CN103605385A - CO2 gas fertilizer fine regulation and control method and device used for solar greenhouse - Google Patents
CO2 gas fertilizer fine regulation and control method and device used for solar greenhouse Download PDFInfo
- Publication number
- CN103605385A CN103605385A CN201310462102.0A CN201310462102A CN103605385A CN 103605385 A CN103605385 A CN 103605385A CN 201310462102 A CN201310462102 A CN 201310462102A CN 103605385 A CN103605385 A CN 103605385A
- Authority
- CN
- China
- Prior art keywords
- photosynthetic rate
- gas
- data
- fertile
- concentration
- 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
Images
Landscapes
- Cultivation Of Plants (AREA)
- Greenhouses (AREA)
Abstract
A CO2 gas fertilizer fine regulation and control method and a device which are used for a solar greenhouse are provided. The device monitors environment information and crop growth information of the greenhouse in real time; and through a photosynthetic rate prediction model based on a BP neural network, the optimal CO2 gas fertilizer quantity demanded is determined and the value of the photosynthetic rate is predicted, and therefore fine regulation and control of CO2 concentration is achieved. According to the invention, the fact that a CO2 gas fertilizer in the solar greenhouse needs to be finely supplied in dependence on crop growth demands is achieved, the quality of greenhouse crops is improved, the yield of the greenhouse crops is risen, and environmental pollution caused by excessive application of the CO2 gas fertilizer is avoided.
Description
Technical field
The present invention relates to a kind of CO for heliogreenhouse
2the fertile finely regulating method and apparatus of gas.
Background technology
Heliogreenhouse is as the Typical Representative of industrialized agriculture, is to have high investment and high production, knowledge and technology height are integrated, the obvious special mode of agriculture of batch production production feature.The various environmental informations of heliogreenhouse have certain controllability, make full use of this advantage, can obtain higher crop quality and higher investment repayment.CO
2it is a kind of important source material of plant growth.During photosynthesis, plant utilization CO
2remove to produce carbohydrates with illumination, for plant growth, therefore an abundant air ambient will be conducive to plant growth.On the other hand, CO
2within should being controlled at rational scope, excessive CO
2not only uneconomical, also can produce negative interaction to environment.Due to CO
2vital role in crop photosynthesis, by CO in greenhouse
2concentration regulates and controls to optimum not only can improve the growth efficiency of chamber crop, and can reduce the impact on global warming.Therefore, to heliogreenhouse CO
2the finely regulating of concentration is significant.
The develop rapidly of Internet of Things provides advantage for the development of greenhouse industry.Internet of Things is comprised of the remote data management center that is distributed in a large number sensing node, the gateway node of monitored area and has an interpersonal interactive function, relates to the multi-door subjects such as wireless communication technology, sensor technology and computer technology.ZigBee technology relies on the advantages such as its low-power consumption, high reliability, in Internet of Things, is widely used.Utilize Internet of Things to provide strong means and instrument for automatic acquisition and the regulation and control of heliogreenhouse environmental information.The applied research of Internet of Things in greenhouse is at present more, but mainly concentrates on the monitoring of greenhouse environment information, less for the fertile auto-control aspect research of plant growth information monitoring aspect, environmental control of greenhouse especially CO2 gas.
Neural network is a kind of mathematical model or computation model of 26S Proteasome Structure and Function of mimic biology neural network.Modern neural network is a kind of Nonlinear Statistical data modeling tool, is commonly used to relation complicated between input and output to carry out modeling, or is used for the pattern of heuristic data.Neural network is similar to a black box, does not need to know internal mechanism, can set up model according to data, finds out the level and smooth and continuous nonlinear relationship between input attributes and measurable attribute.
To heliogreenhouse CO
2the finely regulating of concentration depends on an accurate meticulous CO
2demand model, and CO
2the foundation of demand model and crop photosynthesis capability evaluation are closely bound up.In the research of photosynthetic rate prediction, on the one hand, mostly adopt classic method manually to obtain environmental information parameter at present, the sampling period is longer, can not reflect preferably the situation of change of environmental parameter in greenhouse; On the other hand, the environment of considering during modeling is relative with Factors affecting growth less, and the output of model is pre-measuring plants list leaf photosynthesis speed accurately, thereby can not determine best CO
2the fertile demand of gas.Therefore, the present invention takes full advantage of the acquisition of information advantage of Internet of Things, and heliogreenhouse environment and growth information have been carried out to Real-Time Monitoring, and has set up according to many data photosynthetic rate forecast model and the CO of the different growth phases of Different Crop
2concentration demand model, has realized heliogreenhouse crop CO
2the finely regulating of gas fertilizer.
