CN105892287A - Crop irrigation strategy based on fuzzy judgment and decision making system - Google Patents
Crop irrigation strategy based on fuzzy judgment and decision making system Download PDFInfo
- Publication number
- CN105892287A CN105892287A CN201610302094.7A CN201610302094A CN105892287A CN 105892287 A CN105892287 A CN 105892287A CN 201610302094 A CN201610302094 A CN 201610302094A CN 105892287 A CN105892287 A CN 105892287A
- Authority
- CN
- China
- Prior art keywords
- attribute
- crop
- crops
- decision
- crop irrigation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- 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
- G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
- G05B13/0285—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks and fuzzy logic
Landscapes
- Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a crop irrigation strategy based on fuzzy judgment and a decision making system. The crop irrigation strategy comprises the following steps: S1, establishing and generating a system knowledge base according to sample data; and S2, determining current water demand for crop irrigation via fuzzy judgment according to current growth environment and growth phase data of crops. The crop irrigation strategy and the crop irrigation decision making system can effectively establish and generate a system knowledge base according to sample data to analyze current growth environment and growth phase data of crops so as to acquire accurate irrigation water quantity; compared with the traditional strategy and system based on soil temperature and humidity, the strategy and the system have the advantages that different soil, growth environments and weather conditions and different growth phases of crops are comprehensively considered, so that the water regime of crops can be reflected more directly; and the growth environment and the growth condition of crops are jointly used as a decision making basis for the water demand of the crops, so that the judgment precision can be improved and the utilization rate of water resources is effectively improved.
Description
Technical field
The present invention relates to pattern recognition and water-saving irrigation, particularly in crop irrigation decision-making based on fuzzy judgment
In system.
Background technology
Shortage of water resources is the great difficult problem that countries in the world face, the commonly used traditional ground of China's agricultural irrigation
Face irrigation technique, water efficiency of irrigation is less than 50%, and water serious waste phenomenon, enforcement is based on crop water
The Precision Irrigation of information characteristics is the effective way of agricultural water-saving irrigation.As new and high technology and agricultural production phase
In conjunction with industry, Precision Irrigation is according to practical situations such as soil, weather, irrigating facility, plant growths, right
Irrigation opportunity, the water yield, mode are precisely controlled, and make the water demand of crop reach optimum state, it is achieved water provides
The efficient utilization in source, to obtain optimal economic benefit and environmental benefit.
At present to the irrigation decision great majority of crops all with the soil moisture and humidity as foundation, can not be accurate
What ground reflection crops were actual needs regimen condition.
Therefore, for the problems referred to above, need to design one and can accurately control irrigation volume, to ensure that crops are more
The crop irrigation strategy of good growth and crop irrigation decision system.
Summary of the invention
It is an object of the invention to provide a kind of crop irrigation strategy and crop irrigation decision system, to reach
Crops are realized the purpose of precision irrigation.
In order to solve above-mentioned technical problem, the invention provides a kind of crop irrigation strategy, including walking as follows
Rapid:
Step S1, sets up according to sample data and generates system knowledge base；
Step S2, according to the current growing environment of crops, growth stage data, is determined by fuzzy judgment and works as
The water requirement of front crop irrigation.
Further, in described step S1 according to sample data set up generate system knowledge base method include:
Step S11, gather crop growth environment, each growth stage water requirement data message as sample number
According to, set up crop water requirement linked database, to construct fuzzy information systems；
Step S12, carries out attribute reduction, generating probability decision rules in fuzzy information systems；And
Step S13, utilizes neutral net to be trained yojan, to generate described system knowledge base.
Further, according to the current growing environment of crops, growth stage data in described step S2, mould is passed through
Stick with paste judgement and determine the water requirement of current crop irrigation, i.e.
According to the current growing environment of crops, the data cases of growth stage, adjudicated by Neural Fuzzy
Determine current crop water requirement.
