrigation using big data calculative strategy | |
CN112286263A (en) | Crop regulation and control method, device and system and communication equipment | |
CN110463587A (en) | Scale greenhouse water-saving irrigation system based on LoRa and GA-BP | |
CN112418473A (en) | Crop information processing method, device, equipment and computer storage medium | |
CN110472557A (en) | A kind of method and device of tomato growth monitoring | |
CN117036088A (en) | Data acquisition and analysis method for identifying growth situation of greening plants by AI | |
CN113158750A (en) | Self-feedback learning evaluation method of plant growth model based on convolutional neural network | |
Musa et al. | An intelligent plant dissease detection system for smart hydroponic using convolutional neural network | |
Tangwannawit et al. | An optimization clustering and classification based on artificial intelligence approach for internet of things in agriculture | |
Joseph et al. | Innovative analysis of precision farming techniques with artificial intelligence | |
Mamatha et al. | Machine learning based crop growth management in greenhouse environment using hydroponics farming techniques | |
Anand et al. | Applications of Internet of Things (IoT) in agriculture: The need and implementation | |
Zhangzhong et al. | Development of an evapotranspiration estimation method for lettuce via mobile phones using machine vision: Proof of concept | |
CN109116827A (en) | Heliogreenhouse water-fertilizer integral control method of irrigation and device based on Internet of Things |
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 |