CN114637351B - Greenhouse environment regulation and control method and system for facility crops - Google Patents

Abstract

The invention provides a greenhouse environment regulation method and a greenhouse environment regulation system for facility crops, wherein the greenhouse environment regulation method comprises the following steps: collecting crop variety information and crop state information of a first crop in a first greenhouse; obtaining environmental information of a first crop within the first greenhouse; predicting the growth condition of the first crop by adopting an unequal weight combination prediction method according to the crop variety information, the crop state information and the environment information to obtain a first prediction result; obtaining information on the expected growth condition of the first crop; judging whether the first prediction result reaches the expected growth condition information or not, if not, obtaining a first regulation instruction, and obtaining a standard matching degree training set of the environmental information in the first greenhouse and the crop variety training set; training a feedforward neural network and constructing an environment control model; and obtaining adjustment environment information in a first greenhouse corresponding to the first crop, wherein the adjustment environment information comprises adjustment illumination information and adjustment temperature and humidity information.

Description

A method and system for controlling the environment of a facility crop greenhouse

technical field

The invention relates to the technical field related to artificial intelligence, in particular to a method and system for controlling the environment of a facility crop greenhouse.

Background technique

Facility crops refer to a new type of agricultural production method that uses engineering technology to control environmental conditions and achieve efficient production of animals and plants under controlled environmental conditions. For example, plants such as vegetables are grown in facility greenhouses to create a production environment that is beneficial to plants. , Eliminate the interference of environmental elements unfavorable to plants, and then achieve the purpose of improving crop yield and quality.

The control of the crop growth environment in the production of facility crops is the most important link to ensure the healthy growth of crops. At present, there are generally two ways to adjust the environment: one is to adapt the facility environment to the growth status of the crops, that is, the environment Adjustment after the elements have had adverse effects on crops cannot achieve the purpose of pre-adjustment; the second is to predict the growth status of facility crops, and then achieve pre-adjustment, but due to the relatively low Single, the accuracy is difficult to guarantee.

However, in the process of realizing the technical solution of the invention in the embodiment of the application, the present application found that the above-mentioned technology has at least the following technical problems:

In the prior art, there is a technical problem that the accuracy cannot be guaranteed due to the relatively single dimension of the assessment benchmark for the crop prediction process.

Contents of the invention

The embodiment of the present application provides a method and system for controlling the greenhouse environment of facility crops, which solves the technical problem in the prior art that the accuracy of the crop prediction process is difficult to guarantee due to the relatively single dimension of the evaluation benchmark for the crop prediction process. By collecting the species and growth state information of the facility crops, and then collecting the environmental information in the facility, using the unequal weight combination prediction method combined with the crop variety, growth state information, and environmental information to perform multiple predictions and then integrate them to obtain the crop growth state prediction results , when the growth state prediction results do not meet the expected growth conditions, an environmental control model is constructed to adjust the environmental information in the facility. Based on the unequal weighted combination prediction method, the prediction results of multiple prediction methods can be integrated to improve the environmental accuracy of the facility crop greenhouse. technical effect.

In view of the above problems, the embodiment of the present application provides a method and system for controlling the environment of a greenhouse for facility crops.

In the first aspect, the embodiment of the present application provides a method for controlling the greenhouse environment of facility crops, wherein the method includes: collecting the crop variety information and crop status information of the first crop in the first greenhouse; Environmental information in the first greenhouse; according to the crop variety information, the crop status information and the environmental information, the growth of the first crop is predicted by using the unequal weighted combination forecasting method to obtain the first Prediction result; obtaining the expected growth information of the first crop; judging whether the first forecast result has reached the expected growth information; if the first forecast result has not reached the expected growth information, obtaining the first An adjustment instruction; according to the first adjustment instruction, obtain a standard matching degree training set between the environmental information in the first greenhouse and the crop variety training set; according to the standard matching degree training set and the crop variety training set before training feed the neural network to construct an environmental control model; input the crop variety information of the first crop and the standard matching degree of the first crop into the environmental control model to obtain the first crop corresponding to the first crop The adjusted environment information in the greenhouse, the adjusted environment information includes adjusted light information and adjusted temperature and humidity information.

On the other hand, an embodiment of the present application provides an environmental control system for a facility crop greenhouse, wherein the system includes: a first collection unit configured to collect the crop variety of the first crop in the first greenhouse information and crop status information; a first obtaining unit, the first obtaining unit is used to obtain the environmental information of the first crop in the first greenhouse; a first processing unit, the first processing unit is used to obtain the environmental information of the first crop in the first greenhouse; The crop variety information, the crop status information, and the environmental information use the unequal weighted combination forecasting method to predict the growth of the first crop to obtain a first forecast result; the second obtaining unit, the first The second obtaining unit is used to obtain the expected growth information of the first crop; the first judging unit is used to judge whether the first prediction result reaches the expected growth information; the third obtaining unit , the third obtaining unit is used to obtain a first adjustment instruction if the first prediction result does not reach the expected growth situation information; a fourth obtaining unit, the fourth obtaining unit is used to adjust according to the first An instruction to obtain a standard matching degree training set between the environmental information in the first greenhouse and the crop variety training set; a first construction unit, the first construction unit is used to obtain the standard matching degree training set and the crop variety The training set trains the feedforward neural network to construct an environmental control model; the second processing unit is used to input the crop variety information of the first crop and the standard matching degree of the first crop into the The environment control model is used to obtain the adjusted environment information in the first greenhouse corresponding to the first crop, and the adjusted environment information includes adjusted illumination information and adjusted temperature and humidity information.

In the third aspect, the embodiment of the present application provides a facility crop greenhouse environment control system, including a memory, a processor, and a computer program stored in the memory and operable on the processor, wherein the processor executes the program When implementing the steps of any one of the methods described in the first aspect.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method described in any one of the first aspect is implemented.