Further, described step S11 gathers crop growth environment, the water requirement data of each growth stage
Information, sets up crop water requirement linked database, includes walking as follows constructing the method for fuzzy information systems
Rapid:
Step S111, sets up crop growth environment factor sample set U, water requirement conditional attribute collection C and needs
Water yield decision kind set V；
Step S112, described fuzzy information systems constructs, i.e.
Described fuzzy information systems is four-tuple: G={U, A, V, f}；Wherein
U is domain, the set of the most all crop sample information；
A is community set, i.e. A=C ∪ D, and in formula: C represents conditional attribute, i.e. the soil of crops is wet
The set of degree, the soil moisture, growth stage attribute composition；D represents decision attribute, i.e. crop water requirement
The set of attribute composition；
V is the union of attribute codomain, V=∪ Va, VaRepresent the codomain of attribute a ∈ A, i.e. soil moisture, life
The codomain union of sets collection of long stage and water requirement attribute；
F represents U × A → V information function, gives property value for each object in domain, i.e.X ∈ U,
There are f (x, a) ∈ Va。
Further, described step S1 will carry out attribute reduction, i.e. in fuzzy information systems
Judge attributes similarity, conditional attribute is carried out yojan, it is thus achieved that yojan conditional attribute set C1, its side
Method comprises the steps:
Step S121, defined attribute similarityWherein: X, Y ∈ A, X
Be any two attribute in domain with Y, i.e. A is the union of conditional attribute and decision attribute；Ind () is opinion
Territory U is about the equivalent partition class of attribute；N is equivalent partition class number；
Step S122, the similarity S (c between computation attribute conditional attribute and decision attributei, D), wherein
ci, cj∈ C, i=1 ... m, i ≠ j, m are the number of conditional attribute；According to similarity S (ci, D) value size will
Conditional attribute carries out descending C={c1, c2..., cm}；Wherein
S(c1, D) and >=S (c2, D) >=... >=S (cm, D)；
Step S123, defines yojan property set C1=Φ, in attribute calculate two of which conditional attribute it
Between similarity S (ci, cj), c in formulai, cj∈ C, i, j=1 ... m, i ≠ j, i ＜ j；
if S(ci, cj)≥S(ci, D) and then C1=C-cj；And
Calculate S (C1, D), if S (C1, D) and=S (C, D) then C1=C-cj, else C1=C；
Step S124, until each conditional attribute completes traversal；
Step S125, obtains yojan conditional attribute set C1。
Further, the method utilizing neutral net to be trained yojan in described step S13 includes walking as follows
Rapid:
Step S131, sends into probabilistic neural network input layer by the sample data after condition yojan, and neural
Unit's nodes is equal with conditional attribute set dimension；
Step S133, arranges hidden layer neuron nodes equal with sample number, and neuron uses gaussian kernel letter
Count and determine input/output relation:
Wherein t=1 ... M, k=1 ... Nt；X is the input vector needing to carry out decision-making, has d genus
Property；The value of d is the conditional attribute dimension obtained after yojan；xtkIt is hidden layer vector, in hidden layer
The kth neuron of t class sample；M is total class number of training sample, i.e. equal to the dimension of decision attribute；
Nt is the sample number of t class；And σ is smoothing factor, σ ∈ (0, ∞)；
Step S133, the output belonging to same class hidden neuron done weighted average by weighting layer:
Wherein t=1 ... M；
Step S134, calculates in the output of all neurons and has maximum a posteriori probability density value
The classification of ρ (x)=argmax (t) is as the output result of neutral net；
Step S135, takes the output result decision value as soil water requirement of neutral net, and builds decision-making
Table.
Another aspect, present invention also offers a kind of crop irrigation decision system.
Described crop irrigation decision system, including: it is used for gathering the current growing environment of crops, growth step
The acquisition module of segment data, the server being connected with this crops corresponding data acquisition module；Described server
Be suitable to regulate the water consumption of crop irrigation.
Further, described server is suitable for use with described crop irrigation strategy and carries out water consumption regulation and control.
