Light environment optimization control method and system and intelligent illumination regulation and control multilayer plant factory based on photoelectric agriculture

Abstract

The invention belongs to the technical field of plant factories, and particularly relates to a light environment optimization control method and system and an intelligent illumination regulation and control multi-layer plant factory based on photoelectric agriculture. Light environment optimization control specifically comprises the steps that multi-factor data of a plant growth environment is collected, a photosynthetic rate prediction model based on a least square support vector machine is constructed, and a photosynthetic rate prediction model is constructed; and predicting photosynthetic rate response curves in different light environments. And determining an inflection point of a photosynthetic rate curve through differential operation, and determining an optimal light quality ratio and a light environment regulation strategy based on cost-photosynthetic effect analysis. The factory roof is combined with the photovoltaic panel and the light uniformizing plate, and optimal utilization of natural light and artificial light is achieved. The energy utilization efficiency is improved, the growth efficiency and yield of plants are remarkably improved by precisely regulating and controlling the light environment, and the system is suitable for efficient planting of various plants.

Description

Technical Field

[0001] The present invention belongs to the technical field of plant factories, and particularly relates to a light environment optimization control method, system, and intelligent lighting control multi-layer plant factory based on optoelectronic agriculture. Background Art

[0002] Currently, plant factory systems usually combine photovoltaic power generation technology and LED plant growth lighting devices. Photovoltaic panels are used to convert solar energy into electrical energy to power LED plant growth lights and other devices. The LED devices can adjust the spectral output and light intensity according to the growth requirements and growth stages of plants to promote photosynthesis and growth and development of plants. At the same time, a wireless network is also deployed in the plant factory for real-time collection of various environmental parameters and crop growth information, such as CO2 concentration, air temperature, relative air humidity, soil pH value, EC value, and light flux density, etc. These information provide data support for the intelligent control of the plant factory.

[0003] Although the existing plant factory systems have made remarkable progress in light management and environmental control, there are still some deficiencies. First, in terms of light management, although the LED plant growth lighting devices can adjust the spectral output and light intensity according to the growth requirements of plants, they often lack fine control of the light flux density of different wavelengths and cannot fully meet the fine requirements of plants for light. Second, although the existing plant factory systems can collect various environmental parameters in real time, there are limitations in data processing and analysis, resulting in some data being unable to fully play their roles. Finally, there are still certain lags and inaccuracies in the real-time precise control of environmental conditions by the existing intelligent control systems, which affect the growth efficiency and yield of plants. Summary of the Invention

[0004] The purpose of the present invention is to provide a light environment optimization control method, system, and plant factory system, aiming to solve the problems of insufficient light conditions and high energy consumption in plant cultivation. By combining photovoltaic power generation and light homogenizing plate technology on the factory roof, natural light and LED plant growth lights are used to provide optimized lighting, especially enhanced lighting in the mixed wavelength band (red, blue, green). This system can not only effectively reduce energy costs, but also improve the growth efficiency of plants through uniform lighting conditions, thereby reducing the overall cost of plant cultivation and increasing the yield.

[0005] The present invention achieves the above purpose through the following technical solutions:

[0006] In the first aspect, the present invention proposes a light environment optimization control method, and the method includes:

[0007] Obtain a data set to be analyzed of the plant growth environment, including photosynthetic rate values under different combinations of environmental factors;

[0008] Input the dataset to be analyzed into a photosynthetic rate prediction model pre-constructed based on the LS-SVM algorithm for training, and predict the photosynthetic rate under different light environment conditions based on the trained photosynthetic rate prediction model;

[0009] Determine the input cost, plant yield, and economic benefits during a set growth period based on the photosynthetic rate, and construct a cost-benefit estimation model;

[0010] Construct a cost-photosynthetic rate response curve based on the photosynthetic rate under different light environment conditions and the cost-benefit estimation model, and perform first-order and second-order differential operations on the cost-photosynthetic rate response curve to determine at least one inflection point on the curve;

[0011] Based on cost-photosynthetic effect analysis, evaluate the economic benefits corresponding to each additional unit cost at at least one of the inflection points, and determine the inflection point with the maximum economic benefits and the corresponding light quality ratio;

[0012] Regulate the light environment for plant growth based on the light quality ratio.

[0013] Furthermore, the environmental factors include CO2 concentration, air temperature, air relative humidity, soil pH value, soil EC value, light flux density PPFD, and light flux density PPFDλi at different central wavelengths, where i = 1…m and m is an integer greater than 1.