One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

Since the crop variety information and crop status information of the first crop in the first greenhouse are collected; the environmental information of the first crop in the first greenhouse is obtained; according to the crop variety information, the crop status information and For the environmental information, use the unequal weighted combination forecasting method to predict the growth of the first crop, and obtain the first prediction result; obtain the expected growth information of the first crop; judge whether the first prediction result is Reach the expected growth situation information; if the first prediction result does not reach the expected growth situation information, obtain a first adjustment instruction; according to the first adjustment instruction, obtain the environmental information and crops in the first greenhouse The standard matching training set of the variety training set; the feedforward neural network is trained according to the standard matching training set and the crop variety training set, and an environmental control model is constructed; the crop variety information and the crop variety information of the first crop are combined The standard matching degree of the first crop is input into the environmental control model, and the adjusted environmental information in the first greenhouse corresponding to the first crop is obtained, and the adjusted environmental information includes the technology of adjusting light information and adjusting temperature and humidity information The scheme collects the variety and growth state information of facility crops, and then collects the environmental information in the facility, and uses the unequal weight combination prediction method to combine the crop variety, growth state information, and environmental information to make multiple predictions and then integrate them to obtain the growth state of the crops. Forecast results, when the growth state prediction results do not meet the expected growth conditions, an environmental control model is constructed to adjust the environmental information in the facility, based on the unequal weighted combination prediction method, the prediction results of multiple prediction methods can be integrated, and the greenhouse environment of facility crops can be improved. The technical effect of accuracy.

The above description is only an overview of the technical solution of the present application. In order to better understand the technical means of the present application, it can be implemented according to the contents of the description, and in order to make the above and other purposes, features and advantages of the present application more obvious and understandable , the following specifically cites the specific implementation manner of the present application.

Description of drawings

Fig. 1 provides a schematic flow chart of a greenhouse environment control method for facility crops according to the embodiment of the present application;

Fig. 2 provides a schematic flow chart of the method for obtaining the amount of incoming light in a greenhouse environment regulation method for facility crops according to an embodiment of the present application;

Fig. 3 provides a schematic flow chart of a method for obtaining light intensity in a greenhouse environment regulation method for facility crops according to an embodiment of the present application;

Fig. 4 provides a schematic structural diagram of a greenhouse environment control system for facility crops according to the embodiment of the present application;

Fig. 5 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.

Explanation of reference numerals: first acquisition unit 11, first acquisition unit 12, first processing unit 13, second acquisition unit 14, first judgment unit 15, third acquisition unit 16, fourth acquisition unit 17, first construction Unit 18 , second processing unit 19 , electronic device 300 , memory 301 , processor 302 , communication interface 303 , bus architecture 304 .

Detailed ways

The embodiment of the present application provides a method and system for controlling the greenhouse environment of facility crops, which solves the technical problem in the prior art that the accuracy of the crop prediction process is difficult to guarantee due to the relatively single dimension of the evaluation benchmark for the crop prediction process. By collecting the species and growth state information of the facility crops, and then collecting the environmental information in the facility, using the unequal weight combination prediction method combined with the crop variety, growth state information, and environmental information to perform multiple predictions and then integrate them to obtain the crop growth state prediction results , when the growth state prediction results do not meet the expected growth conditions, an environmental control model is constructed to adjust the environmental information in the facility. Based on the unequal weighted combination prediction method, the prediction results of multiple prediction methods can be integrated to improve the environmental accuracy of the facility crop greenhouse. technical effect.

Application overview

Facility crops refer to a new type of agricultural production method that uses engineering technology to control environmental conditions and achieve efficient production of animals and plants under controlled environmental conditions. For example, plants such as vegetables are grown in facility greenhouses to create a production environment that is beneficial to plants. , eliminate the interference of environmental factors that are unfavorable to plants, and then achieve the purpose of improving crop yield and quality. The control of crop growth environment in the production of facility crops is the most important link to ensure the healthy growth of crops. Currently, there are generally Two types: one is to make adaptive adjustments to the facility environment according to the growth state of the crops, that is, to adjust after the environmental elements have adversely affected the crops, and the purpose of pre-adjustment cannot be achieved; the other is to adjust the growth state of the facility crops Forecasting, and then to achieve pre-adjustment, but due to the relatively single dimension of the crop prediction process evaluation benchmark, the accuracy is difficult to guarantee, but in the prior art, due to the relatively single evaluation standard dimension of the crop prediction process, there is difficulty in accuracy. Safeguard technical issues.

In view of the above technical problems, the general idea of the technical solution provided by this application is as follows:

An embodiment of the present application provides a method for controlling the greenhouse environment of facility crops, wherein the method includes: collecting the crop variety information and crop status information of the first crop in the first greenhouse; Environmental information in the greenhouse; according to the crop variety information, the crop status information and the environmental information, the growth of the first crop is predicted by using an unequal weighted combination prediction method to obtain a first prediction result; obtain The expected growth information of the first crop; judging whether the first predicted result has reached the expected growth information; if the first predicted result has not reached the expected growth information, obtaining a first adjustment instruction; according to The first adjustment instruction is to obtain a standard matching degree training set between the environmental information in the first greenhouse and the crop variety training set; train a feedforward neural network according to the standard matching degree training set and the crop variety training set, Constructing an environmental control model; inputting the crop variety information of the first crop and the standard matching degree of the first crop into the environmental control model to obtain the adjustment in the first greenhouse corresponding to the first crop Environment information, the adjustment of environment information includes adjustment of illumination information and adjustment of temperature and humidity information.

After introducing the basic principles of the present application, various non-limiting implementations of the present application will be specifically introduced below in conjunction with the accompanying drawings.