The invention has the beneficial effects as follows, the crop irrigation strategy of the present invention and crop irrigation decision system energy
Effectively set up according to sample data and generate system knowledge base, to analyze the current growing environment of crops, growth
Phase data, and then obtain precision irrigation water consumption, with traditional according to compared with soil temperature and humidity condition, combines
Close and consider different soil property, growing environment, weather condition and the different growth phases of crops, can be more straight
Ground connection reaction crop water status, by the growing environment of crop and growing state collectively as crop water decision-making
Foundation, can increase judgement precision, is effectively improved the utilization rate of water resource.
Accompanying drawing explanation
The present invention is further described with embodiment below in conjunction with the accompanying drawings.
Fig. 1 is the FB(flow block) of the crop irrigation strategy of the present invention；
Fig. 2 is the theory diagram of the crop irrigation decision system of the present invention.
Detailed description of the invention
In conjunction with the accompanying drawings, the present invention is further detailed explanation.These accompanying drawings are the schematic diagram of simplification,
The basic structure of the present invention is described the most in a schematic way, and therefore it only shows the composition relevant with the present invention.
Embodiment 1
As it is shown in figure 1, present embodiments provide a kind of crop irrigation strategy, comprise the steps:
Step S1, sets up according to sample data and generates system knowledge base；And
Step S2, according to the current growing environment of crops, growth stage data, is determined by fuzzy judgment and works as
The water requirement of front crop irrigation.
Wherein, described sample data includes but not limited to crop growth soil types, soil moisture, soil
The crops such as temperature, relative air humidity, air themperature, atmosphere illumination intensity, wind speed, sunshine time are raw
Long environmental data.
Concrete, in described step S1, the method according to sample data foundation generation system knowledge base includes:
Step S11, gather crop growth environment, each growth stage water requirement data message as sample number
According to, set up crop water requirement linked database, to construct fuzzy information systems；
Step S12, carries out attribute reduction, generating probability decision rules in fuzzy information systems；And
Step S13, utilizes neutral net to be trained yojan, to generate described system knowledge base.
Concrete, according to the current growing environment of crops, growth stage data in described step S2, pass through mould
Stick with paste judgement and determine the water requirement of current crop irrigation, i.e.
According to the current growing environment of crops, the data cases of growth stage, adjudicated by Neural Fuzzy
Determine current crop water requirement.
Concrete, described step S11 gathers crop growth environment, the water requirement data of each growth stage
Information, sets up crop water requirement linked database, includes walking as follows constructing the method for fuzzy information systems
Rapid:
Step S111, sets up crop growth environment factor sample set U, water requirement conditional attribute collection C and needs
Water yield decision kind set V；
Step S112, described fuzzy information systems constructs, i.e.
Described fuzzy information systems is four-tuple: G={U, A, V, f}；Wherein
U is domain, the set of the most all crop sample information；
A is community set, i.e. A=C ∪ D, and in formula: C represents conditional attribute, i.e. the soil of crops is wet
The set of degree, the soil moisture, growth stage attribute composition；D represents decision attribute, i.e. crop water requirement
The set of attribute composition；
V is the union of attribute codomain, V=∪ Va, VaRepresent the codomain of attribute a ∈ A, i.e. soil moisture, life
The codomain union of sets collection of long stage and water requirement attribute, a represents certain conditional attribute；
F represents U × A → V information function, gives property value for each object in domain, i.e.X ∈ U,
There are f (x, a) ∈ Va.X represents some object in domain U, specially sample or treat the object of decision-making.f
Each attribute for each object in domain gives a value of information.