Summary of the invention
The object of the embodiment of the present invention is to provide a kind of CO for heliogreenhouse
2the fertile finely regulating method and apparatus of gas, utilizes the method can make full use of environmental information and plant growth information that Internet of Things easily obtains, realizes heliogreenhouse CO
2the finely regulating of gas fertilizer, solves the low problem of the fertile utilization factor of heliogreenhouse gas, reaches the object of high-yield and high-efficiency.
For achieving the above object, embodiments of the invention provide a kind of CO2 gas for heliogreenhouse fertile finely regulating method, and the device of realizing said method.
The invention discloses a kind of CO for heliogreenhouse
2the fertile finely regulating method of gas, Real-Time Monitoring greenhouse environment information and plant growth information, determine optimum CO
2the fertile demand of gas is also predicted photosynthetic rate value, thereby realizes CO
2the finely regulating of concentration, the photosynthetic rate value of the fertile demand of described optimum gas and prediction is determined by the photosynthetic rate forecast model based on BP neural network.
Described photosynthetic rate forecast model is set up by following steps:
The first step: the obtaining of experimental data: monitor greenhouse environment information and part plant growth information by Internet of Things; By photosynthetic rate instrument, measure crop at the different CO of different light
2single leaf Net Photosynthetic Rate under concentration; By manual measurement method, regularly obtain part plant growth information; Wherein, greenhouse environment information and plant growth information are as the input parameter of model, and single leaf Net Photosynthetic Rate is as the output parameter of model;
Second step: mode input parameter is optimized, reaches the object of eliminating redundant data dimensionality reduction;
The 3rd step: the mode input supplemental characteristic of optimization is divided into neural network model training group and test group at random, neural network parameter is set, set is trained according to substitution network, until reach network training end condition;
The 4th step: the checking of model, the neural network model of having set up with the substitution of prediction group data, the relatively error of photosynthetic rate predicted value and measured value, and computational grid Performance Evaluation index;
The 5th step: if network performance evaluation index reaches requirement, model has been set up, otherwise, network parameter adjusted, repetition training, verification step.
And, the optimization of mode input parameter is realized by following steps:
The first step: use K-means Method to carry out clustering to the inputoutput data of model, obtain the data of discretize, and will to export data be that photosynthetic rate value represents with cluster centre;
Second step: 2 groups or above identical object may appear in the data after discrete, are considered as redundancy object, are deleted, and obtain the discrete data of preliminary abbreviation, wherein, a group observations is called an object;
The 3rd step: calculating each input parameter is the influence value of photosynthetic rate to output parameter, establishes total n input parameter, x
ibe i input parameter, remove successively x
i, remaining n-1 input parameter, may occur 2 or above input parameter is identical and object that output parameter is different calculates the photosynthetic rate difference d that these objects are corresponding
ijif, input parameter identical to as if 2, by large photosynthetic rate value, deduct little photosynthetic rate value, if to as if more than 2, by maximum photosynthesis rate value, deduct minimum photosynthetic rate value, will remove x
irear required difference is sued for peace, as x
iinfluence value to output parameter
The 4th step: the weight of calculating each input parameter
remove the parameter that weight is very little, the mode input parameter being optimized.
In order to improve the adaptability of photosynthetic rate forecast model, set up respectively Different Crop at the photosynthetic rate forecast model of its different growth phases.
In the data acquisition phase of photosynthetic rate forecast model, in order to expand data area, can adopt artificial environment to change intensity of illumination and CO
2concentration, measures respectively different CO under certain intensity of illumination
2the corresponding crop photosynthesis speed of concentration.
Photosynthetic rate forecast model can be determined the CO of Different Crop under different growth phases, varying environment
2the actual demand amount of gas fertilizer, and then realize CO
2the finely regulating of gas fertilizer.
