KR20240078197A - Method for simulating of growing environment for controlling of smart farm to intelleting - Google Patents

Abstract

The embodiment relates to a method of simulating a growth environment for intelligent smart farm control.
Specifically, this growth environment simulation method maintains the same growth environment of crops from various environmental changes as before. In addition, by analyzing the external air environment of farms that had high crop yields in the past, the internal maintenance environment of the smart farm, nutrient solution supply information, and solar energy information for photosynthesis, the current smart farm operation farms calculate yields similar to those of past excellent farms. Controls the environment for
Therefore, the embodiment controls the current smart farm internal environment, nutrient solution, artificial light, etc. to adjust the optimal growth condition for each growth period of excellent farms that had good yields in the past.
Furthermore, environmental conditions are artificially controlled and maintained to enable harvesting similar to the high yields of the past.
And from this, a service is created that connects with actual farms within a virtual space to enable optimal production remotely.

Description

Method for simulating a growing environment for controlling an intelligent smart farm {Method for simulating of growing environment for controlling of smart farm to intelleting}

Disclosed in this specification is a method of controlling and maintaining the current farming state similar to the growth environment in which excellent yields were good in past excellent farms, based on the farming data of past excellent farms in a smart farm system that controls the existing internal environment. It is about etc.

For your reference, this case is the result of an application filed with the support of the ‘2022 Global Startup Business Support Project’ of Gyeonggi Province and Gyeonggi Province Economic and Science Promotion Agency.

Unless otherwise indicated herein, the material described in this section is not prior art to the claims of this application, and is not admitted to be prior art by inclusion in this section.

Recently, changes in crop cultivation conditions have occurred due to the decline and aging of the rural population and climate change. Accordingly, the smart farm system has been introduced as precision agriculture to control the quality of agricultural products and increase production by converging agricultural and ICT technologies. It is increasing.

The smart farm system is a system that artificially supplies the external natural environment with light, temperature, humidity, and CO2 as the main growth environment required for plant growth. It produces clean plants that are independent of the natural environment and can block pests and diseases.

In particular, the light environment, which is an important environmental factor that determines plant growth, receives energy from light and produces substances necessary for internal chemical and metabolic reactions, and light is an important environmental factor in the growth of crops. However, since the amount and quality of light and day length that affect crop growth vary depending on the location, time, and materials that make up the smart farm, it is necessary to understand the nature of the light supplied to the plants.

With the recent introduction of indoor plant cultivation systems, it has become possible to artificially supply the soil and solar energy required for each plant type and growth stage, and then grow the necessary plants in a machine. In addition, this system utilizes natural environment simulation technology that mimics the energy required by plant species and growth period similar to nature, providing an environment in which plants with similar taste and nutrients can be safely grown indoors.

Smart farms that produce plants in large quantities are comprised of various facilities to supply energy sources to plants, and IoT sensors are used to control the facilities, analyze data needed for growth, and maintain an optimal growth environment. A based intelligent system can be configured.

In addition, the prior art in this background is the extent to which the following documents appear.

(Patent Document 0001) KR101902363 B1

For reference, Document 1 discloses adjusting the amount of light required for each crop in relation to the content disclosed herein. Specifically, each crop is irradiated with the most optimal amount of light required for growth, and the amount of light is adjusted so that it can grow at the optimal level in the shortest period of time.

The disclosed contents include maintaining the same growth environment for crops from environmental changes as in existing smart farms, maintaining the external air environment of farms with high crop yields in the past, the internal maintenance environment of smart farms, nutrient solution supply information, and solar energy for photosynthesis. Analyze information, etc. Therefore, we construct a system that controls the environment to produce yields similar to those of past excellent farms in the current smart farm operation farms, and intelligently controls various sensors and drive systems to control the smart farm environment.

In other words, we aim to provide a growth environment simulation method for intelligent smart farm control.

The growth environment simulation method for intelligent smart farm control according to the embodiment is,

In a method of simulating a growing environment for intelligent smart farm control,

Collecting growth information of each excellent farm for a plurality of different crops and yield information of the corresponding crops within the corresponding farm or region from an external farm-related registration information processing device;

Analyzing the relationship between growth information and yield using the collected growth information and crop yield information within the farm or region;

Analyzing the optimal supply baseline for essential energy required for growth for each crop and cropping season;

Predicting the effective daily solar light amount for each region and scheduling daily light supply inside the smart farm;

Predicting the growth conditions of the smart farm by analyzing real-time images of the growth status of crops; and

A step of intelligently controlling the sensors and driving systems inside the smart farm to maintain a growth state that mimics the environment in which past harvests were good;

It aims to solve technical challenges by providing a method of simulating the growth environment inside the current smart farm by analyzing the growth environment with high yields in the past.

