Dynamic optimization method for soilless culture nutrient solution

Abstract

The invention relates to the technical field of soilless culture nutrient solution dynamic optimization, and particularly discloses a soilless culture nutrient solution dynamic optimization method which comprises the steps of multi-source fusion monitoring data set generation, main nutrient element demand prediction, nutrient solution adjustment instruction set generation and nutrient solution adjustment effect evaluation. According to the invention, environment, plant physiology and nutrient solution state data are synchronously acquired, a short-term demand prediction model is utilized to predict nutritional demands, and an adjustment instruction set containing the supplement amount and supplement rate of the current nutrient solution is generated in combination with a plant growth stage, a current nutrient solution state and an environment factor; the adjustment effect of the nutrient solution adjustment instruction set is obtained by comprehensively evaluating the improvement degree of the plant physiological status and the stability of the nutrient solution after adjustment is finished; dynamic matching of nutrient solution supply and plant requirements is achieved, the nutrient utilization efficiency is improved, the adaptability of the system to environment changes is enhanced, and remarkable economic benefits and social benefits are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of dynamic optimization of soilless culture nutrient solution, and more particularly, to a method for dynamically optimizing soilless culture nutrient solution. Background Art

[0002] As an important part of modern agriculture, soilless culture technology provides plants with the necessary nutrients through nutrient solution instead of soil, and has the advantages of high yield, excellent quality, and strong controllability. With the development of facility agriculture, higher requirements are put forward for the precise management of nutrient solution. In order to adapt to the dynamic changes in nutrient requirements of plants at different growth stages and environmental changes, it is necessary to conduct dynamic optimization analysis on soilless culture nutrient solution.

[0003] The following problems still exist in the prior art: 1. Only partial physical and chemical indexes of the nutrient solution are often concerned, and environmental factors (such as light intensity, air temperature, humidity, carbon dioxide concentration, etc.) and plant physiological states (such as leaf area change rate, transpiration rate, etc.) are not comprehensively considered, resulting in inaccurate judgment of plant nutrient requirements, single monitoring data, and lack of multi-source fusion analysis.

[0004] It is impossible to effectively predict the nutrient requirements in the short term in the future based on historical data and current states, and it is difficult to achieve forward-looking adjustment of nutrient solution, often resulting in nutrient supply lagging behind the actual needs of plants.

[0005] When generating nutrient solution adjustment instructions, the plant growth stage, current nutrient solution state, environmental factors, and demand prediction data are not fully combined for comprehensive analysis. The adjustment strategy is relatively fixed and lacks adaptability. At present, only the adjustment instructions for the nutrient solution supplement amount are generated, and the adjustment instructions for the nutrient solution supplement rate are not generated, with obvious adjustment defects and being not conducive to plant growth.

[0006] The existing evaluation of the effect after nutrient solution adjustment mostly focuses on the evaluation of plant physiological states, and does not pay attention to the stability of the nutrient solution after adjustment, making it impossible to scientifically judge the effectiveness of adjustment measures and reducing the comprehensiveness and persuasiveness of the adjustment effect evaluation. Summary of the Invention

[0007] In view of this, in order to solve the problems raised in the above background art, a method for dynamically optimizing soilless culture nutrient solution is proposed.

[0008] The object of the present invention can be achieved by the following technical solutions: The present invention provides a method for dynamically optimizing soilless culture nutrient solution, including the following steps: S1. Generation of multi-source fusion monitoring data set: Synchronously obtain environmental monitoring data, plant physiological state monitoring data, and nutrient solution state monitoring data of the target cultivation area, and generate a multi-source fusion monitoring data set.

[0009] S2. Prediction of the demand for main nutrient elements: Based on the multi-source fusion monitoring data set, run a preset short-term demand prediction model to generate dynamic demand prediction data for main nutrient elements within a preset future time window.

[0010] S3. Generation of nutrient solution adjustment instruction set: Extract the current growth stage of the plants in the target cultivation area, obtain the current nutrient solution status monitoring data and the current environmental monitoring data, and execute an adaptive optimization decision in combination with the dynamic demand prediction data to generate a nutrient solution adjustment instruction set.

[0011] S4. Evaluation of the effect of nutrient solution adjustment: Execute the nutrient solution adjustment instruction set, and based on the adjusted nutrient solution status monitoring data and the plant physiological status monitoring data, evaluate the execution effect index of the nutrient solution adjustment instruction set, thereby evaluating the adjustment effect of the current nutrient solution and making corresponding feedback, where the adjustment effect includes general, good, and very good.

