CN109062290A - A kind of reading intelligent agriculture environmental monitoring system and monitoring method based on big data - Google Patents
A kind of reading intelligent agriculture environmental monitoring system and monitoring method based on big data Download PDFInfo
- Publication number
- CN109062290A CN109062290A CN201810810557.XA CN201810810557A CN109062290A CN 109062290 A CN109062290 A CN 109062290A CN 201810810557 A CN201810810557 A CN 201810810557A CN 109062290 A CN109062290 A CN 109062290A
- Authority
- CN
- China
- Prior art keywords
- greenhouse
- humidity
- soil temperature
- data
- big data
- 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
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D27/00—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00
- G05D27/02—Simultaneous control of variables covered by two or more of main groups G05D1/00 - G05D25/00 characterised by the use of electric means
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to agricultural technology fields, disclose a kind of reading intelligent agriculture environmental monitoring system and monitoring method based on big data, and set-up of control system has greenhouse, and the upper surface of greenhouse is equipped with sun-shading curtain, and sun-shading curtain is connected with screen-roller;Exhaust fan is fixed on the left of greenhouse;The outside surrounding of greenhouse, which is stood, support column, is equipped with solar panel by bolt on support column;The right side of greenhouse is shelved with control cabinet, header tank and medicaments dispensing case respectively;Soil temperature-moisture sensor, green house temperature-humidity sensor and greenhouse detector are respectively fixed with by bolt on the support frame of greenhouse;The inner wall of greenhouse has been bolted intensity of illumination inductor;Present invention simultaneously discloses a kind of control methods.The present invention can real-time dynamic monitoring and adjust agricultural environment to adapt to crop growth environment, improve the economic benefit of crops.
Description
Technical field
The invention belongs to agricultural technology field more particularly to a kind of reading intelligent agriculture environmental monitoring system based on big data and
Monitoring method.
Background technique
Currently, the prior art commonly used in the trade is such that
Currently, to be that one kind combines computer automatic control technology, intelligent sensing technology contour for reading intelligent agriculture wireless supervisory control system
The resource-conserving efficient facility agricultural technology of technological means, it is mainly according to the temperature of the environment, humidity, carbon dioxide contain
The factors such as amount, photosynthetically active radiation and soil regime, to control the indoor indices of temperature, to create suitable plant growth
Suitable environment.It is obviously how accurate, stablize, easily obtain these environmental informations just and become the pass of whole system
Key.With the development of short-distance wireless communication in recent years, emerging sensor network technology is the sensing in intelligent agricultural system
Link provides strong technical guarantee.
Using present emerging Radio Transmission Technology and high-precision sensor, the characteristics of work according to agricultural production, this
Positioning, timing, quantitative principle implement the system of a whole set of modernization farming operations technology and management, basic connotation is root
According to the soil property of plant growth, the investment to crop is adjusted, i.e., on the one hand investigates thoroughly the soil property and productivity inside field
Spatial variability, on the other hand determine crops productive target, positioned " system diagnostics, optimization of C/C composites, Technical form,
Soil productivity is transferred in scientific management ", reaches same income or higher income with investment that is least or most saving, and change
Kind environment, efficiently utilizes all kinds of agricultural resources, obtains economic benefit and environmental benefit.
Mostly still by the way of manually supervising, existing main problem is as follows for existing agricultural management:
1, it by the way of manual measurement, record, can not in real time, dynamically monitor within 24 hours;
2, manually supervise that unstable, error is big, is easy to be disturbed;
3, using artificial monitoring, poor in timeliness easily be easy to cause great economic loss.
4, the date comprision of the prior art, intelligence degree is low, and the data accuracy of detection is poor.Currently based on interdependent
The similarity based method of temperature and humidity or other and agricultural environment related data parameter does not fully consider each element inside dependence
Role's significance level, and the problem of be only labeled dependence as a whole.It causes to be easy to make with setting value comparison
It is big at control deviation, the plant growth of agricultural environment related data parameter sensitivity is had some impact on.
Summary of the invention
In view of the problems of the existing technology, the present invention provides a kind of reading intelligent agriculture environmental monitoring system based on big data
System and monitoring method.
The invention is realized in this way a kind of reading intelligent agriculture environment control method based on big data, comprising:
By big data analysis device to soil temperature-moisture sensor, green house temperature-humidity sensor, greenhouse detector, light
The data detected according to intensity inductor and the soil temperature and humidity, the green house temperature-humidity, greenhouse oxygen gas concentration, intensity of illumination that prestore
Setting value parameter compares and analyzes, and the control instruction after analysis is transferred to screen-roller, exhaust fan, water supply pump, heating dress
It sets, medicaments dispensing case is turned on or off accordingly;
Soil temperature-moisture sensor in soil temperature and humidity Data Detection,
Big data analysis device sets value parameter with the soil temperature and humidity prestored to the data that soil temperature-moisture sensor detects
In comparing and analyzing, it is based on dependence pair, the dependence of multiple soil temperature and humidities continuously detected carries out set
Matching, selection make relationship to the maximum corresponding relationship of the sum of similarity, on the basis of corresponding relationship, find out each relationship to similar
The average value of the sum of degree is compared and analyzed with the soil temperature and humidity setting value parameter of setting;The structure of dependence pair is compatible
The acquisition methods of degree include: dependence to < R1, R2>, R is compared respectively1(C1, A1, D1, CP1, AP1) and R2(C2, A2, D2, CP2,
AP2) in five characteristic quantities, it is compatible to take 1, it is incompatible to take 0;Then, arranged from a high position to low level by weight order this five 0 or
1, obtain a binary number (bbbbb)2, the value range of the value is 0-31, wherein 0 corresponding R1And R2Complete unequal feelings
Condition, 31 corresponding R1And R2Essentially equal situation;On the basis of the binary number, R is defined1And R2Structure compatible degree it is as follows:
Assuming that in two five-tuple R1(C1, A1, D1, CP1, AP1) and R2(C2, A2, D2, CP2, AP2) in, C1With C2It is compatible, A1
With A2It is incompatible, D1With D2It is compatible, CP1With CP2It is compatible, AP1With AP2It is incompatible, then it is obtained according to each feature weight sequence arrangement
Binary number is (10110)2, then R1And R2Structure compatible degree are as follows:
The similarity calculating method of dependence pair includes: dependence to < R1, R2> in element there are soil temperature and humidities
Data are compatible, pass through calculating < R1, R2> corresponding core soil data of the Temperature and Humidity module dominates the soil of soil temperature and humidity data with adjusting
Earth data of the Temperature and Humidity module similarity measures the soil temperature and humidity data similarity of dependence pair, using the calculating side based on Hownet
Method calculates soil temperature and humidity data similarity, and assigns different weight α and β, obtains R1And R2Soil temperature and humidity data it is similar
It spends as follows:
Ss(R1, R2)=α Sw(C1, C2)+βSw(A1, A2);
In formula, Sw(C1, C2) expression < R1, R2> in correspond to the similarity of core soil data of the Temperature and Humidity module, Sw(A1, A2) indicate
It is corresponding to dominate soil temperature and humidity data similarity, α > β and alpha+beta=1;
It is based onWith formula Ss(R1, R2)=α Sw(C1, C2)+βSw(A1,
A2), obtain the similarity calculating method of dependence pair: R1|R2=Sim (R1, R2)=Sc(R1, R2)gSs(R1, R2);
Big data analysis device sets value parameter with the soil temperature and humidity prestored to the data that soil temperature-moisture sensor detects
It in comparing and analyzing, is compared and analyzed using particle swarm algorithm, in particle swarm algorithm, the optimizing phase uses particle swarm algorithm
The feature weight for optimizing characteristic weighing KNN algorithm, specifically includes: initializing population, the position of each particle using random device
Setting with the dimension of speed is n, the position corresponding data of each particle concentrate a record feature weight vector w=(w1,
W2 ..., wn): wherein haveAdaptive value is calculated, and then finds out locally optimal solution and globally optimal solution: being adapted to calculating
When value, position, that is, feature weight of particle is applied in characteristic weighing KNN algorithm, former training sample concentration preceding 70% is regarded
New training sample, rear 30% regards new forecast sample collection, classifies to this forecast sample collection, calculates the accurate of classification
Degree, the accuracy the high more meets adaptive value;Forecast sample integrates the initial soil data of the Temperature and Humidity module label of every record as li=
(li1, li2 ..., lin), it is sorted after prediction soil temperature and humidity data be lj=(lj1, lj2 ..., ljn), li and lj with
Coincidence number is sum, then accuracy rate Accruay=sum/n;
Sorting phase: the feature weight that the optimizing phase is obtained be applied in characteristic weighing KNN algorithm to test sample X into
Row is classified, and the soil temperature and humidity data of all samples in final output test set complete classification.
Further, dependence includes: to set similarity calculating method
There are dependences to set A=(a1, a2…an) and dependence to set B=(b1, b2…bm), it does not lose general
Property, the number of dependence pair is less than or equal to B, i.e. n≤m in A;For each ai∈ A, 1≤i≤n, find several bj∈
B, 1≤j≤m are corresponding to it, different aiCorresponding different bj, then the corresponding relationship sum of set A and set B is as follows:
There is determining corresponding relationship in set A and BIn ΩkIn, for given aiThere is one
bjIt is matching, it is denoted as bj=Ωk(ai);Then define QkSimilarity are as follows:
Two dependences take Ω to the similarity of set A and BkIn maximum value, it may be assumed that
In formula,
Further, the particle swarm algorithm includes:
Particle Swarm is initialized, including the position xi=(x for initializing entire populationi1, xi2... xid) T and speed vi
=(vi1, vi2..., vid)TAnd local optimum and total optimization, wherein id indicates d-th of particle in the i-th generation;
Further, the particle swarm algorithm further comprises:
Each particle is calculated in the fitness value fitness of current positionid=f (xid).Then according to fitness value
Size initializes locally optimal solution pbesti=fitnessiWith total optimization solution gbest=min (fintess1,
fitness2..., fitnessN), i=1,2 ..., N;
Further, the particle swarm algorithm further comprises:
In each iterative process, each particle updates the position and speed of oneself according to following criterion:
vid(t+1)=wvid(t)+c1r1(pld-xid(t))+c2r2(pgd-xid(t))
xid(t+1)=xid(t)+vid(t+1)
Wherein vidFor the speed of particle, xidFor the position of particle, w is inertia weight, and c1 and c2 are acceleration factor, r1With
r2It is random number, PldThe P for globally optimal solutiongdFor locally optimal solution;
Update locally optimal solution pbestiWith total optimization solution gbest;
If total optimization solution gbest reaches the threshold value of setting or has reached the maximum the number of iterations, algorithm is terminated;
Characteristic weighing KNN algorithm specifically includes:
M training sample is inputted, and sets k value size;
First randomly choose k initial closest nodes of A [1]~A [k] sample in training set as sample X to be predicted;
Calculate the weighting Euclidean distance wd (X, A [i]), i of sample X to be predicted and each initial k closest node
=1,2 ... .., k), calculate range formula are as follows:
Wherein n expression sample A [i] attribute number, i.e. A [i]=(3 ... A [i] of A [i] 1, A [i] 2, A [i] is n);
The distance wd asked (X, A [i]) is sorted in ascending order, the maximum distance maxD=of distance wd (X, A [i]) is acquired
Max d (X, A [i]) | and i=1,2 ... .., k };
It successively calculates in training set and is left record at a distance from sample to be tested X, and is farthest with being acquired in the step SB4
Distance maxD is compared, if smaller than maximum distance maxD, maximum distance maxD is updated to the record at a distance from sample to be tested X
Value, then by ascending order adjust the distance wd (X, A [i]) sequence;
The frequency of occurrence of the label of every record in present range wd (X, A [i]) sequence is calculated, and according to occurrence out
Several height sequences;
The preceding L soil temperature and humidity data that sequence is obtained are as the soil temperature and humidity data of sample X.
Another object of the present invention is to provide the reading intelligent agriculture environment control methods described in a kind of realize based on big data
Computer program.
Another object of the present invention is to provide the reading intelligent agriculture environment control methods described in a kind of realize based on big data
Information data processing terminal.
Another object of the present invention is to provide a kind of computer readable storage mediums, including instruction, when it is in computer
When upper operation, so that computer executes the reading intelligent agriculture environment control method based on big data.