Realize CO
2the step of concentration finely regulating be:
The first step: user selects crop varieties and plant growth stage, as the selection foundation of photosynthetic rate forecast model;
Second step: by the real time data of Internet of Things monitoring and the artificial measurement data of part, substitution photosynthetic rate forecast model, prediction photosynthetic rate value is also calculated optimum CO
2concentration, by the current C O with monitoring
2concentration value compares, and makes controlling and carries out decision-making, opens or closes CO
2the fertile device switch of gas.
The invention also discloses a kind of CO for heliogreenhouse
2the fertile finely regulating device of gas, comprises for realizing environmental information and growth information and monitors and control CO
2the Internet of Things monitor node of the fertile device of gas, for realizing CO
2the remote data management center of concentration finely regulating, and for connecting remote data management center and Internet of Things monitor node and realizing the gateway node of data retransmission.Described remote data management center comprises wireless sensor network parameter configuration module, data reception module, data memory module, data query display module and photosynthetic rate prediction and CO
2concentration finely regulating module.Between described gateway node and Internet of Things monitor node, adopt ZigBee wireless communication technique to carry out communication, adopt GPRS long-distance radio communication technology to carry out communication with remote data management center.
In addition, Internet of Things monitor node connects greenhouse environment information sensor, plant growth information sensor and control module, wherein greenhouse environment information Sensor monitoring air themperature, air humidity, intensity of illumination, CO
2concentration, cultivation matrix conductivity and cultivation matrix pH value; Plant growth information sensor is the NDVI sensor of reaction crop chlorophyll level; Control module is for controlling CO
2the solenoid valve of feeder.
Gateway node can embed GPRS module to realize telecommunication.
Accompanying drawing explanation
Fig. 1 is according to the schematic diagram of setting up of photosynthetic rate forecast model of the present invention;
Fig. 2 is according to CO of the present invention
2the regulation process schematic diagram of concentration;
Fig. 3 is according to CO of the present invention
2the structural representation of the fertile finely regulating device of gas;
Fig. 4 is according to monitor node structural representation of the present invention;
Fig. 5 is according to gateway node structural representation of the present invention;
Fig. 6 is according to control data corporation structural representation of the present invention.
Embodiment
Below by drawings and Examples, the technical scheme of the embodiment of the present invention is described in further detail.
The invention discloses a kind of CO for heliogreenhouse
2the fertile finely regulating method of gas is mainly to execute as required CO for heliogreenhouse crop
2, to improve crop yield and quality, and improve CO
2the fertile utilization factor of gas.
Fig. 1 discloses definite optimum CO
2the fertile demand of gas is also predicted the foundation of the photosynthetic rate forecast model of photosynthetic rate value.
Wherein, the process of establishing of photosynthetic rate forecast model comprises the following steps:
S11: the obtaining of experimental data: monitor greenhouse environment information (air themperature, air humidity, intensity of illumination, CO2 concentration, cultivation matrix conductivity and pH value) and plant growth information (the NDVI value of reaction chlorophyll level) by Internet of Things; By photosynthetic rate instrument, measure the single leaf Net Photosynthetic Rate of tomato under the different CO2 concentration of different light; By manual measurement method, regularly obtain tomato growth information (plant height, stem are thick, the number of blade, leaf area); Wherein, greenhouse environment information and plant growth information are as the input parameter of model, and single leaf Net Photosynthetic Rate is as the output parameter of model.
S12: mode input parameter is optimized, reaches the object of eliminating redundant data dimensionality reduction, comprise deletion redundant data, and input parameter is carried out to weight calculation, remove the parameter that weight is very little, the mode input parameter being optimized.
S13: the mode input supplemental characteristic of optimization is divided into neural network model training group and test group at random.Neural network parameter is set, comprises the network number of plies, each node layer number, transition function and training method selection etc.Set is trained according to substitution network, until reach network training end condition.
S14: the checking of model, the neural network model of having set up with the substitution of prediction group data, the relatively error of photosynthetic rate predicted value and measured value, and computational grid Performance Evaluation index (related coefficient, average relative error, mean absolute error and root-mean-square error).
