Method for regulating light supplement for greenhouse plant growth and regulating system thereof

Abstract

The application discloses a kind of greenhouse plant growth light supplementing regulation method and its regulation system, comprising the following steps: S1, obtaining the real-time image of plant;S2, input real-time image into plant growth state prediction model, output the current growth state of plant;S3, according to the current growth state of plant, the best light supplementing scheme is determined using nonlinear programming model;S4, according to the best light supplementing scheme, light supplementing is carried out to plant.The application adjusts the color of light supplementing by judging the current growth state of plant, then uses nonlinear programming model to realize the balance of light supplementing amount and power cost, finds the best light supplementing strategy, provides sufficient light for plant to promote growth at the same time can reduce power cost, saves cost for enterprise, realizes profit promotion.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of plant light supplement, in particular to a greenhouse plant growth light supplement regulation method and a regulation system thereof. BACKGROUND

[0002] In recent years, with the vigorous development of greenhouse planting technology, a greenhouse plant growth monitoring and compensation system has emerged. The greenhouse plant growth monitoring and compensation system monitors the environmental data such as temperature, humidity and light intensity in the greenhouse in real time, and adjusts the environmental data in real time when the environmental data exceeds the normal value and affects the normal growth of plants, so as to ensure the normal growth of plants.

[0003] Photosynthesis of plants is an important part of the growth process of plants. The seven-color spectrum contained in the light required for plant growth does not all play a key role in plants. The most important spectrum colors are green light, blue light and red light. Among them, green and blue spectrum can promote the growth of roots and leaves, and red spectrum is beneficial to the flowering of plants. In the case of insufficient natural light, a light supplement lamp can be turned on to supplement light to promote the growth of plants. However, the cost of electricity generated by light supplement cannot be ignored. Therefore, it is necessary to find the best lighting strategy to reduce the cost of power lighting. SUMMARY

[0004] The technical problem to be solved by the present application is how to optimize and balance plant growth light supplement and power cost.

[0005] To this end, the present application provides a greenhouse plant growth light supplement regulation method and a regulation system thereof, which can maximize the promotion of light supplement to plant growth and minimize the power cost of light supplement.

[0006] The technical solution adopted by the present application to solve the technical problem is: a greenhouse plant growth light supplement regulation method, comprising the following steps: S1, acquiring a real-time image of a plant; S2, inputting the real-time image into a plant growth state prediction model to output the current growth state of the plant; S3, determining an optimal light supplement scheme by using a nonlinear programming model according to the current growth state of the plant; and S4, supplementing light to the plant according to the optimal light supplement scheme.

[0007] Further, the growth state of the plant includes seedling stage, growth stage, flowering stage and mature stage.

[0008] Further, the determination of the optimal light supplement scheme by using the nonlinear programming model comprises:

[0009] establishing a plant growth prediction model;

[0010] establishing a cost function of plant growth;

[0011] establishing a relationship between electron transport rate and photon flux density in plant photosynthesis;

[0012] establishing a prediction model of sunlight intensity;

[0013] determining an optimal light supplement scheme based on the plant growth prediction model, a cost function, the relationship between electron transport rate and photon flux density, the prediction model of sunlight intensity, and in combination with constraint conditions.

[0014] Further, the plant growth prediction model is: wherein w represents the mass of the plant, K represents the growth rate of the plant, t represents time, μ1 represents a control parameter of the nutrient solution, μ2 represents the average light received by the plant per day, and α and β represent weight coefficients of μ1 and μ2 respectively. Further, the cost function of plant growth is: wherein J(μ1, μ2) represents profit, t0 represents an initial time, t f represents the time corresponding to the optimal profit.

[0015] Further, the relationship between electron transport rate and photon flux density is ETR = a(1-e -k×PPFD ), wherein ETR represents electron transport rate, PPFD represents photon flux density, a represents the asymptote of ETR, and k represents the ratio of the initial slope of ETR to a.

[0016] Further, the prediction model of sunlight intensity is: wherein represents the ETR of light supplement from the light supplement lamp, T represents the total number of time steps, C t represents the electricity cost per kilowatt-hour, represents the ETR of light supplement at time step t, represents the ETR generated by sunlight, s t represents the photosynthetic photon flux density of the sun.