[0012] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects: (1) By synchronously obtaining environmental monitoring data, plant physiological status monitoring data, and nutrient solution status monitoring data, the present invention generates a multi-source fusion monitoring data set, realizing comprehensive and accurate monitoring of the cultivation environment and the plant growth status, and providing a reliable basis for subsequent nutrient demand prediction and adjustment.

[0013] By running a preset short-term demand prediction model based on the multi-source fusion monitoring data set, the present invention can generate dynamic demand prediction data for main nutrient elements within a preset future time window, making the nutrient solution adjustment forward-looking, meeting the nutrient needs of plants in advance, and improving the nutrient utilization efficiency.

[0014] By making an adaptive optimization decision in combination with the plant growth stage, the current nutrient solution status, environmental factors, and demand prediction data, the present invention generates a scientific and reasonable nutrient solution supplement amount and supplement rate, realizing the precise matching of the nutrient solution supply and the actual needs of plants, and promoting the healthy growth of plants.

[0015] By comprehensively analyzing the improvement degree of the plant physiological status and the stability of the nutrient solution after the adjustment, the present invention obtains the execution effect index of the nutrient solution adjustment instruction set, forming a closed-loop management system of "monitoring - prediction - adjustment - evaluation - feedback", which can continuously optimize the adjustment strategy according to the adjustment effect, continuously improve the accuracy and effectiveness of nutrient solution management, increase the crop yield and quality, and reduce the production cost. Description of the Drawings

[0016] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0017] Figure 1 It is a schematic flow chart of the method steps of the present invention.

[0018] Figure 2 It is a schematic diagram for predicting the demand for main nutrients of the present invention.

[0019] Figure 3 It is a flow chart for generating the replenishment rate of the current nutrient solution of the present invention. Specific embodiments

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0021] Please refer to Figure 1 As shown, the present invention provides a method for dynamically optimizing a soilless cultivation nutrient solution, including: S1. Generation of a multi-source fusion monitoring data set: synchronously obtain environmental monitoring data, plant physiological state monitoring data, and nutrient solution state monitoring data of a target cultivation area, and generate a multi-source fusion monitoring data set.

[0022] In a specific embodiment of the present invention, the environmental monitoring data includes light intensity, air temperature, air humidity, carbon dioxide concentration, and nutrient solution temperature, the plant physiological state monitoring data includes leaf area change rate and plant transpiration rate, and the nutrient solution state monitoring data includes the concentrations of main nutrient elements.

[0023] It should be noted that the light intensity, air temperature, air humidity, carbon dioxide concentration, and nutrient solution temperature are respectively collected in real time through light sensors, temperature and humidity sensors, carbon dioxide sensors, and nutrient solution temperature sensors deployed in the target cultivation area.

[0024] It should also be noted that the collection methods of the leaf area change rate and the plant transpiration rate are as follows: plant images are collected through image acquisition devices deployed in the target cultivation area, the leaf contours are identified through image segmentation algorithms, the current leaf area is calculated in combination with pixel calibration relationships, and the leaf area change rate is generated by comparing with the historical leaf area. At the same time, the plant transpiration rate is directly measured by installing a preset sap flow sensor on the plant stem.

[0025] It should also be noted that the concentrations of the main nutrient elements in the nutrient solution are collected in real time through the arranged preset ion-selective electrodes, where the main nutrient elements include but are not limited to nitrogen N, phosphorus P, potassium K, calcium Ca, and magnesium Mg.

[0026] In the embodiment of the present invention, by synchronously acquiring environmental monitoring data, plant physiological state monitoring data, and nutrient solution state monitoring data, a multi-source fusion monitoring dataset is generated, realizing comprehensive and accurate monitoring of the cultivation environment and plant growth state, providing a reliable basis for subsequent prediction and adjustment of nutrient requirements.

[0027] S2. Prediction of the demand for main nutrient elements: Based on the multi-source fusion monitoring dataset, a preset short-term demand prediction model is run to generate dynamic demand prediction data for the main nutrient elements within a preset future time window.

[0028] Please refer to Figure 2 As shown, in a specific embodiment of the present invention, the specific process of running the preset short-term demand prediction model is as follows: Extract the current and recent historical environmental monitoring data subset and plant physiological state monitoring data subset from the multi-source fusion monitoring dataset.