S15: if network performance evaluation index reaches requirement, model has been set up, otherwise, network parameter adjusted, repetition training, checking procedure.
Preferably, the S12 step that photosynthetic rate forecast model is set up, concrete implementation step comprises:
S12-1: use K-means Method to carry out clustering to the inputoutput data of model, obtain the data of discretize.And will to export data be that photosynthetic rate value represents with cluster centre;
S12-2: 2 groups or above identical object (group observations is called an object) may appear in the data after discrete, are considered as redundancy object, are deleted, and obtain the discrete data of preliminary abbreviation;
S12-3: calculate the influence value of each input parameter to output parameter (being photosynthetic rate).If total n input parameter, x
ibe i input parameter, remove successively x
i, remaining n-1 input parameter, may occur 2 or above input parameter is identical and object that output parameter is different calculates the photosynthetic rate difference d that these objects are corresponding
ijif (input parameter identical to as if 2, by large photosynthetic rate value, deduct little photosynthetic rate value, if to as if more than 2, by maximum photosynthesis rate value, deduct minimum photosynthetic rate value), will remove x
irear required difference is sued for peace, as x
iinfluence value to output parameter
remove after an input parameter, there is the different object of the identical output parameter of input parameter, each object contains a photosynthetic rate value, if remaining input parameter is identical, photosynthetic rate difference is considered as being caused by the input parameter removing, and thinks that the size of this difference has reflected the influence degree of input parameter to output parameter.
S12-4: the weight of calculating each input parameter
remove the parameter that weight is very little, the mode input parameter being optimized.
Fig. 2 discloses a kind of CO
2concentration finely regulating process, it comprises the following steps:
S21: user selects crop varieties and plant growth stage, as Model Selection foundation;
S22: by the real time data of Internet of Things monitoring, substitution photosynthetic rate forecast model, prediction photosynthetic rate value is also determined optimum CO
2concentration value, by the CO with current monitoring
2concentration value compares, and makes controlling and carries out decision-making, opens or closes CO
2the fertile device switch of gas.
Fig. 3 discloses CO
2the structural representation of the fertile finely regulating device of gas.Comprise remote data management center 31, gateway node 32, monitor node 33, sensor 34 and solenoid valve 35.Wherein, monitor node 33, sensor 34 and solenoid valve 35 can have a plurality of according to application demand.Sensor 34 comprises air temperature sensor, air humidity sensor, CO
2the NDVI sensor of sensor, intensity of illumination sensor, matrix conductivity sensor, matrix pH value sensor, measurement vegetation index.
Its implementation procedure is: by monitor node 33, control each sensor 34 and detect greenhouse environment information and plant growth information, through ZigBee-network, be sent to gateway node 32, through GPRS, be sent to remote data management center 31 again, through photosynthetic rate forecast model, analyze, provide optimum CO
2concentration demand, and according to current C O2 concentration value, sends control command, through GPRS and ZigBee-network, to monitor node 33, by controlling solenoid valve 35, carries out CO
2the switching manipulation of gas bottle device.
Fig. 4 is embodiment of the present invention monitor node structural representation, comprises NDVI sensor 48, the CO of microcontroller and wireless module 41, energy supply control module 42, relay control module 43, matrix pH value sensor 44, matrix conductivity sensor 45, intensity of illumination sensor 46, aerial temperature and humidity sensor 47, measurement vegetation index
2concentration sensor 49.
Microcontroller and wireless module adopt wireless microcontroller module 41, this module is embedded Zigbee protocol, and there is abundant Peripheral Interface.Wherein, CO
2sensor 49, is connected with microcontroller through UART interface; The NDVI sensor 48 of reflection crop chlorophyll level, is connected with microcontroller through TTL-RS232 level shifting circuit; Aerial temperature and humidity sensor 47, is connected with microcontroller through I2C digital interface; Optical sensor 46, is connected with microcontroller through ADC analog interface; Matrix conductivity sensor 45, is connected with microcontroller through ADC analog interface; Matrix pH value sensor 44, is connected with microcontroller through ADC analog interface; Relay control module 43, in order to control electromagnetic valve switch, through digital I O mouth be connected with microcontroller.Power supply processing module 42 provides power supply for each sensor and wireless microcontroller module 41.
