KR20170028721A - System for controling greenhouse environment and parameter of controller of greenhouse - Google Patents

Abstract

A parameter analysis system which controls the parameters of greenhouse controller comprises: a plant modeling unit which performs plant modeling with respect to a greenhouse by using a learning algorithm of a nonlinear model; a greenhouse data receiving unit which collects greenhouse environment setting information, environment information, and state information of at least one actuator from a greenhouse control system; a database unit which stores greenhouse data including at least one of greenhouse environment setting information, environment information, state information of at least one actuator, and greenhouse information according to plant modeling; a parameter deriving unit which derives the parameters of the controller on the basis of the plant modeling and green house data; and parameter transmitting unit which transmits the parameters to the greenhouse control system.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a system for controlling a parameter of a controller of a greenhouse and a greenhouse environment,

The present invention relates to a system for controlling parameters of a controller of a greenhouse and a greenhouse environment.

Facility cultivation is an agriculture that produces high quality crops by making environmental conditions better than greenhouses or in times when cultivation is impossible in the greenhouse due to environmental control of the greenhouse. The greenhouse is implemented in various forms such as a glasshouse, a vinyl greenhouse, a solar combined type, and an artificial light plant.

Facility cultivation requires precise and complex environmental control methods to improve crop productivity and harvest high quality crops. Conventional greenhouse compound environmental control technology is a system in which a sensor, a driver, and a controller are connected in a greenhouse to perform environment control, and a controller and a central system are connected to monitor a greenhouse control situation.

PID (Proportional-Integral-Derivative) control method and On / Off control method are mainly used as the control logic used for the hybrid environment control of the greenhouse. Since the performance of the controller depends on the values of the proportional gain (K _p ), the integral gain (K _i ) and the differential gain (K _d ), the proportional gain (K _p ), the integral gain (K _i ) How to determine the gain (K _d ) can be an important issue.

However, since the parameter values of the PID controller are not directly proportional to the performance and robustness required by the designer, it is difficult to obtain parameters of the PID controller.

In the conventional greenhouse environment precision control system is the setting or fixing of the control logic parameters (proportional gain (K _p), integral gain (K _i), the differential gain (K _d), the offset value). The setting of these parameters depends on the farmer's system operation ability, cultivation knowledge and experience.

In addition, the greenhouse is influenced by the external environment of the greenhouse (external temperature, wind direction, wind speed, etc.) and the greenhouse type (size of the greenhouse, size of the greenhouse window, It is difficult to construct the same control model.

Conventionally, in order to control the greenhouse, it is intuitively controlled depending on the experience of a farm owner or a manager in general. If the growth of the crop is managed based on the experiences of the farm owner or the manager, there is a problem that the growth environment of the crop can not be efficiently controlled.

In Korean Laid-open Patent Application No. 2014-0077720, the learning-based greenhouse control system receives learning data including time, environment setting values, actuator manipulated variables, disturbance, wind speed, and wind direction environment measurement values through a plurality of sensors and the like , Processing the learning data acquired through date calculation, time calculation, environmental difference, disturbance calculation, actuator manipulated variable calculation, compensation operation quantity calculation, etc., and applying a weight to the previously stored data to generate a matrix graph, An optimum parameter for controlling the greenhouse is generated, and a greenhouse is controlled based on the parameters.

In order to precisely control the greenhouse, the greenhouse data of the greenhouse is collected from the greenhouse to provide a method for modeling the plant for the greenhouse. Based on the plant modeling, we want to derive the parameters of the controller suitable for the greenhouse. It is to be understood, however, that the technical scope of the present invention is not limited to the above-described technical problems, and other technical problems may exist.

According to a first aspect of the present invention, there is provided a parameter analysis system for controlling a parameter of a controller of a greenhouse, comprising: a plant modeling unit that performs plant modeling on a greenhouse using a learning algorithm of a non- A greenhouse data receiving unit for collecting environment setting information of the greenhouse, environment information, and status information of at least one driver from the greenhouse control system, environment setting information of the greenhouse, environment information, status information of at least one driver, A parameter derivation unit for deriving parameters of the controller based on the plant modeling and the greenhouse data and a parameter derivation unit for deriving the parameters from the parameters to the greenhouse control system send Section.

