CN103777520B - Drip irrigation autocontrol method based on crop chlorophyll content on-line checking - Google Patents
Drip irrigation autocontrol method based on crop chlorophyll content on-line checking Download PDFInfo
- Publication number
- CN103777520B CN103777520B CN201210411274.0A CN201210411274A CN103777520B CN 103777520 B CN103777520 B CN 103777520B CN 201210411274 A CN201210411274 A CN 201210411274A CN 103777520 B CN103777520 B CN 103777520B
- Authority
- CN
- China
- Prior art keywords
- confluent
- drip irrigation
- water
- optimal
- dynamic
- 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.)
- Expired - Fee Related
Links
Landscapes
- Feedback Control In General (AREA)
Abstract
A kind of automatic dripping irrigation control method of proportion of crop planting, it passes through direct, with plant growth and needing the closely related chlorophyll content in leaf blades of water in dynamic detection plant physiology parameter, the predicted estimate of optimal confluent is carried out by " drip irrigation amount forecast model ", the dynamic calculation of optimal confluent is realized by " dynamic water adjusting module " and " optimal water computing module ", and the optimal control that confluent is adjusted is realized by " water dynamic adjusting range fuzzy control model ", the prediction of confluent can be realized, optimization and Self Adaptive Control, it can be achieved to different geographical, Various Seasonal, the feedwater Self Adaptive Control of variety classes crop under Different climate and DIFFERENT METEOROLOGICAL CONDITIONS, saving irrigation water can be realized, ensure that plant growth is good simultaneously.
Description
Technical field
The present invention relates to a kind of agriculture automatic dripping irrigation control method, crop chlorophyll content on-line checking is based especially on
Drip irrigation control method, belongs to agriculture project and the technical field such as automatically controls.
Background technology
Under the background that electronic technology and automatic control technology are developed rapidly, industrialized agriculture has obtained significant progress, special
It is not that drip irrigation technique is made that tremendous contribution for agriculture water saving, section fertilizer.Existing drip irrigation control technology is mainly two kinds, a kind of
It is that control is timed by setting time, another is by detecting that the humidity of soil (or matrix) carries out feedback control.It is fixed
When control need according to locality, specific environment parameter (aerial temperature and humidity, gas concentration lwevel, substrate temperature etc.), specific
The particular growth period of crop species and crop sets drip irrigation cycle and drip irrigation time, it is therefore desirable to long-term planting experiment
To accumulate the drip irrigation experience of correlation, and it is difficult to accurately control drip irrigation.And fed back based on soil (or matrix) Humidity Detection
Drip irrigation control method, be by setting threshold values and lower threshold values in humidity, when the soil moisture detected less than setting lower valve
Magnetic valve is opened during value and carries out drip irrigation, when the humidity detected is higher than upper threshold values time control magnetic valve stopping drip irrigation, is moved with this
State maintains the humidity of soil (or matrix) between upper threshold values and lower threshold values, and the problem of this control is present is when soil moisture is low
When had influence on the optimum growh of crop, and can be wasted water if control humidity is too high, therefore also be difficult to accomplish
Ensure to save water resource while crop optimum growing environment.Therefore needing research one kind badly being capable of more effective drip irrigation controlling party
Method.
The content of the invention
To overcome the defect of prior art, the present invention proposes a kind of based on crop chlorophyll content is online, dynamic detection
Drip irrigation autocontrol method, the optimum growh of crop can be realized, and can effectively save water resource.
