CN203276052U - Radial basis function neural network-based agricultural temperature control system - Google Patents
Radial basis function neural network-based agricultural temperature control system Download PDFInfo
- Publication number
- CN203276052U CN203276052U CN 201320332878 CN201320332878U CN203276052U CN 203276052 U CN203276052 U CN 203276052U CN 201320332878 CN201320332878 CN 201320332878 CN 201320332878 U CN201320332878 U CN 201320332878U CN 203276052 U CN203276052 U CN 203276052U
- Authority
- CN
- China
- Prior art keywords
- neural network
- neural net
- control system
- basis function
- radial base
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Images
Landscapes
- Feedback Control In General (AREA)
- Greenhouses (AREA)
Abstract
The utility model provides a radial basis function neural network-based agricultural temperature control system. The radial basis function neural network-based agricultural temperature control system includes a plurality of sensors; the plurality of sensors are all in signal connection with a node module; the node module is in signal connection with a coordinator; the coordinator is in signal connection with a relay and a data sample library respectively; the data sample library is respectively connected with a radial basis function neural network controller and an optimizer; and the radial basis function neural network controller and the optimizer are respectively connected with a radial basis function neural network identifier. According to the radial basis function neural network-based agricultural temperature control system of the utility model, control theories, process optimization, system identification, neural network algorithms and the like are fully utilized to perform detection, modeling, control, optimization, scheduling and management on a control process, and therefore, the yield and production efficiency of crops can be increased.
Description
Technical field
The utility model belongs to agriculture temperature acquisition and automatic control technology field, relates to a kind of agriculture temperature control system, particularly a kind of agriculture temperature control system based on radial base neural net.
Background technology
Keeping the interior suitable temperature of warmhouse booth is that crops carry out photosynthetic key factor.But in cold season, be subjected to external environment influence, the temperature in the greenhouse can reduce.Usually make the greenhouse be in air-tight state, to improve temperature in the greenhouse.Make the suitable crop growth of temperature in the greenhouse if carry out simultaneously temperature adjusting, can increase crop yield.Therefore, understand the Changing Pattern of temperature in warmhouse booth, change warmhouse booth and control environment, to improving environment control quality, crop products quality and output, far reaching significance is arranged.
The agricultural temperature controlled processes is the key link that the greenhouse is controlled, and realizes that environment is comparatively complicated.Because controller has that algorithm is simple, reliability is than advantages of higher, be widely used in Temperature Control System of Greenhouse; But the temperature of controller collection has hysteresis phenomenon in various degree, and the temperature of collection tends to produce more obvious overshoot and long period adjustment process, has reduced control system, makes conventional controller be difficult to optimization and controls effect; At present, domesticly adopted computer control system, but basically rested on continued operation level and operator's artificial experience, control accuracy is comparatively coarse, and is accurate not.Therefore, improve agriculture temperature and control quality, improving control accuracy is an important problem.
Summary of the invention
The purpose of this utility model is to improve a kind of agriculture temperature control system based on radial base neural net, can to the key parameter modeling and optimization of agricultural greenhouse, improve temperature and control quality and control accuracy.
For achieving the above object, the technical scheme that the utility model adopts is: a kind of agriculture temperature control system based on radial base neural net, comprise a plurality of sensors, a plurality of sensors all are connected with the node module signal, node module is connected with the telegon wireless network, telegon also is connected with data sample storehouse signal with relay respectively, the data sample storehouse is connected with optimizer with the radial base neural net controller respectively, and the radial base neural net controller is connected with the radial base neural net identifier respectively with optimizing.
Described telegon is connected with the data sample storehouse by gateway.
The utility model control system is controlled parameter by radial base neural net identifier identification system precision, measurement, and the control parameter of measurement is regulated temperature controlled processes by the radial base neural net controller; Data precisely gather, set up the greenhouse temperature model, optimizer optimization data model; Adopt the radial base neural net algorithm, the production of control procedure is more steady, fluctuation is few, reduce equipment loss, reduce working strength, control in real time temperature variable, and then control the Agricultural Greenhouse Temperature controlled quentity controlled variable, guarantee good crop growth environment, and then raising output, reduce costs, increase economic benefit.This control system takes full advantage of control theory, optimizing process, and System Discrimination, neural network algorithm etc. to control procedure detection, modeling, control, optimization, scheduling, management, improve crop yield and production efficiency.
Description of drawings
Fig. 1 is the structural representation of the utility model agricultural temperature control system.
In figure: 1. sensor, 2. node module, 3. telegon, 4. gateway, 5. data sample storehouse, 6. optimizer, 7. radial base neural net identifier, 8. radial base neural net controller, 9. relay.