In addition, according to the embodiment, the growth status and smart farm internal control data of excellent farms are collected by replicating the environment of past excellent farms, and the necessary supply baseline for each crop season is predicted from the collected data to create a smart farm environment. Control.

In addition, the PPFD (Photosynthetic photon flux density) of the target area is calculated by analyzing the annual solar radiation change by hour for plant photosynthesis. Therefore, from this, the internal supply DLI (Day Light Integral) of the photosynthetic effective light amount for each crop is calculated for each sunlight hour, and a light recipe including the required value of the daily effective light amount for each crop is provided.

And, to predict the growth of crops inside the smart farm, the growth status of plants is analyzed from photos taken by the user app. Therefore, the similarity of the environmental simulation of excellent farms for optimal plant growth is measured from the environment supplied from the control system and transmitted to the control system in real time.

In addition, in order to convey the current condition of the plant to the smart farm operator, the condition of the plant is predicted from various environmental information supplied to the plant, and the necessary requirements are delivered to the plant and the smart farm operator from the predicted information.

According to embodiments, past growth environment data of excellent farms are stored, and crop yields are analyzed by analyzing the external environment, internal environment, soil condition, and light supply status for each crop season of the farm. And, based on the analyzed data, the current smart farm internal environment, nutrient solution, artificial light, etc. are controlled to adjust the optimal growth conditions for each growth period of excellent farms with good past yields.

Furthermore, environmental conditions are artificially controlled and maintained to enable harvesting similar to the high yields of the past.

And from this, a service is created that connects with actual farms within a virtual space to enable optimal production remotely.

1 is a diagram conceptually illustrating a method of simulating a growth environment for intelligent smart farm control according to an embodiment.
Figure 2 is a diagram showing the overall system applied to the growth environment simulation method for intelligent smart farm control according to one embodiment.
Figure 3 is a block diagram showing the configuration of a management information processing device applied to a growth environment simulation method for intelligent smart farm control according to an embodiment.
Figure 4 is a flow chart sequentially showing a growth environment simulation method for intelligent smart farm control according to an embodiment.

Figure 1 is a diagram for conceptually explaining a method of simulating a growth environment for intelligent smart farm control according to an embodiment.

As shown in Figure 1, one embodiment first maintains the growth environment of crops from environmental changes like an existing smart farm, and maintains the external air environment of a farm where crop yields were high in the past and the internal maintenance environment of the smart farm, Nutrient solution supply information, solar energy information for photosynthesis, etc. are analyzed. Therefore, we construct a system that controls the environment to produce yields similar to those of past excellent farms in the current smart farm operation farms, and intelligently controls various sensors and drive systems to control the smart farm environment.

To this end, the method of one embodiment is first, in the farm-related registration information processing device 100, for example, the manager collects growth information on excellent farms for a plurality of different crops from public data on excellent smart farm farms and public data on the Korea Meteorological Administration. , acquired by the management information processing device 200. Additionally, information on crop yield within the farm or region is collected.

Therefore, the management information processing device 200 uses the collected growth information and the crop yield information within the farm or region to analyze the relationship between growth information and yield.

In addition, the optimal supply baseline for essential energy required for growth is analyzed for each of these different crops and cropping seasons.

In addition, the effective daily solar light amount is predicted for each of several different regions, and the daily light supply within the smart farm is scheduled.

In addition, the growth conditions of the smart farm are predicted by analyzing real-time captured images of each crop for each crop.

So, based on this information, the sensors and drive systems inside the smart farm are intelligently controlled to maintain a growth state that mimics the environment in which past harvests were good.

Through this, the growth environment within the current smart farm is simulated by analyzing the growth environment with high yields in the past.

Therefore, the growth environment simulation method according to one embodiment stores the growth environment data of past excellent farms and analyzes the crop yield by analyzing the external environment, internal environment, soil condition, and light supply status for each crop season of the farm. . And, based on the analyzed data, the current smart farm internal environment, nutrient solution, artificial light, etc. are controlled to adjust the optimal growth conditions for each growth period of excellent farms with good past yields.

More specifically, it is as follows.

In one embodiment, the growth status and smart farm internal control data of excellent farms are collected by replicating the environment of past excellent farms, and the necessary supply baseline for each crop season is predicted from the collected data to control the smart farm environment. make it possible

To this end, when obtaining the growth information of excellent farms for each crop mentioned above, greenhouse environment information, past crop growth information, production volume, etc. are collected and stored for each region and crop from the open data of excellent smart farm farms. In addition, past daily DLI (Day Light Integral) is collected and stored from public data from the Korea Meteorological Administration, and it is calculated and stored as daily PPDF (Photosynthetic photon flux density) on an hourly basis.