To achieve the above object, the present invention uses following technical scheme：
A kind of drip irrigation control method of the present invention：
Step 1：The detected value c of crop blade face chlorophyll content is input to " drip irrigation amount forecast model "；
Step 2：" drip irrigation amount forecast model " exports drip irrigation amount predicted valueTo " dynamic water adjusting module ", " water dynamic
Adjusting range fuzzy control model " exports water adjusting range Δ w to " dynamic water adjusting module "；
Step 3：" dynamic water adjusting module " is according to inputExist with Δ wIn the range of with mw
Confluent w is incrementally adjusted for unit, i.e., fromStart in units of mw be incremented by until no more thanSimultaneously will
Real-time confluent w and chlorophyll detected value c is input to " optimal confluent computing module ", wherein adjusting process in confluent w
In when w≤0 if not drip irrigation；
Step 4：Confluent w and chlorophyll are detected when " optimal confluent computing module " is adjusted according to confluent in step 3
Value c series of values calculates optimal confluent w*；
Step 5：Optimal confluent w* be input to " drip irrigation amount forecast model " be used for dynamic adjustment " drip irrigation amount forecast model "
Parameter；
Step 6：The drip irrigation amount predicted value of " drip irrigation amount forecast model " outputIt is defeated with " optimal confluent computing module "
Go out w* difference ew" water dynamic adjusting range fuzzy control model " is input to, " optimal confluent calculates mould
The output w* of block " differential dw*/dt also enters into " water dynamic adjusting range fuzzy control model ", and " water dynamically adjusts model
Enclose fuzzy control model " according to the two input numerical value output water adjusting range Δs w；
Step 7：Go to step 1.
Optimal water w* calculating in step 4 of the present invention, i.e. " dynamic water adjusting module " and " optimal confluent
Computing module " the course of work is：
Numerical value i=0 is set, feed water mw=1 milliliters of increment, array A and array B；
Step is 1.：IfThenDrip irrigation is controlled, otherwise A
[i]=0, stops drip irrigation；
Step is 2.：Crop blade face chlorophyll content c is detected, and makes B [i]=c；
Step is 3.：I=i+1 is made, ifStep 1 is gone to, step 4 is otherwise gone to；
Step is 4.：Differential calculation is carried out according to data sequence to array B, and records the 1st differentiation result arranging for 0 data
Sequence, is set to j, i.e. B ' (j)=0 and B ' (j-1) ≠ 0, then makes w*=A (j).
" drip irrigation amount forecast model " described in step 5 of the present invention is built single defeated using general regression neural net (GRNN)
Enter the GRNN network structures of single output, the dynamic state of parameters adjustment process of GRNN nets is as follows：
Numerical value k=0 is set, array C and array D is set；
Step a：Etc. new optimal water w* to be entered；
Step b：If k≤15, C [k]=w*, k=k+1, is transferred to step a；Else if k ＞ 15 are then transferred to step c；
Step c：D [15]=w*, setting numerical value m=1, D [15-m]=C [k-m]；
Step d：If m ＜ 16, step c is transferred to, step e is otherwise transferred to；
Step e：Input time sequence, the parameter of training GRNN nets are used as with array D；
Step f：The output data of future time, i.e. drip irrigation amount predicted value are calculated by GRNN nets
Step g：K=k+1, is transferred to step a；
Wherein, the GRNN network parameters training in step e only need to train smoothing factor, and training method is according to following step
Suddenly：
(i) make smoothing factor with increment the incremental variations in certain scope；
(ii) in learning sample, two samples is removed, with remaining sample training neutral net, are entered with the two samples
Row test；
(iii) Error Absolute Value of test sample, i.e. predicated error are calculated with the network model built；
(iiii) repeat step (ii), (iii), until all training samples are all once used to test, try to achieve prediction
The average value of error and as the object function E of optimizing.
" water dynamic adjusting range fuzzy control model " uses Mamdani type Fuzzy Controls in step 6 of the present invention
Device processed, its input quantity is respectively drip irrigation amount predicted valueAnd the output w* of " optimal confluent computing module " difference ew and optimal give
Water w* change dw*/dt, ew and dw*/dt is respectively through quantizing factor kewAnd kdwProcessing, wherein ew '=kew* ew, dw '=
kdw* (dw*/dt), is then input in fuzzy controller, and the Fuzzy Linguistic Variable of Fuzzy processing, ew ' and dw ' is carried out first
All it is divided into 5 subitems：" negative big " (NB), " negative small " (NS), " zero " (ZE), " just small " (PS), " honest " (PB), each subitem
Membership function is all taken as Gaussian function on respective domain, and as shown in table 1, Δ w ' passes through de-fuzzy to fuzzy inference rule again
Output Δ w ", Δ w " is multiplied by scale factor k afterwardswWater adjusting range Δ w is exported afterwards, form is as follows：
The fuzzy inference rule of table 1
Compared with prior art, beneficial effects of the present invention are as follows：
Existing drip irrigation control technology, such as passage time are controlled and by Temperature and Humidity Control drip irrigation, are all by indirect
Mode predicts water requirements of crops, is required for carrying out specific crop substantial amounts of early stage planting experiment acquisition empirical data, then
It is controlled as body evidence, the excellent effect that decide plantation of empirical data；In addition, to different crops, drip irrigation control
Strategy and mode otherness it is larger, therefore universality is poor；Furthermore, to different weather, season and region, existing control can not
Realize Self Adaptive Control.