Specific implementation process
Below in conjunction with the drawings and specific embodiments, the utility model is elaborated.
As shown in Figure 1, the utility model agricultural temperature control system, comprise a plurality of sensors 1, these a plurality of sensors 1 all are connected with node module 2 signals, node module 2 is connected with telegon 3 signals, and telegon 3 also is connected with gateway 4 with relay 9 respectively, and gateway 4 is connected with data sample storehouse 5 signals, data sample storehouse 5 is connected with optimizer 6 with radial base neural net controller 8 respectively, and radial base neural net controller 8 is connected with radial base neural net identifier 7 respectively with optimizer 6.
Telegon 3, the temperature data sample that is used for the agricultural greenhouse diverse geographic location of receiving node module 2 transmission, then the temperature data sample of the agricultural greenhouse diverse geographic location that receives is transferred to data sample storehouse 5 by gateway 4, node module 2 less radio-frequencies transmit data and are about 75 meters to telegon 3 transmission ranges, interconnect respond well.Telegon 3 is strengthened the data effect that the wireless module signal sends, and can by the RS232 serial ports, data be sent data to gateway 4; Be used for the controlled quentity controlled variable after receive data Sample Storehouse 5 is processed by the parametric variable of gateway 4 transmission, the real-time pilot relay 9 of controlled quentity controlled variable after processing according to this parametric variable;
In formula (1),
V p Be greenhouse volume, unit
m 3 C p Gas thermal capacitance for air;
T out Be steam medial temperature in the greenhouse;
T in Be the greenhouse medial temperature;
h c It is the convection current heat exchange factor;
A c The cooling surface area of greenhouse interior conduit, unit
m 2 ρIt is the greenhouse structure additional coefficient;
V m The greenhouse Principles of Natural Ventilation Rate, unit
m 3 / s κIt is greenhouse covered structure transfer coefficient;
Q rad The tectal solar radiation in greenhouse, unit
w/m 2 λ E is the crops transpiration rates;
Q h The conditioning equipment radiation, unit
w/m 2 The heat that the heat that the heat that exchanges by earth's surface in the greenhouse as can be known on the right of formula (1), the exchange heat when ventilating inside and outside the greenhouse, crop transpiration absorb and adjustment amount equipment are regulated.Obtain through differentiate and Laplace transformation arrangement:
By formula (2) as can be known,
MBe the variable that is subject to greenhouse temperature impact, the built-in variables such as Principles of Natural Ventilation Rate are wherein arranged in the greenhouse in gas gas thermal capacitance, greenhouse volume and greenhouse.
L (s)By outdoor temperature
T out (t), crops transpiration rate λ E, conditioning equipment radiation
Q h (t)Consist of Deng environmental variance.The inertia that thus should the agricultural temperature control system be thought of as the disturbance situation adds the time lag link, is the transport function that agriculture temperature is controlled output.Traditional inertia adds in the time lag link, and system is static gain,
TBeing system time constant, is system's pure delay time.
Comprehensive above-mentioned agriculture temperature model adds time lag link compare of analysis with typical inertia, can obtain (3) formula transport function
Wherein
And the data model of setting up is transferred to optimizer 6; Be used for receiving the optimum control amount of radial base neural net controller 8 outputs, after this optimum control amount is carried out the parametric variable processing, flow to telegon 3 by gateway;
Optimizer 6 is used for the data model that receive data Sample Storehouse 5 transmits, and the data model that receives is transferred to radial base neural net identifier 7;
Radial base neural net identifier 7, the data model after processing for the normalization data that receives optimizer 6 transmission then input-single output relation identification control system by the radial base neural net algorithm, and definite radial base neural net is controlled parameter more.The radial base neural net identifier makes control system improve precision, and antijamming capability is strong.
Radial base neural net controller 8 be used for to receive the control parameter of radial base neural net identifier 7 transmission, and the control parameter that receives is carried out optimizing, obtains a kind of optimum control amount, and this optimum control amount is transferred to data sample storehouse 5;
the course of work of the utility model agricultural temperature control system: the temperature data sample of zones of different position in a plurality of sensor 1 Real-time Collection warmhouse booths sends to node module 2, node module 2 is by the less radio-frequency sensing technology, a plurality of temperature samples data that receive are sent to telegon 3, telegon 3 passes to data sample storehouse 5 by gateway 4 in real time with the temperature samples data, data model is set up according to the temperature samples data that receive in data sample storehouse 5, and data model is imported optimizer 6, the data of 6 pairs of collections of optimizer carry out passing to radial base neural net identifier 7 after normalized, radial base neural net identifier 7 reads the temperature data of optimizer 6, utilize the data of optimizer 6, identification system is train RBF Neural Network, dynamic characteristic with simulation system.Predicated error between the output of data and radial base neural net output is used to provide the training signal of radial base neural net, and adopts the mode of error back propagation that network is trained, and completes the identification to device.After identification, the data model is carried out simulation modification, and choose the control parameter in radial base neural net identifier 8, control parameter and choose the radial base neural net weights
W:
Width parameter process of iteration adjustment formula is:
The process of iteration adjustment formula of center vector is:
The control parameter of network weight, width parameter and center vector by choosing radial base neural net identifier 7, make radial base neural net identifier 7 become a system of linear equations from being input to output, namely only after the input temp sample value drops on optimizer 6 zones in the input space, radial base neural net identifier 7 is just made response.