[0017] Further, the constraint conditions include: wherein t = i, i+1, …, T; D represents the required DPI of the plant during the entire photoperiod, m represents the length of each time step, U LED represents the maximum ETR that can be reached by the light supplement lamp, and i represents a positive integer.

[0018] Further, the optimal light supplement amount and total electricity cost are calculated by using a nonlinear programming model, and the light intensity of the light supplement lamp is adjusted according to the optimal light supplement amount.

[0019] The application also provides a greenhouse plant growth light supplement regulation system, comprising:

[0020] An imaging device for taking a plant image;

[0021] An LED light for supplementing light for the plant;

[0022] A controller, the real-time image of the plant taken by the imaging device is transmitted to the controller, and the controller runs the regulation method of the greenhouse plant growth light supplement.

[0023] The beneficial effects of the present application are that the regulation method of the greenhouse plant growth light supplement and the regulation system thereof adjust the color of the light supplement by judging the current growth state of the plant, and then use a nonlinear programming model to balance the light supplement amount and the power cost, find the best light supplement lighting strategy, provide sufficient light for the plant to promote growth while reducing power cost, save cost for enterprises, and realize profit improvement. BRIEF DESCRIPTION OF DRAWINGS

[0024] The present application will be further described below in conjunction with the drawings and examples.

[0025] Figure 1 is a flowchart of the regulation method of the greenhouse plant growth light supplement of the present application. DETAILED DESCRIPTION

[0026] The present application will now be further described in conjunction with the drawings. These drawings are all simplified schematic diagrams, and only schematically show the basic structure of the present application, and therefore only show the structures related to the present application.

[0027] In the description of the present application, it should be understood that the orientations or positional relationships indicated by the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential" are based on the orientations or positional relationships shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and therefore cannot be understood as indicating or implying that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application. In addition, the features defined as "first" and "second" can explicitly or implicitly include one or more of the features. In the description of the present application, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0028] In the description of the present application, it should be noted that unless otherwise explicitly specified and limited, the terms "mounting", "connection", "connecting" should be understood broadly, for example, it can be fixed connection, or detachable connection, or integrally connected, it can be mechanical connection, or electrical connection, it can be directly connected, or indirectly connected through intermediate medium, or internal communication of two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0029] As shown in Figure 1 The method for regulating greenhouse plant growth light compensation of the present application is characterized in that it comprises the following steps: S1, obtaining a real-time image of the plant; S2, inputting the real-time image into a plant growth state prediction model to output the current growth state of the plant; S3, determining the optimal light compensation scheme by using a nonlinear programming model according to the current growth state of the plant; and S4, compensating the light for the plant according to the optimal light compensation scheme.

[0030] That is, the present application will first determine the current growth state of the plant before compensating the light for the plant, and then formulate the optimal light compensation scheme according to the growth state of the plant, so that a balance between promoting the growth of the plant and the cost of electricity can be found, which is beneficial to saving the cost for the enterprise.

[0031] For example, the growth state of the plant includes seedling stage, growth stage, flowering stage and mature stage. For example, during the seedling stage of the plant, blue light is selected for light compensation, which is beneficial to promoting the growth of the root system and the leaves of the plant. During the growth stage of the plant, green light is selected for light compensation, which is beneficial to the growth of the plant. During the flowering stage of the plant, red light is selected for light compensation, which is beneficial to the flowering of the plant. Therefore, different colors of light are selected for light compensation when the plant is in different growth states.

[0032] It should be noted that the plant growth state prediction model can predict the current growth state of the plant according to the growth index of the plant. The growth index includes fresh weight, dry weight, height, leaf area, leaf diameter and other parameters that can reflect the state of the plant. The plant growth state prediction model is obtained through training, and the training process includes: collecting RGB images and depth images of the plant at different growth stages, and pre-processing the RGB images and depth images (including denoising, normalizing color and depth information, adjusting image size, etc.), marking the growth state of the plant in the pre-processed RGB images and depth images as a training image set, dividing the training image set into a training set, a test set and a validation set according to a set proportion, training, testing and verifying the neural network model respectively, and finally obtaining the plant growth state prediction model with a prediction accuracy that meets the standard.