Embodiment one

As shown in Figure 1, the embodiment of the present application provides a method for controlling the greenhouse environment of facility crops, wherein the method includes:

S100: collecting crop variety information and crop status information of the first crop in the first greenhouse;

S200: Obtain environmental information of the first crop in the first greenhouse;

Specifically, facility crops include: facility cultivation, such as greenhouse vegetables, fruits, etc.; facility breeding, such as animal breeding; facility edible fungi, such as the cultivation of beneficial bacteria such as lactic acid bacteria. Different facility crops have different dependencies on the growth environment. In short, in order to ensure the crop growth environment elements: such as temperature, humidity, oxygen concentration, carbon dioxide concentration, pH, salinity, light and other information are completely controllable, generally use large-scale A walk-in phytotron serves as a growing environment for crops.

The first greenhouse refers to an area that provides a growth environment for crops, and the internal growth environmental elements must be fully controllable; the environmental information in the first greenhouse refers to the information on various environmental elements in the first greenhouse, Exemplarily: such as a large walk-in artificial climate chamber, which can control environmental element information such as indoor temperature, light, carbon dioxide concentration, and pH.

The first crop refers to the crops cultivated in the first greenhouse, which can be planted crops, cultivated crops and beneficial bacteria crops. Exemplarily: as grape crops cultivated in large-scale walk-in artificial climate chambers, in It is not affected by the natural environment, and grapes can be cultivated out of season according to demand, with a high degree of freedom. The crop variety information refers to the type of the first crop, for example: grape, cabbage, orange and other variety information; the crop status information refers to the real-time growth status index information of the first crop, for example: Growth status indicators of grapes cultivated in a large walk-in artificial climate chamber, including but not limited to grape size, grape color, grape leaf color, grape chlorophyll content, net photosynthetic rate, superoxide dismutase enzyme and malondialdehyde content , training time and other indicator information.

By collecting crop variety information and crop status information, different crop varieties have different ideal growth states in the same environment. By storing crop variety information and crop status information in one-to-one correspondence, it is convenient for the later step to quickly Evaluate the insufficiency of real-time crop status information to facilitate timely adjustments.

S300: According to the crop variety information, the crop status information and the environmental information, use the unequal weight combination forecasting method to predict the growth of the first crop, and obtain a first forecast result;

Specifically, the unequal weight combination forecasting method refers to integrating multiple forecasting methods to process crop variety information, crop status information and environmental information to predict the growth status of the first crop. For example, the regression forecasting method is used based on Historical data evaluates the crop status information of the current crop variety information and crop status information at a certain time node in the future; then uses the Kalman filter prediction method to predict the growth status of the crop at a preset time node in the future based on the current crop variety information and environmental information predict.

Furthermore, the regression prediction method can combine historical data to obtain the trend relationship of crop status information over time, and then evaluate the crop status information at a certain time point in the future; the Kalman filter prediction method can be aimed at dynamically changing environmental information, only Consider the crop status of the previous time node to realize the prediction of the crop status of the next time node.

Furthermore, the first prediction result refers to the information representing the growth state of the crop obtained by integrating the two prediction results with different weights. The way of assigning weights is an example without limitation: input the two prediction results into 6 Based on the weight distribution channel constructed by facility crop experts for information interaction and isolation, six weight distribution results are obtained, and then the average value of the weights obtained by the two prediction results is calculated separately to obtain the weights of the two prediction results, and then integrated to obtain the first prediction result.

The growth of the first crop is predicted by the unequal weighted combination prediction method. Compared with relying on a single prediction method, the first prediction result integrating multiple prediction results can more accurately and objectively characterize the estimated growth state of the first crop.

S400: Obtain the expected growth information of the first crop;

S500: Judging whether the first prediction result meets the expected growth situation information;

Specifically, the expected growth information of the first crop refers to the optimal growth state of the first crop at different cultivation time nodes in the first greenhouse artificially set based on theory, for example: as in a large step For the grape crops cultivated in the indoor artificial climate, the indicators of the expected growth information correspond to the indicators of the growth status one by one, and the indicators of the expected growth information are given specific values and stored in correspondence with the cultivation time nodes of the grape crops, which is convenient for future steps. Call for feedback in a timely manner.

Comparing the growth state index of the first crop corresponding to the first prediction result under the same time node and the expected growth information one by one, storing the difference information between the predicted growth state index and the expected growth information of the first crop, The storage form is exemplarily such as: [indicator type, unqualified degree], if the index information is the content of malondialdehyde in grapes, it is in the form of: [content of malondialdehyde, predicted value-expected value], etc. By comparing the first prediction result with the expected growth situation information, and obtaining the difference degree information of the difference index information, reference data can be provided for the subsequent environmental adjustment.

S600: If the first prediction result does not meet the expected growth situation information, obtain a first adjustment instruction;

Specifically, the first adjustment instruction refers to that after the traversal and comparison between the first forecast result and the expected growth situation information is completed, in order to ensure that the growth state of the first crop meets the expected growth situation information, the generation of information on the first greenhouse Instructions for regulating environmental information. By timely adjusting the environmental information in the first greenhouse, the occurrence of difference information between the first forecast result and the expected growth information is avoided, thereby achieving the technical effect of guaranteeing the growth status of the first crop in advance.

S700: Obtain a standard matching degree training set between the environmental information in the first greenhouse and the crop variety training set according to the first adjustment instruction;

Specifically, the crop variety training set refers to the information of various crop varieties cultivated in the first greenhouse, for example: apples, oranges, grapes and other varieties cultivated in large walk-in artificial climate chambers; The above-mentioned standard matching degree training set refers to the difference degree information obtained by matching the optimal first greenhouse environment information in different growth states of crop varieties, and then comparing with the current environment information, for example: For a large walk-in artificial climate chamber, the controllable environmental elements include information such as temperature, light, pH, and dry humidity. Apples, oranges, and grapes correspond to three sets of temperature, light, pH, and dry humidity at the same time node. The specific value of the same crop species at different time nodes also corresponds to the specific values of multiple sets of temperature, light, pH, dry humidity and other information, and the matched environmental element information is compared with the real-time environmental information to obtain the standard matching training set.