The present invention by direct, dynamic detection plant physiology parameter with plant growth and needing the closely related blade and blade of water
Chlorophyll contents, the predicted estimate of optimal confluent is carried out by " drip irrigation amount forecast model ", is passed through " dynamic water adjusting module "
" optimal confluent computing module " realizes the dynamic calculation of optimal confluent, and by the way that " water dynamic adjusting range is obscured
Control module " realizes the optimal control of confluent adjustment, can realize the prediction, optimization and Self Adaptive Control of confluent, can be real
Now to the feedwater Self Adaptive Control of the variety classes crop under different geographical, Various Seasonal, Different climate and DIFFERENT METEOROLOGICAL CONDITIONS
With save irrigation water, while ensuring that plant growth is good.
Brief description of the drawings
Fig. 1 is the operation principle block diagram of the inventive method；
The flow chart that Fig. 2 dynamically adjusts for GRNN network parameters in the present invention；
Fig. 3 is the theory diagram of fuzzy controller in the present invention.
Embodiment
Below in conjunction with the accompanying drawings and specific embodiment the invention will be further described.
Embodiment 1
As shown in figure 1, a kind of drip irrigation control method：
Step 1：The detected value c of crop blade face chlorophyll content is input to " drip irrigation amount forecast model "；
Step 2：" drip irrigation amount forecast model " exports drip irrigation amount predicted valueTo " dynamic water adjusting module ", " water dynamic
Adjusting range fuzzy control model " exports water adjusting range Δ w to " dynamic water adjusting module "；
Step 3：" dynamic water adjusting module " is according to inputExist with Δ wIn the range of with mw
Confluent w is incrementally adjusted for unit, i.e., fromStart in units of mw be incremented by until no more thanSimultaneously will
Real-time confluent w and chlorophyll detected value c is input to " optimal confluent computing module ", wherein adjusting process in confluent w
In when w≤0 if not drip irrigation；
Step 4：Confluent w and chlorophyll are detected when " optimal confluent computing module " is adjusted according to confluent in step 3
Value c series of values calculates optimal confluent w*；
Step 5：Optimal confluent w* be input to " drip irrigation amount forecast model " be used for dynamic adjustment " drip irrigation amount forecast model "
Parameter；
Step 6：The drip irrigation amount predicted value of " drip irrigation amount forecast model " outputWith the output of " optimal confluent computing module "
W* difference" water dynamic adjusting range fuzzy control model " is input to, " optimal confluent calculates mould
The output w* of block " differential dw*/dt also enters into " water dynamic adjusting range fuzzy control model ", and " water dynamically adjusts model
Enclose fuzzy control model " according to the two input numerical value output water adjusting range Δs w；
Step 7：Go to step 1.
Embodiment 2
In the present invention, optimal water w* calculating, i.e. " dynamic water adjusting module " and " optimal confluent computing module "
The course of work is：
Numerical value i=0 is set, feed water mw=1 milliliters of increment, array A and array B；
Step is 1.：IfThenDrip irrigation is controlled, otherwise A
[i]=0, stops drip irrigation；
Step is 2.：Crop blade face chlorophyll content c is detected, and makes B [i]=c；
Step is 3.：I=i+1 is made, ifStep 1 is gone to, step 4 is otherwise gone to；
Step is 4.：Differential calculation is carried out according to data sequence to array B, and records the 1st differentiation result arranging for 0 data
Sequence, is set to j, i.e. B ' (j)=0 and B ' (j-1) ≠ 0, then makes w*=A (j).