Concrete, described step S1 will carry out attribute reduction, i.e. in fuzzy information systems
Judge attributes similarity, conditional attribute is carried out yojan, it is thus achieved that yojan conditional attribute set C1, its side
Method comprises the steps:
Step S121, defined attribute similarityWherein: X, Y ∈ A, X
Be any two attribute in domain with Y, i.e. A is the union of conditional attribute and decision attribute, wherein X and
Y can be conditional attribute or decision attribute；Ind () is the domain U equivalent partition class about attribute；N is equivalent partition class number；
Step S122, the similarity S (c between computation attribute conditional attribute and decision attributei, D), wherein
ci, cj∈ C, i=1 ... m, i ≠ j, m are the number of conditional attribute；According to similarity S (ci, D) value size will
Conditional attribute carries out descending C={c1, c2... cm}；Wherein
S(c1, D) and >=S (c2, D) >=... >=S (cm, D)；
Step S123, defines yojan property set C1=Φ, in attribute calculate two of which conditional attribute it
Between similarity S (ci, cj), c in formulai, cj∈ C, i, j=1 ... m, i ≠ j, i ＜ j；
if S(ci, cj)≥S(ci, D) and then C1=C-cj；And
Calculate S (C1, D), if S (C1, D) and=S (C, D) then C1=C-cj, else C1=C；
Concrete, according to the size of conditional attribute and decision attribute similarity by after conditional attribute descending sort,
Similarity between relatively two conditional attributes.If the similarity between two conditional attributes is than certain condition
Similarity between attribute and decision attribute is big, then it is assumed that between the two conditional attribute, the probability of redundancy is big,
Then using that less for similarity between conditional attribute and decision attribute conditional attribute as redundant attributes, remaining
Conditional attribute as the conditional attribute after yojan.Calculate yojan postcondition attribute and yojan precondition attribute it
Between similarity equal, then it is assumed that the certain redundancy of redundant attributes is unnecessary.Otherwise the condition after yojan belongs to
The conditional attribute that property is the most original.
Step S124, until each conditional attribute completes traversal；
Step S125, obtains yojan conditional attribute set C1。
Concrete, the method utilizing neutral net to be trained yojan in described step S13 includes walking as follows
Rapid:
Step S131, sends into probabilistic neural network input layer by the sample data after condition yojan, and neural
Unit's nodes is equal with conditional attribute set dimension；
Step S133, arranges hidden layer neuron nodes equal with sample number, and neuron uses gaussian kernel letter
Count and determine input/output relation:
Wherein t=1 ... M, k=1 ... Nt；X is the input vector needing to carry out decision-making, has d attribute；
The value of d is the conditional attribute dimension obtained after yojan；xtkIt is hidden layer vector, for t in hidden layer
The kth neuron of class sample；M is total class number of training sample, i.e. equal to the dimension of decision attribute；Nt
It it is the sample number of t class；And σ is smoothing factor, σ ∈ (0, ∞)；
Step S133, the output belonging to same class hidden neuron done weighted average by weighting layer:
Wherein t=1 ... M；ΦtkIt it is the output valve of previous step；vtIt is that weighting layer is belonging to identical in hidden layer
Weighted average is done in the output of the hidden neuron of one class；
Step S134, calculates in the output of all neurons and has maximum a posteriori probability density value
ρ (x)=argmax (vt) classification as the output result of neutral net；
Step S135, takes the output result decision value as soil water requirement of neutral net, and builds decision-making
Table.
Embodiment 2
On the basis of embodiment 1, the present embodiment 2 additionally provides a kind of crop irrigation decision system, including:
For gathering the current growing environment of crops, the acquisition module of growth stage data, with this crops respective counts
The server being connected according to acquisition module；Described server is suitable to regulate the water consumption of crop irrigation.
Concrete, acquisition module includes: soil moisture sensor, soil temperature sensor, air humidity pass
Sensor, air temperature sensor, intensity of illumination sensor and air velocity transducer, raw to gather lane crop respectively
Long soil types, soil moisture, the soil moisture, relative air humidity, air themperature, atmosphere illumination intensity,
The crop growth environment data such as wind speed, sunshine time, and the growing environment data of acquisition are passed through wireless network
Network sends server to.
Each sensor can be by a controller as transmission node, after collecting the data of each sensor
Send to server, and by controller, each data acquisition collected and be transmitted all by wireless transmission
Prior art can be used to realize.