Another object of the present invention is to provide a kind of realize to state the environment control method of the reading intelligent agriculture based on big data
Reading intelligent agriculture environmental monitoring system based on big data, the reading intelligent agriculture environmental monitoring system based on big data are provided with
Greenhouse;
The upper surface of greenhouse is equipped with sun-shading curtain, and sun-shading curtain passes through spool and the screen-roller for being mounted on upper surface on the left of greenhouse
Connection;
Exhaust fan has been bolted on the left of the greenhouse;
The outside surrounding of the greenhouse, which is stood, support column, is equipped with solar panel by bolt on support column;
The right side of the greenhouse is shelved with control cabinet, header tank and medicaments dispensing case respectively;
The control cabinet is electrically connected to solar panel;
The header tank is connected by the water service pipe being socketed on water supply pump and the support frame of greenhouse;
It is equipped with medicine spraying tube along support frame on the support frame of the greenhouse, multiple rotary nozzles are fastened on medicine spraying tube;
Soil temperature-moisture sensor is respectively fixed with by bolt on the support frame of the greenhouse, green house temperature-humidity senses
Device and greenhouse detector;
The inner wall of the greenhouse has been bolted intensity of illumination inductor.
Further, the fixed heating installation on the support frame of bolt is provided at the top of the water service pipe;
The lower section of the water service pipe was equipped with a atomizer;
Big data analysis device is provided in the control cabinet, by signal wire respectively with soil temperature-moisture sensor, greenhouse
Temperature Humidity Sensor, greenhouse detector, intensity of illumination inductor, screen-roller, exhaust fan, water supply pump, heating installation, medicine
Object adjustment case is connected;
Device is connected with printing device to the control cabinet by wireless communication, and the bottom hung of printing device has collecting box;
The inside of the medicaments dispensing case is divided into several subregions by partition;It is embedded on the side wall of the medicaments dispensing case
More pencils, are connected to the bottom of medicaments dispensing case;The bottom end of the pencil is connected with closure patch, is electrically connected to medicaments dispensing
The timer in bottom portion;The inside of the medicaments dispensing case is equipped with blender by bolt;
The front surface of the pencil is carved with graduation mark, and is pasted with mark label.
The advantages and positive effects of the present invention are:
The present invention to the network node in greenhouse, largely believe in real time by the environment such as temperature collection, humidity, illumination, gas concentration
Breath, accurately obtains the soil informations such as soil moisture, compaction, conductivity, pH value, nitrogen, these information are converged in data
Node sinks provide reliable basis for accuracy controlling;Big data analysis server analyzes the data collected, and helps to give birth to
Production person launches capital goods in the agricultural sector targeted specifically, intelligently controls the movements such as temperature, illumination, ventilation, sprinkling drug, it can be achieved that certainly
Dynamicization controls light application time and intensity and automatic irrigation;The present invention uninterruptedly, in real time can carry out agricultural environment for 24 hours
Monitoring, error is smaller, strong antijamming capability, can effectively reduce the loss of economic benefit, and arable land can be better achieved
The reasonable efficient modernization Precision management using with agricultural of resource, promotes the efficient management and use of China's cultivated land resource, has
Help the raising of farmland management level and agricultural production efficiency.
Big data analysis device of the present invention sets the data that soil temperature-moisture sensor detects with the soil temperature and humidity prestored
During value parameter compares and analyzes, it is based on dependence pair, by the dependence of multiple soil temperature and humidities continuously detected to collection
Conjunction is matched, and selection makes relationship to the maximum corresponding relationship of the sum of similarity, on the basis of corresponding relationship, finds out each relationship
To the average value of the sum of similarity, compared and analyzed with the soil temperature and humidity setting value parameter of setting;The knot of dependence pair
The acquisition methods of structure compatible degree include: dependence to < R1, R2>, R is compared respectively1(C1, A1, D1, CP1, AP1) and R2(C2, A2,
D2, CP2, AP2) in five characteristic quantities, it is compatible to take 1, it is incompatible to take 0;Then, this is arranged from a high position to low level by weight order
Five 0 or 1, obtain a binary number (bbbbb)2, the value range of the value is 0-31, wherein 0 corresponding R1And R2Not phase completely
Deng situation, 31 corresponding R1And R2Essentially equal situation;On the basis of the binary number, R is defined1And R2Structure it is compatible
It spends as follows:
It solves currently based on interdependent temperature and humidity or other and agricultural environment related data
The similarity based method of parameter does not fully consider the problem of role's significance level of each element inside dependence, solves and sets
In value comparison, control deviation is small, provides favourable conditions, this hair for the plant growth of agricultural environment related data parameter sensitivity
Bright regulation method can also be applied to regulate and control the probiotics living environment in soil and fertilizer;Control cabinet control of the present invention
Green house temperature-humidity degree sensor (JASUN-TH03/04), greenhouse detector (AGP800-NO2), intensity of illumination inductor
(QLS60) regulation method is identical as the control method of soil temperature-moisture sensor, ensure that the intelligent control of parameters.
Big data analysis device of the present invention sets the data that soil temperature-moisture sensor detects with the soil temperature and humidity prestored
It during value parameter compares and analyzes, is compared and analyzed using particle swarm algorithm, in particle swarm algorithm, the optimizing phase uses particle
The feature weight of group's algorithm optimization characteristic weighing KNN algorithm, specifically includes: initializing population, each grain using random device
The dimension of the position and speed of son is n, and the position corresponding data of each particle concentrates the feature weight vector w=of a record
(w1, w2 ..., wn): wherein haveAdaptive value is calculated, and then finds out locally optimal solution and globally optimal solution, can get
Accurate comparative analysis data, accuracy improve nearly 8 percentage points compared with the prior art.
Detailed description of the invention
Fig. 1 is the reading intelligent agriculture environmental monitoring system structural schematic diagram provided in an embodiment of the present invention based on big data;
Fig. 2 is the solar panel of the reading intelligent agriculture environmental monitoring system provided in an embodiment of the present invention based on big data
Structural schematic diagram;
Fig. 3 is the medicaments dispensing case of the reading intelligent agriculture environmental monitoring system provided in an embodiment of the present invention based on big data
Structural schematic diagram;
In figure: 1, ground;2, support frame;3, support column;4, water service pipe;5, control cabinet;6, water supply pump;7, header tank;
8, atomizer;9, heating installation;10, solar panel;11, soil temperature-moisture sensor;12, green house temperature-humidity senses
Device;13, greenhouse detector;14, intensity of illumination inductor;15, screen-roller;16, exhaust fan;17, sun-shading curtain;18, it sprays
Pipe;19, rotary nozzle;20, medicaments dispensing case;20-1, partition;20-2, pencil;20-3, patch is blocked;20-4, blender;
20-5, timer.