Embodiment 3
As shown in Fig. 2 heretofore described " drip irrigation amount forecast model " is using general regression neural net (GRNN), build
The GRNN network structures of single-input single-output, the dynamic state of parameters of GRNN nets adjusts process idiographic flow and is：
Numerical value k=0 is set, array C and array D is set；
Step a：Etc. new optimal water w* to be entered；
Step b：If k≤15, C [k]=w*, k=k+1, is transferred to step a；Else if k ＞ 15 are then transferred to step c；
Step c：D [15]=w*, setting numerical value m=1, D [15-m]=C [k-m]；
Step d：If m ＜ 16, step c is transferred to, step e is otherwise transferred to；
Step e：Input time sequence, the parameter of training GRNN nets are used as with array D；
Step f：The output data of future time, i.e. drip irrigation amount predicted value are calculated by GRNN nets
Step g：K=k+1, is transferred to step a；
Wherein, the GRNN network parameters training in step e only need to train smoothing factor, and training method is according to following step
Suddenly：
(i) make smoothing factor with increment the incremental variations in certain scope；
(ii) in learning sample, two samples is removed, with remaining sample training neutral net, are entered with the two samples
Row test；
(iii) Error Absolute Value of test sample, i.e. predicated error are calculated with the network model built；
(iiii) repeat step (ii), (iii), until all training samples are all once used to test, try to achieve prediction
The average value of error and as the object function E of optimizing.
Embodiment 4
As shown in figure 3, " water dynamic adjusting range fuzzy control model " of the present invention is using Mamdani patterns paste
Controller, its input quantity is respectively drip irrigation amount predicted valueAnd the output w* of " optimal confluent computing module " difference ew and optimal
Confluent w* change dw*/dt, ew and dw*/dt is respectively through quantizing factor kewAnd kdwProcessing, wherein ew '=kww*ew、dw′
=kdw* (dw*/dt), is then input in fuzzy controller, and Fuzzy processing, ew ' and dw ' fuzzy language change are carried out first
Amount is all divided into 5 subitems：" negative big " (NB), " negative small " (NS), " zero " (ZE), " just small " (PS), " honest " (PB), each subitem
Membership function be all taken as Gaussian function on respective domain, as shown in table 1, Δ w ' passes through deblurring to fuzzy inference rule again
Δ w ", Δ w " are exported after change and is multiplied by scale factor kwWater adjusting range Δ w is exported afterwards, and form is as follows：
The fuzzy inference rule of table 2
Claims (2)
1. a kind of automatic dripping irrigation control method of proportion of crop planting, it is characterized in that：
Step 1：The detected value c of crop blade face chlorophyll content is input to " drip irrigation amount forecast model "；
Step 2：" drip irrigation amount forecast model " exports drip irrigation amount predicted valueTo " dynamic water adjusting module ", " water is dynamically adjusted
Range ambiguities control module " exports water adjusting range Δ w to " dynamic water adjusting module "；
Step 3：" dynamic water adjusting module " is according to inputExist with Δ wIn the range of using mw to be single
Position incrementally adjust confluent w, i.e., fromStart in units of mw be incremented by until no more thanSimultaneously will be real-time
Confluent w and chlorophyll detected value c be input to " optimal confluent computing module ", wherein confluent w adjustment during such as
Then not drip irrigation during fruit w≤0；
Step 4：Confluent w and chlorophyll detected value c when " optimal confluent computing module " is adjusted according to confluent in step 3
Series of values calculates optimal confluent w*；
Step 5：Optimal confluent w* be input to " drip irrigation amount forecast model " be used for dynamic adjustment " drip irrigation amount forecast model " ginseng
Number；
Step 6：The drip irrigation amount predicted value of " drip irrigation amount forecast model " outputWith the output w* of " optimal confluent computing module " it
Difference" water dynamic adjusting range fuzzy control model " is input to, " optimal confluent computing module "
Output w* differential dw*/dt also enters into " water dynamic adjusting range fuzzy control model ", " water dynamic adjusting range mould
Paste control module " according to the two input numerical value output water adjusting range Δs w；
Step 7：Go to step 1.