Send control parameter network weights, width parameter and the center vector chosen to radial base neural net controller 8, radial base neural net controller 8 pairs of network weights, width parameter and center vectors carry out the iterative learning optimizing, obtain one group of optimum control amount, then by radial base neural net controller 8 output temperatures
U (k):
E (k)For
kPredicated error between the constantly output of data is exported with radial base neural net is used to provide the training signal of radial base neural net.
k p ,
k i ,
k d Be respectively ratio, integration, differential coefficient.It is that the PID control law is dissolved into new controller among neural network that radial base neural net is controlled controller 8.Radial base neural net controller 8 provides the System Discrimination ability, adjusts online the PID controller
k p ,
k i ,
k d Ability.
After radial base neural net identifier 7 and radial base neural net controller 8 identification control procedures, iterative learning is chosen the optimum online PID of adjustment controller
k p ,
k i ,
k d , result feedback to data sample storehouse 5, then is sent to telegon 3 by gateway 4, telegon 3 will be adjusted relay 9, and relay 9 is effectively controlled spraying plant, ventilation unit, sun-shading equipment and is regulated the apparatus such as agriculture temperature.
The utility model control system is by the less radio-frequency sensing technology, gather Agricultural Greenhouse Temperature numerical value, analyze the environmental factor in greenhouse own to the impact of agriculture temperature, by the heat of earth's surface exchange in the greenhouse, the exchange heat when ventilating inside and outside the greenhouse, the heat of crop transpiration absorption and the heat that adjustment amount equipment is regulated; Thus, set up the mathematical model that agriculture temperature is controlled output-transfer function; With radial base neural net identifier identification system, raising precision, and the mathematical model data are carried out radial base neural net control data, extract and control parameter, with the setting value of optimal value as controller, control topworks's action, realize temperature optimization is controlled.
This control system can improve automatization level, the steady production situation of control module, the usefulness that increases production run, reduction consumption by image data, modeling and optimization control system; Improve simultaneously production efficiency, reduced systematic error, improved precision.
Claims (2)
1. agriculture temperature control system based on radial base neural net, it is characterized in that, comprise a plurality of sensors (1), a plurality of sensors (1) all are connected with node module (2) signal, node module (2) is connected with telegon (3) signal, telegon (3) also is connected 5 with relay (9) with the data sample storehouse respectively) signal is connected, data sample storehouse (5) is connected with optimizer (6) with radial base neural net controller (8) respectively, radial base neural net controller (8) is connected with radial base neural net identifier (7) respectively with optimizer (6).
2. the agriculture temperature control system based on radial base neural net according to claim 1, is characterized in that, described telegon (3) is connected with data sample storehouse (5) by gateway (4).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201320332878 CN203276052U (en) | 2013-06-09 | 2013-06-09 | Radial basis function neural network-based agricultural temperature control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201320332878 CN203276052U (en) | 2013-06-09 | 2013-06-09 | Radial basis function neural network-based agricultural temperature control system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN203276052U true CN203276052U (en) | 2013-11-06 |
Family
ID=49506423
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201320332878 Expired - Fee Related CN203276052U (en) | 2013-06-09 | 2013-06-09 | Radial basis function neural network-based agricultural temperature control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN203276052U (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105468054A (en) * | 2015-12-10 | 2016-04-06 | 长江大学 | Brake temperature supervising device and intelligent control method |
| CN105807811A (en) * | 2016-03-14 | 2016-07-27 | 东华大学 | Remote greenhouse temperature control system based on WI-FI |
| CN105979257A (en) * | 2016-05-17 | 2016-09-28 | 京东方科技集团股份有限公司 | VGA signal measuring device and method |
| CN106773720A (en) * | 2017-01-25 | 2017-05-31 | 张彩芬 | A kind of warmhouse booth environment automatic control system |