Specific embodiment
In order to further understand the content, features and effects of the present invention, the following examples are hereby given, and cooperate attached drawing
Detailed description are as follows.
In the prior art, it by the way of manual measurement, record, can not in real time, dynamically monitor within 24 hours;Artificial supervision
Unstable, error is big, is easy to be disturbed;Using artificial monitoring, poor in timeliness easily be easy to cause great economic loss.
Structure of the invention is explained in detail with reference to the accompanying drawing.
As shown in Figure 1-Figure 3, the reading intelligent agriculture environmental monitoring system setting provided in an embodiment of the present invention based on big data
There is greenhouse 1, the upper surface of greenhouse 1 is equipped with sun-shading curtain 17, and sun-shading curtain 17 is by spool and is mounted on upper surface on the left of greenhouse
Screen-roller 15 connects;
The left side of the greenhouse 1 has been bolted exhaust fan 16;
The outside surrounding of the greenhouse 1, which is stood, support column 3, is equipped with solar panel 10 by bolt on support column 3;
The right side of the greenhouse 1 is shelved with control cabinet 5, header tank 7 and medicaments dispensing case 20 respectively;
The control cabinet 5 is electrically connected to solar panel 2;
The header tank 7 is connected by the water service pipe 4 being socketed on water supply pump 6 and the support frame 2 of greenhouse 1;
It is equipped with medicine spraying tube 18 along support frame 2 on the support frame 2 of the greenhouse 1, multiple rotations are fastened on medicine spraying tube 18
Turn spray head 19;
On the support frame 2 of the greenhouse 1 by bolt be respectively fixed with soil moisture wet sensor (ESM101-01T) 11,
Green house temperature-humidity degree sensor (JASUN-TH03/04) 12 and greenhouse detector (AGP800-NO2) 13;
The inner wall of the greenhouse 1 has been bolted intensity of illumination inductor (QLS60) 14.
As the preferred embodiment of the present invention, the top of the water service pipe 4 is provided with bolt and is fixed on support frame 2
Heating installation 9.
As the preferred embodiment of the present invention, the lower section of the water service pipe 4 was equipped with a atomizer 8.
As the preferred embodiment of the present invention, it is provided with big data analysis device in the control cabinet 5, is distinguished by signal wire
With soil moisture wet sensor (ESM101-01T) 11, green house temperature-humidity degree sensor (JASUN-TH03/04) 12, greenhouse gas
Detector (AGP800-NO2) 13, screen-roller 15, exhaust fan 16, water supply pump 17, supplies intensity of illumination inductor (QLS60) 14
Heater device 9, medicaments dispensing case 20 are connected.
As the preferred embodiment of the present invention, device is connected with printing device to the control cabinet 5 by wireless communication, printing
The bottom hung of equipment has collecting box.
As the preferred embodiment of the present invention, the inside of the medicaments dispensing case 20 is several points by partition 20-1 points
Area;It is embedded with more pencil 20-2 on 20 side wall of medicaments dispensing case, is connected to the bottom of medicaments dispensing case 20;The pencil
The bottom end of 20-2, which is connected with, blocks patch 20-3, is electrically connected to the timer 2 0-5 of 20 bottom of medicaments dispensing case;The drug tune
The inside of agent case 20 is equipped with blender 20-4 by bolt.
As the preferred embodiment of the present invention, the front surface of the pencil 20-2 is carved with graduation mark, and is pasted with mark label.
The operation principle of the present invention is that: the control cabinet 5 of greenhouse 1 is by big data analysis device to soil moisture wet sensor
(ESM101-01T) 11, green house temperature-humidity degree sensor (JASUN-TH03/04) 12, greenhouse detector (AGP800-NO2)
13, intensity of illumination inductor (QLS60) 14 is analyzed and summarized, and is controlled screen-roller 15, exhaust fan 16, water supply pump 17, supplied
Heater device 9, medicaments dispensing case 20 are turned on or off, and then the growing environments of the crops inside adjust automatically greenhouse 1;Control
The data that cabinet 5 processed is analyzed can be carried out printing by printing device and stay shelves;Solar panel 10 can convert solar energy into electrical energy,
It is powered for control cabinet 5, renewable resource is effectively utilized.
Below with reference to concrete analysis, the invention will be further described.