2. the automatic dripping irrigation control method described in claim 1, it is characterized in that：In the step 4 optimal confluent w* according to
Lower step is calculated：
Numerical value i=0 is set, feed water mw=1 milliliters of increment, array A and array B；
Step is 1.：IfThenDrip irrigation is controlled, otherwise A [i]
=0, stop drip irrigation；
Step is 2.：Crop blade face chlorophyll content c is detected, and makes B [i]=c；
Step is 3.：I=i+1 is made, ifGo to step 1., otherwise go to step 4.；
Step is 4.：Differential calculation is carried out according to data sequence to array B, and it is 0 data sorting to record the 1st differentiation result,
J, i.e. B ' (j)=0 and B ' (j-1) ≠ 0 are set to, then makes w*=A (j)；
" drip irrigation amount forecast model " described in claim 1, it is characterized in that using general regression neural net (GRNN), building single defeated
Enter the GRNN network structures of single output, the dynamic state of parameters adjustment process of GRNN nets is calculated according to following steps：
Numerical value k=0 is set, array C and array D is set；
Step a：Etc. new optimal confluent w* to be entered；
Step b：If k≤15, C [k]=w*, k=k+1, is transferred to step a；Else if k ＞ 15 are then transferred to step c；
Step c：D [15]=w*, setting numerical value m=1, D [15-m]=C [k-m]；
Step d：If m ＜ 16, step c is transferred to, step e is otherwise transferred to；
Step e：Input time sequence, the parameter of training GRNN nets are used as with array D；
Step f：The output data of future time, i.e. drip irrigation amount predicted value are calculated by GRNN nets
Step g：K=k+1, is transferred to step a；
Wherein, the GRNN network parameters training in step e only need to train smoothing factor, and training method is according to following steps：
(i) make smoothing factor with increment the incremental variations in certain scope；
(ii) in learning sample, two samples is removed, with remaining sample training neutral net, are surveyed with the two samples
Examination；
(iii) Error Absolute Value of test sample, i.e. predicated error are calculated with the network model built；
(iiii) repeat step (ii), (iii), until all training samples are all once used to test, try to achieve predicated error
Average value and as the object function E of optimizing；
" water dynamic adjusting range fuzzy control model " described in claim 1, it is characterized in that：Pasted using Mamdani patterns
Controller, its input quantity is respectively drip irrigation amount predicted valueAnd the output w* of " optimal confluent computing module " difference ew and optimal
Confluent w* change dw*/dt, ew and dw*/dt is respectively through quantizing factor kewAnd kdwProcessing, wherein ew '=kew*ew、dw′
=kdw* (dw*/dt), is then input in fuzzy controller, and Fuzzy processing, ew ' and dw ' fuzzy language change are carried out first
Amount is all divided into 5 subitems：" negative big " (NB), " negative small " (NS), " zero " (ZE), " just small " (PS), " honest " (PB), each subitem
Membership function Gaussian function is all taken as on respective domain, fuzzy inference rule is as shown in the table, Δ w ' again pass through mould from
Δ w ", Δ w " are exported after gelatinization and is multiplied by scale factor kwWater adjusting range Δ w is exported afterwards, and form is as follows：
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210411274.0A CN103777520B (en) | 2012-10-25 | 2012-10-25 | Drip irrigation autocontrol method based on crop chlorophyll content on-line checking |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210411274.0A CN103777520B (en) | 2012-10-25 | 2012-10-25 | Drip irrigation autocontrol method based on crop chlorophyll content on-line checking |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103777520A CN103777520A (en) | 2014-05-07 |
| CN103777520B true CN103777520B (en) | 2017-10-13 |
Family
ID=50569899
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210411274.0A Expired - Fee Related CN103777520B (en) | 2012-10-25 | 2012-10-25 | Drip irrigation autocontrol method based on crop chlorophyll content on-line checking |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103777520B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4663703A (en) * | 1985-10-02 | 1987-05-05 | Westinghouse Electric Corp. | Predictive model reference adaptive controller |