[0029] It should be noted that the environmental monitoring data subset includes time series data of light intensity, air temperature, air humidity, and carbon dioxide concentration, and the plant physiological state monitoring data subset includes time series data of leaf area change rate and plant transpiration rate. After aligning the above two data subsets according to the time stamp, they are input into the preset short-term demand prediction model.

[0030] Input the environmental monitoring data subset and the plant physiological state monitoring data subset into the preset short-term demand prediction model.

[0031] It should be noted that the preset short-term demand prediction model is configured to learn the dynamic mapping relationship between the combination of current and recent historical environmental data and plant physiological state data and the future short-term change in the demand for main nutrient elements. The model processes the input data through a mapping function completed by internal training, and the mapping function is expressed as , where represents the standardized matrix of the environmental monitoring data subset, represents the standardized matrix of the plant physiological state monitoring data subset, is the non-linear mapping relationship obtained by the model through training with historical data, is the change trend of the relative absorption rate of the main nutrient elements (nitrogen N, phosphorus P, potassium K, calcium Ca, magnesium Mg) within the preset future time window output.

[0032] Output the relative absorption rate change trend value of the main nutrient elements within the preset future time window by the preset short-term demand prediction model as the dynamic demand prediction data.

[0033] In the embodiment of the present invention, by running a preset short-term demand prediction model based on a multi-source fusion monitoring data set, dynamic demand prediction data of the main nutrient elements within a preset future time window can be generated, making the adjustment of nutrient solution forward-looking, meeting the nutritional needs of plants in advance, and improving the nutrient utilization efficiency.

[0034] S3. Generation of nutrient solution adjustment instruction set: Extract the current growth stage of the plants in the target cultivation area, obtain the current nutrient solution state monitoring data and the current environmental monitoring data, and combine the dynamic demand prediction data to execute an adaptive optimization decision to generate a nutrient solution adjustment instruction set.

[0035] It should be noted that the current growth stage of the plants is extracted from the plant growth manual of the target cultivation area, and the current nutrient solution state monitoring data and the current environmental monitoring data are both extracted from the multi-source fusion monitoring data set.

[0036] In a specific embodiment of the present invention, the specific process of executing the adaptive optimization decision is as follows: Based on the concentrations of the main nutrient elements in the current nutrient solution state monitoring data and the target lower limit concentration and target upper limit concentration of each main nutrient element corresponding to each growth stage of the plants stored in the database, perform deviation analysis to evaluate the deviation value between the concentration of each main nutrient element in the current nutrient solution and the preset target concentration range.

[0037] In a specific embodiment of the present invention, the specific method for evaluating the deviation value between the concentration of each main nutrient element in the current nutrient solution and the preset target concentration range is as follows: Match the current growth stage of the plants in the target cultivation area with the target lower limit concentration and target upper limit concentration of each main nutrient element corresponding to each growth stage of the plants to obtain the target lower limit concentration and target upper limit concentration of each main nutrient element corresponding to the current growth stage of the plants.

[0038] When the concentration of a certain main nutrient element in the current nutrient solution is less than the target lower limit concentration of this main nutrient element, subtract the concentration from the target lower limit concentration of this main nutrient element, and use the ratio of the difference value to the target lower limit concentration as the deviation value of this main nutrient element.

[0039] When the concentration of a certain main nutrient element in the current nutrient solution is greater than the target upper limit concentration of this main nutrient element, subtract the target upper limit concentration from the concentration of this main nutrient element, and use the ratio of the difference value to the target upper limit concentration as the deviation value of this main nutrient element.

[0040] When the concentration of a certain main nutrient element in the current nutrient solution is between the target lower limit concentration and the target upper limit concentration of the main nutrient element, the deviation value of the main nutrient element is recorded as 0.

[0041] In summary, the deviation values of the concentrations of the main nutrient elements in the current nutrient solution from the preset target concentration ranges are obtained.

[0042] Fusing the dynamic demand prediction data, calculate the demand change coefficients of the main nutrient elements within a preset future time window.

[0043] It should be noted that the specific method for calculating the demand change coefficients of the main nutrient elements within a preset future time window is as follows: Extract the relative absorption rate change trend values of the main nutrient elements within a preset future time window from the dynamic demand prediction data and denote them as , where represents the number of the main nutrient element, .

[0044] Calculate the demand change coefficients of the main nutrient elements within a preset future time window , , where is the preset sensitivity coefficient.