Reading intelligent agriculture environment control method provided in an embodiment of the present invention based on big data, comprising:
By big data analysis device to soil temperature-moisture sensor, green house temperature-humidity sensor, greenhouse detector, light
The data detected according to intensity inductor and the soil temperature and humidity, the green house temperature-humidity, greenhouse oxygen gas concentration, intensity of illumination that prestore
Setting value parameter compares and analyzes, and the control instruction after analysis is transferred to screen-roller, exhaust fan, water supply pump, heating dress
It sets, medicaments dispensing case is turned on or off accordingly;
Soil temperature-moisture sensor in soil temperature and humidity Data Detection,
Big data analysis device sets value parameter with the soil temperature and humidity prestored to the data that soil temperature-moisture sensor detects
In comparing and analyzing, it is based on dependence pair, the dependence of multiple soil temperature and humidities continuously detected carries out set
Matching, selection make relationship to the maximum corresponding relationship of the sum of similarity, on the basis of corresponding relationship, find out each relationship to similar
The average value of the sum of degree is compared and analyzed with the soil temperature and humidity setting value parameter of setting;The structure of dependence pair is compatible
The acquisition methods of degree include: dependence to < R1, R2>, R is compared respectively1(C1, A1, D1, CP1, AP1) and R2(C2, A2, D2, CP2,
AP2) in five characteristic quantities, it is compatible to take 1, it is incompatible to take 0;Then, arranged from a high position to low level by weight order this five 0 or
1, obtain a binary number (bbbbb)2, the value range of the value is 0-31, wherein 0 corresponding R1And R2Complete unequal feelings
Condition, 31 corresponding R1And R2Essentially equal situation;On the basis of the binary number, R is defined1And R2Structure compatible degree it is as follows:
Assuming that in two five-tuple R1(C1, A1, D1, CP1, AP1) and R2(C2, A2, D2, CP2, AP2) in, C1With C2It is compatible, A1
With A2It is incompatible, D1With D2It is compatible, CP1With CP2It is compatible, AP1With AP2It is incompatible, then it is obtained according to each feature weight sequence arrangement
Binary number is (10110)2, then R1And R2Structure compatible degree are as follows:
The similarity calculating method of dependence pair includes: dependence to < R1, R2> in element there are soil temperature and humidities
Data are compatible, pass through calculating < R1, R2> corresponding core soil data of the Temperature and Humidity module dominates the soil of soil temperature and humidity data with adjusting
Earth data of the Temperature and Humidity module similarity measures the soil temperature and humidity data similarity of dependence pair, using the calculating side based on Hownet
Method calculates soil temperature and humidity data similarity, and assigns different weight α and β, obtains R1And R2Soil temperature and humidity data it is similar
It spends as follows:
Ss(R1, R2)=α Sw(C1, C2)+βSw(A1, A2);
In formula, Sw(C1, C2) expression < R1, R2> in correspond to the similarity of core soil data of the Temperature and Humidity module, Sw(A1, A2) indicate
It is corresponding to dominate soil temperature and humidity data similarity, α > β and alpha+beta=1;
It is based onWith formula Ss(R1, R2)=α Sw(C1, C2)+βSw
(A1, A2), obtain the similarity calculating method of dependence pair: R1|R2=Sim (R1, R2)=Sc(R1, R2)gSs(R1, R2);
Big data analysis device sets value parameter with the soil temperature and humidity prestored to the data that soil temperature-moisture sensor detects
It in comparing and analyzing, is compared and analyzed using particle swarm algorithm, in particle swarm algorithm, the optimizing phase uses particle swarm algorithm
The feature weight for optimizing characteristic weighing KNN algorithm, specifically includes: initializing population, the position of each particle using random device
Setting with the dimension of speed is n, the position corresponding data of each particle concentrate a record feature weight vector w=(w1,
W2 ..., wn): wherein haveAdaptive value is calculated, and then finds out locally optimal solution and globally optimal solution: being adapted to calculating
When value, position, that is, feature weight of particle is applied in characteristic weighing KNN algorithm, former training sample concentration preceding 70% is regarded
New training sample, rear 30% regards new forecast sample collection, classifies to this forecast sample collection, calculates the accurate of classification
Degree, the accuracy the high more meets adaptive value;Forecast sample integrates the initial soil data of the Temperature and Humidity module label of every record as li=
(li1, li2 ..., lin), it is sorted after prediction soil temperature and humidity data be lj=(lj1, lj2 ..., ljn), li and lj with
Coincidence number is sum, then accuracy rate Accruay=sum/n;
Sorting phase: the feature weight that the optimizing phase is obtained be applied in characteristic weighing KNN algorithm to test sample X into
Row is classified, and the soil temperature and humidity data of all samples in final output test set complete classification.
Dependence to set similarity calculating method include:
There are dependences to set A=(a1, a2…an) and dependence to set B=(b1, b2…bm), it does not lose general
Property, the number of dependence pair is less than or equal to B, i.e. n≤m in A;For each ai∈ A, 1≤i≤n, find several bj∈
B, 1≤j≤m are corresponding to it, different aiCorresponding different bj, then the corresponding relationship sum of set A and set B is as follows:
There is determining corresponding relationship in set A and BIn ΩkIn, for given aiThere is one
bjIt is matching, it is denoted as bj=Ωk(ai);Then define ΩkSimilarity are as follows:
Two dependences take Ω to the similarity of set A and BkIn maximum value, it may be assumed that
In formula,
The particle swarm algorithm includes:
Particle Swarm is initialized, including the position xi=(x for initializing entire populationi1, xi2... xid) T and speed vi
=(vi1, vi2..., vid)TAnd local optimum and total optimization, wherein id indicates d-th of particle in the i-th generation;
The particle swarm algorithm further comprises:
Each particle is calculated in the fitness value fitness of current positionid=f (xid).Then according to fitness value
Size initializes locally optimal solution pbesti=fitnessiWith total optimization solution gbest=min (fintess1,
fitness2..., fitnessN), i=1,2 ..., N;
The particle swarm algorithm further comprises:
In each iterative process, each particle updates the position and speed of oneself according to following criterion:
vid(t+1)=wvid(t)+c1r1(pld-xid(t))+c2r2(pgd-xid(t))
xid(t+1)=xid(t)+vid(t+1)
Wherein vidFor the speed of particle, xidFor the position of particle, w is inertia weight, and c1 and c2 are acceleration factor, r1With
r2It is random number, PldThe P for globally optimal solutiongdFor locally optimal solution;
Update locally optimal solution pbestiWith total optimization solution gbest;
If total optimization solution gbest reaches the threshold value of setting or has reached the maximum the number of iterations, algorithm is terminated;
Characteristic weighing KNN algorithm specifically includes:
M training sample is inputted, and sets k value size;
First randomly choose k initial closest nodes of A [1]~A [k] sample in training set as sample X to be predicted;
Calculate the weighting Euclidean distance wd (X, A [i]), i of sample X to be predicted and each initial k closest node
=1,2 ... .., k), calculate range formula are as follows:
Wherein n expression sample A [i] attribute number, i.e. A [i]=(3 ... A [i] of A [i] 1, A [i] 2, A [i] is n);
The distance wd asked (X, A [i]) is sorted in ascending order, the maximum distance maxD=of distance wd (X, A [i]) is acquired
Max d (X, A [i]) | and i=1,2 ... .., k };
It successively calculates in training set and is left record at a distance from sample to be tested X, and is farthest with being acquired in the step SB4
Distance maxD is compared, if smaller than maximum distance maxD, maximum distance maxD is updated to the record at a distance from sample to be tested X
Value, then by ascending order adjust the distance wd (X, A [i]) sequence;
The frequency of occurrence of the label of every record in present range wd (X, A [i]) sequence is calculated, and according to occurrence out
Several height sequences;
The preceding L soil temperature and humidity data that sequence is obtained are as the soil temperature and humidity data of sample X.