| CN101422124A (en) * | 2008-12-12 | 2009-05-06 | 河北工业大学 | Greenhouse intelligent drip-irrigation device |
| CN202035353U (en) * | 2011-01-14 | 2011-11-16 | 吉林省农机装备科技创新中心 | Accurate drip irrigation system with independent consciousness |
| ES2377394A1 (en) * | 2010-02-10 | 2012-03-27 | Treelogic Telem�?Tica Y Lógica Racional Para La Empresa Europea S.L. | Irrigation system based on artificial intelligence. (Machine-translation by Google Translate, not legally binding) |
-
2012
- 2012-10-25 CN CN201210411274.0A patent/CN103777520B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4663703A (en) * | 1985-10-02 | 1987-05-05 | Westinghouse Electric Corp. | Predictive model reference adaptive controller |
| CN101422124A (en) * | 2008-12-12 | 2009-05-06 | 河北工业大学 | Greenhouse intelligent drip-irrigation device |
| ES2377394A1 (en) * | 2010-02-10 | 2012-03-27 | Treelogic Telem�?Tica Y Lógica Racional Para La Empresa Europea S.L. | Irrigation system based on artificial intelligence. (Machine-translation by Google Translate, not legally binding) |
| CN202035353U (en) * | 2011-01-14 | 2011-11-16 | 吉林省农机装备科技创新中心 | Accurate drip irrigation system with independent consciousness |
Non-Patent Citations (2)
| Title |
|---|
| 《一种新型温室滴灌控制算法》;徐立鸿;《农业工程学报》;20031130;第19卷;全文 * |
| 向先全.《基于模糊识别和遗传神经网络的渤海叶绿素a预测研究》.《海洋环境科学》.2011,第30卷(第2期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103777520A (en) | 2014-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Iddio et al. | Energy efficient operation and modeling for greenhouses: A literature review | |
| CN106227038A (en) | Grain drying tower intelligent control method based on neutral net and fuzzy control | |
| WO2023179167A1 (en) | Crop irrigation water demand prediction method based on aquacrop model and svr | |
| CN106613783A (en) | Universal intelligent irrigation system and control method therefor | |
| Pacco | Simulation of temperature control and irrigation time in the production of tulips using Fuzzy logic | |
| WO2020199453A1 (en) | Seedbed scheduling method and system capable of precisely predicting illumination, and medium | |
| CN114365614A (en) | Water and fertilizer accurate regulation and control method, intelligent equipment and system based on Internet of things | |
| CN105184400A (en) | Tobacco field soil moisture prediction method | |
| Zhou | Intelligent control of agricultural irrigation based on reinforcement learning | |
| CN103777520B (en) | Drip irrigation autocontrol method based on crop chlorophyll content on-line checking | |
| Marinescu et al. | Advanced control strategies for irrigation systems | |
| Mohammed et al. | An intelligent irrigation system based on fuzzy logic control: A case study for Moroccan oriental climate region | |
| US20120310375A1 (en) | A nonlinear intelligent pulse-controller | |
| CN105842398B (en) | A kind of plant growth fertilizer Consumption Analysis device and method | |
| Yan et al. | Design and verification of fuzzy neural network automatic control algorithm in intelligent agriculture | |
| Rivera et al. | A new automated drip irrigation and fertigation system for sugarcane crops | |
| Wang et al. | Integrated Intelligent Management system of Water and Fertilizer based on Internet of things | |
| Pawłowski et al. | Event-based control for a greenhouse irrigation system | |
| CN107015480A (en) | A kind of intelligent greenhouse irrigation system based on generalized predictive control and Internet of Things | |
| Sun et al. | Greenhouse intelligent control system based on indoor and outdoor environmental data fusion | |
| Ma et al. | Simulation of crop evaportranspiration based on BP neural network model and grey relational analysis | |
| CN117236650B (en) | Water-fertilizer integrated intelligent pump house control method | |
| Zhang et al. | Design and Development of Precise Mango Irrigation Decision-Making System Based on Lora | |
| Qiu et al. | Intelligent control system of water and fertilizer in greenhouse based on tomato phenotype discrimination and growth environment prediction | |
| Yan et al. | Research on the Current Situation and Development of Intelligent Precision Fertilizer Technology |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20171013 Termination date: 20211025 |