Wherein, described server is suitable for use with crop irrigation strategy as described in Example 1 and carries out water consumption
Regulation and control.
Concrete, server, according to crop growth environment data and current growth stage, carries out fuzzy determining
Plan, it is judged that the water requirement of current crops, determines the crop irrigation electromagnetic valves opening time.Server is by electricity
The unlatching information of pond valve is sent to controller by wireless network, controls the open and close of electromagnetic valve, finally
Realize the accurate control of the water demand of crop.
With the above-mentioned desirable embodiment according to the present invention for enlightenment, by above-mentioned description, related work
Personnel can carry out various change and amendment completely in the range of without departing from this invention technological thought.
The content that the technical scope of this invention is not limited in description, it is necessary to according to right
Determine its technical scope.
Claims (8)
1. a crop irrigation strategy, it is characterised in that comprise the steps:
Step S1, sets up according to sample data and generates system knowledge base；And
Step S2, according to the current growing environment of crops, growth stage data, is determined by fuzzy judgment and works as
The water requirement of front crop irrigation.
Crop irrigation strategy the most according to claim 1, it is characterised in that
In described step S1, the method according to sample data foundation generation system knowledge base includes:
Step S11, gather crop growth environment, each growth stage water requirement data message as sample number
According to, set up crop water requirement linked database, to construct fuzzy information systems；
Step S12, carries out attribute reduction, generating probability decision rules in fuzzy information systems；And
Step S13, utilizes neutral net to be trained yojan, to generate described system knowledge base.
Crop irrigation strategy the most according to claim 1 and 2, it is characterised in that
According to the current growing environment of crops, growth stage data in described step S2, true by fuzzy judgment
The water requirement of settled front crop irrigation, i.e.
According to the current growing environment of crops, the data cases of growth stage, adjudicated by Neural Fuzzy
Determine current crop water requirement.
Crop irrigation strategy the most according to claim 3, it is characterised in that
Described step S11 gathers crop growth environment, the water requirement data message of each growth stage, builds
Vertical crop water requirement linked database, comprises the steps: constructing the method for fuzzy information systems
Step S111, sets up crop growth environment factor sample set U, water requirement conditional attribute collection C and needs
Water yield decision kind set V；
Step S112, described fuzzy information systems constructs, i.e.
Described fuzzy information systems is four-tuple: G={U, A, V, f}；Wherein
U is domain, the set of the most all crop sample information；
A is community set, i.e. A=C ∪ D, and in formula: C represents conditional attribute, i.e. the soil of crops is wet
The set of degree, the soil moisture, growth stage attribute composition；D represents decision attribute, i.e. crop water requirement
The set of attribute composition；
V is the union of attribute codomain, V=∪ Va, VaRepresent the codomain of attribute a ∈ A, i.e. soil moisture, life
The codomain union of sets collection of long stage and water requirement attribute；
F represents U × A → V information function, gives property value for each object in domain, i.e.
There are f (x, a) ∈ Va。
Crop irrigation strategy the most according to claim 4, it is characterised in that in described step S1
Fuzzy information systems will carry out attribute reduction, i.e.