[0045] In a specific embodiment of the present invention, the preset sensitivity coefficient generally comes from a large amount of historical experimental data, long-term production practice experience, and research results on specific crops. In terms of value, it is usually adjusted according to factors such as crop type, growth stage, and environmental conditions, and the common value range is between 0 and 1. For example, for leafy vegetables that are sensitive to nutrient requirements and grow rapidly, during the rapid growth period, may take a relatively large value, such as 0.6 - 0.8, to respond more quickly to changes in nutrient requirements, while for crops with slow growth and relatively stable nutrient requirements, may take a value between 0.1 and 0.3.

[0046] It should be further noted that the design logic of the above formula is to quantify the demand changes of the main nutrient elements within a preset future time window. By extracting the relative absorption rate change trend values of the main nutrient elements, it reflects the dynamic changes in the crop's demand for different nutrient elements. On this basis, the preset sensitivity coefficient , adjusting the relative absorption rate change trend by amplifying or reducing it, and then calculating the demand change coefficient. This way, when the relative absorption rate change trend is positive (i.e., demand increases), the coefficient calculation will increase the expected supply of that nutrient element accordingly. When the relative absorption rate change trend is negative (i.e., demand decreases), the supply can be timely reduced, achieving dynamic optimization of nutrient solution composition to meet the nutritional needs of crops at different times and in different states.

[0047] Combined with the light intensity, air temperature, air humidity and carbon dioxide concentration in the current environmental monitoring data, the constraint coefficient of environmental factors on the absorption efficiency of nutrient elements is evaluated.

[0048] In a specific embodiment of the present invention, the specific method of evaluating the constraint coefficient of environmental factors on nutrient element absorption efficiency is: extracting the optimal values corresponding to light intensity, air temperature, air humidity and carbon dioxide concentration of plants during their growth process from the database.

[0049] Obtain the absolute value deviations between the current environment's light intensity, air temperature, air humidity, and carbon dioxide concentration and their corresponding optimal values, subtract the absolute value deviations from the set reference deviations, and then compare the difference with the set reference deviations to obtain the constraint coefficients of the current environment's light intensity, air temperature, air humidity, and carbon dioxide concentration on the nutrient absorption efficiency.

[0050] Based on the light intensity, air temperature, air humidity and carbon dioxide concentration of the current environment, a comprehensive analysis of the constraint coefficients of nutrient element absorption efficiency was conducted to obtain the constraint coefficients of environmental factors on nutrient element absorption efficiency.

[0051] It should be noted that the specific method of obtaining the constraint coefficient of the environmental factors on the absorption efficiency of nutrient elements is as follows: the constraint coefficients of the current environment's light intensity, air temperature, air humidity and carbon dioxide concentration on the absorption efficiency of nutrient elements are recorded as 、 、 and .

[0052] Calculate the constraint coefficient of environmental factors on nutrient absorption efficiency , ,in, 、 、 and Respectively represent the weights of the constraint coefficients corresponding to light intensity, air temperature, air humidity and carbon dioxide concentration, Represents a natural constant.

[0053] In a specific embodiment of the present invention, in soilless cultivation, the constraint coefficient of environmental factors on the absorption efficiency of plant nutrient elements can be calculated by weighted calculation of the constraint coefficients of light intensity, air temperature, air humidity, and carbon dioxide concentration and their corresponding proportion weights, where the proportion weight of air temperature is usually the largest. This is because temperature directly affects the enzyme activity, membrane permeability, and respiration intensity of root cells. Light intensity mainly indirectly regulates the root absorption ability by affecting the synthesis of photosynthesis products, but its effect can only be reflected through the transport of photosynthetic products to the roots, with timeliness and influence range inferior to temperature. Air humidity mainly affects the transpiration rate, thereby changing the efficiency of nutrient transport with water, which is an indirect effect and has a relatively low intensity. Carbon dioxide concentration indirectly affects the root energy supply by affecting the photosynthetic efficiency of the above-ground part, and its constraint effect on the absorption efficiency is relatively weaker. Generally speaking, air temperature usually occupies a dominant position in the proportion weights of various environmental factors, followed by light intensity, air humidity, and carbon dioxide concentration. Therefore, 、 、 and can take values of 0.25, 0.5, 0.15, and 0.1.

[0054] Based on the deviation value, the demand change coefficient, and the constraint coefficient, coupling processing is performed to generate the supplementary amount of the current nutrient solution.

[0055] It should be noted that the specific formula for generating the supplementary amount of the current nutrient solution is expressed as: where, represents the supplementary amount of the current nutrient solution, represents the deviation value between the concentration of the th main nutrient element in the current nutrient solution and the preset target concentration range, respectively represent the supplementary amount of the nutrient solution required corresponding to the unit concentration deviation and the unit demand change coefficient of the th main nutrient element stored in the database, represents the number of main nutrient elements.