According to a second aspect of the present invention, there is provided a greenhouse control system including a parameter receiving unit for receiving parameters of a controller from a parameter analysis system, a sensor unit for monitoring environmental information of a greenhouse and status information of a driver, A database unit for storing logic, at least one driver, a controller for controlling the driver, and a management unit.

A system for precisely controlling a greenhouse environment by controlling parameters of a controller of a greenhouse according to the third aspect of the present invention includes a parameter analysis system and a greenhouse control system wherein the parameter analysis system uses a learning algorithm of a non- A plant modeling method comprising: performing plant modeling on a greenhouse and calculating parameters based on greenhouse data including at least one of the plant modeling and environment information of the greenhouse, environmental information, status information of at least one driver, And the parameter is transmitted to the greenhouse control system, wherein the greenhouse control system receives the parameter of the controller from the parameter analysis system, and based on the environment information of the greenhouse and the pre-input environment setting information, At least one phrase Select one of the groups and, on the basis of the environment information of the greenhouse to select the parameters of the controller, and may be configured to control the actuator selected via the controller.

The above-described task solution is merely exemplary and should not be construed as limiting the present invention. In addition to the exemplary embodiments described above, there may be additional embodiments described in the drawings and the detailed description of the invention.

According to any one of the above-described objects of the present invention, parameters of an optimal controller for a driver can be derived by analyzing plant modeling and greenhouse data of a greenhouse. In addition, it is possible to control the greenhouse environment in real time using parameters received from the parameter analysis system. In addition, the control logic of the driver can be appropriately adjusted according to the size of the greenhouse, the material structure, and the characteristics of the crop, thereby minimizing variations in the operation skill of the greenhouse control system and the cultivation techniques of the greenhouse and maximizing the production of uniform quality crops can do.

1 is a configuration diagram of a greenhouse environment precise control system according to an embodiment of the present invention.
Figure 2 is a block diagram of the parameter analysis system shown in Figure 1, in accordance with an embodiment of the present invention.
3 is a block diagram of the greenhouse control system shown in FIG. 1, in accordance with one embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, which will be readily apparent to those skilled in the art. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. In order to clearly illustrate the present invention, parts not related to the description are omitted, and similar parts are denoted by like reference characters throughout the specification.

Throughout the specification, when a part is referred to as being "connected" to another part, it includes not only "directly connected" but also "electrically connected" with another part in between . Also, when an element is referred to as "comprising ", it means that it can include other elements as well, without departing from the other elements unless specifically stated otherwise.

In this specification, the term " part " includes a unit realized by hardware, a unit realized by software, and a unit realized by using both. Further, one unit may be implemented using two or more hardware, or two or more units may be implemented by one hardware.

In this specification, some of the operations or functions described as being performed by the terminal or the device may be performed in the server connected to the terminal or the device instead. Similarly, some of the operations or functions described as being performed by the server may also be performed on a terminal or device connected to the server.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings.

1 is a configuration diagram of a greenhouse environment precise control system according to an embodiment of the present invention.

Referring to FIG. 1, a greenhouse environment precise control system may include a parameter analysis system 100 and a greenhouse control system 110. However, since the precise control system for the greenhouse environment of FIG. 1 is only one embodiment of the present invention, the present invention is not limited to FIG. 1, have.

The controller used in the greenhouse environment precise control system may be at least one of a Proportional-Integral (PI) controller, a Proportional-Integral-Derivative (PID) controller, and an Off-Set controller. Since the performance of the controller varies depending on the values of the proportional gain K _p , the integral gain K _i and the differential gain K _d , the proportional gain K _p , the integral gain K _i , And the derivative gain (K _d ) are important issues.