Judge attributes similarity, conditional attribute is carried out yojan, it is thus achieved that yojan conditional attribute set C1, its side
Method comprises the steps:
Step S121, defined attribute similarityWherein: X, Y ∈ A, X
Be any two attribute in domain with Y, i.e. A is the union of conditional attribute and decision attribute；Ind () is opinion
Territory U is about the equivalent partition class of a certain attribute；N is equivalent partition class number；
Step S122, the similarity S (c between computation attribute conditional attribute and decision attributei, D), wherein
ci, cj∈ C, i=1 ... m, i ≠ j, m are the number of conditional attribute；
Step S123, defines yojan property set C1=Φ, in attribute calculate two of which conditional attribute it
Between similarity S (ci, cj), c in formulai, cj∈ C, i, j=1 ... m, i ≠ j, i ＜ j；
Step S124, until each conditional attribute completes traversal；
Step S125, obtains yojan conditional attribute set C1。
Crop irrigation strategy the most according to claim 5, it is characterised in that
The method utilizing neutral net to be trained yojan in described step S13 comprises the steps:
Step S131, sends into probabilistic neural network input layer by the sample data after condition yojan, and neural
Unit's nodes is equal with conditional attribute set dimension；
Step S133, arranges hidden layer neuron nodes equal with sample number, and neuron uses gaussian kernel letter
Count and determine input/output relation:
Wherein t=1 ... M, k=1 ... Nt；X is the input vector needing to carry out decision-making, has d genus
Property；The value of d is the conditional attribute dimension obtained after yojan；xtkIt is hidden layer vector, in hidden layer
The kth neuron of t class sample；M is total class number of training sample, i.e. equal to the dimension of decision attribute；
Nt is the sample number of t class；And σ is the sliding factor, σ ∈ (0, ∞)；
Step S133, the output belonging to same class hidden neuron done weighted average by weighting layer:
Wherein t=1 ... M；
Step S134, calculates in the output of all neurons and has maximum a posteriori probability density value
The classification of ρ (x)=argmax (t) is as the output result of neutral net；
Step S135, takes the output result decision value as soil water requirement of neutral net, and builds decision-making
Table.
7. a crop irrigation decision system, it is characterised in that including: be used for gathering crops and work as previous existence
Long environment, the acquisition module of growth stage data, the service being connected with this crops corresponding data acquisition module
Device；
Described server is suitable to regulate the water consumption of crop irrigation.
Crop irrigation decision system the most according to claim 7, it is characterised in that described server
It is suitable for use with crop irrigation strategy as claimed in claim 1 and carries out water consumption regulation and control.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610302094.7A CN105892287B (en) | 2016-05-09 | 2016-05-09 | Crop irrigation strategy and decision system based on fuzzy judgment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610302094.7A CN105892287B (en) | 2016-05-09 | 2016-05-09 | Crop irrigation strategy and decision system based on fuzzy judgment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105892287A true CN105892287A (en) | 2016-08-24 |
| CN105892287B CN105892287B (en) | 2018-12-18 |
Family
ID=56703256
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610302094.7A Expired - Fee Related CN105892287B (en) | 2016-05-09 | 2016-05-09 | Crop irrigation strategy and decision system based on fuzzy judgment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105892287B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106489687A (en) * | 2016-10-28 | 2017-03-15 | 深圳前海弘稼科技有限公司 | The control method of irrigation rig and control device |
| CN106707757A (en) * | 2017-01-23 | 2017-05-24 | 中国农业大学 | Dynamic regulation and control method and system for irrigation time |
| CN107169413A (en) * | 2017-04-12 | 2017-09-15 | 上海大学 | A kind of human facial expression recognition method of feature based block weight |