Fig. 5 is embodiment of the present invention gateway node structural representation.Comprise microcontroller and wireless module 51, energy supply control module 52, relay control module 53.Microcontroller and wireless module adopt wireless microcontroller module 51, and wireless microcontroller module as the telegon of ZIgBee network, is responsible for starting ZigBee-network in gateway node.GPRS module 53 is connected with microcontroller 51 by UART interface.Power supply processing module 52 provides power supply for microcontroller 51 and GPRS module 53.
Fig. 6 is the control data corporation structural representation of the embodiment of the present invention, comprises Internet of Things parameter configuration module 61, data reception module 62, data memory module 63, data query display module 64 and CO2 concentration finely regulating module 65.Wherein, Internet of Things parameter configuration module 61, for being configured to system, comprising collection period and calibration sensor is set; Data reception module 62 is for receiving the GPRS data of gateway node; Data memory module 63 is for storing Monitoring Data; Data query display module 64 is inquired about greenhouse data for user; CO
2concentration finely regulating module 65, according to user's input information, as selected crop varieties and growth phase, selects photosynthetic rate prediction model to carry out photosynthetic rate prediction, calculates optimum CO2 concentration value, and in conjunction with current C O
2concentration value provides controls judgement.
Finally it should be noted that: above embodiment is only in order to the technical scheme of the embodiment of the present invention to be described but not be limited, although the embodiment of the present invention is had been described in detail with reference to preferred embodiment, those of ordinary skill in the art is to be understood that: it still can be modified or be equal to replacement the technical scheme of the embodiment of the present invention, and these modifications or be equal to replacement and also can not make amended technical scheme depart from the spirit and scope of embodiment of the present invention technical scheme.
Claims (10)
1. the CO for heliogreenhouse
2the fertile finely regulating method of gas, comprises Real-Time Monitoring greenhouse environment information and plant growth information, determines optimum CO
2the fertile demand of gas and prediction photosynthetic rate value, thus realize CO
2the finely regulating of concentration, is characterized in that: described optimum CO
2the photosynthetic rate value of the fertile demand of gas and prediction is determined by the photosynthetic rate forecast model based on BP neural network.
2. CO according to claim 1
2the fertile finely regulating method of gas, is characterized in that: described photosynthetic rate forecast model is set up by following steps:
The first step: the obtaining of experimental data: monitor greenhouse environment information and crop some growth information by Internet of Things; By photosynthetic rate instrument, measure crop at the different CO of different light
2single leaf Net Photosynthetic Rate under concentration; By manual measurement method, regularly obtain crop some growth information; Wherein, greenhouse environment information and plant growth information are as the input parameter of model, and single leaf Net Photosynthetic Rate is as the output parameter of model;
Second step: mode input parameter is optimized, reaches the object of eliminating redundant data dimensionality reduction;
The 3rd step: the mode input supplemental characteristic of optimization is divided into neural network model training group and test group at random, neural network parameter is set, set is trained according to substitution network, until reach network training end condition;
The 4th step: the checking of model, the neural network model of having set up with the substitution of prediction group data, the relatively error of photosynthetic rate predicted value and measured value, and computational grid Performance Evaluation index;
The 5th step: if network performance evaluation index reaches requirement, model has been set up, otherwise, network parameter adjusted, repetition training, verification step.
3. CO according to claim 2
2the fertile finely regulating method of gas, is characterized in that: the optimization to mode input parameter realizes by following steps:
The first step: use K-means Method to carry out clustering to the inputoutput data of model, obtain the data of discretize, and will to export data be that photosynthetic rate value represents with cluster centre;
Second step: 2 groups or above identical object may appear in the data after discrete, are considered as redundancy object, are deleted, and obtain the discrete data of preliminary abbreviation, wherein, a group observations is called an object;
The 3rd step: calculating each input parameter is the influence value of photosynthetic rate to output parameter, establishes total n input parameter, x
ibe i input parameter, remove successively x
i, remaining n-1 input parameter, may occur 2 or above input parameter is identical and object that output parameter is different calculates the photosynthetic rate difference d that these objects are corresponding
ijif, input parameter identical to as if 2, by large photosynthetic rate value, deduct little photosynthetic rate value, if to as if more than 2, by maximum photosynthesis rate value, deduct minimum photosynthetic rate value, will remove x
irear required difference is sued for peace, as x
iinfluence value to output parameter
The 4th step: the weight of calculating each input parameter
remove the parameter that weight is very little, the mode input parameter being optimized.