[0014] Furthermore, after obtaining the dataset to be analyzed of plant growth environment data, it further includes:

[0015] Exclude abnormal data points and perform normalization processing on the dataset to be analyzed; and,

[0016] Perform correlation screening, determine the gray correlation coefficients between each environmental factor and the photosynthetic rate based on the gray relational analysis method, and perform sorting and screening according to the magnitudes of the gray correlation coefficients to obtain the screened dataset to be analyzed.

[0017] Furthermore, the determining the input cost, plant yield, and economic benefits during a set growth period based on the photosynthetic rate and constructing a cost-benefit estimation model includes:

[0018] Determine the equipment cost: where ci is the investment cost of each piece of equipment;

[0019] Determine the energy consumption cost: C 能源 = ∑ t (P 市电，t ·E 市电，t -P 光伏，t ·E 光伏，t )·dt, where P 市电 t and P光伏 Let \(t\) be the price of grid power and the selling price of PV power generation at the \(t\)-th time period, and \(E\) 市电 \(_t\) and \(E\) 光伏 \(_t\) be the grid power compensation and the PV power generation feeding into the grid respectively;

[0020] Determine the input cost: \(C = C\) 设备 \(_1 + C\) 能源 ;

[0021] Determine the economic benefit: \(B = Y\cdot P\) 作物 \(_1 - C\) 设备 \(_2 - C\) 能源 \(_3\), where \(P\) 作物 \(_1\) is the unit crop price; \(Y\) is the predicted yield within one growth cycle of the plant, which has a linear relationship with the photosynthetic rate \(P\) n \(_1\), \(Y = k\cdot P\) n \(_1 + b\), where the parameters \(k\), \(b\) are related to the plant species.

[0022] Furthermore, perform first-order and second-order differential operations on the cost - photosynthetic rate response curve to determine at least one inflection point on the curve, including:

[0023] Perform first-order differentiation on the cost - photosynthetic rate response curve to obtain \(P'_n=\frac{dP_n}{dC}\), where \(P'_n\) represents the change rate of the photosynthetic rate with respect to the input cost;

[0024] Perform second-order differentiation on the cost - photosynthetic rate response curve to obtain \(P''_{mn}=\frac{d^2P_n}{dC^2}\) 2 \(P_n\) 2 , where \(P''_n\) represents the change of the photosynthetic rate change rate with respect to the light intensity;

[0025] Use the hill-climbing method to determine at least one inflection point on the cost - photosynthetic rate response curve where \(P''_n\) is close to zero.

[0026] Furthermore, based on the cost - photosynthetic effect analysis, evaluate the economic benefit corresponding to each unit increase in cost at at least one of the inflection points, and determine the inflection point with the maximum economic benefit and the corresponding light quality ratio, including:

[0027] Determine the increase in the photosynthetic rate corresponding to each unit increase in the input cost at the inflection point, and determine the inflection point with the maximum economic benefit corresponding to each unit increase in the input cost among several inflection points;

[0028] Determine the increase in the photosynthetic rate at the inflection point with the maximum economic benefit;

[0029] Based on the relationship between the increase in the photosynthetic rate and the preset threshold, determine the inflection point with the maximum photosynthetic rate and use it as the target inflection point;

[0030] Determine the light quality ratio according to the photosynthetic rate at the target inflection point.

[0031] Second aspect, the present invention proposes a light environment optimization control system, which is applied to execute the light environment optimization control method described in any one of the above, and the system includes:

[0032] A data acquisition module, configured to acquire a dataset to be analyzed of the plant growth environment, and the dataset to be analyzed includes photosynthetic rate values under different combinations of environmental factors;

[0033] A first prediction module, configured to input the dataset to be analyzed into a photosynthetic rate prediction model pre-constructed based on the LS-SVM algorithm for training, and predict the photosynthetic rate under different light environment conditions based on the trained photosynthetic rate prediction model;

[0034] A second prediction module, configured to determine the input cost, plant yield, and economic benefit within a set growth period based on the photosynthetic rate, and construct a cost-benefit estimation model;

[0035] A first analysis module, configured to construct a cost-photosynthetic rate response curve based on the photosynthetic rate under different light environment conditions and the cost-benefit estimation model, and perform first-order and second-order differential operations on the cost-photosynthetic rate response curve to determine at least one inflection point on the curve;

[0036] A second analysis module, configured to evaluate the economic benefit corresponding to each additional unit cost at at least one of the inflection points based on cost-photosynthetic effect analysis, and determine the inflection point with the maximum economic benefit and the corresponding light quality ratio;

[0037] A light environment regulation module, configured to regulate the light environment for plant growth based on the light quality ratio.