| CN107991888A (en) * | 2018-01-03 | 2018-05-04 | 常州市兰翔电器有限公司 | Agricultural automation embedded integration system and its method of work based on machine learning |
| 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 |
| CN108762084A (en) * | 2018-06-14 | 2018-11-06 | 淮安信息职业技术学院 | Irrigation system of rice field based on fuzzy control decision and method |
| CN111346688A (en) * | 2018-12-24 | 2020-06-30 | 航天信息股份有限公司 | Wheat dampening control method and device |
| CN112352523A (en) * | 2020-09-09 | 2021-02-12 | 安徽农业大学 | Tea garden water and fertilizer irrigation control method and system based on intelligent decision |
| CN112772384A (en) * | 2021-01-28 | 2021-05-11 | 深圳市协润科技有限公司 | Agricultural water irrigation system and method based on convolutional neural network |
| CN113673866A (en) * | 2021-08-20 | 2021-11-19 | 上海寻梦信息技术有限公司 | Crop decision method, model training method and related equipment |
| CN114708495A (en) * | 2022-03-09 | 2022-07-05 | 中国农业科学院农田灌溉研究所 | Multi-source irrigation information fusion decision-making method and system |
| CN115392582A (en) * | 2022-09-01 | 2022-11-25 | 广东工业大学 | Crop yield prediction method based on incremental fuzzy rough set attribute reduction |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101236410A (en) * | 2007-12-29 | 2008-08-06 | 中国农业大学 | Intelligent irrigation fertilizing decision-making control system |
| US20080255684A1 (en) * | 2002-11-18 | 2008-10-16 | Universiti Putra Malaysia | Artificial intelligence device and corresponding methods for selecting machinability data |
| CN105045091A (en) * | 2015-07-14 | 2015-11-11 | 河海大学常州校区 | Dredging process intelligent decision analysis method based on fuzzy neural control system |
-
2016
- 2016-05-09 CN CN201610302094.7A patent/CN105892287B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080255684A1 (en) * | 2002-11-18 | 2008-10-16 | Universiti Putra Malaysia | Artificial intelligence device and corresponding methods for selecting machinability data |
| CN101236410A (en) * | 2007-12-29 | 2008-08-06 | 中国农业大学 | Intelligent irrigation fertilizing decision-making control system |
| CN105045091A (en) * | 2015-07-14 | 2015-11-11 | 河海大学常州校区 | Dredging process intelligent decision analysis method based on fuzzy neural control system |
Non-Patent Citations (2)
| Title |
|---|
| GUIFEN CHEN 等: ""Research of Irrigation Control System Based on Fuzzy Neural Network"", 《2011 INTERNATIONAL CONFERENCE ON MECHATRONIC SCIENCE, ELECTRIC ENGINEERING AND COMPUTER》 * |
| 陈双叶 等: ""一种基于粗糙集的模糊信息融合方法及应用"", 《中国工程科学》 * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106489687A (en) * | 2016-10-28 | 2017-03-15 | 深圳前海弘稼科技有限公司 | The control method of irrigation rig and control device |
| CN106707757A (en) * | 2017-01-23 | 2017-05-24 | 中国农业大学 | Dynamic regulation and control method and system for irrigation time |
| CN107169413A (en) * | 2017-04-12 | 2017-09-15 | 上海大学 | A kind of human facial expression recognition method of feature based block weight |
| CN107169413B (en) * | 2017-04-12 | 2021-01-12 | 上海大学 | Facial expression recognition method based on feature block weighting |
| CN107991888A (en) * | 2018-01-03 | 2018-05-04 | 常州市兰翔电器有限公司 | Agricultural automation embedded integration system and its method of work based on machine learning |
| 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 |
| CN108762084A (en) * | 2018-06-14 | 2018-11-06 | 淮安信息职业技术学院 | Irrigation system of rice field based on fuzzy control decision and method |
| CN111346688B (en) * | 2018-12-24 | 2021-08-24 | 航天信息股份有限公司 | Wheat dampening control method and device |
| CN111346688A (en) * | 2018-12-24 | 2020-06-30 | 航天信息股份有限公司 | Wheat dampening control method and device |
| CN112352523A (en) * | 2020-09-09 | 2021-02-12 | 安徽农业大学 | Tea garden water and fertilizer irrigation control method and system based on intelligent decision |
| CN112352523B (en) * | 2020-09-09 | 2022-10-04 | 安徽农业大学 | Tea garden water and fertilizer irrigation control method and system based on intelligent decision |
| CN112772384A (en) * | 2021-01-28 | 2021-05-11 | 深圳市协润科技有限公司 | Agricultural water irrigation system and method based on convolutional neural network |
| CN112772384B (en) * | 2021-01-28 | 2022-12-20 | 深圳市协润科技有限公司 | Agricultural water irrigation system and method based on convolutional neural network |