In the above-described embodiments, can come wholly or partly by software, hardware, firmware or any combination thereof real
It is existing.When using entirely or partly realizing in the form of a computer program product, the computer program product include one or
Multiple computer instructions.When loading on computers or executing the computer program instructions, entirely or partly generate according to
Process described in the embodiment of the present invention or function.The computer can be general purpose computer, special purpose computer, computer network
Network or other programmable devices.The computer instruction may be stored in a computer readable storage medium, or from one
Computer readable storage medium is transmitted to another computer readable storage medium, for example, the computer instruction can be from one
A web-site, computer, server or data center pass through wired (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)
Or wireless (such as infrared, wireless, microwave etc.) mode is carried out to another web-site, computer, server or data center
Transmission).The computer-readable storage medium can be any usable medium or include one that computer can access
The data storage devices such as a or multiple usable mediums integrated server, data center.The usable medium can be magnetic Jie
Matter, (for example, floppy disk, hard disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid state hard disk Solid
State Disk (SSD)) etc..
The above is only the preferred embodiments of the present invention, and is not intended to limit the present invention in any form,
Any simple modification made to the above embodiment according to the technical essence of the invention, equivalent variations and modification, belong to
In the range of technical solution of the present invention.
Claims (10)
1. a kind of reading intelligent agriculture environmental monitoring system and monitoring method based on big data, which is characterized in that described based on big number
According to reading intelligent agriculture environment control method include:
It is strong to soil temperature-moisture sensor, green house temperature-humidity sensor, greenhouse detector, illumination by big data analysis device
The data of degree inductor detection and the soil temperature and humidity, green house temperature-humidity, greenhouse oxygen gas concentration, intensity of illumination setting prestored
Value parameter compares and analyzes, and the control instruction after analysis is transferred to screen-roller, exhaust fan, water supply pump, heating installation, medicine
Object adjustment case is turned on or off accordingly;
Soil temperature-moisture sensor in soil temperature and humidity Data Detection,
Big data analysis device carries out the data that soil temperature-moisture sensor detects with the soil temperature and humidity setting value parameter prestored
In comparative analysis, it is based on dependence pair, the dependence of multiple soil temperature and humidities continuously detected matches set,
Selection makes relationship to the maximum corresponding relationship of the sum of similarity, on the basis of corresponding relationship, find out each relationship to similarity it
The average value of sum is compared and analyzed with the soil temperature and humidity setting value parameter of setting;The structure compatible degree of dependence pair
Acquisition methods include: dependence to < R1, R2>, R is compared respectively1(C1, A1, D1, CP1, AP1) and R2(C2, A2, D2, CP2, AP2)
In five characteristic quantities, it is compatible to take 1, it is incompatible to take 0;Then, this five 0 or 1 are arranged from a high position to low level by weight order, is obtained
To a binary number (bbbbb)2, the value range of the value is 0-31, wherein 0 corresponding R1And R2Complete unequal situation, 31
Corresponding R1And R2Essentially equal situation;On the basis of the binary number, R is defined1And R2Structure compatible degree it is as follows:
Assuming that in two five-tuple R1(C1, A1, D1, CP1, AP1) and R2(C2, A2, D2, CP2, AP2) in, C1With C2It is compatible, A1With A2
It is incompatible, D1With D2It is compatible, CP1With CP2It is compatible, AP1With AP2It is incompatible, then according to the sequence arrangement of each feature weight obtain two into
Number processed is (10110)2, then R1And R2Structure compatible degree are as follows:
The similarity calculating method of dependence pair includes: dependence to < R1, R2> in element there are soil temperature and humidity data
It is compatible, pass through calculating < R1, R2> corresponding core soil data of the Temperature and Humidity module dominates the soil temperature of soil temperature and humidity data with adjusting
Humidity data similarity measures the soil temperature and humidity data similarity of dependence pair, using based on the calculation method of Hownet
Soil temperature and humidity data similarity is calculated, and assigns different weight α and β, obtains R1And R2Soil temperature and humidity data similarity such as
Under:
Ss(R1, R2)=α Sw(C1, C2)+βSw(A1, A2);
In formula, Sw(C1, C2) expression < R1, R2> in correspond to the similarity of core soil data of the Temperature and Humidity module, Sw(A1, A2) indicate to correspond to
Dominate soil temperature and humidity data similarity, α > β and alpha+beta=1;
It is based onWith formula Ss(R1, R2)=α Sw(C1, C2)+βSw(A1, A2),
Obtain the similarity calculating method of dependence pair: R1|R2=Sim (R1, R2)=Sc(R1, R2)gSs(R1, R2);
Big data analysis device carries out the data that soil temperature-moisture sensor detects with the soil temperature and humidity setting value parameter prestored
It in comparative analysis, is compared and analyzed using particle swarm algorithm, in particle swarm algorithm, the optimizing phase is optimized using particle swarm algorithm
The feature weight of characteristic weighing KNN algorithm, specifically includes: using random device initialize population, the position of each particle and
The dimension of speed is n, the position corresponding data of each particle concentrate a record feature weight vector w=(w1, w2 ...,
Wn): wherein havingAdaptive value is calculated, and then finds out locally optimal solution and globally optimal solution: when calculating adaptive value,
Position, that is, feature weight of particle is applied in characteristic weighing KNN algorithm, concentrates preceding 70% to regard newly former training sample
Training sample, rear 30% regards new forecast sample collection, classifies to this forecast sample collection, calculates the accuracy of classification, quasi-
The exactness the high more meets adaptive value;Forecast sample integrate every record initial soil data of the Temperature and Humidity module label as li=(li1,
Li2 ..., lin), it is sorted after prediction soil temperature and humidity data be lj=(lj1, lj2 ..., ljn), li and lj be overlapped it is a
Number is sum, then accuracy rate Accruay=sum/n;
Sorting phase: the feature weight that the optimizing phase is obtained is applied in characteristic weighing KNN algorithm to be divided to test sample X
Class, the soil temperature and humidity data of all samples in final output test set, completes classification.