When the first adjustment command is generated, the crop variety training set and the standard matching training set are immediately generated to provide training data for the subsequent construction of the environmental control model, which improves the adaptability of the output control parameters to the first crop and the first greenhouse.

S800: Train a feed-forward neural network according to the standard matching degree training set and the crop variety training set to construct an environmental control model;

Specifically, the optimal environment information in multiple sets of standard matching degree training sets is used as output identification information, and multiple sets of crop variety training sets and multiple sets of standard matching degree training sets are set as input training data sets; preferably, the corresponding Multiple sets of output identification information and input training data sets are divided into a ratio of 9:1, 9 ratios of the data sets are used to build the model, and 1 ratio of the data set is used to measure the stability of the model.

The environmental control model is an intelligent model based on feed-forward neural network training. After the neural network model framework is constructed based on the feed-forward neural network, multiple groups of output identification information and input training data sets of 9 ratios are called to pair with the feed-forward neural network. Build a neural network model framework for training. When the model reaches the preset accuracy, use a data set with a ratio of 1 to evaluate the stability of the model accuracy. Repeat this process to complete multiple iterations of training, and then complete the construction of the environmental control model. The construction is complete The final environmental control model can match the more accurate optimal environmental information adapted to the first crop in the adjusted environmental information in the first greenhouse when inputting the standard matching degree between the crop variety and the first crop.

S900: Input the crop variety information of the first crop and the standard matching degree of the first crop into the environmental control model to obtain adjusted environmental information in the first greenhouse corresponding to the first crop, The adjusting environment information includes adjusting illumination information and adjusting temperature and humidity information.

Specifically, after the construction of the environmental control model is completed, input the crop variety information of the first crop and the standard matching degree of the first crop into the environmental control model to obtain the adjustment of environmental elements that can lead the first crop to grow to the desired growth state Information, an exemplary output format is: a=[adjustment index, adjustment degree], where a is a vector, recorded as the adjustment environment information.

Further, some preferred examples of adjusting environmental information: Adjustment of environmental indicators of grape crops: Adjusting light information: a=[lighting information, light intensity, light duration, etc.]; adjusting temperature information: b=[temperature information, temperature value] ;Adjust humidity information: c=[humidity information, moisture content adjustment value], etc. The environmental information of the first greenhouse is adaptively adjusted by adjusting the environmental information, thereby ensuring that the growth state of the first crop reaches the desired growth state.

Further, based on the crop variety information, the crop status information and the environmental information, the unequal weighted combination prediction method is used to predict the growth of the first crop to obtain a first prediction result, step S300 includes:

S310: Obtain a second prediction result through a regression prediction method according to the crop variety information and the crop state information;

S320: Obtain a third prediction result through a Kalman filter prediction method according to the crop variety information and the environmental information;

S330: Based on the second prediction result and the third prediction result, the unequal weighted combination forecasting method is used to predict the growth of the first crop to obtain a first prediction result.

Specifically, the second prediction result refers to the prediction result obtained by using the regression prediction method to evaluate the future crop state information based on the crop variety information and crop state information. The evaluation method is preferably collected by historical data. The growth state information of different crop variety information at different cultivation time nodes can be obtained by combining multiple sets of crop variety information and growth state information stored in time series. Under the premise of the current crop variety information and crop state information, the The change trend of the crop state information in the next step is regressively evaluated, and the implementation method is not limited. An example: the growth state information of different crop varieties in the first greenhouse can be used to train the neural network model based on the growth state information at different cultivation time nodes The intelligent model constructed can then obtain a model for evaluating future crop status information based on crop variety information and crop status information. Since the data processed by this model is generally structured data, the simplest backpropagation neural network model can be used , which can speed up the training speed and processing efficiency.

The third prediction result refers to the result of using the Kalman filter prediction method to evaluate the crop variety information and environmental information on the subsequent growth state of the crop. The characteristic of the Kalman filter prediction method is that it only needs to know the prediction result of the previous state The error of the future state can be determined, which is suitable for the environmental information that needs dynamic changes. The Kalman filter prediction method can determine the growth state information of the crop variety in the environmental information at the current time node and the expected growth state at the current time node. The deviation of the information can be used to obtain the prediction results of the future crop growth status information.

After obtaining the second prediction result and the third prediction result, integrate the second prediction result and the third prediction result using the unequal weight combination prediction method in step S300, and then obtain the first prediction result, through multiple evaluations dimension, which improves the credibility of the prediction results.

Further, after inputting the crop variety information of the first crop and the standard matching degree of the first crop into the environmental control model, step S900 further includes:

S910: Construct and train a discrimination network according to the standard matching degree training set, the crop variety training set and the generated data of the environmental control model;

S920: Obtain the accuracy rate of the output data of the environmental control model based on the identification network;

S930: Filter the output data of the environment control model according to the accuracy rate.

Specifically, in order to ensure the accuracy of the output information of the environmental control model, the training data is used to construct the identification network in parallel, and the accuracy of the output value is evaluated when the environmental control model is completed in the subsequent step; the identification network refers to the use of standard The matching degree training set and the crop variety training set are used as the input training data set, and the generated data satisfying the preset accuracy of the environmental control model is used as the output identification data to construct a system for evaluating the accuracy of the output information of the environmental control model.

The screening of the output data of the environmental control model can be achieved through the identification network, that is, the environmental adjustment information output by the environmental control model does not all meet the preset accuracy, and only the environmental adjustment information that meets the preset accuracy is adjusted, which will not meet the preset accuracy. The accurate environmental adjustment information is marked and sent to the staff for processing, which improves the fault tolerance rate of the model.

Further, the method also includes S1000:

S1010: Obtain the greenhouse structure of the first greenhouse;

S1020: Obtain light input according to the greenhouse structure of the first greenhouse;

S1030: Obtain the light-transmitting material of the first greenhouse;

S1040: Obtain light intensity according to the light-transmitting material;

S1060: Based on the adjusted illumination information, obtain first supplementary light information according to the incoming light amount and the incoming light intensity.