The parameter analysis system 100 performs plant modeling on a greenhouse using a learning algorithm of a nonlinear model, and performs plant modeling based on plant modeling and environment setting information of the greenhouse, environment information, state information of at least one driver, The greenhouse control system 110 can derive the parameters based on the greenhouse data including at least one of them. Here, the parameter may be at least one of a proportional gain (K _p ), an integral gain (K _i ), a differential gain (K _d ) and an offset value.

The parameter values according to an exemplary embodiment of the present invention may have variable characteristics in the form of dynamic parameters that are changed according to the driver conditions to suit each greenhouse. For example, in a PI controller, the proportional gain (K _p ) and the integral gain (K _i ) may have dynamic parameter characteristics that vary depending on the greenhouse conditions.

Parameter analysis system 100 is offset, and this calculated one then obtain and the range of the input values of the greenhouse plant input minimum value, intermediate value, maximum value, performing a greenhouse plant modeling (Offset) value and the proportional gain (K _p) The intermediate value, and the maximum value of the integral gain K _i can be calculated to obtain the output value of the plant.

The greenhouse control system 110 receives the parameter of the controller from the parameter analysis system 100, selects one of the at least one driver based on the environment information of the greenhouse and the pre-input environment setting information, Based on which parameters of the controller can be selected and the driver selected through the controller can be controlled.

Generally, each component of the greenhouse environment precise control system of FIG. 1 is connected through a network 120. The network refers to a connection structure in which information can be exchanged between each node such as terminals and servers. Examples of such a network include a 3rd Generation Partnership Project (3GPP), a Long Term Evolution (LTE), a WIMAX World Interoperability for Microwave Access), Wi-Fi, 3G, 4G, and the like.

Hereinafter, the operation of each component of the greenhouse environment precise control system of FIG. 1 will be described in more detail.

2 is a block diagram of the parameter analysis system 100 shown in FIG. 1, in accordance with an embodiment of the present invention.

2, the parameter analysis system 100 may include a plant modeling unit 200, a greenhouse data receiving unit 210, a database unit 220, a parameter derivation unit 230, and a parameter transfer unit 240 have. However, the parameter analysis system 100 shown in FIG. 2 is only one embodiment of the present invention, and various modifications are possible based on the components shown in FIG.

The plant modeling unit 200 may perform plant modeling on the greenhouse using a learning algorithm of a non-linear model. The plant in the greenhouse can be temperature, humidity and CO ₂ .

For example, the plant modeling unit 200 can perform plant modeling on temperature, humidity, and carbon dioxide (CO ₂ ) of a greenhouse. Here, the greenhouse temperature, the greenhouse humidity, and the greenhouse carbon dioxide can not be expressed by a certain function formula since they have various forms depending on the structure, size, material, and external environment of the greenhouse. Accordingly, the plant modeling unit 200 applies an error back propagation algorithm to a multi-layer perceptron structure of a neural network, which is a learning algorithm for representing a non-linear model, Humidity, and greenhouse carbon dioxide.

Multilayer perceptron used in the field of neural networks is a nonlinear model that overcomes the limited function approximation ability which is a disadvantage of the linear model.

The error back propagation algorithm is a steepest descent method that extends the least mean square (LMS) algorithm for linear models to multi-layers as a supervised learning method.

The error back propagation algorithm can adaptively improve the connection strength in the neural network by back propagating the error between the given target output and the actual output of the neural network.

On the other hand, the structure of the multilayer perceptron is composed of an input layer, a hidden layer, and an output layer.

The contents of the multi-layer perceptron structure and the error back propagation algorithm of the neural network are obvious to those skilled in the art, and therefore, detailed description thereof will be omitted.

The plant modeling unit 200 can output the increase / decrease of the temperature, humidity, or carbon dioxide of the greenhouse using the operating conditions and environmental factors of at least one driver as input values of the learning algorithm. That is, the learning algorithm can set the operating condition and the environmental factor of at least one driver as input values, and can use the increase / decrease of the temperature, humidity, or carbon dioxide of the greenhouse as the output value.