| CN106920174A (en) * | 2017-03-09 | 2017-07-04 | 中国农业科学院农业经济与发展研究所 | A kind of greenhouse heating control system and method |
| CN110069032A (en) * | 2019-04-19 | 2019-07-30 | 淮阴工学院 | A kind of eggplant greenhouse intelligent checking system based on wavelet neural network |
| CN111272224A (en) * | 2020-03-03 | 2020-06-12 | 四川飨誉食界供应链管理有限公司 | Agricultural ecological industrial park intelligent monitoring system and method |
-
2013
- 2013-06-09 CN CN 201320332878 patent/CN203276052U/en not_active Expired - Fee Related
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105468054A (en) * | 2015-12-10 | 2016-04-06 | 长江大学 | Brake temperature supervising device and intelligent control method |
| CN105468054B (en) * | 2015-12-10 | 2018-10-23 | 长江大学 | The intelligent control method of brake temperature monitoring device |
| CN105807811A (en) * | 2016-03-14 | 2016-07-27 | 东华大学 | Remote greenhouse temperature control system based on WI-FI |
| CN105979257A (en) * | 2016-05-17 | 2016-09-28 | 京东方科技集团股份有限公司 | VGA signal measuring device and method |
| CN105979257B (en) * | 2016-05-17 | 2018-06-26 | 京东方科技集团股份有限公司 | A kind of VGA signal measurement apparatus and method |
| CN106773720A (en) * | 2017-01-25 | 2017-05-31 | 张彩芬 | A kind of warmhouse booth environment automatic control system |
| CN106920174A (en) * | 2017-03-09 | 2017-07-04 | 中国农业科学院农业经济与发展研究所 | A kind of greenhouse heating control system and method |
| CN110069032A (en) * | 2019-04-19 | 2019-07-30 | 淮阴工学院 | A kind of eggplant greenhouse intelligent checking system based on wavelet neural network |
| CN110069032B (en) * | 2019-04-19 | 2021-04-23 | 淮阴工学院 | Eggplant greenhouse environment intelligent detection system based on wavelet neural network |
| CN111272224A (en) * | 2020-03-03 | 2020-06-12 | 四川飨誉食界供应链管理有限公司 | Agricultural ecological industrial park intelligent monitoring system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN203276052U (en) | Radial basis function neural network-based agricultural temperature control system | |
| Pasgianos et al. | A nonlinear feedback technique for greenhouse environmental control | |
| Ding et al. | Precise control and prediction of the greenhouse growth environment of Dendrobium candidum | |
| CN108386902B (en) | A kind of intelligent heat-exchange station secondary network mean temperature control method | |
| CN104155925A (en) | Henhouse micro climatic environment intelligent control system based on wireless sensor network | |
| CN103226348B (en) | A kind of edible fungi mushroom house set of circumstances medium-long range controls system and method | |
| CN103995553B (en) | The points distributing method of a kind of ash tree flower mushroom room Temperature Humidity Sensor | |
| CN110069032B (en) | Eggplant greenhouse environment intelligent detection system based on wavelet neural network | |
| CN107329511A (en) | Based on the vegetable aquaculture luminous environment high efficiency regulatory method and system between suitable root warm area | |
| CN116360331B (en) | Universal irrigation automation control system and control method | |
| CN103631285A (en) | CAN bus-based barton environment temperature control system | |
| Zhou et al. | Applications of Internet of Things in the facility agriculture | |
| CN107991964A (en) | A kind of indoor environment intellectual monitoring control method and the system for realizing this method | |
| CN106920174A (en) | A kind of greenhouse heating control system and method | |
| CN113485498A (en) | Indoor environment comfort level adjusting method and system based on deep learning | |
| CN105557388A (en) | Wireless and intelligent carbon dioxide regulating and controlling method and system for facility crops | |
| CN109213240A (en) | A kind of strawberry greenhouse wireless monitor and control system based on self adaptive control | |
| Al-Aubidy et al. | Real-time monitoring and intelligent control for greenhouses based on wireless sensor network | |
| CN111459033A (en) | Grey prediction fuzzy PID control method and equipment for water and fertilizer irrigation | |
| Shujiang et al. | Design of greenhouse environment controller based on fuzzy adaptive algorithm | |
| Singh et al. | IoT-based greenhouse technologies for enhanced crop production: A comprehensive study of monitoring, control, and communication techniques | |
| CN211177306U (en) | Intelligent energy-saving control system of air conditioner cooling system based on neural network | |
| KR101959886B1 (en) | Server and method for determining actuator parameter of greenhouse | |
| CN116225114B (en) | Intelligent environmental control system and method for crop growth controllable agricultural greenhouse based on big data | |
| Magsumbol et al. | An automated temperature control system: A fuzzy logic approach |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20131106 Termination date: 20140609 |