[0033] It should be noted that the RGB image of the plant is collected to show the appearance of the plant, and the depth image of the plant is collected to collect the depth information of the plant, and then the height information of the plant is converted. Since the plant species in the greenhouse is diverse, not only plants like tomatoes but also plants like lettuce need to be predicted, so when collecting images, both RGB images and depth images need to be collected. The RGB image is a 24-bit portable network graphics (PNG) image with three channels, and the depth image is an 8-bit PNG image with a single channel.

[0034] After obtaining the current growth state of the plant, the optimal light supplement scheme can be determined by using a nonlinear programming model. Specifically, it includes: establishing a plant growth prediction model; establishing a cost function of plant growth; establishing a relationship between electron transport rate and photon flux density in plant photosynthesis; establishing a prediction model of sunlight intensity; determining the optimal light supplement scheme based on the plant growth prediction model, the cost function, the relationship between the electron transport rate and the photon flux density, the prediction model of sunlight intensity and the constraint conditions. The nonlinear programming model is equivalent to a constrained optimization problem model, the main goal of which is to maximize plant growth through light supplement while minimizing electricity costs. The nonlinear programming model not only considers the daily light requirements of plants, but also considers the changes in sunlight and electricity costs.

[0035] First, data of the plant species planted in the greenhouse need to be collected, including the optimal spectrum and light intensity information at each growth stage. The plant growth prediction model is: In the formula, w represents the mass of the plant, K represents the growth rate of the plant, t represents time (unit: day), μ1 represents the control parameter of the nutrient solution, μ2 represents the average light received by the plant per day, and α and β represent the weight coefficients of μ1 and μ2, respectively. In order to control the growth of the plant within the planned range at the time of harvest, the concentration of the nutrient solution at the root of the plant and the average light received by the plant per day need to be controlled. In the plant growth prediction model, the growth rate K of the plant is considered to be constant. The cost function of plant growth is: In the formula, J(μ1, μ2) represents the profit, t0 represents the initial time, t f represents the time corresponding to the optimal profit. According to the cost function, the optimal μ1 and μ2 can be found to maximize the profit.

[0036] There are two important parameters in plant photosynthesis: electron transport rate (ETR) and photon flux density (PPFD). ETR is the parameter of LED light supplement lamp, which is through electronic lighting. The photon flux density of sunlight is the parameter of sunlight. The effects of the two on plants cannot be directly equivalent, so the two need to be converted. ETR is defined as the number of electrons transported through the photosystem per unit leaf area per second. The sum of ETR in 24 hours is called daylight photochemical integral (DPI). The relationship between ETR and photon flux density is: ETR = a (1-e -k×PPFD ), wherein ETR represents electron transport rate, PPFD represents photon flux density, a represents the asymptote of ETR, and k represents the ratio of the initial slope of ETR to a.

[0037] For light supplement illumination, the optimization goal is to minimize the total light provided by the light supplement lamp to meet the requirements of the set daylight photochemical integral and photoperiod. When light supplement is performed, the intensity of sunlight also needs to be considered. Assuming that the current sunlight intensity is insufficient and light supplement needs to be performed, and then the light supplement lamp is turned on, but after a period of time, the sunlight intensity becomes strong. If the previous light supplement intensity is still used, it will cause waste of electricity and provide too much light for the plant. Therefore, the prediction of sunlight intensity is added in the present application. The prediction model of sunlight intensity is: , wherein represents the ETR vector of light supplement from the light supplement lamp, T represents the total number of time steps, C t represents the electricity cost per kilowatt hour (unit: yuan), represents the light supplement ETR at the time step t, represents the ETR generated by sunlight, s t represents the photosynthetic photon flux density of the sun. The sunlight intensity prediction model is used to predict the sunlight intensity in a day.

[0038] After the above several models are constructed, the constraint conditions can be set to obtain the optimal solution. The constraint conditions include: , wherein t = i, i+1,..., T; D represents the daily light amount required by the plant during the entire photoperiod, m represents the length of each time step (unit: second), U LED represents the maximum ETR that can be reached by the light supplement lamp, and i represents a positive integer (for example, 1, 2, 3,...). The constraint condition can ensure that the optimal DPI is provided to the plant, and the limitation of D, the lower limit and upper limit of ETR can be ensured according to the minimum value and maximum value of the light intensity of the light supplement lamp.