Taking the plant modeling of temperature as an example, assuming that the target temperature amount when the operating condition of the driver reaches the indoor temperature of the greenhouse under the operating temperature (set temperature) is Var_Temp, the temperature change value at the time t + and the temperature change from t to t + 1.

The temperature change value can be expressed by the following equation (1).

The temperature output of the driver can be expressed by Equation (2).

The input value learning data can be extracted from Temp_out [t + 1] = {Actuator1 (x) + Actuator2 (x) + ...} in the past history data of the greenhouse. These data can be data for performing plant modeling of temperature.

The greenhouse data receiving unit 210 may collect environment setting information of the greenhouse, environment information, and status information of at least one driver from the greenhouse control system 110. Here, the environment setting information may be a target set value for temperature, humidity, or carbon dioxide.

Environmental information may include, for example, the properties (greenhouse type, size, material, etc.) of the greenhouse, interior or exterior information of the greenhouse, and the like. The status information of the driver may include, for example, information on the driver holding and type, and data on the driver's operation history.

The greenhouse data receiving unit 210 can collect environment setting information of the greenhouse, environment information, and status information of the driver from the greenhouse control system 110 in real time.

The database unit 220 may store greenhouse data including at least one of environment setting information of the greenhouse, environment information, status information of at least one driver, and greenhouse information according to the plant modeling.

The database unit 220 stores input and output data between respective components in the parameter analysis system 100 and inputs and outputs data between components outside the parameter analysis system 100 and the parameter analysis system 100. [ Quot; One example of the database unit 220 includes a hard disk drive, a ROM (Read Only Memory), a RAM (Random Access Memory), a flash memory, a memory card, and the like, both inside and outside the parameter analysis system 100.

The parameter derivation unit 230 can derive the parameters of the controller based on the plant modeling and the greenhouse data. Here, the controller may be at least one of a Proportional-Integral (PI) controller, a Proportional-Integral-Derivative (PID) controller, and an Off-Set controller. The parameter may be at least one of a proportional gain (K _p ), an integral gain (K _i ) and an offset value.

These parameters can be changed dynamically according to the greenhouse environment. Also, since the performance of the controller depends on the proportional gain (K _p ), the integral gain (K _i ), and the offset value, how to derive the parameter becomes an important problem.

For example, the parameter derivation unit 230 obtains the range of input values of the plant modeling, calculates the input values of the plant modeling as a minimum value, an intermediate value, and a maximum value, and calculates an offset value, a proportional gain value, , The intermediate value, and the maximum value to calculate the output value of the plant modeling. Then, the parameter derivation unit 230 can apply the output value of the plant modeling to the virtual control value of the greenhouse environment, and when selecting the parameter later, the parameter can be selected based on the output value.

The parameter derivation unit 230 can derive an error by comparing the target set value and the actual value with respect to temperature, humidity, or carbon dioxide, and derive the parameter based on the error. That is, the parameter derivation unit 230 may derive a parameter for reducing an error between the target set value and the actual value for temperature, humidity, or carbon dioxide. Here, the error can be judged as an error value of the operated driver control.

For example, assuming that environmental information = {temperature, humidity, carbon dioxide}, the error value for the entire environment is Error_environment (t) = Error_temperature (t) + Error_humidity (t) + Error_CO_2 (t) = actual temperature (t), Error_humidity (t) = set humidity (t) - actual humidity (t) t), Error_Carbon (t) = Set CO2 (t) - Actual CO2 (t). Therefore, the total environmental error value is assumed to be an error with respect to the entire driver operation over the entire time, and the error of all the actuators can be represented by the total sum of the values obtained by subtracting the actual value from the target set value for each driver. Accordingly, the parameter derivation unit 230 can increase or decrease the parameter of the controller for each driver in consideration of the error value.

Further, the parameter derivation unit 230 may increase or decrease the offset value when the on / off control is performed.

In addition, the parameter derivation unit 230 may generate learning data for each driver based on the collected environment information and state information of at least one driver, and may derive the parameters of the controller for each driver based on the learning data for each driver have. For example, the parameter derivation unit 230 may be based on the driver-specific learning data, such as a parameter for a skylight, a parameter for a sight, and a parameter for illumination as driver.