| CN113673866A (en) * | 2021-08-20 | 2021-11-19 | 上海寻梦信息技术有限公司 | Crop decision method, model training method and related equipment |
| CN114708495A (en) * | 2022-03-09 | 2022-07-05 | 中国农业科学院农田灌溉研究所 | Multi-source irrigation information fusion decision-making method and system |
| CN114708495B (en) * | 2022-03-09 | 2024-04-09 | 中国农业科学院农田灌溉研究所 | Multi-source irrigation information fusion decision method and system |
| CN115392582A (en) * | 2022-09-01 | 2022-11-25 | 广东工业大学 | Crop yield prediction method based on incremental fuzzy rough set attribute reduction |
| CN115392582B (en) * | 2022-09-01 | 2023-11-14 | 广东工业大学 | Crop yield prediction method based on increment fuzzy rough set attribute reduction |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105892287B (en) | 2018-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105892287A (en) | Crop irrigation strategy based on fuzzy judgment and decision making system | |
| CN102402185B (en) | Deficit irrigation controlling method based on fuzzy control | |
| CN106779418A (en) | Water contamination accident Intelligent Decision-making Method based on neutral net and evidence theory | |
| CN108419339A (en) | Multifunctional LED intelligent road lamp system based on LoRa technologies | |
| CN104408562A (en) | Photovoltaic system generating efficiency comprehensive evaluation method based on BP (back propagation) neural network | |
| CN104399682A (en) | Intelligent decision pre-warning system for sweeping of photovoltaic power station components | |
| CN101894270A (en) | Method for full-automatic sample selection oriented to classification of remote-sensing images | |
| Mayilvaganan et al. | ANN and Fuzzy Logic Models for the Prediction of groundwater level of a watershed | |
| CN105868887A (en) | Building comprehensive energy efficiency analysis method based on subentry measure | |
| An et al. | Application of new technology of intelligent robot plant protection in ecological agriculture | |
| CN106371316A (en) | PSO-LSSVM-based on-line control method and apparatus for dosing of water island | |
| CN106682764A (en) | Method for predicting other day air-conditioning load of public building based on parallel prediction strategy | |
| CN108762084A (en) | Irrigation system of rice field based on fuzzy control decision and method | |
| CN106971241A (en) | The method that sewage quality data are predicted based on fuzzy neural network | |
| CN109408896A (en) | A kind of anerobic sowage processing gas production multi-element intelligent method for real-time monitoring | |
| Zhang et al. | Urban traffic flow prediction model based on BP artificial neural network in Beijing area | |
| CN110503303A (en) | cloud-Bayesian network-based intelligent macro site selection method for offshore wind farm | |
| Xia et al. | Environmental factor assisted chlorophyll-a prediction and water quality eutrophication grade classification: A comparative analysis of multiple hybrid models based on a SVM | |
| CN115206444A (en) | Optimal drug dosage prediction method based on FCM-ANFIS model | |
| Mo et al. | An Improved BP Neural Network based on IPSO and Its Application. | |
| Simsek et al. | ESTIMATION OF NUTRIENT CONCENTRATIONS IN RUNOFF FROM BEEF CATTLE FEEDLOT USING ADAPTIVE NEURO-FUZZY INFERENCE SYSTEMS. | |
| CN102354376A (en) | Method for supplementing and correcting wind measurement data | |
| Pierre et al. | AI Based Real-Time Weather Condition Prediction with Optimized Agricultural Resources | |
| Santosh et al. | Development of IoT based intelligent irrigation system using particle swarm optimization and XGBoost techniques | |
| Sarmadian et al. | Neural computing model for prediction of soil cation exchange capacity: a data mining approach. |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220119 Address after: 213002 building 8-5, Huashan Road, Xinbei District, Changzhou City, Jiangsu Province Patentee after: Jiangsu Zhishui Intelligent Technology Co.,Ltd. Address before: 213022, No. 200, Jinling North Road, Xinbei District, Jiangsu, Changzhou Patentee before: CHANGZHOU CAMPUS OF HOHAI University |
|
| 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: 20181218 |