4. CO according to claim 2
2the fertile finely regulating method of gas, is characterized in that, sets up respectively Different Crop at the photosynthetic rate forecast model of its different growth phases.
5. CO according to claim 2
2the fertile finely regulating method of gas, is characterized in that, in the data acquisition phase of photosynthetic rate forecast model, in order to expand data area, can adopt artificial environment to change intensity of illumination and CO
2concentration, measures respectively different CO under certain intensity of illumination
2the corresponding crop photosynthesis speed of concentration.
6. CO according to claim 2
2the fertile finely regulating method of gas, is characterized in that, photosynthetic rate forecast model can be determined the CO of Different Crop under different growth phases, varying environment
2the actual demand amount of gas fertilizer, and then realize CO
2the finely regulating of gas fertilizer.
7. CO according to claim 1 and 2
2the fertile finely regulating method of gas, is characterized in that, realizes CO
2the step of concentration finely regulating be:
The first step: user selects crop varieties and plant growth stage, as the selection foundation of photosynthetic rate forecast model;
Second step: by the real time data of Internet of Things monitoring and the artificial measurement data of part, substitution photosynthetic rate forecast model, prediction photosynthetic rate value is also calculated optimum CO
2concentration, by the current C O with monitoring
2concentration value compares, and makes controlling and carries out decision-making, opens or closes CO
2the fertile device switch of gas.
8. the CO for heliogreenhouse
2the fertile finely regulating device of gas, comprises for realizing environmental information and some growth information monitoring and controlling CO
2the Internet of Things monitor node of the fertile device of gas, for realizing CO
2the remote data management center of concentration finely regulating, and for connecting remote data management center and Internet of Things monitor node and realizing the gateway node of data retransmission; Described remote data management center comprises wireless sensor network parameter configuration module, data reception module, data memory module, data query display module and photosynthetic rate prediction and CO
2concentration finely regulating module; It is characterized in that:
Between described gateway node and Internet of Things monitor node, adopt ZigBee wireless communication technique to carry out communication, gateway node and remote data management center adopt GPRS long-distance radio communication technology to carry out communication.
9. CO according to claim 8
2the fertile finely regulating device of gas, is characterized in that, Internet of Things monitor node connects greenhouse environment information sensor, part plant growth information sensor and control module, wherein greenhouse environment information Sensor monitoring air themperature, air humidity, intensity of illumination, CO
2concentration, cultivation matrix conductivity and cultivation matrix pH value; Plant growth information sensor is the NDVI sensor of reaction crop chlorophyll level; Control module is for controlling CO
2the solenoid valve of feeder.