Also, the parameter derivation unit 230 can derive the parameters differently according to the target environment information. For example, with respect to the skylight as the driver, the parameters of the case where the target environment information is the temperature and the case where the humidity is the humidity may be different.

Also, the parameter derivation unit 230 may derive the parameters for each driver in consideration of each driver and target environment information.

For example, the parameter derivation unit 230 generates learning data by setting the length of the learning pattern based on environmental data, temperature, humidity, set values for carbon dioxide, and operation history data of the driver according to the growth characteristics of the crop It is possible.

In addition, the parameter derivation unit 230 may generate a control logic algorithm of the controller for the driver through the driver-specific learning data, and may generate the driver-specific control logic through the combination of the controllers. If a new driver control logic algorithm that does not have a control logic algorithm is required, the parameter derivation unit 230 uses the control logic algorithm of the driver most similar to the existing driver characteristic to generate a new driver control logic algorithm Can be estimated.

The parameter derivation unit 230 extracts environmental control information of the greenhouse in the greenhouse control system 110 through the environment setting information of the greenhouse, the environment information, and the status information of the driver received from the greenhouse control system 110 , And if the greenhouse environment control information is similar to the type of the learning data for each driver or if the greenhouse environment control information is different from the predicted value of the driver, the driver's operation history can be compared to check whether the driver is abnormal. If the greenhouse environment control performance of the controller for each driver is lower than the performance of the existing control level, the parameter derivation unit 230 may replace the controller logic algorithm of the existing driver with the control algorithm of the existing driver,

The parameter transmission unit 240 may transmit the derived parameters and the driver-specific control logic to the greenhouse control system 110.

Those skilled in the art will recognize that the plant modeling unit 200, the greenhouse data receiving unit 210, the database unit 220, the parameter derivation unit 230, and the parameter transfer unit 240 may be separately implemented, It will be appreciated that the present invention can be implemented integrally.

FIG. 3 is a block diagram of the greenhouse control system 110 shown in FIG. 1, in accordance with an embodiment of the present invention.

3, the greenhouse control system 110 includes a parameter receiving unit 300, a sensor unit 310, a database unit 320, a driver 330, a controller 340, a management unit 350, and a transmission unit 360 ). However, the greenhouse control system 110 shown in FIG. 3 is only one embodiment of the present invention, and various modifications are possible based on the components shown in FIG.

The parameter receiving unit 300 can receive parameters of the controller from the parameter analysis system 100. [ Here, the parameter may be at least one of a proportional gain (K _p ), an integral gain (K _i ), and an offset value.

In addition, the parameter receiving unit 300 can receive driver-specific control logic from the parameter analysis system 100. [

The sensor unit 310 can monitor environmental information of the greenhouse and status information of the driver. Here, the environmental information of the greenhouse may include, for example, attributes (greenhouse type, size, material, etc.) of the greenhouse, internal or external information of the greenhouse, and the like. The status information of the driver may include, for example, information on the driver holding and type, and data on the driver's operation history.

The database unit 320 may store parameters received by the parameter receiving unit 300 and control logic for each driver.

The database unit 320 may further store priorities of drivers according to environment information of the greenhouse. For example, the database portion 320 may store priorities in order of driver for temperature, humidity, and carbon dioxide.

The database unit 320 stores data input and output between the respective components in the greenhouse control system 110 and inputs and outputs data between components outside the greenhouse control system 110 and the greenhouse control system 110. [ Quot; One example of such a database unit 320 includes a ROM (Read Only Memory), a RAM (Random Access Memory), a flash memory, a memory card, and the like which are present inside or outside the greenhouse control system 110.

The driver 330 may include a skylight, a side window, a curtain, a boiler, an illuminator, an air heater, a CO ₂ supply, and the like, for controlling a greenhouse environment.

The controller 340 may control at least one driver 330. The controller 340 may be at least one of a Proportional-Integral (PI) controller, a Proportional-Integral-Derivative (PID) controller, and an Off-Set controller.