Additionally, when analyzing the relationship between growth information and yield, the correlation between yield and external environmental factors provided by the smart farm system is analyzed to predict yield using machine learning. Therefore, the correlation between internal environmental factors, information such as nutrient supply and solar power supply, and yield is calculated.

In particular, the optimal supply baseline for essential energy required for growth is analyzed for each crop and cropping season, and in this case, the daily photosynthetic effective light amount for each region is calculated based on the light compensation point and light saturation point for each crop. In addition, real-time PPFD is measured from the calculated value of the daily photosynthetic effective light delivered inside the smart farm by applying the solar light transmittance according to the material of the smart farm structure and the measured value of the PAR (Photosynthetically Active Radiation) sensor installed inside the smart farm. do. Therefore, the cumulative light amount standard is set by matching the optimal pattern within the crop's DLI standard range.

In other words, the PPFD of the target area is calculated by analyzing the annual solar radiation change in hourly average solar radiation for plant photosynthesis. Therefore, from this, the internal supply DLI for each daylight hours is calculated from the photosynthetic effective light amount for each crop, thereby providing a light recipe including the required value of the daily effective light amount for each crop.

In this way, one embodiment predicts the daily effective solar light amount for each region and schedules the daily light supply inside the smart farm. In other words, the daily light supply schedule to be supplied within the smart farm is performed based on the DLI baseline set above. Therefore, by analyzing real-time solar power supply information, a time schedule is created that intelligently and effectively supplies the daily cumulative amount of light, thereby controlling light retention and shading.

Additionally, one embodiment analyzes the growth state of plants from photos taken by a user app to predict crop growth within a smart farm. In addition, the similarity of environmental simulations of excellent farms for optimal plant growth is measured from the environment supplied from the control system and transmitted to the control system in real time.

In addition, in order to convey the current condition of the plant to the smart farm operator, the condition of the plant is predicted from various environmental information supplied to the plant, and the necessary needs are delivered to the plant and smart farm operator from the predicted information.

Specifically, the growth conditions of the smart farm are predicted by analyzing real-time captured images of the crop's growth status. In this case, the user takes a picture of the crop's condition in real time using a smartphone app and sends it. Therefore, the nutritional status of the plant is predicted from the transmitted photos, and the degree of growth is predicted by comparing this with the growth status of each crop.

Additionally, the schedule for supplying additional nutrient sources to plants can be re-created from information predicting the growth state of the crop. In addition, it also performs app service processing by delivering plant status information and supply plans for future plant growth to the user app so that the user can refer to smart farm operations.

In addition, the sensors and driving systems within the smart farm are intelligently controlled to maintain a growth state that mimics the environment in which past harvests were good. In this case, the various driving systems of the smart farm internal system are intelligently controlled based on previously calculated or predicted scheduling. Operate it with So, it is operated to adjust the growth conditions to the environment of the time when the harvest was good.

Additionally, in this control method, information on external environmental factors for control is obtained, such as real-time smart farm monitoring information, nutrient solution supply and harvest schedule information, energy supply and use information within the smart farm, and real-time abnormal climate information. Additionally, smart farm operators may directly calculate and enter information.

Figure 2 is a diagram showing the overall system applied to the growth environment simulation method for intelligent smart farm control according to one embodiment.

As shown in Figure 2, the system applied to the growth environment simulation method according to one embodiment is largely comprised of a farm-related registration information processing device 100, a management information processing device (or manager terminal) 200, and a cultivation facility ( It includes a sensor and a driving device) (300).

The farm-related registration information processing device 100 is used to obtain growth information of excellent farms for each crop. For example, an external device that holds public data on excellent smart farm farms, such as a farm (or crop) brokerage device or a Korea Meteorological Administration management information processing device. Therefore, greenhouse environment information, past crop growth information, production volume, etc. are collected and stored by region and crop from the public data of excellent smart farm farms. In addition, past daily DLI (Day Light Integral) is collected and stored from public data from the Korea Meteorological Administration, and this is calculated and stored as daily PPDF (Photosynthetic photon flux density) on an hourly basis.