Specifically, the amount of light information adjustment generally involves the amount and intensity of incoming light, so it is necessary to change the light transmittance of the first greenhouse, that is, the structure of the greenhouse. An example without limitation is as follows:

The greenhouse structure of the first greenhouse refers to the internal structure characteristics of the first greenhouse, for example, information such as: light entrance area, light entrance area area, light entrance angle, greenhouse height, greenhouse laying angle toward the light surface, etc.; The amount of light entering refers to the amount of light entering the first greenhouse within a preset time, preferably using the light entering time for indirect characterization, and the preset time is preferably 24 hours; the light-transmitting material refers to the light entering surface of the first greenhouse The material information, for example: such as glass type, glass color, glass thickness and other information; the light intensity refers to the acceptable light intensity interval obtained according to the material information of the light entrance surface of the first greenhouse and the current progress Light intensity, where the intensity of incoming light can be characterized by brightness.

The first supplementary light information refers to adjusting the amount of incoming light and the intensity of incoming light according to the adjusted light information to achieve the result after adjusting the preset adjustment amount in the light information, thereby achieving the goal of ensuring the first crop in the first greenhouse. The technical effect of healthy growth.

Further, as shown in FIG. 2, based on the greenhouse structure according to the first greenhouse, the amount of incoming light is obtained, and step S1020 includes:

S1021: Determine whether the greenhouse structure is a single-roof greenhouse;

S1022: If the greenhouse structure is a single-roof greenhouse, obtain the elevation angle of the rear roof, the intersection angle between the front roof and the ground, and the length of the rear slope of the first greenhouse;

S1023: Calculate and obtain the incoming light amount according to the elevation angle of the rear roof, the intersection angle between the front roof and the ground, and the length of the rear slope.

Specifically, generally speaking, the greenhouse structure will be set as a single-roof greenhouse, which is convenient for adjusting the amount of light. For a single-roof greenhouse: in order to ensure sufficient sunlight exposure, the sloped roof in the east-west direction is generally used; the rear roof The elevation angle refers to the raising angle of the sloping roof on the west side relative to the ground, and the intersection angle between the front roof and the ground refers to the angle of intersection of the sloping roof on the east side relative to the ground; the length of the back slope Refers to the roof length information of the rear roof and the front roof. According to the elevation angle of the rear roof, the intersection angle between the front roof and the ground, and the length of the back slope, the duration of light entering per unit area within a preset time can be determined, which is recorded as the amount of light entering, which is convenient for subsequent information feedback processing.

Further, as shown in FIG. 3 , based on the light-transmitting material, the incoming light intensity is obtained. Step S1040 includes:

S1041: Obtain the light attenuation intensity of the light-transmitting material according to the light-transmitting material;

S1042: Obtain real-time light intensity;

S1043: Obtain the incoming light intensity according to the real-time light intensity and the light attenuation intensity.

Specifically, the light attenuation intensity of the light-transmitting material refers to the difference between the light intensity transmitted through the outer surface of the light-transmitting material and the inner surface of the light-transmitting material when the light touches it; The real-time light intensity of the outer surface of the light-transmitting material, the said incoming light intensity can be calculated using the following formula: incoming light intensity=real-time light intensity-light attenuation intensity. The calculation results are stored to facilitate subsequent information feedback processing.

Further, the method also includes step S1100:

S1110: Analyzing the anti-pollution level of the light-transmitting material to obtain a first anti-pollution level;

S1120: Determine a first cleaning cycle according to the first anti-fouling level;

S1130: Clean the first greenhouse according to the first cleaning cycle.

Specifically, the first anti-pollution level refers to information that characterizes the ability of the light-transmitting material to retain dirt, and is exemplarily determined by collecting the area of dirt left by the light-transmitting material in the same environment within a preset time period. The larger the area, the higher the first anti-pollution level of the light-transmitting material; the smaller the area, the lower the first anti-fouling level of the light-transmitting material.

When the first anti-fouling level satisfies the preset level, it indicates that the dirty area of the preset time period has affected the light transmission, and the first cleaning cycle needs to be set to clean the first greenhouse, wherein the first cleaning cycle Less than or equal to half of the preset time period. In turn, the enforceability of the environmental adjustment information is guaranteed, and the healthy growth of the first crop is guaranteed.

To sum up, the method and system for controlling the greenhouse environment of facility crops provided by the embodiment of the present application have the following technical effects:

1. The embodiment of the present application provides a method and system for controlling the greenhouse environment of facility crops, which solves the technical problem in the prior art that the accuracy is difficult to guarantee due to the relatively single dimension of the evaluation benchmark for the prediction process of crops. By collecting the species and growth state information of the facility crops, and then collecting the environmental information in the facility, using the unequal weight combination prediction method combined with the crop variety, growth state information, and environmental information to perform multiple predictions and then integrate them to obtain the crop growth state prediction results , when the growth state prediction results do not meet the expected growth conditions, an environmental control model is constructed to adjust the environmental information in the facility. Based on the unequal weighted combination prediction method, the prediction results of multiple prediction methods can be integrated to improve the environmental accuracy of the facility crop greenhouse. technical effect.

2. The screening of the output data of the environmental control model can be realized through the identification network, that is, the environmental adjustment information output by the environmental control model does not all meet the preset accuracy, and only adjusting the environmental adjustment information that meets the preset accuracy will not meet the requirements. The environmental adjustment information with preset accuracy is marked and sent to the staff for processing, which improves the fault tolerance rate of the model.