The management unit 350 selects one of the at least one driver 330 based on the environment information of the greenhouse and the inputted environment setting information, selects the parameter of the controller 340 based on the environment information of the greenhouse, The driver can be controlled through the controller 340. Here, the parameter may have a different parameter value for each driver.

Although not shown, the management unit 350 may include a driver selection unit that selects one of the drivers 330, and a parameter selection unit that selects a parameter of the controller 340. [

The management unit 350 may select a parameter value of the controller based on the input environment setting information, and may control the selected driver through the controller using the selected parameter value.

The management unit 350 compares the target set values for the temperature, humidity, and carbon dioxide of the greenhouse with the current greenhouse environment to determine which driver should be operated. In addition, the management unit 350 may set a priority order among the at least one drivers 330 or may select which of the at least one drivers 330 to control in parallel.

The management unit 350 can select any one of the at least one drivers 330 based on the priorities of the drivers. In addition, the management unit 350 may select the parameters in the control logic corresponding to the selected driver according to the environment information of the greenhouse, and apply the selected parameters to the selected driver.

For example, the management unit 350 can set and update the priority of the driving period and the plurality of operations of the plurality of drivers by target environment information (e.g., temperature, humidity, or CO ₂ ).

By controlling the selected driver, the management unit 350 can measure the rate of change of the environmental information of the greenhouse corresponding to the environment setting information.

If the rate of change is equal to or less than the preset rate of change, the management unit 350 can maintain the selected operation of the selected driver for a predetermined time period even if the selected condition of the selected driver is satisfied according to the changed environment information of the greenhouse by controlling the selected driver .

For example, when the temperature measured in the greenhouse is a low temperature that is lower than the target set temperature (for example, the temperature of the greenhouse does not rise after the heater operation), the control conditions of other actuators , And is lower than the external humidity), the control operation of the other driver can be delayed.

As another example, if the temperature measured in the greenhouse is higher than the target set temperature and the outside temperature of the greenhouse is lower than the greenhouse room temperature (for example, the temperature does not fall after the opening of the skylight) The control operation of the other driver can be delayed even if the control condition (for example, when the internal humidity of the greenhouse falls within the upper limit range of the target humidity and the external humidity is higher) is established.

The transmission unit 360 can transmit environment setting information, environment information, and status information of at least one driver to the parameter analysis system 100 in real time.

Those skilled in the art will recognize that the parameter receiving unit 300, the sensor unit 310, the database unit 320, the driver 330, the controller 340, the management unit 350 and the transmission unit 360 may be separately implemented, It will be appreciated that one or more of these may be implemented in unison.

An embodiment of the present invention may also be embodied in the form of a program stored on a medium executed by a computer or a recording medium including instructions executable by the computer.

Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. In addition, the computer-readable medium can include both computer storage media and communication media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Communication media typically includes any information delivery media, including computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave, or other transport mechanism.

It will be understood by those skilled in the art that the foregoing description of the present invention is for illustrative purposes only and that those of ordinary skill in the art can readily understand that various changes and modifications may be made without departing from the spirit or essential characteristics of the present invention. will be. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive. For example, each component described as a single entity may be distributed and implemented, and components described as being distributed may also be implemented in a combined form.

It is intended that the present invention covers the modifications and variations of this invention provided they come within the scope of the appended claims and their equivalents. .

100: Parameter analysis system
110: Greenhouse control system

Claims (18)