10. CO according to claim 8
2the fertile finely regulating device of gas, is characterized in that, gateway node can embed GPRS module to realize telecommunication.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310462102.0A CN103605385B (en) | 2013-09-30 | 2013-09-30 | A kind of CO for heliogreenhouse 2the fertile finely regulating method of gas |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310462102.0A CN103605385B (en) | 2013-09-30 | 2013-09-30 | A kind of CO for heliogreenhouse 2the fertile finely regulating method of gas |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103605385A true CN103605385A (en) | 2014-02-26 |
| CN103605385B CN103605385B (en) | 2016-01-27 |
Family
ID=50123620
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310462102.0A Active CN103605385B (en) | 2013-09-30 | 2013-09-30 | A kind of CO for heliogreenhouse 2the fertile finely regulating method of gas |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103605385B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105446142A (en) * | 2015-12-25 | 2016-03-30 | 中国农业大学 | Greenhouse CO2 gas fertilizer increasing method, device and system |
| CN105557388A (en) * | 2015-12-14 | 2016-05-11 | 西北农林科技大学 | Wireless and intelligent carbon dioxide regulating and controlling method and system for facility crops |
| CN106200605A (en) * | 2016-09-18 | 2016-12-07 | 王燕红 | The release of gas intelligence, management, control system |
| CN107593188A (en) * | 2017-09-26 | 2018-01-19 | 上海应用技术大学 | A kind of greenhouse production greenery vegetables plant CO2Feed method for determination of amount |
| CN107678410A (en) * | 2017-09-30 | 2018-02-09 | 中国农业大学 | It is a kind of towards the intelligent control method of greenhouse, system and controller |
| CN108124013A (en) * | 2017-12-22 | 2018-06-05 | 扬州市职业大学 | A kind of Internet of Things comprehensive training platform |
| CN108848138A (en) * | 2018-05-30 | 2018-11-20 | 深圳大图科创技术开发有限公司 | A kind of good environmental monitoring system of monitoring effect |
| CN110823291A (en) * | 2019-11-27 | 2020-02-21 | 山东建筑大学 | Method and system for monitoring indoor temperature and humidity environment of building based on K-means clustering algorithm |
| CN112449956A (en) * | 2020-11-16 | 2021-03-09 | 中国科学院合肥物质科学研究院 | Micro-nano ozone green prevention and control device |
| CN115428636A (en) * | 2020-11-11 | 2022-12-06 | 河南省新乡市农业科学院 | Wheat foliar fertilizer application method and application thereof |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010046939A1 (en) * | 2008-10-25 | 2010-04-29 | Microlaben S.R.L. | Wireless system for greenhouse monitoring and control |
| CN102736596A (en) * | 2012-06-11 | 2012-10-17 | 南京农业大学 | Multi-scale greenhouse environment control system based on crop information fusion |
| CN202886979U (en) * | 2012-11-19 | 2013-04-17 | 吉林农业大学 | Agricultural production remote monitoring and intelligent decision making system based on Internet of Things |
| CN103076784A (en) * | 2012-12-30 | 2013-05-01 | 同济大学 | Greenhouse environmental monitoring system based on wireless sensor network and GPRS (general packet radio service) |
| CN103105246A (en) * | 2012-12-31 | 2013-05-15 | 北京京鹏环球科技股份有限公司 | Greenhouse environment forecasting feedback method of back propagation (BP) neural network based on improvement of genetic algorithm |
| CN103235620A (en) * | 2013-04-19 | 2013-08-07 | 河北农业大学 | Greenhouse environment intelligent control method based on global variable prediction model |
-
2013
- 2013-09-30 CN CN201310462102.0A patent/CN103605385B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010046939A1 (en) * | 2008-10-25 | 2010-04-29 | Microlaben S.R.L. | Wireless system for greenhouse monitoring and control |
| CN102736596A (en) * | 2012-06-11 | 2012-10-17 | 南京农业大学 | Multi-scale greenhouse environment control system based on crop information fusion |
| CN202886979U (en) * | 2012-11-19 | 2013-04-17 | 吉林农业大学 | Agricultural production remote monitoring and intelligent decision making system based on Internet of Things |
| CN103076784A (en) * | 2012-12-30 | 2013-05-01 | 同济大学 | Greenhouse environmental monitoring system based on wireless sensor network and GPRS (general packet radio service) |
| CN103105246A (en) * | 2012-12-31 | 2013-05-15 | 北京京鹏环球科技股份有限公司 | Greenhouse environment forecasting feedback method of back propagation (BP) neural network based on improvement of genetic algorithm |
| CN103235620A (en) * | 2013-04-19 | 2013-08-07 | 河北农业大学 | Greenhouse environment intelligent control method based on global variable prediction model |
Non-Patent Citations (3)
| Title |
|---|
| 王伟珍等: "基于BP神经网络的温室番茄光合作用速率预测模型研究", 《中国农业工程学会2011年学术年会论文集》 * |