[0039] The nonlinear programming model can solve the optimal light supplement amount and total electricity cost, and the light intensity of the light supplement lamp is adjusted according to the optimal light supplement amount. In the light supplement process, the growth of the feedback plant can be monitored in real time, and if the growth of the plant is not as expected, the light intensity and color need to be changed again to adapt to the situation.

[0040] The application also provides a greenhouse plant growth light supplement regulation system, comprising: an imaging device for shooting plant images; an LED light supplement lamp for supplementing light to plants; and a controller, wherein the real-time image of the plant shot by the imaging device is transmitted to the controller, and the controller runs the greenhouse plant growth light supplement regulation method. The imaging device can shoot RGB images and depth images of the plant, and the imaging device is controlled by the controller. After the controller obtains the optimal light supplement scheme, the light supplement lamp can be controlled to supplement light. The light supplement lamp has three colors (blue, green and red), and the corresponding color is opened according to the current growth state of the plant, and the light intensity is adjusted according to the optimal light supplement amount.

[0041] In summary, the greenhouse plant growth light supplement regulation method and regulation system of the application adjust the color of light supplement by judging the current growth state of the plant, and then use a nonlinear programming model to balance the light supplement amount and the power cost, so as to find the optimal light supplement strategy, provide sufficient light for promoting the growth of the plant, reduce the power cost, save the cost for enterprises, and realize profit increase.

[0042] With the above ideal embodiments according to the application as the inspiration, through the above description, relevant personnel can make various changes and modifications without deviating from the technical idea of the application. The technical scope of the application is not limited to the content in the specification, and must be determined by the scope of the claims.

Claims

1. A method of regulating light supplementation for greenhouse plant growth, characterized in that, The method comprises the following steps: S1, acquiring a real-time image of the plant; S2, inputting the real-time image into a plant growth state prediction model to output a current growth state of the plant; S3, determining an optimal light supplement scheme by using a nonlinear programming model according to the current growth state of the plant; The step of determining the optimal light supplement scheme by using the nonlinear programming model comprises: establishing a plant growth prediction model; establishing a cost function of plant growth; establishing a relationship between an electron transport rate and a photon flux density in photosynthesis of the plant; establishing a prediction model of sunlight intensity; determining the optimal light supplement scheme based on the plant growth prediction model, the cost function, the relationship between the electron transport rate and the photon flux density, the prediction model of sunlight intensity, and a constraint condition; The plant growth prediction model is: , wherein represents the mass of the plant, represents the growth rate of the plant, represents time, represents a control parameter of the nutrient solution, represents the average light amount received by the plant per day, , respectively represent the weight coefficients of and . The cost function of plant growth is: wherein, represents the profit, represents the initial time, represents the time corresponding to the optimal profit; The relationship between the electron transport rate and the photon flux density is: where ETR represents the electron transport rate, PPFD represents the photon flux density, represents the asymptote of ETR, represents the ratio of the initial slope of ETR to a; A prediction model for the sunlight intensity is: wherein ETRcompl denotes the complement light ETR from the complement light, T denotes the total number of time steps, denotes the electricity price per kilowatt hour, ETRcompl(t) denotes the complement light ETR at time step t, denotes the sunlight generated ETR, denotes the solar photosynthetic photon flux density; The constraints include: where t = i, i+1,..., T; D represents the daily average amount of light required to be received by the plant during the entire photoperiod, m represents the length of each time step, U LED represents the maximum ETR that the supplemental light lamp is capable of achieving, i represents a positive integer; S4, supplementing light to the plant according to the optimal light supplement scheme.

2. The method of claim 1, wherein the greenhouse plant growth light supplementation is regulated by, The growth state of the plant comprises a seedling stage, a growth stage, a flowering stage, and a mature stage.

3. The method of claim 1, wherein the greenhouse plant growth light supplementation is regulated by, The optimal light supplement amount and total electricity cost are calculated by using the nonlinear programming model, and the light intensity of the light supplement lamp is adjusted according to the optimal light supplement amount.

4. A regulated system for supplemental lighting of greenhouse plant growth, characterized in that, The method comprises: an imaging device for capturing a plant image; an LED light supplement lamp for supplementing light to the plant; a controller, wherein a real-time image of the plant captured by the imaging device is transmitted to the controller, and the controller runs the method for regulating and controlling light supplement for greenhouse plant growth according to any one of claims 1-3.

Images