A parameter analysis system for controlling parameters of a controller of a greenhouse,
A plant modeling unit for performing plant modeling on a greenhouse using a learning algorithm of a nonlinear model;
A greenhouse data receiving unit for collecting environment setting information of the greenhouse, environment information, and status information of at least one driver from the greenhouse control system;
A database unit for storing greenhouse data including at least one of environment setting information of the greenhouse, environment information, status information of at least one driver, and greenhouse information according to the plant modeling;
A parameter derivation unit for deriving parameters of the controller based on the plant modeling and the greenhouse data; And
A parameter transmission unit for transmitting the parameter to the greenhouse control system,
The parameter analysis system comprising:
The method according to claim 1,
Wherein the controller is at least one of a Proportional-Integral (PI) controller, a Proportional-Integral-Derivative (PID) controller, and an Off-Set controller.
3. The method of claim 2,
Wherein the parameter is at least one of a proportional gain (K _p ), an integral gain (K _i ) and an offset value.
The method according to claim 1,
Wherein the learning algorithm applies an Error Back Propagation algorithm to a Multi-Layer Perceptron structure of a Neural Network.
5. The method of claim 4,
Wherein the learning algorithm takes the operating conditions and the environmental factors of the at least one driver as input values and outputs the increase / decrease of temperature, humidity or carbon dioxide (CO ₂ ) of the greenhouse as an output.
The method according to claim 1,
Wherein the greenhouse data receiver collects environment setting information of the greenhouse, environment information, and status information of a driver from the greenhouse control system in real time.
The method according to claim 1,
The environment setting information is a target set value for temperature, humidity, or carbon dioxide,
Wherein the parameter derivation unit derives an error by comparing the target set value and the actual value with respect to the temperature, the humidity, or the carbon dioxide,
And derive the parameter based on the error.
The method according to claim 1,
Wherein the parameter derivation unit generates learning data for each driver based on the collected environment information and the state information of the at least one driver,
Wherein the parameters of the controller are derived differently for each driver based on the driver-specific learning data.
In a greenhouse control system,
A parameter receiving unit for receiving a parameter of the controller from the parameter analysis system;
A sensor unit for monitoring environmental information of the greenhouse and status information of the driver;
A database unit for storing the received parameters and control logic for each driver;
At least one driver;
A controller for controlling the driver; And
Management,
Wherein the management unit selects one of the at least one driver based on the environment information of the greenhouse and the pre-input environment setting information, selects a parameter of the controller based on environmental information of the greenhouse, And controls the selected driver.
10. The method of claim 9,
Wherein the database unit further stores priority for each driver according to each environment information.
11. The method of claim 10,
Wherein the management unit selects any one of the at least one driver based on the driver-specific priority.
10. The method of claim 9,
Wherein the management unit measures the rate of change of environmental information of the greenhouse corresponding to the environment setting information by controlling the selected driver.
13. The method of claim 12,
Wherein the control unit controls the selected driver to maintain the operation of the selected driver for a preset time even if the selected control unit satisfies other control conditions of the selected driver according to the changed environment information of the greenhouse when the rate of change is less than a predetermined rate of change Greenhouse control system.
10. The method of claim 9,
Wherein the controller is at least one of a Proportional-Integral (PI) controller, a Proportional-Integral-Derivative (PID) controller, and an Off-Set controller.
15. The method of claim 14,
Wherein the parameter is at least one of a proportional gain (K _p ), an integral gain (K _i ) and an offset value.
10. The method of claim 9,
A transmission unit for transmitting environment setting information of the greenhouse, environment information, and status information of at least one driver to the parameter analysis system in real time;
Wherein the greenhouse control system further comprises:
10. The method of claim 9,
Said parameter having different parameter values for each driver,
Wherein the management unit selects a parameter value of the controller for the environment setting information previously input.
A system for precisely controlling a greenhouse environment by controlling parameters of a controller of the greenhouse,
Parameter analysis system; And
Greenhouse control system
≪ / RTI >
Wherein the parameter analysis system comprises:
The plant modeling is performed for the greenhouse using the learning algorithm of the nonlinear model,
Deriving a parameter based on the plant modeling and the greenhouse data including at least one of the environment setting information of the greenhouse, the environment information, the state information of at least one driver, and the greenhouse information according to the plant modeling,
And to transmit the parameter to the greenhouse control system,
The greenhouse control system includes:
Receiving parameters of the controller from the parameter analysis system,
Selecting one of the at least one driver based on environmental information of the greenhouse and pre-input environment setting information,
Selecting parameters of the controller based on environmental information of the greenhouse,
And to control the selected driver via the controller.

Images