The management information processing device 200 maintains the same growth environment of crops from environmental changes as in existing smart farms, and maintains the external air environment of farms with high crop yields in the past, the internal maintenance environment of the smart farm, nutrient solution supply information, Analyze solar information for photosynthesis. Therefore, current smart farm operations control the environment to produce yields similar to those of past excellent farms. And, in order to control this environment, various sensors and drive systems are adjusted to suit the environment. Specifically, according to one embodiment, the management information processing device 200 acquires growth information on excellent farms for a plurality of different crops from public data on excellent smart farm farms and public data on the Korea Meteorological Administration. Additionally, information on the crop yield within the farm or region is obtained. Then, the relationship between growth information and yield is analyzed using the collected growth information and the crop yield within the farm or region. In addition, the optimal supply baseline for essential energy required for growth is analyzed for each of these different crops and cropping seasons. In addition, the effective daily solar light amount is predicted for each of several different regions, and the daily light supply within the smart farm is scheduled. In addition, the growth conditions of the smart farm are predicted by analyzing real-time captured images of each crop for each crop. So, based on this information, the sensors and drive systems inside the smart farm are intelligently controlled to maintain a growth condition that mimics the environment in which past harvests were good.

The cultivation facility 300 is installed in different places where the user wants to cultivate, and operates the internal sensors and drive system under the control of the management information processing device to maintain a growth state that mimics the environment in which good harvests were achieved in the past. do.

Figure 3 is a block diagram showing the configuration of a management information processing device applied to a growth environment simulation method for intelligent smart farm control according to an embodiment.

As shown in FIG. 3, the management information processing device 200 applied to the growth environment simulation method according to one embodiment largely includes a key signal input unit 201, an I/F unit 202, a storage medium 203, It includes a display unit 204 and a main processing unit 205.

The key signal input unit 201 provides various setting information for simulating a growth environment according to an embodiment, such as device information about the farm-related registration information processing device 100 and cultivation facility 300, and crop and region information. Receive user setting information such as input.

The I/F unit 202 is connected to an external farm-related registration information processing device 100, a cultivation facility 300, a camera, etc., to collect growth information or to create a growth state that simulates an environment in which past harvests were good. It provides various control information for maintenance and also receives images of each crop.

The storage medium 203 contains such growth information and various analysis information, such as information analyzing the relationship between growth information and yield, or analyzing the optimal supply baseline for essential energy required for growth for each crop and cropping season. Information is classified and stored by crop, cropping season, and region.

The display unit 204 displays various growth information and analysis information under the control of the main processing unit 205.

The main processing unit 205 controls each of the above-described units, and as described above, maintains the same growth environment for crops from various environmental changes. In addition, by analyzing the external air environment of farms that had high crop yields in the past, the internal maintenance environment of the smart farm, nutrient solution supply information, and solar energy information for photosynthesis, the current smart farm operation farms calculate yields similar to those of past excellent farms. Controls the environment for

Figure 4 is a flow chart sequentially showing a growth environment simulation method for intelligent smart farm control according to an embodiment.

As shown in Figure 4, the growth environment simulation method for intelligent smart farm control according to one embodiment first assumes the growth environment simulation method for intelligent smart farm control in the same manner as the existing method.

In this state, according to one embodiment, first, the farm-related registration information processing device collects the growth information of each excellent farm for a plurality of different crops (S401). Additionally, in these cases, information on the crop yield within the farm or region is collected.

In other words, greenhouse environment information, past crop growth information, production volume, etc. are collected and stored by region and crop from the public data of excellent smart farm farms. In addition, past daily DLI is collected and stored from public data from the Korea Meteorological Administration, and it is calculated and stored as daily PPDF in hourly units.

Then, the relationship between growth information and yield is analyzed using the collected growth information and the crop yield information within the farm or region (S402).

In other words, to predict yield using machine learning, the correlation between yield and external environmental factors provided by the smart farm system is analyzed. Therefore, the correlation between internal environmental factors, information such as nutrient supply and solar power supply, and yield is calculated.

Next, the optimal supply baseline for essential energy required for growth is analyzed for each crop and cropping season (S403).

In this case, the daily photosynthetic effective light amount for each region is calculated based on the light compensation point and light saturation point for each crop. In addition, the real-time PPFD is measured from the daily photosynthetic effective light delivered inside the smart farm, calculated by applying the solar transmittance according to the material of the smart farm structure, and measured values such as the PAR sensor installed inside the smart farm. Therefore, the cumulative light amount standard is set by matching the optimal pattern within the crop's DLI standard range.

Then, the effective daily solar light amount is predicted for each region, and the daily light supply within the smart farm is scheduled (S404).

In other words, the daily light supply schedule to be supplied within the smart farm is performed based on the DLI baseline set above. Therefore, by analyzing real-time solar power supply information, a time schedule is created that intelligently and effectively supplies the daily cumulative amount of light, thereby controlling light retention and shading.

In addition, the growth conditions of the smart farm are predicted by analyzing real-time images of the growth status of each crop (S405).