Embodiment two

Based on the same inventive concept as that of a greenhouse environment regulation method for facility crops in the foregoing embodiments, as shown in FIG. 4 , an embodiment of the present application provides a greenhouse environment regulation system for facility crops, wherein the system includes:

The first collection unit 11, the first collection unit 11 is used to collect crop variety information and crop status information of the first crop in the first greenhouse;

A first obtaining unit 12, configured to obtain environmental information of the first crop in the first greenhouse;

The first processing unit 13, the first processing unit 13 is configured to use the unequal weighted combination prediction method to carry out the growth of the first crop according to the crop variety information, the crop status information and the environmental information. Forecast, obtain the first forecast result;

A second obtaining unit 14, the second obtaining unit 14 is used to obtain the expected growth information of the first crop;

A first judging unit 15, the first judging unit 15 is used to judge whether the first prediction result reaches the expected growth situation information;

A third obtaining unit 16, the third obtaining unit 16 is configured to obtain a first adjustment instruction if the first prediction result does not meet the expected growth situation information;

A fourth obtaining unit 17, the fourth obtaining unit 17 is configured to obtain a standard matching degree training set between the environmental information in the first greenhouse and the crop variety training set according to the first adjustment instruction;

The first construction unit 18, the first construction unit 18 is used to train the feedforward neural network according to the standard matching degree training set and the crop variety training set, and construct an environmental control model;

The second processing unit 19 is configured to input the crop variety information of the first crop and the standard matching degree of the first crop into the environmental control model to obtain the first crop Corresponding to the adjusted environment information in the first greenhouse, the adjusted environment information includes adjusted illumination information and adjusted temperature and humidity information.

Further, the method also includes:

A second collection unit, the second collection unit is used to collect crop variety information and crop status information of the first crop in the first greenhouse;

a fifth obtaining unit, the fifth obtaining unit is used to obtain environmental information of the first crop in the first greenhouse;

A third processing unit, the third processing unit is used to predict the growth of the first crop by using the unequal weight combination prediction method according to the crop variety information, the crop status information and the environmental information, Obtain the first prediction result;

A sixth obtaining unit, the sixth obtaining unit is used to obtain the expected growth information of the first crop;

A second judging unit, the second judging unit is used to judge whether the first prediction result reaches the expected growth situation information;

A seventh obtaining unit, the seventh obtaining unit is configured to obtain a first adjustment instruction if the first prediction result fails to meet the expected growth situation information;

An eighth obtaining unit, configured to obtain a standard matching degree training set between the environmental information in the first greenhouse and the crop variety training set according to the first adjustment instruction;

A second construction unit, the second construction unit is used to train a feed-forward neural network according to the standard matching degree training set and the crop variety training set to construct an environmental control model;

a fourth processing unit, the fourth processing unit is configured to input the crop variety information of the first crop and the standard matching degree of the first crop into the environmental control model, and obtain the corresponding The adjusted environment information in the first greenhouse, the adjusted environment information includes adjusted illumination information and adjusted temperature and humidity information.

Further, the method also includes:

A ninth obtaining unit, the ninth obtaining unit is used to obtain a second prediction result through a regression prediction method according to the crop variety information and the crop state information;

A tenth obtaining unit, the tenth obtaining unit is used to obtain a third prediction result through the Kalman filter prediction method according to the crop variety information and the environmental information;

A first prediction unit, the first prediction unit is used to predict the growth of the first crop based on the second prediction result and the third prediction result and the unequal weighted combination prediction method to obtain the first prediction result.

Further, the method also includes:

A third construction unit, the third construction unit is used to construct and train a discrimination network according to the standard matching degree training set, the crop variety training set and the generated data of the environmental control model;

An eleventh obtaining unit, the eleventh obtaining unit is used to obtain the accuracy rate of the output data of the environmental control model based on the identification network;

A first screening unit, configured to screen the output data of the environmental control model according to the accuracy rate.

Further, the method also includes:

a twelfth obtaining unit for obtaining the greenhouse structure of the first greenhouse;

A thirteenth obtaining unit, the thirteenth obtaining unit is used to obtain the amount of incoming light according to the greenhouse structure of the first greenhouse;

A fourteenth obtaining unit, the fourteenth obtaining unit is used to obtain the light-transmitting material of the first greenhouse;

A fifteenth obtaining unit, the fifteenth obtaining unit is used to obtain the incoming light intensity according to the light-transmitting material;

A sixteenth obtaining unit, configured to obtain first supplementary light information based on the adjusted illumination information and according to the incoming light amount and the incoming light intensity.

Further, the method also includes:

A third judging unit, the third judging unit is used to judge whether the greenhouse structure is a single-roof greenhouse;

The seventeenth obtaining unit, the seventeenth obtaining unit is used to obtain the elevation angle of the rear roof, the intersection angle between the front roof and the ground, and the length of the rear slope of the first greenhouse if the greenhouse structure is a single-roof greenhouse;

An eighteenth obtaining unit, the eighteenth obtaining unit is used to calculate and obtain the incoming light amount according to the elevation angle of the rear roof, the intersection angle between the front roof and the ground, and the length of the rear slope.

Further, the method also includes:

A nineteenth obtaining unit, the nineteenth obtaining unit is configured to obtain the light attenuation intensity of the light-transmitting material according to the light-transmitting material;

A twentieth obtaining unit, the twentieth obtaining unit is used to obtain real-time light intensity;

A twenty-first obtaining unit, the twenty-first obtaining unit is configured to obtain the incoming light intensity according to the light intensity and the light attenuation intensity.

Further, the method also includes:

A twenty-second obtaining unit, the twenty-second obtaining unit is used to analyze the anti-pollution level of the light-transmitting material to obtain the first anti-pollution level;

A first determination unit, the first determination unit is used to determine a first cleaning cycle according to the first anti-fouling level;

A first execution unit, the first execution unit is used to clean the first greenhouse according to the first cleaning cycle.

Exemplary electronic device

The electronic device of the embodiment of the present application is described below with reference to FIG. 5 ,

Based on the same inventive concept as the method for regulating the greenhouse environment of facility crops in the foregoing embodiments, an embodiment of the present application also provides a system for regulating the environment of greenhouses for facility crops, including: a processor, the processor is coupled with a memory, and the The memory is used to store a program, and when the program is executed by the processor, the system can execute the method described in any one of the first aspect.