2. the reading intelligent agriculture environment control method based on big data as described in claim 1, which is characterized in that
Dependence to set similarity calculating method include:
There are dependences to set A=(a1, a2…an) and dependence to set B=(b1, b2…bm), without loss of generality, A
The number of middle dependence pair is less than or equal to B, i.e. n≤m;For each ai∈ A, 1≤i≤n, find several bj∈ B, 1≤
J≤m is corresponding to it, different aiCorresponding different bj, then the corresponding relationship sum of set A and set B is as follows:
There is determining corresponding relationship in set A and BIn ΩkIn, for given aiThere is a bjWith
Matching, be denoted as bj=Ωk(ai);Then define ΩkSimilarity are as follows:
Two dependences take Ω to the similarity of set A and BkIn maximum value, it may be assumed that
In formula,
3. the reading intelligent agriculture environment control method based on big data as described in claim 1, which is characterized in that
The particle swarm algorithm includes:
Particle Swarm is initialized, including the position xi=(x for initializing entire populationi1, xi2... xid) T and speed vi=
(vi1, vi2..., vid)TAnd local optimum and total optimization, wherein id indicates d-th of particle in the i-th generation.
4. the reading intelligent agriculture environment control method based on big data as described in claim 1, which is characterized in that
The particle swarm algorithm further comprises:
Each particle is calculated in the fitness value fitness of current positionid=f (xid).Then according to the size of fitness value,
Initialize locally optimal solution pbesti=fitnessiWith total optimization solution gbest=min (fintess1, fitness2...,
fitnessN), i=1,2 ..., N.
5. the reading intelligent agriculture environment control method based on big data as described in claim 1, which is characterized in that
The particle swarm algorithm further comprises:
In each iterative process, each particle updates the position and speed of oneself according to following criterion:
vid(t+1)=wvid(t)+c1r1(pld-xid(t))+c2r2(pgd-xid(t))
xid(t+1)=xid(t)+vid(t+1)
Wherein vidFor the speed of particle, xidFor the position of particle, w is inertia weight, and c1 and c2 are acceleration factor, r1And r2It is
Random number, PldThe P for globally optimal solutiongdFor locally optimal solution;
Update locally optimal solution pbestiWith total optimization solution gbest;
If total optimization solution gbest reaches the threshold value of setting or has reached the maximum the number of iterations, algorithm is terminated;
Characteristic weighing KNN algorithm specifically includes:
M training sample is inputted, and sets k value size;
First randomly choose k initial closest nodes of A [1]~A [k] sample in training set as sample X to be predicted;
Weighting Euclidean distance wd (X, A [i]), the i=1 of sample X to be predicted and each initial k closest node are calculated,
2 ... .., k), calculate range formula are as follows:
Wherein n expression sample A [i] attribute number, i.e. A [i]=(3 ... A [i] of A [i] 1, A [i] 2, A [i] is n);
The distance wd asked (X, A [i]) is sorted in ascending order, the maximum distance maxD=max of distance wd (X, A [i]) is acquired
D (X, A [i]) | and i=1,2 ... .., k };
Successively calculate in training set and be left record at a distance from sample to be tested X, and with the maximum distance that is acquired in the step SB4
MaxD is compared, if smaller than maximum distance maxD, maximum distance maxD is updated to the distance value of the record Yu sample to be tested X, then
By ascending order adjust the distance wd (X, A [i]) sequence;
The frequency of occurrence of the label of every record in present range wd (X, A [i]) sequence is calculated, and according to frequency of occurrence
Height sorts;
The preceding L soil temperature and humidity data that sequence is obtained are as the soil temperature and humidity data of sample X.
6. a kind of calculating for realizing the reading intelligent agriculture environment control method described in Claims 1 to 5 any one based on big data
Machine program.
7. a kind of information for realizing the reading intelligent agriculture environment control method described in Claims 1 to 5 any one based on big data
Data processing terminal.
8. a kind of computer readable storage medium, including instruction, when run on a computer, so that computer is executed as weighed
Benefit requires the reading intelligent agriculture environment control method described in 1-5 any one based on big data.
9. a kind of intelligence based on big data for realizing the reading intelligent agriculture environment control method described in claim 1 based on big data
Agricultural environment monitoring system, which is characterized in that the reading intelligent agriculture environmental monitoring system based on big data is provided with greenhouse;
The upper surface of greenhouse is equipped with sun-shading curtain, and sun-shading curtain is connected by spool with the screen-roller for being mounted on upper surface on the left of greenhouse
It connects;
Exhaust fan has been bolted on the left of the greenhouse;
The outside surrounding of the greenhouse, which is stood, support column, is equipped with solar panel by bolt on support column;
The right side of the greenhouse is shelved with control cabinet, header tank and medicaments dispensing case respectively;
The control cabinet is electrically connected to solar panel;
The header tank is connected by the water service pipe being socketed on water supply pump and the support frame of greenhouse;
It is equipped with medicine spraying tube along support frame on the support frame of the greenhouse, multiple rotary nozzles are fastened on medicine spraying tube;
On the support frame of the greenhouse by bolt be respectively fixed with soil temperature-moisture sensor, green house temperature-humidity sensor, with
And greenhouse detector;
The inner wall of the greenhouse has been bolted intensity of illumination inductor.