In this case, the user takes pictures of the crop's condition in real time using a smartphone app and sends them. Therefore, the nutritional status of the plant is predicted from the transmitted photos, and the degree of growth is predicted by comparing this with the growth status of each crop.

Therefore, based on these various analysis information, the sensors and drive system inside the smart farm are intelligently controlled to maintain a growth state that simulates an environment with good past harvests (S406).

In other words, the various driving systems of the smart farm internal system are operated intelligently based on previously calculated or predicted scheduling. So, it is operated to adjust the growth conditions to the environment of the time when the harvest was good.

Therefore, the growth environment simulation method according to one embodiment first stores the growth environment data of past excellent farms, analyzes the external environment, internal environment, soil condition, and light supply status for each crop season of the farm, and determines the crop yield. Analyze. And, based on the analyzed data, the current smart farm internal environment, nutrient solution, artificial light, etc. are controlled to adjust the optimal growth conditions for each growth period of excellent farms with good past yields.

As described above, one embodiment maintains the same growth environment for crops from various environmental changes as before. In addition, by analyzing the external air environment of farms that had high crop yields in the past, the internal maintenance environment of the smart farm, nutrient solution supply information, and solar energy information for photosynthesis, the current smart farm operation farms calculate yields similar to those of past excellent farms. Controls the environment for

Therefore, the current smart farm internal environment, nutrient solution, artificial light, etc. are controlled to adjust the optimal growth conditions for each growth period of excellent farms that had good yields in the past.

Furthermore, environmental conditions are artificially controlled and maintained to enable harvesting similar to the high yields of the past.

And from this, a service is created that connects with actual farms within a virtual space to enable optimal production remotely.

100: Farm-related registration information processing device
200: Management information processing device
300: Cultivation facility

Claims (3)

In a method of simulating a growing environment for intelligent smart farm control,
In the smart farm excellent farm open data of the external farm-related registration information processing device, excellent farm growth information, including greenhouse environment information, past crop growth information, and production volume, for each multiple different crops is collected by region and crop. The first step is collecting;
Obtain the past daily DLI (Day Light Integral) from the public data of the Korea Meteorological Administration registered and managed by the Korea Meteorological Administration and convert it into daily PPDF (Photosynthetic photon flux density) on an hourly basis. The second step of collecting growth information;
A third step of analyzing the relationship between growth information and yield using each of the collected growth information and the crop yield information within the farm or region;
A fourth step of analyzing the optimal supply baseline for essential energy required for growth for each crop and cropping season;
A fifth step of calculating the daily photosynthetic effective light amount for each region based on the light compensation point and light saturation point for each crop in each region;
The sixth step of measuring real-time PPFD from the daily photosynthetic effective light delivered inside the smart farm, calculated by applying the solar light transmittance according to the material of the smart farm structure, and the measured value of the PAR (Photosynthetically Active Radiation) sensor installed inside the smart farm. ;
A seventh step of setting a cumulative light intensity standard by matching the optimal pattern within the DLI standard range of the crop;
An eighth step of analyzing real-time solar power supply information based on the set DLI baseline and creating a time schedule for supplying the daily cumulative amount of light to be supplied within the smart farm;
A ninth step of providing a light recipe including the necessary value of the daily effective light amount for each crop by calculating the internally supplied DLI for each sunlight hour based on the photosynthetic effective light amount for each crop;
A tenth step of predicting the growth conditions of the smart farm by analyzing real-time captured images of the growth status of each crop for each crop;
An 11th step of rescheduling the supply of additional nutrient sources to the plant using the predicted growth condition information;
A twelfth step of measuring the similarity of environmental simulation of excellent farms for plant growth from the predicted growth condition information and supplied environmental information; and
A 13th step of controlling the operations of sensors and drive systems within the smart farm based on the information from the first to twelfth steps to maintain a growth state simulating an environment in which past yields were good;
A growth environment simulation method for intelligent smart farm control comprising: In claim 1,
The third step is,
To predict yield using machine learning, the correlation between yield and external environmental factors provided by the smart farm system is analyzed, and the correlation between internal environmental factors, information on nutrient supply and solar power supply, and yield is calculated. ;
A growth environment simulation method for intelligent smart farm control characterized by . In claim 2,
The ninth step is,
Step 9-1 of taking and transmitting a photo of the state of the crop using a smartphone app in real time according to the user's key operation;
Step 9-2 of predicting the nutritional status of the plant from the transmitted photo; and
Step 9-3 of predicting the degree of growth by comparing the predicted state and the growth state for each cropping period;
A growth environment simulation method for intelligent smart farm control comprising:

Images