The electronic device 300 includes: a processor 302 , a communication interface 303 , and a memory 301 . Optionally, the electronic device 300 may further include a bus architecture 304 . Wherein, the communication interface 303, the processor 302, and the memory 301 can be connected to each other through a bus architecture 304; the bus architecture 304 can be a peripheral component interconnect (PCI for short) bus or an extended industry standard architecture (extended industry standard architecture, for short) EISA) bus, etc. The bus architecture 304 can be divided into address bus, data bus, control bus and so on. For ease of representation, only one thick line is used in FIG. 5 , but it does not mean that there is only one bus or one type of bus.

The processor 302 may be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for controlling the program execution of the present application.

Communication interface 303, using any system such as a transceiver for communicating with other devices or communication networks, such as Ethernet, radio access network (radio access network, RAN), wireless local area network (wireless local area networks, WLAN), wired access network etc.

Memory 301 can be ROM or other types of static storage devices that can store static information and instructions, RAM or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (electrically erasable Programmable read-only memory, EEPROM), read-only disc (compactdiscread-only memory, CD-ROM) or other optical disc storage, optical disc storage (including compact disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), magnetic disk storage medium or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, without limitation. The memory may exist independently and be connected to the processor through the bus architecture 304 . Memory can also be integrated with the processor.

Wherein, the memory 301 is used to store computer-executed instructions for implementing the solution of the present application, and the execution is controlled by the processor 302 . The processor 302 is configured to execute the computer-executed instructions stored in the memory 301 , thereby realizing a method for controlling the environment of a facility crop greenhouse provided by the above-mentioned embodiments of the present application.

An embodiment of the present application provides a computer-readable storage medium, wherein a computer program is stored on the storage medium, and when the computer program is executed by a processor, the method described in any one of the embodiments is implemented.

Optionally, the computer-executed instructions in the embodiments of the present application may also be referred to as application program codes, which is not specifically limited in the embodiments of the present application.

The embodiment of the present application provides a method and system for controlling the greenhouse environment of facility crops, which solves the technical problem in the prior art that the accuracy of the crop prediction process is difficult to guarantee due to the relatively single dimension of the evaluation benchmark for the crop prediction process. By collecting the species and growth state information of the facility crops, and then collecting the environmental information in the facility, using the unequal weight combination prediction method combined with the crop variety, growth state information, and environmental information to perform multiple predictions and then integrate them to obtain the crop growth state prediction results , when the growth state prediction results do not meet the expected growth conditions, an environmental control model is constructed to adjust the environmental information in the facility. Based on the unequal weighted combination prediction method, the prediction results of multiple prediction methods can be integrated to improve the environmental accuracy of the facility crop greenhouse. technical effect.

Those of ordinary skill in the art can understand that the first, second, and other numbers involved in the present application are only for convenience of description, and are not used to limit the scope of the embodiments of the present application, nor do they indicate the sequence. "And/or" describes the association relationship of associated objects, indicating that there may be three types of relationships, for example, A and/or B may indicate: A exists alone, A and B exist simultaneously, and B exists independently. The character "/" generally indicates that the contextual objects are an "or" relationship. "At least one" means one or more. At least two means two or more. "At least one", "any one" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural item(s). For example, at least one item (one, species) of a, b, or c can represent: a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, c can be single or Multiple.

In the above embodiments, all or part of them may be implemented by software, hardware, firmware or any combination thereof. When implemented using software, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the processes or functions according to the embodiments of the present application will be generated in whole or in part. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable system. The computer refers to

The instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server or data center by wire ( Such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) transmission to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that can be accessed by a computer, or a data storage device including a server, a data center, and the like integrated with one or more available media. The available medium may be a magnetic medium (for example, a floppy disk, a hard disk, or a magnetic tape), an optical medium (for example, DVD), or a semiconductor medium (for example, a solid state disk (Solid State Disk, SSD)).

The various illustrative logic units and circuits described in the embodiments of the present application can be implemented by a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic systems, Discrete gate or transistor logic, discrete hardware components, or any combination of the above designed to implement or operate the described functions. The general-purpose processor may be a microprocessor, and optionally, the general-purpose processor may also be any conventional processor, controller, microcontroller or state machine. A processor may also be implemented by a combination of computing systems, such as a digital signal processor and a microprocessor, multiple microprocessors, one or more microprocessors combined with a digital signal processor core, or any other similar configuration to accomplish.

The steps of the method or algorithm described in the embodiments of the present application may be directly embedded in hardware, a software unit executed by a processor, or a combination of both. The software unit may be stored in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, removable disk, CD-ROM or any other storage medium in the art. Exemplarily, the storage medium can be connected to the processor, so that the processor can read information from the storage medium, and can write information to the storage medium. Optionally, the storage medium can also be integrated into the processor. The processor and the storage medium can be set in the ASIC, and the ASIC can be set in the terminal. Optionally, the processor and the storage medium may also be arranged in different components in the terminal. These computer program instructions can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby The instructions provide steps for implementing the functions specified in the flow chart or blocks of the flowchart and/or the block or blocks of the block diagrams.

Although the application has been described in conjunction with specific features and embodiments thereof, it will be apparent that various modifications and combinations can be made thereto without departing from the spirit and scope of the application. Accordingly, the specification and drawings are merely exemplary illustrations of the application defined herewith and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the application. Apparently, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the application belong to the scope of the application and its equivalent technology, the application intends to include these modifications and variations.