10. the reading intelligent agriculture environmental monitoring system based on big data as claimed in claim 9, which is characterized in that the water flowing
The fixed heating installation on the support frame of bolt is provided at the top of pipe;
The lower section of the water service pipe was equipped with a atomizer;
Big data analysis device is provided in the control cabinet, it is warm and humid with soil temperature-moisture sensor, greenhouse respectively by signal wire
Spend sensor, greenhouse detector, intensity of illumination inductor, screen-roller, exhaust fan, water supply pump, heating installation, drug tune
Agent case is connected;
Device is connected with printing device to the control cabinet by wireless communication, and the bottom hung of printing device has collecting box;
The inside of the medicaments dispensing case is divided into several subregions by partition;More are embedded on the side wall of the medicaments dispensing case
Pencil is connected to the bottom of medicaments dispensing case;The bottom end of the pencil is connected with closure patch, is electrically connected to medicaments dispensing bottom
The timer in portion;The inside of the medicaments dispensing case is equipped with blender by bolt;
The front surface of the pencil is carved with graduation mark, and is pasted with mark label.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810810557.XA CN109062290A (en) | 2018-07-13 | 2018-07-13 | A kind of reading intelligent agriculture environmental monitoring system and monitoring method based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810810557.XA CN109062290A (en) | 2018-07-13 | 2018-07-13 | A kind of reading intelligent agriculture environmental monitoring system and monitoring method based on big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109062290A true CN109062290A (en) | 2018-12-21 |
Family
ID=64834966
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810810557.XA Pending CN109062290A (en) | 2018-07-13 | 2018-07-13 | A kind of reading intelligent agriculture environmental monitoring system and monitoring method based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109062290A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110934015A (en) * | 2019-11-05 | 2020-03-31 | 西安德贝盈农业科技有限公司 | Simple shed for vegetable planting |
CN112753540A (en) * | 2020-12-30 | 2021-05-07 | 四川省阆中蚕种场 | Irrigation system for mulberry field |
CN113312735A (en) * | 2021-05-19 | 2021-08-27 | 太原理工大学 | DMA partition method for urban water supply pipe network |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20130032618A (en) * | 2011-09-23 | 2013-04-02 | 유천승 | The apparatus and method of vinyl house remote control with gtg electric heater and snow removing work |
CN104852989A (en) * | 2015-05-29 | 2015-08-19 | 北京东方海岸物联网科技有限责任公司 | A smart agriculture monitoring system based on Web of Things |
CN104991974A (en) * | 2015-07-31 | 2015-10-21 | 中国地质大学(武汉) | Particle swarm algorithm-based multi-label classification method |
CN105607681A (en) * | 2016-02-23 | 2016-05-25 | 湖南人文科技学院 | Agricultural informatization production wireless monitoring system |
CN105975458A (en) * | 2016-05-03 | 2016-09-28 | 安阳师范学院 | Fine-granularity dependence relationship-based method for calculating Chinese long sentence similarity |
CN106125803A (en) * | 2016-08-16 | 2016-11-16 | 江西科技师范大学 | Agricultural greenhouse monitoring system |
CN206805334U (en) * | 2017-05-22 | 2017-12-26 | 青岛理工大学 | Intelligent greenhouse photovoltaic comprehensive application system |
CN207185742U (en) * | 2017-09-26 | 2018-04-06 | 中国热带农业科学院湛江实验站 | A kind of sprayer for being easy to ratio quota |
-
2018
- 2018-07-13 CN CN201810810557.XA patent/CN109062290A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20130032618A (en) * | 2011-09-23 | 2013-04-02 | 유천승 | The apparatus and method of vinyl house remote control with gtg electric heater and snow removing work |
CN104852989A (en) * | 2015-05-29 | 2015-08-19 | 北京东方海岸物联网科技有限责任公司 | A smart agriculture monitoring system based on Web of Things |
CN104991974A (en) * | 2015-07-31 | 2015-10-21 | 中国地质大学(武汉) | Particle swarm algorithm-based multi-label classification method |
CN105607681A (en) * | 2016-02-23 | 2016-05-25 | 湖南人文科技学院 | Agricultural informatization production wireless monitoring system |
CN105975458A (en) * | 2016-05-03 | 2016-09-28 | 安阳师范学院 | Fine-granularity dependence relationship-based method for calculating Chinese long sentence similarity |
CN106125803A (en) * | 2016-08-16 | 2016-11-16 | 江西科技师范大学 | Agricultural greenhouse monitoring system |
CN206805334U (en) * | 2017-05-22 | 2017-12-26 | 青岛理工大学 | Intelligent greenhouse photovoltaic comprehensive application system |
CN207185742U (en) * | 2017-09-26 | 2018-04-06 | 中国热带农业科学院湛江实验站 | A kind of sprayer for being easy to ratio quota |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110934015A (en) * | 2019-11-05 | 2020-03-31 | 西安德贝盈农业科技有限公司 | Simple shed for vegetable planting |
CN112753540A (en) * | 2020-12-30 | 2021-05-07 | 四川省阆中蚕种场 | Irrigation system for mulberry field |
CN113312735A (en) * | 2021-05-19 | 2021-08-27 | 太原理工大学 | DMA partition method for urban water supply pipe network |
CN113312735B (en) * | 2021-05-19 | 2022-06-03 | 太原理工大学 | DMA partition method for urban water supply pipe network |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN209517198U (en) | A kind of wisdom agricultural standardization management system | |
CN109062290A (en) | A kind of reading intelligent agriculture environmental monitoring system and monitoring method based on big data | |
CN107329511A (en) | Based on the vegetable aquaculture luminous environment high efficiency regulatory method and system between suitable root warm area | |
CN204576316U (en) | A kind of greenhouse intelligent control system | |
Zhou et al. | Applications of Internet of Things in the facility agriculture | |
CN110109193A (en) | A kind of eggplant greenhouse temperature intellectualized detection device based on DRNN neural network | |
CN105353739A (en) | Smart agricultural management system | |
CN110741914A (en) | Rice field automatic water-saving irrigation system and method based on recurrent neural network | |
CN110119169A (en) | A kind of tomato greenhouse temperature intelligent early warning system based on minimum vector machine | |
CN110119767A (en) | A kind of cucumber green house temperature intelligent detection device based on LVQ neural network | |
CN110533547A (en) | Fruits and vegetables water-fertilizer conditioning method and device and computer readable storage medium | |
CN114868505B (en) | Intelligent liquid manure control cabinet | |
Anand et al. | Applications of Internet of Things (IoT) in agriculture: The need and implementation | |
CN112526909A (en) | Wisdom agricultural equipment system based on thing networking | |
KR20200044604A (en) | Smart Farm Control System Using Smart Farm Control History | |
CN215736244U (en) | Wisdom irrigation system suitable for oranges and tangerines are planted | |
Zhangzhong et al. | Development of an evapotranspiration estimation method for lettuce via mobile phones using machine vision: Proof of concept | |
CN116225114B (en) | Intelligent environmental control system and method for crop growth controllable agricultural greenhouse based on big data | |
CN108628266A (en) | Intelligent cultivation greenhouse based on big data analysis monitors system | |
CN109041951A (en) | A kind of agricultural breeding is mechanical and control method | |
CN110825118A (en) | Multi-unmanned aerial vehicle cooperative farmland spraying method based on deep learning algorithm | |
CN205755995U (en) | A kind of intelligence greenhouse system | |
Muneeswaran et al. | Instinctual Synced Ventilation for Mushroom Growing using IoT | |
Gao et al. | Application of Artificial Intelligence System Design Based on Genetic Algorithm In Horticultural Cultivation | |
Tiple et al. | IoT based Weather Monitoring System Using OSSA & MA Techniques |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181221 |
|
WD01 | Invention patent application deemed withdrawn after publication |