[0056] Based on the air temperature and the nutrient solution temperature in the current environmental monitoring data and the standard supplementary rate of the nutrient solution stored in the database, analysis is performed to generate the supplementary rate of the current nutrient solution.

[0057] Please refer to Figure 3As shown, in a specific embodiment of the present invention, the specific method for generating the replenishment rate of the current nutrient solution is as follows: Obtain the absolute value of the temperature deviation between the air temperature and the nutrient solution temperature in the current environmental monitoring data, and compare the absolute value of the temperature deviation with the temperature deviation threshold. If the absolute value of the temperature deviation is less than or equal to the temperature deviation threshold, the standard replenishment rate of the nutrient solution remains unchanged. If the absolute value of the temperature deviation is greater than the temperature deviation threshold, multiply the absolute value of the temperature deviation by the proportion of the replenishment rate reduction required corresponding to the unit temperature deviation stored in the database to obtain the required proportion of the replenishment rate reduction for the current nutrient solution, and use the product of the standard replenishment rate of the nutrient solution and the required proportion of the replenishment rate reduction as the replenishment rate of the current nutrient solution.

[0058] It should be noted that when the absolute value of the temperature deviation between the air temperature and the nutrient solution temperature is greater than the temperature deviation threshold, the replenishment rate decreases because a too large temperature difference is likely to cause an imbalance in the osmotic pressure of root cells, physiological damage, break the transpiration-absorption balance, and also trigger the risk of microbial and root respiration. For example, when the liquid temperature is too low in a high-temperature environment, the water absorption capacity of the roots is limited, and rapid replenishment of the nutrient solution will exacerbate plant water loss and salt damage. While too high a liquid temperature will lead to root hypoxia and abnormal microbial reproduction. Increasing the replenishment rate cannot solve the fundamental problem but will instead exacerbate concentration fluctuations and increase energy consumption. Therefore, there is no situation of increasing the replenishment rate.

[0059] In a specific embodiment of the present invention, the temperature deviation threshold can be set to 5°C, which is obtained from a large number of physiological experiments and production practices. Research shows that when the temperature difference of the roots of most crops reaches 5°C, the mitochondrial membrane potential of the root tip cells decreases, the ATP synthesis efficiency begins to decline, the number of root hairs decreases, and the nutrient absorption efficiency significantly decreases. From the production data, when the temperature difference is controlled within 5°C, the crop yield fluctuation < 5%. When it exceeds 5°C, the yield decreases by an average of 12%. This temperature deviation threshold of 5°C can effectively balance the physiological functions of the roots and environmental adaptability, ensure the nutrient absorption efficiency and the stable growth of crops, so it is widely used as the key threshold for temperature difference management.

[0060] In summary, the generated replenishment amount and replenishment rate of the current nutrient solution are used as the nutrient solution adjustment instruction set.

[0061] The embodiment of the present invention generates a scientific and reasonable nutrient solution replenishment amount and replenishment rate through adaptive optimization decision-making by combining the plant growth stage, the current nutrient solution state, environmental factors, and demand prediction data, realizing the precise matching of the nutrient solution supply and the actual needs of plants, and promoting the healthy growth of plants.

[0062] S4. Nutrient solution adjustment effect evaluation: Execute the nutrient solution adjustment instruction set, and based on the adjusted nutrient solution status monitoring data and plant physiological status monitoring data, evaluate the execution effect index of the nutrient solution adjustment instruction set, thereby evaluating the adjustment effect of the current nutrient solution and providing corresponding feedback, where the adjustment effect includes general, good, and very good.

[0063] In a specific embodiment of the present invention, the specific process of evaluating the execution effect index of the nutrient solution adjustment instruction set is as follows: Based on the leaf area change rate and transpiration rate change rate in the adjusted plant physiological status monitoring data and the leaf area change rate and transpiration rate change rate before adjustment, the improvement degree of the plant physiological status after the adjustment is obtained through physiological status analysis.

[0064] It should be noted that the specific process of obtaining the improvement degree of the plant physiological status after the adjustment is as follows: Subtract the leaf area change rate before adjustment from the leaf area change rate after adjustment to obtain the difference in leaf area change rate before and after adjustment.

[0065] Subtract the transpiration rate change rate before adjustment from the transpiration rate change rate after adjustment to obtain the difference in transpiration rate change rate before and after adjustment.