Claims (7)

1. A greenhouse environment regulation method for facility crops, which is characterized by comprising the following steps:

collecting crop variety information and crop state information of a first crop in a first greenhouse;

obtaining environmental information of the first crop within the first greenhouse;

predicting the growth condition of the first crop by adopting an unequal weight combined prediction method according to the crop variety information, the crop state information and the environment information to obtain a first prediction result;

obtaining information on the expected growth of the first crop;

judging whether the first prediction result reaches the expected growth condition information or not;

if the first prediction result does not reach the expected growth condition information, obtaining a first adjusting instruction;

according to the first adjusting instruction, a standard matching degree training set of the environmental information in the first greenhouse and a crop variety training set is obtained;

training a feedforward neural network according to the standard matching degree training set and the crop variety training set to construct an environment control model;

inputting the crop variety information of the first crop and the standard matching degree of the first crop into the environment control model to obtain adjusted environment information in the first greenhouse corresponding to the first crop, wherein the adjusted environment information comprises adjusted illumination information and adjusted temperature and humidity information;

obtaining a greenhouse structure of the first greenhouse;

obtaining the light inlet quantity according to the greenhouse structure of the first greenhouse;

obtaining a light-transmitting material of the first greenhouse;

obtaining light entering intensity according to the light-transmitting material;

based on the adjusted illumination information, obtaining first supplementary illumination information according to the light incoming amount and the light incoming intensity;

the obtaining of the amount of incoming light according to the greenhouse structure of the first greenhouse includes:

judging whether the greenhouse structure is a single-roof greenhouse;

if the greenhouse structure is a single-roof greenhouse, obtaining the elevation angle of the rear roof, the intersection angle of the front roof and the ground and the length of a rear slope of the first greenhouse;

calculating according to the elevation angle of the rear roof, the intersection angle of the front roof and the ground and the length of the rear slope to obtain the light entering amount;

according to the printing opacity material, obtain into luminous intensity, include:

obtaining the illumination attenuation intensity of the light-transmitting material according to the light-transmitting material;

obtaining real-time illumination intensity;

and obtaining the light incoming intensity according to the illumination intensity and the illumination attenuation intensity.

2. The method of claim 1, wherein the predicting the growth of the first crop using the unequal weight combined prediction method according to the crop variety information, the crop state information, and the environment information to obtain a first prediction result comprises:

obtaining a second prediction result by a regression prediction method according to the crop variety information and the crop state information;

obtaining a third prediction result through a Kalman filtering prediction method according to the crop variety information and the environment information;

and predicting the growth condition of the first crop by adopting the unequal weight combined prediction method based on the second prediction result and the third prediction result to obtain a first prediction result.

3. The method of claim 1, wherein said entering said crop variety information for said first crop and said first crop's standard match into said environmental control model further comprises:

constructing and training an identification network according to the standard matching degree training set and the crop variety training set and the generation data of the environment control model;

obtaining the accuracy of the output data of the environment control model based on the identification network;

and screening the output data of the environment control model according to the accuracy.

4. The method of claim 1, wherein the method further comprises:

performing anti-fouling grade analysis on the light-transmitting material to obtain a first anti-fouling grade;

determining a first cleaning period according to the first anti-fouling grade;

cleaning the first greenhouse according to the first cleaning period.

5. A facility crop greenhouse environment regulation system, the system comprising:

the first acquisition unit is used for acquiring crop variety information and crop state information of a first crop in the first greenhouse;

a first obtaining unit, configured to obtain environmental information of the first crop in the first greenhouse;

the first processing unit is used for predicting the growth condition of the first crop by adopting an unequal weight combined prediction method according to the crop variety information, the crop state information and the environment information to obtain a first prediction result;

a second obtaining unit, configured to obtain information on expected growth conditions of the first crop;

a first judging unit, configured to judge whether the first prediction result reaches the expected growth condition information;

a third obtaining unit, configured to obtain a first adjustment instruction if the first prediction result does not reach the expected growth condition information;

a fourth obtaining unit, configured to obtain, according to the first adjustment instruction, a standard matching degree training set of the environmental information in the first greenhouse and a crop variety training set;

a first construction unit, configured to construct an environment control model according to the standard matching degree training set and the crop variety training set training feed-forward neural network;

a second processing unit, configured to input the crop variety information of the first crop and the standard matching degree of the first crop into the environment control model, and obtain adjusted environment information in the first greenhouse corresponding to the first crop, where the adjusted environment information includes adjusted illumination information and adjusted temperature and humidity information;

a twelfth obtaining unit for obtaining a greenhouse structure of the first greenhouse;

a thirteenth obtaining unit for obtaining an amount of incoming light in accordance with a greenhouse structure of the first greenhouse;

a fourteenth obtaining unit, configured to obtain a light-transmitting material of the first greenhouse;

a fifteenth obtaining unit, configured to obtain light incoming intensity according to the light-transmitting material;

a sixteenth obtaining unit, configured to obtain first supplementary lighting information according to the light incoming amount and the light incoming intensity based on the adjusted lighting information;

a third judging unit, configured to judge whether the greenhouse structure is a single-roof greenhouse;

a seventeenth obtaining unit configured to obtain a rear roof elevation angle, a front roof intersection angle with the ground, and a rear slope length of the first greenhouse if the greenhouse structure is a single-roof greenhouse;

an eighteenth obtaining unit, configured to obtain the light entering amount by calculation according to the rear roof elevation angle, the intersection angle of the front roof and the ground, and the rear slope length;

a nineteenth obtaining unit, configured to obtain, according to the light-transmitting material, an illumination attenuation intensity of the light-transmitting material;

a twentieth obtaining unit for obtaining a real-time illumination intensity;

a twenty-first obtaining unit, configured to obtain the light incoming intensity according to the illumination intensity and the illumination attenuation intensity.

6. A facility crop greenhouse environment regulation system, comprising: a processor coupled to a memory, the memory for storing a program, wherein the program, when executed by the processor, causes a system to perform the method of any of claims 1 to 4.

7. A computer-readable storage medium, characterized in that the storage medium has stored thereon a computer program which, when being executed by a processor, carries out the method of any one of claims 1 to 4.

Images