[0038] Third aspect, the present invention proposes an intelligent light regulation multi-layer plant factory based on optoelectronic agriculture, and the multi-layer plant factory includes a factory roof, a planting rack, a growth lighting module, and the light environment optimization control system as described above; wherein,

[0039] At least two layers of planting racks are arranged below the factory roof, and the factory roof is interspersed with photovoltaic panels and light homogenizing plates. The photovoltaic panels are used to convert solar energy into electrical energy to supply power to the growth lighting module, and the light homogenizing plates are used to evenly distribute natural light to the upper layer of the planting rack;

[0040] The data acquisition module is arranged on each layer below the upper layer of the planting rack, and is configured to periodically acquire the dataset to be analyzed of the plant growth environment on the planting rack;

[0041] The growth lighting module is arranged on each layer below the upper layer of the planting rack, and is signal-connected to the light environment regulation module, and is configured to receive the light quality ratio to dynamically adjust the spectral output and intensity of the growth lighting module, and supplement light for the plants below the upper layer of the planting rack.

[0042] Furthermore, the growth lighting module is specifically a hybrid light source, including a red light band, a blue light band, and a green light band.

[0043] The beneficial effects of the present invention are as follows:

[0044] 1. The light environment optimization control method proposed by the present invention can accurately predict the photosynthetic rate response curve under different light environment conditions by obtaining the dataset to be analyzed of the plant growth environment and constructing a photosynthetic rate prediction model based on the LS-SVM algorithm. By performing first-order and second-order differential operations on the response curve, the optimal light intensity inflection point is determined, and combined with cost-photosynthetic effect analysis, the optimization regulation of the light quality ratio is realized. This method not only improves the light energy utilization efficiency but also reduces the energy consumption cost, significantly improving the plant growth efficiency and crop yield. In addition, combined with photovoltaic power generation and light homogenizing plate technology, the present invention provides continuous, stable, and uniform lighting conditions for plants, further optimizing the production benefits of the plant factory.

[0045] 2. The present invention realizes the precise control of the plant growth environment by combining photovoltaic power generation, light homogenizing plate technology, and the light environment optimization control system. In particular, the light environment optimization control system is used to dynamically adjust the spectral output and intensity of the LED light source, that is, dynamically adjust the light quality ratio, to match the lighting requirements of different growth stages of plants. This refined light environment regulation not only improves the plant growth efficiency but also effectively reduces the energy consumption, realizing green and efficient agricultural production. Description of the Drawings

[0046] Figure 1 It is a schematic flow chart of the light environment optimization control method provided by the embodiment of the present application;

[0047] Figure 2 It is a schematic structural diagram of the light environment optimization control system provided by the embodiment of the present application;

[0048] Figure 3 It is a schematic structural diagram of an intelligent lighting regulation multi-layer plant factory based on photovoltaic agriculture provided by the embodiment of the present application;

[0049] Figure 3 In the figure, 1, factory roof; 2, planting rack; 3, growth lighting module; 4, photovoltaic panel; 5, light homogenizing plate; 6, upper layer; 7, lower layer. Specific Embodiments

[0050] The following further describes the present application in detail with reference to the drawings. It is necessary to point out here that the following specific embodiments are only used to further illustrate the present application and cannot be understood as limiting the protection scope of the present application. Those skilled in the art can make some non-essential improvements and adjustments to the present application according to the above application content.

[0051] Example 1

[0052] As Figure 1 shown, this embodiment proposes a light environment optimization control method, and the method includes the following steps:

[0053] S1. Obtain the dataset to be analyzed of the plant growth environment, including the photosynthetic rate values under different combinations of environmental factors; specifically, the environmental factors include CO2 concentration, air temperature, air relative humidity, soil pH value, soil EC value, photosynthetic photon flux density PPFD, and photosynthetic photon flux density PPFDλi at different central wavelengths, where i = 1…m and m is an integer greater than 1.

[0054] In some embodiments, after obtaining the dataset to be analyzed of the plant growth environment data, it further includes:

[0055] Exclude abnormal data points and perform normalization processing on the dataset to be analyzed; and,

[0056] Perform correlation screening, determine the gray correlation coefficients between each environmental factor and the photosynthetic rate based on the gray relational analysis method, and perform sorting and screening according to the magnitudes of the gray correlation coefficients to obtain the screened dataset to be analyzed.

[0057] It can be understood that the above correlation screening is used to screen out the environmental factors highly correlated with the photosynthetic rate from the original dataset to be analyzed. Based on the gray relational analysis method, the gray correlation coefficients between each environmental factor and the photosynthetic rate can be determined, and this coefficient reflects the degree of association between the environmental factor and the photosynthetic rate. By performing sorting and screening according to the magnitudes of the gray correlation coefficients, a more concise but information-rich dataset to be analyzed can be obtained. This helps the subsequent construction and optimization control process of the photosynthetic rate prediction model, and can focus on those environmental factors that have a significant impact on the photosynthetic rate.

[0058] S2. Construct a photosynthetic rate prediction model based on LS-SVM (Least Squares Support Vector Machine algorithm), input the dataset to be analyzed into the photosynthetic rate prediction model for training, and predict the photosynthetic rate under different light environment conditions according to the trained photosynthetic rate prediction model;

[0059] More specifically, construct a crop photosynthetic rate prediction model based on the LS-SVM algorithm as follows:

[0060]

[0061] where k(ci,c) is the Gaussian kernel function, ai is the Lagrange multiplier, b is the bias term, M is the number of training samples, and the training samples are the photosynthetic rate values under different combinations of environmental factors in the dataset to be analyzed.

[0062] S3. Determine the input cost, plant yield, and economic benefits during the set growth period based on the photosynthetic rate, and construct a cost-benefit estimation model.

[0063] More specifically, S3 includes the following steps:

[0064] Determine the equipment cost: where \(c_i\) is the investment cost of each piece of equipment, including the construction cost of the photovoltaic system;

[0065] Determine the energy consumption cost:

[0066] The photovoltaic system is connected to the grid in the "self-generation for self-use, surplus electricity sold to the grid" mode, that is, when the load is insufficient, the excess photovoltaic power generation is sold to the grid; when the photovoltaic power generation is insufficient, the mains electricity is used for power supplement.

[0067] C 能源 =\(\sum\) t (P 市电，t \(\cdot\)E 市电，t - P 光伏，t \(\cdot\)E 光伏，t )\(\cdot\)dt, where \(P 市电，t \) and \(P 光伏，t \) are the mains electricity price and the photovoltaic power generation selling price in the \(t\)-th period respectively, and \(E 市电，t \) and \(E 光伏，t \) are the mains electricity supplement power and the photovoltaic power generation sold to the grid respectively. The situations of insufficient load and insufficient photovoltaic power generation correspond to the situations of \(E 市电，t = 0\) and \(E 光伏，t = 0\) respectively. Among them, the total power consumption \(E t = E 市电，t + E 自用，t is determined based on the light quality ratio, and \(E 自用，t \) is the power for self-generation for self-use;

[0068] Determine the input cost: \(C = C 设备 + C 能源 \);

[0069] Determine the economic benefits: \(B = Y\cdot P 作物 - C 设备 - C 能源 \), where \(P 作物 \) is the unit crop price; \(Y\) is the predicted yield of the plant in one growth cycle, which is linearly related to the photosynthetic rate \(P n \), \(Y = k\cdot P n + b\), where the parameters \(k\), \(b\) are related to the plant species.

[0070] S4. Construct a cost - photosynthetic rate response curve based on the photosynthetic rates under the different light environment conditions and the cost - benefit estimation model, and perform first - order and second - order differential operations on the cost - photosynthetic rate response curve to determine at least one inflection point on the curve.

[0071] More specifically, S4 includes the following steps:

[0072] Perform a first - order differential on the cost - photosynthetic rate response curve to obtain p'n = dpn / dc, where P'n represents the change rate of the photosynthetic rate with respect to the input cost;

[0073] Perform a second - order differential on the cost - photosynthetic rate response curve to obtain PImn = d 2 pn / dc 2 , where P”n represents the change of the photosynthetic rate change rate with respect to the light intensity;

[0074] Use the hill - climbing method to determine at least one inflection point on the cost - photosynthetic rate response curve where P"n is close to zero.

[0075] S5. Based on the cost - photosynthetic effect analysis, evaluate the economic benefits corresponding to each unit increase in cost at at least one of the inflection points, and determine the inflection point with the maximum economic benefits and the corresponding light quality ratio

[0076] More specifically, S5 includes the following steps:

[0077] Determine the increase in the photosynthetic rate corresponding to each unit increase in the input cost at the inflection point, and determine the inflection point with the maximum economic benefits corresponding to each unit increase in the input cost among several inflection points;

[0078] Determine the increase in the photosynthetic rate at the inflection point with the maximum economic benefits;

[0079] Based on the relationship between the increase in the photosynthetic rate and the preset threshold, determine the inflection point with the maximum photosynthetic rate and use it as the target inflection point;

[0080] Determine the light quality ratio according to the photosynthetic rate at the target inflection point.

[0081] S6. Regulate the light environment for plant growth based on the light quality ratio.

[0082] In some alternative embodiments, in step S6, the fuzzy - control PID algorithm is used to perform a differential comparison between the real - time measured light flux density FFPD, the light flux density PPFDλi of different central wavelengths, and the target value of the light environment control scheme, and adjust the PWM duty cycle of the LED light source to achieve fine regulation of the light intensity, light quality, and light period.

[0083] PWM duty - cycle increment formula:

[0084] ΔDλi = Dλi0 - kλi·(PPFDλi - PPFDλi0)

[0085] Wherein, Dλi0 is the initial duty cycle, and Kλi is the proportionality coefficient.

[0086] Incremental PID adjustment formula:

[0087] ADi 入 i = ADλi - kλi·(PPFDλi - PPFDλi0)

[0088] Supplementary light duration control: Read DLI in real time. When DLI exceeds the target value, stop supplementary light; otherwise, continue supplementary light.

[0089] According to the above embodiments of the present invention, in specific implementation, the light environment optimization control method includes the following processes:

[0090] 1. Data collection and preprocessing: Collect and preprocess sample data.

[0091] 2. Establishment of photosynthesis prediction model: Construct a photosynthetic rate prediction model based on LS-SVM.

[0092] 3. Construct a cost-benefit estimation model

[0093] 4. Determine the cost-photosynthetic rate response curve and determine at least one inflection point.

[0094] 5. Determine the inflection point with the maximum economic benefit and the corresponding light quality ratio.

[0095] 6. Real-time light environment control: Implement real-time light environment control according to the optimized light quality ratio and inflection point information.

[0096] Combined with Figure 2 , based on the same inventive concept, in another embodiment of the present invention, a light environment optimization control system is proposed, which is applied to execute the above light environment optimization control method. The system includes:

[0097] A data acquisition module, configured to acquire a dataset to be analyzed of the plant growth environment, where the dataset to be analyzed includes photosynthetic rate values under different combinations of environmental factors;

[0098] A first prediction module, configured to input the dataset to be analyzed into a photosynthetic rate prediction model pre-constructed based on the LS-SVM algorithm for training, and predict the photosynthetic rate under different light environment conditions based on the trained photosynthetic rate prediction model;

[0099] A second prediction module, configured to determine the input cost, plant yield and economic benefit within a set growth period based on the photosynthetic rate, and construct a cost-benefit estimation model;

[0100] The first analysis module is used to construct a cost - photosynthetic rate response curve based on the photosynthetic rate under the different light environment conditions and the cost - benefit estimation model, and perform first - order and second - order differential operations on the cost - photosynthetic rate response curve to determine at least one inflection point on the curve;

[0101] The second analysis module is used to evaluate the economic benefits corresponding to each unit increase in cost at at least one of the inflection points based on cost - photosynthetic effect analysis, and determine the inflection point with the maximum economic benefits and the corresponding light quality ratio;

[0102] The light environment regulation module is used to regulate the light environment for plant growth based on the light quality ratio.

[0103] It should be noted here that each module in the above - mentioned light environment optimization control system corresponds to steps S1 to S6 in implementing the above - mentioned light environment optimization control method. The examples and application scenarios realized by multiple modules and the corresponding steps are the same, but are not limited to the content disclosed in the above - mentioned Embodiment 1.

[0104] Combined Figure 3 , in another embodiment of the present invention, an intelligent lighting - regulated multi - layer plant factory based on photovoltaic agriculture is proposed. The multi - layer plant factory includes a factory roof 1, a planting rack 2, a growth lighting module 3, and the light environment optimization control system as described above; among them,

[0105] At least two layers of planting racks 2 are arranged below the factory roof 1. The factory roof 1 is interspersed with photovoltaic panels 4 and light - homogenizing plates 5. The photovoltaic panels 4 are used to convert solar energy into electrical energy to supply power to the growth lighting module 3, and the light - homogenizing plates 5 are used to evenly distribute natural light to the upper layer of the planting rack 2;

[0106] Combined Figure 3 , in some optional embodiments, the factory roof adopts a design with photovoltaic panels and light - homogenizing plates interspersed. The function of the photovoltaic panels is to convert solar energy into electrical energy for supplying power to the growth lighting module 3 (LED plant growth lamp) and other devices. The light - homogenizing plates are used to evenly distribute natural light to the lower planting area. The arrangement interval of the photovoltaic panels is determined by the natural light irradiation angle and intensity of the factory. Generally, it is designed that the photovoltaic panels occupy 50% of the roof area, and the light - homogenizing plates occupy the other half of the area.

[0107] The data acquisition module is arranged on each lower layer 7 below the upper layer 6 of the planting rack 2, and is used to periodically acquire a dataset to be analyzed of the plant growth environment on the planting rack 2; specifically, environmental parameter information can be collected by using the wireless network arranged in the plant factory.

[0108] The growth lighting module 3 is arranged on each lower layer 7 below the upper layer 6 of the planting rack 2 and is signal-connected to the light environment control module, and is used to receive the light quality ratio to dynamically adjust the spectral output and intensity of the growth lighting module 3, so as to supplement light for the plants below the upper layer 6 of the planting rack 2.

[0109] It should be noted that the growth lighting module 3 is arranged on each lower layer 7 below the upper layer 6 of the planting rack 2, but is not limited to a specific position, as long as it can provide growth lighting for the plants corresponding to that layer.

[0110] Specifically, the growth lighting module 3 is a mixed light source, including a red light band, a blue light band and a green light band.

[0111] It should be noted that when the above-mentioned light environment optimization control system is specifically implemented, in order to find the optimal light quality ratio, the initial light quality ratio of the plants needs to be set in the system. The initial initial light quality ratio can be obtained from the existing better light quality ratio parameters, and the red, blue and green light powers are uniformly changed at a certain step length. After a certain time interval, the environmental parameters are read to estimate the photosynthetic rate. After cycling through a (red, blue, green light power) change cycle, the optimal light quality ratio interval is found. In the optimal (red, blue, green light power) light quality ratio interval, the optimal light quality ratio determined in the previous cycle is used as the initial optimal light quality ratio, and a new step length is determined to change the red, blue and green light powers.

[0112] It can be understood that the above multi-layer plant factory includes the following processes in specific applications:

[0113] (1) The photovoltaic panel converts solar energy into electrical energy to supply the growth lighting module.

[0114] (2) The light homogenizing plate evenly distributes natural light to the upper layer of the planting rack.

[0115] (3) The data acquisition module periodically acquires the dataset to be analyzed of the plant growth environment.

[0116] (4) The first prediction module constructs and trains a photosynthetic rate prediction model, the second prediction module constructs a cost-benefit estimation model, and then comprehensively constructs a cost-photosynthetic rate response curve.

[0117] (5) The first analysis module determines at least one inflection point on the curve.

[0118] (6) The second analysis module conducts a cost-photosynthetic effect analysis to determine the inflection point with the maximum economic benefit and the corresponding light quality ratio.

[0119] (7) The light environment control module conducts lighting control based on the light quality ratio.

[0120] More specifically, in the light environment control module, the PWM technology and the fuzzy control PID algorithm are used to achieve precise control of the LED light source. According to the light flux density FFPD measured in real time and the light flux density PPFDλi of different central wavelengths, a differential comparison is made with the target value of the light environment control scheme, and the PWM duty cycle of the LED light source is adjusted to achieve fine control of light intensity, light quality, and light period.

[0121] In some alternative embodiments, when conducting planting experiments in a plant factory, finding the optimal light quality ratio is a core step, which is directly related to the growth efficiency and yield of plants. In the initial stage, the growth lighting module 3 uses the optimal light quality ratio of the corresponding plants provided in existing literature as the initial value, and then makes fine adjustments through a series of experimental steps to achieve the optimal effect.

[0122] First, an initial light quality ratio is set according to the literature data, which is usually the lighting conditions found to be more beneficial to the target plants in previous studies. Then, in the plant factory, the spectral output and intensity of the LED lights are adjusted in real time to accurately simulate this initial light quality ratio condition. During the experiment, the growth of the plants is closely monitored, including indicators such as growth rate and biomass accumulation. At the same time, by collecting environmental parameter information and using the light environment optimization control system for data analysis, the impact of the current light quality ratio on plant growth is evaluated.

[0123] Finally, based on the experimental data and the model prediction results, the light quality ratio is gradually adjusted through multiple iterative experiments until the light quality ratio that maximizes the plant growth efficiency is found, thereby achieving precise optimization of the lighting conditions.

[0124] Exemplarily, in the specific planting experiment of the intelligent lighting control multi-layer plant factory based on the present invention's optoelectronic agriculture, when the planting rack is set to 4 layers, the topmost planting rack directly uses sunlight, and the remaining layers use LED light sources. The solar energy is distributed to the four layers of plants through the photovoltaic panels on the factory roof, that is, wavelength transportation and space-time transportation are realized. Wavelength transportation specifically transports most of the unusable wavelengths in solar light to the wavelengths required by plants. Space-time transportation specifically means that when sunlight is strong, the excess solar energy is used to generate electricity through solar panels to supply the LED light sources. When sunlight is insufficient, relatively cheap commercial power can be used to supply the LED system.

[0125] In some alternative embodiments, the design of the photovoltaic system grid connection allows the use of commercial power to supply power to the plant LED supplementary lights during periods of weak light intensity (such as at night or on cloudy days). Especially during the low electricity consumption period, the electricity price is low. By using electricity during off-peak hours, the operating cost can be significantly reduced. This method effectively combines renewable energy and traditional electricity, optimizes the utilization efficiency of resources, and provides continuous lighting conditions for the healthy growth of aquatic plants.

[0126] Exemplarily, assume that the power generation efficiency of the photovoltaic panel is 20%. When the photovoltaic panel is operating at full load, it can provide approximately 200 W of electricity per square meter of LED lights per day. The electro-optical conversion efficiency of the LED lights is 50%, and 50% of the electrical energy is used for lighting. The light quality ratio is R / B / G (red / blue / green): 4 / 2 / 1. Through measurement, the irradiance of the LED plant growth light in the red light band is 120 μmol / m 2 / s, and the irradiance in the blue light band is 80 μmol / m 2 / s. Compared with natural light, the light intensity of the LED lamps in the red and blue light bands is significantly enhanced. The red light irradiance has increased by approximately 6 times, and the blue light irradiance has increased by approximately 8 times.

[0127] Under optimized lighting conditions, during the duckweed cultivation experiment, the growth rate of duckweed has increased significantly. The experimental data shows that under traditional cultivation conditions (under natural light, the solar irradiance is approximately 50 μmol / m 2 / s): the growth rate of duckweed is approximately 5 - 7 grams per square meter per day. Under the cultivation conditions of the present invention (combining photovoltaic power generation and LED supplementary lighting, the red and blue light irradiances are 120 and 80 μmol / m 2 / s respectively): the growth rate of duckweed has increased to 20 - 25 grams per square meter per day. This significant increase in the growth rate is mainly attributed to the enhanced directional lighting provided by the LED plant growth lights, especially the precise supplementation in the red and blue light bands, which greatly improves the photosynthesis efficiency of duckweed, thereby accelerating its growth cycle.

[0128] It can be understood that the intelligent lighting control multi-layer plant factory based on photoelectric agriculture of the present invention is not only applicable to the cultivation of duckweed, but also applicable to other common plants, not limited to aquatic plants, such as algae, calamus, etc. Different plants have different lighting requirements. The above light environment optimization control system can adjust the spectral output of the LED lights according to the photosynthesis response of different plants to meet their specific growth needs.

[0129] In another embodiment provided by the present invention, there is also provided a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above light environment optimization control methods are implemented.

[0130] In another embodiment provided by the present invention, there is also provided a computer program product containing instructions. When it runs on a computer, it causes the computer to execute the steps of any of the above light environment optimization control methods in the embodiments.

[0131] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can 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 a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part.

[0132] The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from a website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more integrated available media. The available medium may be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)).

[0133] The above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A light environment optimization control method, characterized in that: The method comprises: Obtain the data set to be analyzed of the plant growth environment, including the photosynthetic rate values ​​under different combinations of environmental factors; Inputting the data set to be analyzed into a photosynthetic rate prediction model pre-constructed based on the LS-SVM algorithm for training, and predicting the photosynthetic rate under different light environment conditions based on the trained photosynthetic rate prediction model; Determining the input cost, plant yield and economic benefit within a set growth cycle based on the photosynthetic rate, and constructing a cost-benefit estimation model; Constructing a cost-photosynthetic rate response curve based on the photosynthetic rate under the different light environment conditions and the cost-benefit estimation model, and performing first-order and second-order differential operations on the cost-photosynthetic rate response curve to determine at least one inflection point on the curve; Based on the cost-photosynthetic effect analysis, the economic benefit corresponding to each unit cost increase at at least one of the inflection points is evaluated, and the inflection point with the greatest economic benefit and the corresponding light quality ratio are determined; The light environment for plant growth is regulated based on the light quality ratio.

2. A light environment optimization control method according to claim 1, characterized in that: The environmental factors include CO2 concentration, air temperature, air relative humidity, soil pH value, soil EC value, light flux density PPFD, and light flux density PPFDλi at different central wavelengths, i=1...m, m is an integer greater than 1.

3. A light environment optimization control method according to claim 2, characterized in that: After obtaining the data set to be analyzed of the plant growth environment data, the method further includes: Eliminating abnormal data points and normalizing the data set to be analyzed; and, Correlation screening was performed, and the gray correlation coefficient between each environmental factor and the photosynthetic rate was determined based on the gray correlation analysis method. The data were sorted and screened according to the size of the gray correlation coefficient to obtain the screened data set to be analyzed.

4. A light environment optimization control method according to claim 3, characterized in that: Determining the input cost, plant yield and economic benefit within a set growth cycle based on the photosynthetic rate, and constructing a cost-benefit estimation model, includes: Determine the cost of the equipment: Where ci is the investment cost of each equipment; Determine the cost of energy consumption: C 能源 =∑ t (P 市电，t ·E 市电，t -P 光伏，t ·E 光伏，t )·dt, where P 市电 t and P 光伏 t are the city electricity price and photovoltaic power generation grid-connected price in the tth period, E 市电 t and E 光伏 t are the mains power replenishment power and photovoltaic power generation power. Determine input cost: C = C 设备 +C 能源 ; Determine economic benefits: B = Y·P 作物 -C 设备 -C 能源 , where P 作物 is the unit crop price; Y is the predicted yield of the plant in one growth cycle, which is related to the photosynthetic rate P n Into a linear relationship, Y = k·P n +b, where parameters k and b are related to the plant species.

5. A light environment optimization control method according to claim 4, characterized in that: Performing first-order and second-order differential operations on the cost-photosynthetic rate response curve to determine at least one inflection point on the curve includes: Taking the first-order differential of the cost-photosynthetic rate response curve, we get p'n = dpn / dc, where P'n represents the rate of change of photosynthetic rate with input cost; Taking the second-order differential of the cost-photosynthetic rate response curve, we get PImn=d 2 pn / dc 2 , P”n represents the rate of change of photosynthetic rate with the change of light intensity; The ramp method was used to determine at least one inflection point on the cost-photosynthetic rate response curve where P"n was close to zero.

6. A light environment optimization control method according to claim 5, characterized in that: The cost-photosynthetic effect analysis is based on evaluating the economic benefit corresponding to each unit cost increase at at least one of the inflection points, and determining the inflection point with the greatest economic benefit and the corresponding light quality ratio, including: Determine the increase in photosynthetic rate corresponding to each increase in unit input cost at the inflection point, and determine the maximum inflection point of economic benefit corresponding to each increase in unit input cost among the inflection points; Determine the increase in photosynthetic rate at the inflection point of maximum economic benefit; Based on the relationship between the photosynthetic rate increase and the preset threshold, determining the inflection point where the photosynthetic rate is maximum and using it as the target inflection point; The light quality ratio is determined according to the photosynthetic rate at the target inflection point.

7. Light environment optimization control system, characterized in that: Applied to executing the light environment optimization control method according to any one of claims 1 to 6, the system comprises: A data acquisition module, used to acquire a data set to be analyzed of a plant growth environment, wherein the data set to be analyzed includes photosynthetic rate values ​​under different combinations of environmental factors; The first prediction module is used to input the data set to be analyzed into a photosynthetic rate prediction model pre-constructed based on the LS-SVM algorithm for training, and predict the photosynthetic rate under different light environment conditions based on the trained photosynthetic rate prediction model; A second prediction module is used to determine the input cost, plant yield and economic benefit within a set growth cycle based on the photosynthetic rate, and to construct a cost-benefit estimation model; A first analysis module is used to construct a cost-photosynthetic rate response curve based on the photosynthetic rate under the different light environment conditions and the cost-benefit estimation model, and perform first-order and second-order differential operations on the cost-photosynthetic rate response curve to determine at least one inflection point on the curve; The second analysis module is used to evaluate the economic benefit corresponding to each unit cost increase at at least one of the inflection points based on cost-photosynthetic effect analysis, and determine the inflection point with the maximum economic benefit and the corresponding light quality ratio; The light environment control module is used to control the light environment for plant growth based on the light quality ratio.

8. Intelligent light control multi-layer plant factory based on photovoltaic agriculture, characterized by: The multi-storey plant factory comprises a factory roof, a planting rack, a growth lighting module and a light environment optimization control system as claimed in claim 7; wherein, At least two layers of planting racks are arranged under the factory roof, and photovoltaic panels and light-diffusing plates are alternately distributed on the factory roof. The photovoltaic panels are used to convert solar energy into electrical energy to power the growth lighting module, and the light-diffusing plates are used to evenly distribute natural light to the upper layer of the planting racks; The data acquisition module is arranged at each layer below the upper layer of the planting rack, and is used to periodically acquire the data set to be analyzed of the plant growth environment on the planting rack; The growth lighting module is arranged at each layer below the upper layer of the planting rack and is connected to the light environment control module signal to receive the light quality ratio to dynamically adjust the spectral output and intensity of the growth lighting module to provide supplementary light for the plants below the upper layer of the planting rack.

9. The intelligent light-controlled multi-storey plant factory based on photovoltaic agriculture according to claim 8 is characterized in that: The growth lighting module is specifically a mixed light source, including a red light band, a blue light band and a green light band.

Images