[0066] Subtract the difference in leaf area change rate and the difference in transpiration rate change rate before and after adjustment from their corresponding reference values respectively, and then take the ratio of the difference to the corresponding reference value, and add the two ratio results to obtain the improvement degree of the plant physiological status after the adjustment.

[0067] It should be further noted that the rationality of obtaining the improvement degree of the plant physiological status after the adjustment is reflected in the following: Based on the two core physiological indicators of leaf area change rate and transpiration rate change rate, the leaf area intuitively reflects the plant growth and propagation ability, and the transpiration rate is related to the water and nutrient absorption efficiency. The two jointly determine the plant physiological status. Through the dual logic of "comparing the difference before and after adjustment + normalizing with the reference value", first, the actual impact of the adjustment is reflected by the difference, and then the ratio with the reference value is used to eliminate the dimensional difference of the indicators, so that the two different-dimensional indicators of leaf area and transpiration rate can be quantitatively added. The finally synthesized improvement degree not only focuses on the core physiological needs of the plant, but also realizes the collaborative evaluation of multiple indicators through standardization processing, can scientifically reflect the true optimization effect of the nutrient solution adjustment on the plant physiological status, and conforms to the goal of promoting plant healthy growth through precise nutrient regulation in soilless cultivation.

[0068] Based on the concentration of each main nutrient element at each monitoring time point in the adjusted nutrient solution status monitoring data, perform stability analysis to obtain the nutrient solution stability after the adjustment.

[0069] In a specific embodiment of the present invention, the specific process of obtaining the stability of the nutrient solution after adjustment is as follows: Compare the concentrations of each main nutrient element at each monitoring time point after adjustment with the preset target concentration range of each main nutrient element. When the concentration of a certain main nutrient element at a certain monitoring time point is not within the preset target concentration range of this main nutrient element, then record this monitoring time point as the starting time point of unstable concentration, and record the time interval between the starting monitoring time point after adjustment and the starting time point of unstable concentration as the concentration stability duration.

[0070] It should be noted that the preset target concentration range of each main nutrient element is obtained by combining the target lower limit concentration and the target upper limit concentration of this main nutrient element.

[0071] Take the difference between the concentration stability duration after adjustment and the set reference concentration stability duration, and calculate the ratio of the difference to the set reference concentration stability duration to obtain the stability of the nutrient solution after adjustment.

[0072] Perform weighted calculation and summation on the improvement degree of the plant physiological state and the stability of the nutrient solution after adjustment and their corresponding proportion weights to obtain the execution effect index of the nutrient solution adjustment instruction set.

[0073] In a specific embodiment of the present invention, when calculating the execution effect index of the nutrient solution adjustment instruction set, the proportion weight of the improvement degree of the plant physiological state is usually larger. This is because the plant physiological state directly reflects the actual effect of nutrient adjustment on crop growth and is the core index for measuring cultivation effects. While the stability of the nutrient solution mainly characterizes the stability of the concentration physicochemical properties of nutrient components and is the environmental basis for maintaining the healthy growth of plants. Its essence is to provide suitable conditions for plant physiological activities. In contrast, the improvement degree of the plant physiological state can better reflect the final effect of the adjustment measures and is a direct manifestation of the cultivation goal. The stability of the nutrient solution belongs to the guarantee means. Therefore, in the weighted calculation, the weight of the improvement degree of the plant physiological state is usually higher to highlight the attention to the core needs of plant growth. Therefore, the proportion weights of the improvement degree of the plant physiological state and the stability of the nutrient solution can be taken as 0.6 and 0.4 respectively.

[0074] In a specific embodiment of the present invention, the specific method for evaluating the adjustment effect of the current nutrient solution is as follows: Compare the execution effect index of the nutrient solution adjustment instruction set with the execution effect index intervals corresponding to each adjustment effect stored in the database. If the execution effect index of the nutrient solution adjustment instruction set is within the execution effect index interval corresponding to a certain adjustment effect, then take this adjustment effect as the adjustment effect of the current nutrient solution.

[0075] In the embodiments of the present invention, by comprehensively analyzing the improvement degree of the plant physiological state and the nutrient solution stability after the adjustment is completed, the execution effect index of the nutrient solution adjustment instruction set is obtained, forming a closed-loop management system of "monitoring - prediction - adjustment - evaluation - feedback", which can continuously optimize the adjustment strategy according to the adjustment effect, continuously improve the accuracy and effectiveness of nutrient solution management, increase crop yield and quality, and reduce production costs.

[0076] The above content is only an example and illustration of the concept of the present invention. Those skilled in the art of the present technology can make various modifications or supplements to the described specific embodiments or use similar methods for substitution, as long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they should fall within the protection scope of the present invention.

Claims

1. A method for dynamically optimizing a soilless culture nutrient solution, characterized in that It includes the following steps: S1. Generation of multi-source fusion monitoring dataset: Synchronously obtain the environmental monitoring data, plant physiological state monitoring data, and nutrient solution state monitoring data of the target cultivation area, and generate a multi-source fusion monitoring dataset; S2. Prediction of the demand for main nutrient elements: Based on the multi-source fusion monitoring dataset, run a preset short-term demand prediction model to generate dynamic demand prediction data for main nutrient elements within a preset future time window; S3. Generation of nutrient solution adjustment instruction set: Extract the current growth stage of the plants in the target cultivation area, obtain the current nutrient solution state monitoring data and current environmental monitoring data, and combine the dynamic demand prediction data to execute an adaptive optimization decision to generate a nutrient solution adjustment instruction set; S4. Evaluation of the effect of nutrient solution adjustment: Execute the nutrient solution adjustment instruction set, and based on the adjusted nutrient solution state monitoring data and plant physiological state monitoring data, evaluate the execution effect index of the nutrient solution adjustment instruction set, thereby evaluating the adjustment effect of the current nutrient solution and giving corresponding feedback, where the adjustment effect includes general, good, and very good.

2. The dynamic optimization method for soilless cultivation nutrient solution according to claim 1, wherein: The environmental monitoring data includes light intensity, air temperature, air humidity, carbon dioxide concentration, and nutrient solution temperature. The plant physiological state monitoring data includes leaf area change rate and plant transpiration rate. The nutrient solution state monitoring data includes the concentrations of various main nutrient elements.

3. The dynamic optimization method for soilless culture nutrient solution according to claim 2, wherein: The specific process of running the preset short-term demand prediction model is as follows: Extract the current and recent historical environmental monitoring data subset and plant physiological state monitoring data subset from the multi-source fusion monitoring dataset; Input the environmental monitoring data subset and plant physiological state monitoring data subset into the preset short-term demand prediction model; The preset short-term demand prediction model outputs the relative absorption rate change trend value of the main nutrient elements within the preset future time window as the dynamic demand prediction data.

4. A method for dynamically optimizing a soilless cultivation nutrient solution according to claim 3, characterized in that: The specific process of executing the adaptive optimization decision is as follows: Conduct deviation analysis based on the concentrations of various main nutrient elements in the current nutrient solution state monitoring data and the target lower limit concentration and target upper limit concentration of various main nutrient elements corresponding to each growth stage of the plants stored in the database, and evaluate the deviation value between the concentrations of various main nutrient elements in the current nutrient solution and the preset target concentration range; Fuse the dynamic demand prediction data and calculate the demand change coefficient of various main nutrient elements within the preset future time window; Combine the light intensity, air temperature, air humidity, and carbon dioxide concentration in the current environmental monitoring data to evaluate the constraint coefficient of environmental factors on the nutrient element absorption efficiency; Conduct coupling processing based on the deviation value, the demand change coefficient, and the constraint coefficient to generate the supplement amount of the current nutrient solution; Analyze based on the air temperature and nutrient solution temperature in the current environmental monitoring data and the standard supplement rate of the nutrient solution stored in the database to generate the supplement rate of the current nutrient solution; In summary, the generated supplement amount and supplement rate of the current nutrient solution are used as the nutrient solution adjustment instruction set.

5. A method for dynamically optimizing a soilless culture nutrient solution according to claim 4, characterized in that: The specific method for evaluating the deviation value between the concentrations of various main nutrient elements in the current nutrient solution and the preset target concentration range is: Match the current growth stage of the plants in the target cultivation area with the target lower limit concentration and the target upper limit concentration of each main nutrient element corresponding to each growth stage of the plants, so as to obtain the target lower limit concentration and the target upper limit concentration of each main nutrient element corresponding to the current growth stage of the plants; If the concentration of a certain main nutrient element in the current nutrient solution is less than the target lower limit concentration of this main nutrient element, subtract the target lower limit concentration of this main nutrient element from the concentration, and take the ratio of the difference to the target lower limit concentration as the deviation value of this main nutrient element; If the concentration of a certain main nutrient element in the current nutrient solution is greater than the target upper limit concentration of this main nutrient element, subtract the target upper limit concentration from the concentration of this main nutrient element, and take the ratio of the difference to the target upper limit concentration as the deviation value of this main nutrient element; If the concentration of a certain main nutrient element in the current nutrient solution is between the target lower limit concentration and the target upper limit concentration of this main nutrient element, record the deviation value of this main nutrient element as 0; In summary, obtain the deviation values of the concentrations of each main nutrient element in the current nutrient solution from the preset target concentration range.

6. A method for dynamically optimizing a soilless cultivation nutrient solution according to claim 4, characterized in that: The specific method for evaluating the constraint coefficient of environmental factors on the absorption efficiency of nutrient elements is as follows: Extract the optimal values corresponding to the light intensity, air temperature, air humidity, and carbon dioxide concentration of the plants during the growth process from the database; Obtain the absolute value deviations between the light intensity, air temperature, air humidity, and carbon dioxide concentration of the current environment and their corresponding optimal values respectively, subtract the absolute value deviations from the set reference deviation, and take the ratio of the difference to the set reference deviation to obtain the constraint coefficients of the light intensity, air temperature, air humidity, and carbon dioxide concentration of the current environment on the absorption efficiency of nutrient elements respectively; Perform weighted calculation and summation on the constraint coefficients of the light intensity, air temperature, air humidity, and carbon dioxide concentration of the current environment on the absorption efficiency of nutrient elements respectively with the corresponding proportion weights to obtain the constraint coefficient of environmental factors on the absorption efficiency of nutrient elements.

7. A soilless cultivation nutrient solution dynamic optimization method according to claim 4, characterized in that: The specific method for generating the replenishment rate of the current nutrient solution is as follows: Obtain the absolute value deviation of the temperature between the air temperature and the nutrient solution temperature in the current environmental monitoring data, and compare it with the temperature deviation threshold. If the absolute value deviation of the temperature is less than the temperature deviation threshold, keep the standard replenishment rate of the nutrient solution unchanged. If the absolute value deviation of the temperature is greater than the temperature deviation threshold, multiply the absolute value deviation of the temperature by the proportion of the required reduced replenishment rate corresponding to the unit temperature deviation stored in the database to obtain the required reduced replenishment rate proportion of the current nutrient solution, and take the product of the standard replenishment rate of the nutrient solution and the required reduced replenishment rate proportion as the replenishment rate of the current nutrient solution.

8. A dynamic optimization method for soilless culture nutrient solution according to claim 5, characterized in that: The specific process for evaluating the execution effect index of the nutrient solution adjustment instruction set is as follows: Based on the leaf area change rate and transpiration rate change rate in the monitored data of the plant physiological state after adjustment and the leaf area change rate and transpiration rate change rate before adjustment, obtain the improvement degree of the plant physiological state after the adjustment is completed through physiological state analysis; Based on the concentration of each main nutrient element in the adjusted nutrient solution status monitoring data at each monitoring time point, stability analysis is carried out to obtain the stability of the nutrient solution after the adjustment ends; The improvement degree of the plant physiological state and the stability of the nutrient solution after the adjustment ends are weighted and calculated with the corresponding proportion weights and summed to obtain the execution effect index of the nutrient solution adjustment instruction set.

9. A method for dynamically optimizing a soilless culture nutrient solution according to claim 8, characterized in that: The specific process of obtaining the stability of the nutrient solution after the adjustment ends is as follows: Compare the concentration of each main nutrient element at each monitoring time point after the adjustment with the preset target concentration range of each main nutrient element. When the concentration of a certain main nutrient element at a certain monitoring time point is not within the preset target concentration range of this main nutrient element, record this monitoring time point as the starting time point of unstable concentration, and record the interval duration between the starting monitoring time point after the adjustment and the starting time point of unstable concentration as the concentration stability duration; Subtract the concentration stability duration after the adjustment from the set reference concentration stability duration, and take the ratio of the difference to the set reference concentration stability duration to obtain the stability of the nutrient solution after the adjustment ends.

10. A method for dynamically optimizing a soilless cultivation nutrient solution according to claim 9, characterized in that: The specific method for evaluating the adjustment effect of the current nutrient solution is: compare the execution effect index of the nutrient solution adjustment instruction set with the execution effect index intervals corresponding to each adjustment effect stored in the database. If the execution effect index of the nutrient solution adjustment instruction set is within the execution effect index interval corresponding to a certain adjustment effect, then take this adjustment effect as the adjustment effect of the current nutrient solution.

Images