| 王伟珍等: "基于BP神经网络的温室番茄光合作用速率预测模型研究", 《中国农业工程学会2011年学术年会论文集》, 22 October 2011 (2011-10-22) * |
| 项美晶: "基于信息融合的温室环境因子调控优化研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105557388A (en) * | 2015-12-14 | 2016-05-11 | 西北农林科技大学 | Wireless and intelligent carbon dioxide regulating and controlling method and system for facility crops |
| CN105446142A (en) * | 2015-12-25 | 2016-03-30 | 中国农业大学 | Greenhouse CO2 gas fertilizer increasing method, device and system |
| CN106200605A (en) * | 2016-09-18 | 2016-12-07 | 王燕红 | The release of gas intelligence, management, control system |
| CN107593188A (en) * | 2017-09-26 | 2018-01-19 | 上海应用技术大学 | A kind of greenhouse production greenery vegetables plant CO2Feed method for determination of amount |
| CN107678410A (en) * | 2017-09-30 | 2018-02-09 | 中国农业大学 | It is a kind of towards the intelligent control method of greenhouse, system and controller |
| CN108124013A (en) * | 2017-12-22 | 2018-06-05 | 扬州市职业大学 | A kind of Internet of Things comprehensive training platform |
| CN108848138A (en) * | 2018-05-30 | 2018-11-20 | 深圳大图科创技术开发有限公司 | A kind of good environmental monitoring system of monitoring effect |
| CN108848138B (en) * | 2018-05-30 | 2021-05-28 | 廊坊思迪科技服务有限公司 | Environment monitoring system with good monitoring effect |
| CN110823291A (en) * | 2019-11-27 | 2020-02-21 | 山东建筑大学 | Method and system for monitoring indoor temperature and humidity environment of building based on K-means clustering algorithm |
| CN115428636A (en) * | 2020-11-11 | 2022-12-06 | 河南省新乡市农业科学院 | Wheat foliar fertilizer application method and application thereof |
| CN112449956A (en) * | 2020-11-16 | 2021-03-09 | 中国科学院合肥物质科学研究院 | Micro-nano ozone green prevention and control device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103605385B (en) | 2016-01-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103605385B (en) | A kind of CO for heliogreenhouse 2the fertile finely regulating method of gas | |
| CN102183621B (en) | Aquaculture dissolved oxygen concentration online forecasting method and system | |
| CN102736596B (en) | Multi-scale greenhouse environment control system based on crop information fusion | |
| CN104656617B (en) | Environmental control of greenhouse system and method based on Internet of Things and cloud computing technology | |
| CN106842923B (en) | Greenhouse environment multi-factor coordination control method based on crop physiology and energy consumption optimization | |
| CN205389816U (en) | Long -range accurate irrigation system of solar energy based on thing networking | |
| CN112668394B (en) | On-line prediction method and system for agricultural greenhouse production | |
| CN105005234A (en) | Intelligent greenhouse environment remote measurement and control system based on zigbee | |
| CN108614601A (en) | A kind of facility luminous environment regulation and control method of fusion random forests algorithm | |
| CN109392676A (en) | A kind of system of the cloud algorithm platform control fertigation based on block chain structure | |
| CN110119169A (en) | A kind of tomato greenhouse temperature intelligent early warning system based on minimum vector machine | |
| CN205388723U (en) | Warmhouse booth environment intellectual detection system and regulation and controlling system | |
| CN110119767A (en) | A kind of cucumber green house temperature intelligent detection device based on LVQ neural network | |
| CN204129504U (en) | Based on the greenhouse control system of Internet of Things | |
| CN113349045A (en) | Double-tower-based continuous water culture pasture cultivation control system and working method thereof | |
| CN103210818A (en) | Intelligent soil moisture content monitoring control system based on ZigBee technology | |
| Jiang et al. | WSN-based control system of CO2 concentration in greenhouse | |
| CN211177306U (en) | Intelligent energy-saving control system of air conditioner cooling system based on neural network | |
| CN207039650U (en) | Long-range multiterminal implant system based on IOT technologies | |
| CN116957141A (en) | Intelligent irrigation prediction method and system based on transducer model | |
| CN111126827A (en) | Input-output accounting model construction method based on BP artificial neural network | |
| CN116520917A (en) | Internet of things intelligent optimization monitoring method and system for agricultural product environment of greenhouse | |
| CN116430930A (en) | Forest farm environment balance adjustment equipment | |
| CN105934041A (en) | Illumination control system for plants | |
| CN201765087U (en) | Online calibrating device of pressure transmitter |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |