Nutrient solution concentration regulation and control method and system for potato aeroponic culture

Abstract

The invention discloses a nutrient solution concentration regulation and control method and system for potato aeroponic cultivation, and relates to the technical field of fertilization, and the method comprises the following steps: extracting root feature data and concentration feature data; establishing a concentration trend prediction model based on the root feature data and the concentration feature data, and predicting the concentration change trend of the nutrient solution under different conditions by using the concentration trend prediction model; analyzing the change trend of the nutrient solution concentration under different conditions by using a feature analysis algorithm, and identifying key factors influencing the stability of the nutrient solution concentration; and based on the key factors, the nutrient solution is dynamically prepared. Key factors influencing the concentration stability are identified through a feature analysis algorithm, and the nutrient solution ratio is dynamically regulated and controlled, so that intelligent management and accurate supply of the nutrient solution concentration are realized, and effective support is provided for nutrition optimization of the potato aeroponic culture whole period.

Description

Technical Field

[0001] The present invention relates to the technical field of fertilization, and in particular to a method and system for controlling the concentration of a nutrient solution for potato aeroponics. Background Art

[0002] Soilless cultivation technology has been widely used in recent years. Among them, aeroponics, as a new cultivation method, has gradually demonstrated its unique advantages in potato cultivation. Aeroponics achieves efficient recycling of nutrient solution by atomizing the nutrients dissolved in water and spraying them to the plant roots through pipes. In the aeroponic process of potatoes, the regulation of nutrient solution concentration is crucial, because the growth of potato roots and the formation of tubers have strict requirements on the concentration of nutrient solution. Potatoes at different growth stages have different requirements for nutrient solution concentration. For example, during the vegetative growth period, a lower concentration is conducive to promoting root development, while during the tuber enlargement period, an appropriate increase in nutrient solution concentration can promote tuber growth. In order to achieve precise control of concentration, aeroponic systems are usually equipped with real-time monitoring devices that can dynamically adjust the nutrient solution concentration according to the growth status of potatoes and environmental conditions to ensure that the plants can obtain the best nutrient supply.

[0003] However, existing technologies mostly rely on manual experience and judgment, and lack real-time monitoring of root characteristics and nutrient solution components, resulting in delayed concentration control; empirical ratios are difficult to adapt to the needs of different growth stages and can easily cause nutritional imbalance; and the impact of environmental changes on concentration cannot be predicted, and the control accuracy is insufficient, thus affecting the nutrient supply effect and yield stability of potato mist culture.

[0004] Currently, no effective solutions have been proposed for the problems in related technologies. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the present invention proposes a method and system for controlling the nutrient solution concentration for potato aeroponics. This solves the problems proposed in the above-mentioned background technology, such as the existing reliance on manual experience judgment, lack of real-time monitoring of root characteristics and nutrient solution components, resulting in delayed concentration control; the empirical ratio is difficult to adapt to the needs of different growth stages, which can easily cause nutritional imbalance; and the inability to predict the impact of environmental changes on concentration, resulting in insufficient control accuracy, which affects the nutrient supply effect and yield stability of potato aeroponics.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: According to one aspect of the present invention, a method for controlling the concentration of a nutrient solution for potato aeroponics is provided, comprising: Obtain potato root temperature distribution images and concentration data of various components of the aeroponic nutrient solution, and extract root system characteristic data and concentration characteristic data; Based on the root system characteristic data and concentration characteristic data, a concentration trend prediction model was established, and the concentration trend prediction model was used to predict the concentration trend of the nutrient solution under different conditions; The characteristic analysis algorithm is used to analyze the trend of changes in nutrient solution concentration under different conditions, identify the key factors affecting the stability of nutrient solution concentration, and dynamically adjust the nutrient solution based on the key factors.

[0007] Furthermore, the temperature distribution image of the potato root system and the concentration data of each component of the aeroponic nutrient solution are obtained, and the root system characteristic data and concentration characteristic data are extracted, including: The obtained root temperature distribution image and the concentration data of each component of the aeroponic nutrient solution were subjected to denoising, filtering and smoothing to remove duplicate data, missing values ​​and outliers, and obtain complete root temperature distribution images and concentration data of each component of the aeroponic nutrient solution; Initialize the data model, extract high-frequency feature indicators from the temperature distribution image and concentration data, and sort them; Construct a coding mapping dictionary to perform differential compression and feature value encoding on the extracted high-frequency features; Construct a feature data tree based on high-frequency feature sequences to record the combined path information of temperature distribution images and concentration data; Traverse from the bottom of the feature data tree, generate a combination path, extract key feature patterns and update the feature set; Statistical analysis was performed on the feature set to extract root system feature data and concentration feature data.

[0008] Furthermore, based on the root system characteristic data and concentration characteristic data, a concentration trend prediction model is established, and the concentration trend prediction model is used to predict the concentration change trend of the nutrient solution under different conditions, including: Divide root characteristic data and concentration characteristic data, and construct training sets and validation sets; Initialize the key parameters of the concentration trend prediction model and randomly generate initial solutions in the parameter search space as the initial structure configuration of the concentration trend model; The training set is input into the initial concentration trend prediction model to calculate the error, which is used as the initial fitness value of the concentration trend prediction model. The performance of the initial concentration trend prediction model is evaluated using the validation set. The parameters of the initial concentration trend prediction model are optimized through multiple iterations to obtain the final concentration trend prediction model. The final concentration trend prediction model is optimized using the model optimization algorithm, and the optimized concentration trend prediction model is used to predict the changes in nutrient solution concentration under different conditions, and the concentration change trends of the nutrient solution under different conditions are output.

[0009] Furthermore, the final concentration trend prediction model is optimized using a model optimization algorithm, and the optimized concentration trend prediction model is used to predict the changes in nutrient solution concentration under different conditions. The output of the nutrient solution concentration change trends under different conditions includes: Randomly initialize the structural parameters of the concentration trend prediction model as the initial solution of the current optimal concentration trend prediction model; Iteratively test the effect of each structural parameter combination on prediction accuracy and retain the structural parameter combination of the concentration trend prediction model with the smallest error; Determine whether the structural parameter combination of the current concentration trend prediction model meets the error constraint. If not, replace the current concentration trend prediction model and continue testing; The perturbation algorithm is used to adjust the structural parameters of the concentration trend prediction model, escape from the local optimum and continue to perform iterative optimization search; Comparing the error performance of the concentration trend prediction model before optimization and the concentration trend prediction model after optimization, if the error value of the concentration trend prediction model after optimization is smaller than the error value of the concentration trend prediction model before optimization, updating the structural parameters of the optimized concentration trend prediction model; If the maximum number of iterations is reached, the optimized concentration trend prediction model is output to predict the changes in nutrient solution concentration under different conditions, and the trends of nutrient solution concentration changes under different conditions are output.

[0010] Furthermore, the perturbation algorithm is used to adjust the structural parameters of the concentration trend prediction model, escape from the local optimum and continue to perform iterative optimization search, including: Initialize the structural parameters of the concentration trend model, generate a set of candidate structures and calculate their prediction errors as fitness; Select the target structure combination according to the fitness ranking, perform simulated crossover and replace the structure combination with the worst performance; Perform mutation operations on the candidate structure combination set and combine it with simulated annealing mechanism to enhance local search capabilities; Evaluate the fitness of the new structure combination. If it is better than the current optimal structure, replace it. Otherwise, retain the original structure and continue the iterative search. The structural perturbation and fitness update process is executed cyclically, constantly jumping out of the local optimum and continuing to perform iterative optimization search.

[0011] Furthermore, mutation operations are performed on the candidate structure combination set, and the simulated annealing mechanism is combined to enhance the local search capability, including: Randomly select the current structure combination and calculate the fitness of the current structure combination, and generate a new candidate structure through mutation operation; Calculate the new fitness value based on the mutated structural combination to determine whether it is better than the current solution. If the new structural solution is better than the current solution, it will replace the current solution; otherwise, decide whether to accept the worst solution through the simulated annealing mechanism; Perform simulated annealing temperature reduction operations to continuously optimize local solutions and enhance local search capabilities.

[0012] Furthermore, a feature analysis algorithm is used to analyze the trend of nutrient solution concentration changes under different conditions, identifying the key factors affecting the stability of nutrient solution concentration. Based on these key factors, the nutrient solution is dynamically adjusted, including: Acquire nutrient solution concentration data under different environmental conditions and perform Boolean discretization to construct a feature set for concentration change trend analysis; Initialize the candidate set of factors that affect the concentration trend and set the initial weight of each factor; Randomly select concentration data samples under different environmental conditions and calculate the correlation coefficient between each influencing factor and concentration fluctuation; Through the importance assessment algorithm, the environmental parameters and operating parameters related to concentration stability are screened out; Establish a concentration change regression model under multiple environmental conditions to quantify the contribution of each influencing factor to concentration fluctuations; Verify the stability of each influencing factor in different environmental combinations, determine the core influencing factor set, and use the core influencing factors as the key factors affecting the stability of nutrient solution concentration; Based on key factors, the spray frequency, nutrient solution replenishment rhythm and nutrient solution composition ratio are dynamically adjusted to achieve precise control and optimization of the nutrient solution concentration during potato mist cultivation.

[0013] Furthermore, through the importance assessment algorithm, the environmental parameters and operating parameters related to concentration stability were screened out, including: Randomly select several candidate parameter combinations in the environmental parameter space as the initial analysis set; Calculate the influence weight of each parameter combination on the stability of nutrient solution concentration as the importance evaluation index; Select the parameter combination that currently has the greatest impact on concentration stability as the benchmark reference group; Update the weight coefficient and correlation score of each parameter. If it is found that the new parameter combination has a better effect on stability than the baseline reference group, then update the baseline reference group. Otherwise, eliminate it and add new candidate parameters in the parameter space. If the maximum number of iterations is reached, the environmental parameters and operating parameters related to concentration stability are screened out.

[0014] Furthermore, the influence weight of each parameter combination on the stability of nutrient solution concentration is calculated as the importance evaluation index including: Construct a mapping relationship model between nutrient solution concentration changes and parameter combinations to extract concentration fluctuation response characteristics; Perform disturbance simulation on each parameter combination and record the changing trend of concentration stability index under different parameter combinations; According to the concentration fluctuation characteristics and parameter combination disturbance results, the impact weight corresponding to each parameter combination is calculated as the importance evaluation index.

[0015] According to another aspect of the present invention, a nutrient solution concentration control system for potato aeroponics is provided, the system comprising: The data management module is used to obtain the temperature distribution image of the potato root system and the concentration data of each component of the aeroponic nutrient solution, and extract the root system characteristic data and concentration characteristic data; The trend prediction module is used to establish a concentration trend prediction model based on root characteristic data and concentration characteristic data, and use the concentration trend prediction model to predict the concentration change trend of the nutrient solution under different conditions; The trend analysis and control module is used to analyze the trend of changes in nutrient solution concentration under different conditions using a feature analysis algorithm, identify the key factors affecting the stability of nutrient solution concentration, and dynamically adjust the nutrient solution based on the key factors.

[0016] The beneficial effects of the present invention are: 1. This invention accurately captures potato root characteristics and nutrient solution concentration characteristics, establishes a concentration trend prediction model, and enables early prediction of nutrient solution concentration changes under different environmental conditions. By using a feature analysis algorithm to identify key factors affecting concentration stability and dynamically adjust the nutrient solution ratio accordingly, it helps improve the scientific and targeted nature of concentration control, thereby achieving intelligent management and precise supply of nutrient solution concentration, and providing effective support for nutritional optimization throughout the potato aeroponics cycle.

[0017] 2. The present invention constructs a concentration trend prediction model and combines it with a model optimization algorithm to achieve adaptive adjustment of structural parameters, thereby improving the accuracy and stability of concentration change trend prediction. It uses a perturbation mechanism and simulated annealing strategy to effectively avoid falling into local optimality, and dynamically predicts and responds to nutrient solution concentration under various environmental conditions, thereby providing systematic support for achieving precise regulation of nutrient solution concentration. It is suitable for the concentration management needs in the complex environment of potato aeroponics.

[0018] 3. The present invention uses a feature analysis algorithm to identify key factors affecting the stability of nutrient solution concentration. Combining data analysis and regression modeling of multiple environmental conditions, it achieves accurate modeling and quantitative interpretation of concentration change trends, dynamically adjusts spray frequency, replenishment rhythm, and nutrient ratio, and helps to achieve precise control of nutrient solution concentration, thereby improving the systematicity and responsiveness of the concentration control process, and providing a stable and reliable nutrient supply strategy support for potato aeroponics. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 This is a flow chart of a method for controlling nutrient solution concentration in potato aeroponics according to an embodiment of the present invention; Figure 2 The present invention is a block diagram of a nutrient solution concentration control system for potato aeroponics according to an embodiment of the present invention.

[0021] In the picture: 1. Data management module; 2. Trend prediction module; 3. Trend analysis and control module. DETAILED DESCRIPTION

[0022] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0023] In the description of the present invention, unless otherwise specified, "plurality" means two or more. In addition, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0024] According to an embodiment of the present invention, a method and system for controlling nutrient solution concentration for potato aeroponics are provided.

[0025] The present invention will now be further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, the method for controlling the concentration of nutrient solution for potato aeroponics according to an embodiment of the present invention includes: S1. Obtaining a temperature distribution image of potato roots and concentration data of various components of the aeroponic nutrient solution, and extracting root characteristic data and concentration characteristic data; Specifically, the concentration data of each component can be obtained by using nutrient solution component detection equipment (including spectrometers, electrochemical sensors, etc.), and the three-dimensional structural image of the root system can be obtained by using a radar detector, and the temperature distribution image of the root system can be obtained by using an infrared camera.

[0026] Specifically, concentration data include: Major elements: Nitrogen ( 、 ),phosphorus( ), potassium ( ),calcium( ),magnesium( ),sulfur( )wait.

[0027] Trace elements: iron (Fe), zinc (Zn), manganese (Mn), copper (Cu), boron (B), molybdenum (Mo), etc.

[0028] Auxiliary indicators: EC value (electrical conductivity), pH value, etc.

[0029] Specifically, concentration characteristic data include concentration change trends (time series), fluctuation amplitudes and stability indicators of different element concentrations, correlations between components (such as the interaction between potassium and calcium), concentration regulation sensitivity (the response intensity of concentration changes to root status), stage concentration characteristics (characteristic patterns in different growth stages), etc.

[0030] Specifically, the root characteristic data include root temperature distribution (average value, gradient, fluctuation), root activity index (respiration rate-related temperature characteristics), temperature and humidity coupling characteristics of the root zone, root spatial distribution characteristics (root length density, coverage range), root temperature and nutrient solution concentration response characteristics (relationship between temperature and absorption rate), etc.

[0031] S2. Based on the root system characteristic data and concentration characteristic data, a concentration trend prediction model (i.e., deep belief network model DBN) is established, and the concentration trend prediction model is used to predict the concentration trend of the nutrient solution under different conditions; S3. Use feature analysis algorithms to analyze the trend of nutrient solution concentration changes under different conditions, identify key factors affecting the stability of nutrient solution concentration, and dynamically adjust the nutrient solution based on these key factors.

[0032] Specifically, the key factors affecting the stability of nutrient solution concentration include environmental parameter key factors and operating parameter key factors. Environmental parameter key factors include root temperature distribution, air humidity and temperature, light intensity and photoperiod, and mist chamber gas composition (such as 、 ) concentration, pH value and EC value of the nutrient solution itself, etc.; key factors of operating parameters include spray frequency and duration, rehydration cycle and rehydration volume, nutrient solution formula adjustment strategy, nutrient solution circulation system settings, etc.

[0033] In this optional embodiment, the temperature distribution image of the potato root system and the concentration data of each component of the aeroponic nutrient solution are obtained, and the root system characteristic data and concentration characteristic data are extracted, including: The obtained root temperature distribution image and the concentration data of each component of the aeroponic nutrient solution were subjected to denoising, filtering and smoothing to remove duplicate data, missing values ​​and outliers, and obtain complete root temperature distribution images and concentration data of each component of the aeroponic nutrient solution; Initialize the data model, extract high-frequency feature indicators from the temperature distribution image and concentration data, and sort them; Construct a coding mapping dictionary to perform differential compression and feature value encoding on the extracted high-frequency features; Construct a feature data tree based on high-frequency feature sequences to record the combined path information of temperature distribution images and concentration data; Traverse from the bottom of the feature data tree, generate a combination path, extract key feature patterns and update the feature set; Statistical analysis was performed on the feature set to extract root system feature data and concentration feature data.

[0034] Specifically, the method first obtains potato root temperature distribution images and concentration data of various components of the aeroponic nutrient solution. The data is then denoised, filtered, and smoothed to remove duplicate data, missing values, and outliers, ensuring data integrity. Subsequently, the data model is initialized, and high-frequency feature indicators from the temperature distribution and concentration data are extracted and ranked according to importance. A coding mapping dictionary is constructed, and high-frequency feature differentials are compressed and eigenvalue encoded. Next, a feature data tree is constructed based on the high-frequency feature sequence, recording the combined path information of the temperature and concentration data. By traversing the bottom of the feature data tree, a combined path is generated and key feature patterns are extracted. Finally, the feature set is statistically analyzed to extract root and concentration feature data, providing a basis for further regulation and prediction. This improves data processing accuracy and model prediction capabilities.

[0035] In this optional embodiment, a concentration trend prediction model is established based on the root characteristic data and the concentration characteristic data, and the concentration trend prediction model is used to predict the concentration change trend of the nutrient solution under different conditions, including: Divide root characteristic data and concentration characteristic data, and construct training sets and validation sets; Initialize the key parameters of the concentration trend prediction model and randomly generate initial solutions in the parameter search space as the initial structure configuration of the concentration trend model; The training set is input into the initial concentration trend prediction model to calculate the error, which is used as the initial fitness value of the concentration trend prediction model. The performance of the initial concentration trend prediction model is evaluated using the validation set. The parameters of the initial concentration trend prediction model are optimized through multiple iterations to obtain the final concentration trend prediction model. The final concentration trend prediction model is optimized using the model optimization algorithm, and the optimized concentration trend prediction model is used to predict the changes in nutrient solution concentration under different conditions, and the concentration change trends of the nutrient solution under different conditions are output.

[0036] Specifically, the root characteristic data and concentration characteristic data are first divided, and a training set and a validation set are constructed to ensure the representativeness and completeness of the data set. Then, the key parameters of the concentration trend prediction model are initialized, and the initial solution is randomly generated in the parameter search space as the initial configuration of the concentration trend model. The training set is input into the initial model, the error is calculated and the initial fitness value is obtained, and then the performance of the initial model is evaluated using the validation set. By optimizing the initial model parameters through multiple iterations, the final concentration trend prediction model is gradually obtained. Finally, the final model is further optimized using the model optimization algorithm, and it is used to predict the changes in nutrient solution concentration under different conditions, output the expected concentration change trend, and provide data support for precise control. This can accurately predict the concentration change trend under different conditions, improving the control efficiency and stability of the system.

[0037] In this optional embodiment, the final concentration trend prediction model is optimized using a model optimization algorithm, and the optimized concentration trend prediction model is used to predict the change in nutrient solution concentration under different conditions. The output of the nutrient solution concentration change trend under different conditions includes: Randomly initialize the structural parameters of the concentration trend prediction model as the initial solution of the current optimal concentration trend prediction model; Iteratively test the effect of each structural parameter combination on prediction accuracy and retain the structural parameter combination of the concentration trend prediction model with the smallest error; Determine whether the structural parameter combination of the current concentration trend prediction model meets the error constraint. If not, replace the current concentration trend prediction model and continue testing; The perturbation algorithm is used to adjust the structural parameters of the concentration trend prediction model, escape from the local optimum and continue to perform iterative optimization search; Comparing the error performance of the concentration trend prediction model before optimization and the concentration trend prediction model after optimization, if the error value of the concentration trend prediction model after optimization is smaller than the error value of the concentration trend prediction model before optimization, updating the structural parameters of the optimized concentration trend prediction model; If the maximum number of iterations is reached, the optimized concentration trend prediction model is output to predict the changes in nutrient solution concentration under different conditions, and the trends of nutrient solution concentration changes under different conditions are output.

[0038] Specifically, the structural parameters of the concentration trend prediction model are first randomly initialized as the initial solution of the current optimal model. Then, the influence of each structural parameter combination on the prediction accuracy is iteratively tested, and the structural parameter combination with the smallest error is retained. Next, it is determined whether the error of the current model meets the constraint conditions. If not, the current model is replaced and the test is continued. The perturbation algorithm is used to adjust the model structural parameters to avoid falling into the local optimal solution, and the iterative optimization search is continued. During the optimization process, the error performance of the model before and after optimization is compared. If the error after optimization is smaller, the model parameters are updated. If the maximum number of iterations is reached, the optimized model is output, and the model is used to predict the changes in nutrient solution concentration under different conditions, and the corresponding concentration change trend is output. This makes it possible to accurately predict the concentration change trend under different environmental conditions, thereby improving the accuracy and stability of the system.

[0039] Specifically, the model optimization algorithm is a greedy algorithm, an optimization strategy that always selects the current optimal solution at each iteration, in order to quickly approach the overall optimal solution. In the present invention, the greedy algorithm is used to optimize the concentration trend prediction model: first, the model structure parameters are randomly initialized, and in each iteration, the parameter combination with the smallest prediction error is selected as the current optimal solution; if a new parameter combination is found to further reduce the error, the model structure is immediately updated. Through continuous iteration and local perturbation search, the model can gradually approach the optimal state. This improves the model's optimization efficiency, reduces search redundancy, and significantly enhances prediction accuracy.

[0040] In this optional embodiment, using a perturbation algorithm to adjust the structural parameters of the concentration trend prediction model, jumping out of the local optimum and continuing to perform iterative optimization search includes: Initialize the structural parameters of the concentration trend model, generate a set of candidate structures and calculate their prediction errors as fitness; Select the target structure combination according to the fitness ranking, perform simulated crossover and replace the structure combination with the worst performance; Perform mutation operations on the candidate structure combination set and combine it with simulated annealing mechanism to enhance local search capabilities; Specifically, the formula for performing mutation operation on the candidate structure combination set is: ; Where, levy (Levi) represents the mutation value, which controls the change amplitude of the model structure configuration and determines the formation of the new candidate structure combination set after the perturbation operation; u is a random variable that obeys the normal distribution, representing the randomness of “prediction error” or “model bias”, and affecting the disturbance amplitude of the current candidate structure combination set; v is a random variable that obeys the normal distribution, indicating the randomness of the “model structure configuration” and affecting the jump degree of the variation of the current candidate structure combination set;β express levy The parameter of the distribution, usually set to 1.5, controls the jumpiness of the mutation operation. Smaller values ​​will lead to more local searches. Γ(·) represents the Gamma function, a mathematical function used to normalize the distribution process and represents the adjustment coefficient at different mutation stages.

[0041] Evaluate the fitness of the new structure combination. If it is better than the current optimal structure, replace it. Otherwise, retain the original structure and continue the iterative search. The structural perturbation and fitness update process is executed cyclically, constantly jumping out of the local optimum and continuing to perform iterative optimization search.

[0042] Specifically, the structural parameters of the concentration trend prediction model are first initialized, multiple candidate structure sets are generated, and the prediction error of each candidate structure is calculated as the fitness value. The candidate structures are sorted according to the fitness value, the target structure combination is selected, and the structure combination with the worst performance is replaced by a simulated crossover operation. Next, the candidate structure set is mutated, and the simulated annealing mechanism is combined to enhance the local search capability, thereby avoiding falling into the local optimal solution. The fit of the new structure combination is evaluated. If it is better than the current optimal structure, it is replaced; otherwise, the original structure is retained and the iterative search continues. By continuously executing the structural perturbation and fitness update process, the local optimal solution is jumped out, and the iterative optimization search is continued to obtain the optimal concentration trend prediction model. Therefore, through perturbation and mutation operations, the model avoids the local optimal problem, improves the prediction accuracy and the global optimization capability of the model.

[0043] Specifically, the perturbation algorithm is a transit search algorithm, a heuristic global optimization method suitable for escaping local optima in complex search spaces. In the present invention, the algorithm generates a set of candidate structures by initializing structural parameters and calculates their prediction error as fitness. It is then sorted by fitness, simulated crossover and mutation operations are performed, and a simulated annealing mechanism is introduced to enhance local search capabilities. Through repeated perturbations and fitness updates, the search for more optimal structural combinations is continued, avoiding falling into local minima. This enhances the globality and adaptability of the model structure search and improves the accuracy and robustness of the concentration trend prediction model.

[0044] In this optional embodiment, performing a mutation operation on the candidate structure combination set and combining a simulated annealing mechanism to enhance the local search capability includes: Randomly select the current structure combination and calculate the fitness of the current structure combination, and generate a new candidate structure through mutation operation; Calculate the new fitness value based on the mutated structural combination to determine whether it is better than the current solution. If the new structural solution is better than the current solution, it will replace the current solution; otherwise, decide whether to accept the worst solution through the simulated annealing mechanism; Perform simulated annealing temperature reduction operations to continuously optimize local solutions and enhance local search capabilities.

[0045] Specifically, based on the transit search algorithm, the present invention expands the population diversity by introducing a crossover mutation operation to prevent the result from falling into a local optimal solution; in addition, the ideas of simulated annealing and variable neighborhood search algorithms are borrowed to efficiently search for binary features. At the same time, control parameters are set to balance the capabilities of global search and local search to improve convergence accuracy.

[0046] In this optional embodiment, a characteristic analysis algorithm is used to analyze the trend of nutrient solution concentration changes under different conditions to identify key factors affecting the stability of nutrient solution concentration. Based on these key factors, dynamic nutrient solution allocation includes: Acquire nutrient solution concentration data under different environmental conditions and perform Boolean discretization to construct a feature set for concentration change trend analysis; Initialize the candidate set of factors that affect the concentration trend and set the initial weight of each factor; Randomly select concentration data samples under different environmental conditions and calculate the correlation coefficient between each influencing factor and concentration fluctuation; Through the importance assessment algorithm, the environmental parameters and operating parameters related to concentration stability are screened out; Establish a concentration change regression model under multiple environmental conditions to quantify the contribution of each influencing factor to concentration fluctuations; Verify the stability of each influencing factor in different environmental combinations, determine the core influencing factor set, and use the core influencing factors as the key factors affecting the stability of nutrient solution concentration; Based on key factors, the spray frequency, nutrient solution replenishment rhythm and nutrient solution composition ratio are dynamically adjusted to achieve precise control and optimization of the nutrient solution concentration during potato mist cultivation.

[0047] Specifically, the nutrient solution concentration data under different environmental conditions is first obtained and Boolean discretization is performed to construct a feature set for concentration change trend analysis. Subsequently, the candidate set of influencing factors is initialized, the initial weights are set, and the correlation between each candidate factor and concentration fluctuations is calculated by randomly sampling. The importance assessment algorithm is used to screen out significantly correlated environmental and operational parameters, and a concentration change regression model is constructed to quantify the contribution of each factor to concentration fluctuations. The stability performance of each factor under multiple environmental combinations is further evaluated, and the core influencing factor set is finally determined. Based on the identified key factors, the spray frequency, nutrient solution replenishment rhythm and ratio are dynamically adjusted to achieve precise control of the nutrient solution concentration in the potato mist culture system. This allows the identification of the core driving factors of concentration stability and the optimization of the control strategy.

[0048] Specifically, the feature analysis algorithm is a dendritic cell algorithm, a heuristic learning algorithm that mimics the biological immune system and has strong pattern recognition and classification capabilities. In the present invention, the dendritic cell algorithm is used to analyze the changing trends of nutrient solution concentration under different environmental conditions and identify key factors affecting concentration stability. Through this algorithm, the system can extract highly correlated factors from concentration data and evaluate their impact on concentration fluctuations. Ultimately, by screening parameters related to stability, the nutrient solution ratio and control strategy are dynamically adjusted. This improves the analysis accuracy of concentration changes, helps to accurately adjust the nutrient solution ratio, and optimizes the growth environment.

[0049] In this optional embodiment, the environmental parameters and operating parameters related to concentration stability are screened out through the importance assessment algorithm, including: Randomly select several candidate parameter combinations in the environmental parameter space as the initial analysis set; Calculate the influence weight of each parameter combination on the stability of nutrient solution concentration as the importance evaluation index; Select the parameter combination that currently has the greatest impact on concentration stability as the benchmark reference group; Update the weight coefficient and correlation score of each parameter. If it is found that the new parameter combination has a better effect on stability than the baseline reference group, then update the baseline reference group. Otherwise, eliminate it and add new candidate parameters in the parameter space. If the maximum number of iterations is reached, the environmental parameters and operating parameters related to concentration stability are screened out.

[0050] Specifically, multiple candidate parameter combinations are first randomly selected in the environmental parameter space to form the initial analysis set, and the weight of each group's influence on the stability of the nutrient solution concentration is calculated as an importance evaluation indicator. Subsequently, the parameter combination with the greatest current influence is selected as the benchmark reference group, and the weights and correlations of each parameter are dynamically updated. If the new combination has a better effect on concentration stability than the benchmark group, it is replaced and iterations continue; otherwise, the combination is eliminated, and new candidate parameters are added to the parameter space to maintain exploration capabilities. Finally, when the maximum number of iterations is reached, the core environmental parameters and operating parameters related to concentration stability are screened out. This achieves efficient identification of key influencing factors and provides a quantifiable and traceable decision-making basis for subsequent nutrient solution regulation.

[0051] Specifically, the importance assessment algorithm is the black hole algorithm, a global optimization algorithm based on gravitational attraction that simulates the process of stars orbiting a black hole and being gradually absorbed. In this paper, the black hole algorithm randomly selects candidate parameter combinations from the environmental parameter space, calculates the weight of their impact on the stability of the nutrient solution concentration, and continuously updates the current optimal parameter set. If the new combination outperforms the baseline combination, it is updated; otherwise, it is eliminated and new parameter candidates are added, and the process is repeated until the maximum number of iterations is reached. This improves the accuracy and reliability of the stability analysis.

[0052] In this optional embodiment, the weight of each parameter combination on the stability of the nutrient solution concentration is calculated as an importance evaluation index including: Construct a mapping relationship model between nutrient solution concentration changes and parameter combinations to extract concentration fluctuation response characteristics; Perform disturbance simulation on each parameter combination and record the changing trend of concentration stability index under different parameter combinations; According to the concentration fluctuation characteristics and parameter combination disturbance results, the impact weight corresponding to each parameter combination is calculated as the importance evaluation index.

[0053] According to another embodiment of the present invention, Figure 2 As shown, a nutrient solution concentration control system for potato aeroponics is also provided, the system comprising: Data management module 1 is used to obtain the temperature distribution image of potato roots and the concentration data of each component of the aeroponic nutrient solution, and extract the root characteristic data and concentration characteristic data; Trend prediction module 2 is used to establish a concentration trend prediction model based on the root system characteristic data and the concentration characteristic data, and use the concentration trend prediction model to predict the concentration change trend of the nutrient solution under different conditions; The trend analysis and control module 3 is used to analyze the trend of changes in nutrient solution concentration under different conditions using a feature analysis algorithm, identify key factors affecting the stability of nutrient solution concentration, and dynamically adjust the nutrient solution based on the key factors.

[0054] In order to facilitate understanding of the above technical solutions of the present invention, the following describes in detail the control of nutrient solution concentration for potato aeroponics in the actual process of the present invention.

[0055] 1. Root temperature and nutrient solution concentration data acquisition and feature extraction: 1) Acquire root temperature distribution images: Using infrared thermal imaging technology, real-time images of the potato root zone's temperature distribution are captured. Image processing techniques are used to extract root temperature signature data. For example, if the root zone temperature ranges from 18°C ​​to 22°C during a given acquisition, this data can be divided into zones and statistically analyzed for root distribution within these temperature ranges.

[0056] 2) Obtain nutrient solution concentration data: Use conductivity meters and pH meters to measure the concentration of each component in the nutrient solution in real time. ), potassium ( ) and pH values, assuming the following concentration data: Nitrogen concentration ( ):150ppm.

[0057] Potassium concentration ( ):200ppm.

[0058] pH value: 5.8.

[0059] 3) Extract root system characteristic data and concentration characteristic data: The acquired root temperature distribution image is processed to extract features such as temperature fluctuation range and root distribution density: Root temperature fluctuation range: ±2°C.

[0060] Root distribution density: The root distribution density in the root zone is 0.8 roots / cm².

[0061] Fluctuation analysis was performed on the concentration data to calculate the following concentration characteristics: Nitrogen concentration fluctuation range: ±10ppm.

[0062] Potassium concentration fluctuation range: ±15ppm.

[0063] pH stability: Fluctuation range is 5.6-6.0.

[0064] 2. Construction and prediction of concentration trend prediction model based on deep belief network (DBN): 1) Data Preparation: Based on the collected root temperature distribution and nutrient solution concentration fluctuation characteristics, a dataset was created and fed into the Deep Belief Network (DBN) model. Assuming a training set and a validation set, the dataset size was 1,000 sets of samples, each containing root temperature, concentration fluctuation amplitude, and pH value.

[0065] 2) Model Building: We used a Deep Belief Network (DBN) for training, setting the network to 3 layers with 100 neurons per layer. Initially, we set the learning rate to 0.01 and the number of iterations to 500. We trained the network and obtained the optimal model parameters using backpropagation, greedy algorithms, and gradient descent optimization.

[0066] 3) Assume that under certain prediction conditions, the root temperature is 20°C, the nitrogen concentration is 160 ppm, the potassium concentration is 220 ppm, and the pH is 5.9. The DBN model is used to predict the output of the prediction results as follows: Predicted nitrogen concentration: 155 ppm (fluctuation range is ±10 ppm).

[0067] Predicted potassium concentration: 210 ppm (fluctuation range is ±12 ppm).

[0068] Predicted pH value: 5.85 (fluctuation range: ±0.1).

[0069] 3. Concentration Trend Analysis, Key Factor Identification, and Dynamic Allocation Mechanism: 1) Feature analysis and influencing factor identification: Use feature analysis algorithms (such as information gain, decision tree algorithm, dendritic cell algorithm, etc.) to analyze the prediction results and identify the most critical influencing factors. Suppose that during the analysis, the following influencing factors are obtained: The pH value has a greater impact on concentration stability, with a weight of 0.45.

[0070] The influence weight of root temperature fluctuation on concentration change is 0.35.

[0071] The influence weight of the fluctuation of potassium concentration in the nutrient solution on the concentration change is 0.2.

[0072] It can be concluded that pH value is the most critical factor affecting concentration stability.

[0073] 2) Dynamic allocation strategy: Based on the prediction results and key factor identification results, the system automatically adjusts the spray frequency and nutrient solution ratio. When the root temperature rises, increase the Concentration, reduction The concentration was adjusted and the pH was adjusted to the target range (5.8-6.0) using a buffer, as shown in Table 1: Table 1. Dynamic Allocation Strategy

[0074] Therefore, at a temperature of 22°C, the potassium concentration is increased to 230ppm to promote root absorption; the nitrogen concentration is adjusted to 150ppm to avoid excess; and the pH value is maintained in the appropriate range of 5.8-5.9.

[0075] In summary, with the help of the above technical solutions of the present invention, the present invention constructs a concentration trend prediction model and combines the model optimization algorithm to realize the adaptive adjustment of structural parameters, thereby improving the accuracy and stability of the concentration change trend prediction, and utilizing the perturbation mechanism and simulated annealing strategy to effectively avoid falling into the local optimum, and dynamically predict and respond to the nutrient solution concentration under a variety of environmental conditions, thereby providing systematic support for the precise regulation of the nutrient solution concentration, and is suitable for the concentration management needs in the complex environment of potato fog cultivation. The present invention identifies the key factors that affect the stability of the nutrient solution concentration through a feature analysis algorithm, combines data analysis and regression modeling of multiple environmental conditions, realizes precise modeling and quantitative interpretation of the concentration change trend, dynamically adjusts the spray frequency, supply rhythm and nutrient ratio, and helps to achieve precise regulation of the nutrient solution concentration, thereby improving the systematicity and responsiveness of the concentration control process, and providing stable and reliable nutrient supply strategy support for potato fog cultivation.

[0076] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for controlling the concentration of nutrient solution for potato aeroponics, characterized in that: include: Obtain potato root temperature distribution images and concentration data of various components of the aeroponic nutrient solution, and extract root system characteristic data and concentration characteristic data; Based on the root system characteristic data and concentration characteristic data, a concentration trend prediction model was established, and the concentration trend prediction model was used to predict the concentration trend of the nutrient solution under different conditions; The characteristic analysis algorithm is used to analyze the trend of changes in nutrient solution concentration under different conditions, identify the key factors affecting the stability of nutrient solution concentration, and dynamically adjust the nutrient solution based on the key factors.

2. The method for controlling the concentration of nutrient solution for potato aeroponics according to claim 1, wherein: The step of obtaining the temperature distribution image of potato roots and the concentration data of each component of the aeroponic nutrient solution, and extracting the root characteristic data and concentration characteristic data includes: The obtained root temperature distribution image and the concentration data of each component of the aeroponic nutrient solution were subjected to denoising, filtering and smoothing to remove duplicate data, missing values ​​and outliers, and obtain complete root temperature distribution images and concentration data of each component of the aeroponic nutrient solution; Initialize the data model, extract high-frequency feature indicators from the temperature distribution image and concentration data, and sort them; Construct a coding mapping dictionary to perform differential compression and feature value encoding on the extracted high-frequency features; Construct a feature data tree based on high-frequency feature sequences to record the combined path information of temperature distribution images and concentration data; Traverse from the bottom of the feature data tree, generate a combination path, extract key feature patterns and update the feature set; Statistical analysis was performed on the feature set to extract root system feature data and concentration feature data.

3. The method for controlling the concentration of nutrient solution for potato aeroponics according to claim 1, wherein: The method of establishing a concentration trend prediction model based on the root system characteristic data and the concentration characteristic data, and using the concentration trend prediction model to predict the concentration change trend of the nutrient solution under different conditions includes: Divide root characteristic data and concentration characteristic data, and construct training sets and validation sets; Initialize the key parameters of the concentration trend prediction model and randomly generate initial solutions in the parameter search space as the initial structure configuration of the concentration trend model; The training set is input into the initial concentration trend prediction model to calculate the error, which is used as the initial fitness value of the concentration trend prediction model. The performance of the initial concentration trend prediction model is evaluated using the validation set. The parameters of the initial concentration trend prediction model are optimized through multiple iterations to obtain the final concentration trend prediction model. The final concentration trend prediction model is optimized using the model optimization algorithm, and the optimized concentration trend prediction model is used to predict the changes in nutrient solution concentration under different conditions, and the concentration change trends of the nutrient solution under different conditions are output.

4. The method for controlling the concentration of nutrient solution for potato aeroponics according to claim 3, wherein: The model optimization algorithm is used to optimize the final concentration trend prediction model, and the optimized concentration trend prediction model is used to predict the change of nutrient solution concentration under different conditions. The output of the change trend of nutrient solution concentration under different conditions includes: Randomly initialize the structural parameters of the concentration trend prediction model as the initial solution of the current optimal concentration trend prediction model; Iteratively test the effect of each structural parameter combination on prediction accuracy and retain the structural parameter combination of the concentration trend prediction model with the smallest error; Determine whether the structural parameter combination of the current concentration trend prediction model meets the error constraint. If not, replace the current concentration trend prediction model and continue testing; The perturbation algorithm is used to adjust the structural parameters of the concentration trend prediction model, escape from the local optimum and continue to perform iterative optimization search; Comparing the error performance of the concentration trend prediction model before optimization and the concentration trend prediction model after optimization, if the error value of the concentration trend prediction model after optimization is smaller than the error value of the concentration trend prediction model before optimization, updating the structural parameters of the optimized concentration trend prediction model; If the maximum number of iterations is reached, the optimized concentration trend prediction model is output to predict the changes in nutrient solution concentration under different conditions, and the trends of nutrient solution concentration changes under different conditions are output.

5. The method for controlling the concentration of nutrient solution for potato aeroponics according to claim 4, wherein: The method of adjusting the structural parameters of the concentration trend prediction model by using a perturbation algorithm, escaping from the local optimum and continuing to perform iterative optimization search includes: Initialize the structural parameters of the concentration trend model, generate a set of candidate structures and calculate their prediction errors as fitness; Select the target structure combination according to the fitness ranking, perform simulated crossover and replace the structure combination with the worst performance; Perform mutation operations on the candidate structure combination set and combine it with simulated annealing mechanism to enhance local search capabilities; Evaluate the fitness of the new structure combination. If it is better than the current optimal structure, replace it. Otherwise, retain the original structure and continue the iterative search. The structural perturbation and fitness update process is executed cyclically, constantly jumping out of the local optimum and continuing to perform iterative optimization search.

6. The method for controlling the concentration of nutrient solution for potato aeroponics according to claim 5, wherein: The mutation operation on the candidate structure combination set and the combination with the simulated annealing mechanism to enhance the local search capability include: Randomly select the current structure combination and calculate the fitness of the current structure combination, and generate a new candidate structure through mutation operation; Calculate the new fitness value based on the mutated structural combination to determine whether it is better than the current solution. If the new structural solution is better than the current solution, it will replace the current solution; otherwise, decide whether to accept the worst solution through the simulated annealing mechanism; Perform simulated annealing temperature reduction operations to continuously optimize local solutions and enhance local search capabilities.

7. The method for controlling nutrient solution concentration for potato aeroponics according to claim 1, wherein: The characteristic analysis algorithm is used to analyze the trend of changes in nutrient solution concentration under different conditions and identify key factors affecting the stability of nutrient solution concentration; Based on key factors, dynamic nutrient solution allocation includes: Acquire nutrient solution concentration data under different environmental conditions and perform Boolean discretization to construct a feature set for concentration change trend analysis; Initialize the candidate set of factors that affect the concentration trend and set the initial weight of each factor; Randomly select concentration data samples under different environmental conditions and calculate the correlation coefficient between each influencing factor and concentration fluctuation; Through the importance assessment algorithm, the environmental parameters and operating parameters related to concentration stability are screened out; Establish a concentration change regression model under multiple environmental conditions to quantify the contribution of each influencing factor to concentration fluctuations; Verify the stability of each influencing factor in different environmental combinations, determine the core influencing factor set, and use the core influencing factors as the key factors affecting the stability of nutrient solution concentration; Based on key factors, the spray frequency, nutrient solution replenishment rhythm and nutrient solution composition ratio are dynamically adjusted to achieve precise control and optimization of the nutrient solution concentration during potato mist cultivation.

8. The method for controlling nutrient solution concentration for potato aeroponics according to claim 7, wherein: The environmental parameters and operating parameters related to concentration stability screened out by the importance assessment algorithm include: Randomly select several candidate parameter combinations in the environmental parameter space as the initial analysis set; Calculate the influence weight of each parameter combination on the stability of nutrient solution concentration as the importance evaluation index; Select the parameter combination that currently has the greatest impact on concentration stability as the benchmark reference group; Update the weight coefficient and correlation score of each parameter. If it is found that the new parameter combination has a better effect on stability than the baseline reference group, then update the baseline reference group. Otherwise, eliminate it and add new candidate parameters in the parameter space. If the maximum number of iterations is reached, the environmental parameters and operating parameters related to concentration stability are screened out.

9. The method for controlling nutrient solution concentration for potato aeroponics according to claim 8, wherein: The calculation of the influence weight of each parameter combination on the stability of the nutrient solution concentration as an importance evaluation index includes: Construct a mapping relationship model between nutrient solution concentration changes and parameter combinations to extract concentration fluctuation response characteristics; Perform disturbance simulation on each parameter combination and record the changing trend of concentration stability index under different parameter combinations; According to the concentration fluctuation characteristics and parameter combination disturbance results, the impact weight corresponding to each parameter combination is calculated as the importance evaluation index.

10. A nutrient solution concentration control system for potato aeroponics, used to implement the nutrient solution concentration control method for potato aeroponics according to any one of claims 1 to 9, characterized in that: The system includes: The data management module is used to obtain the temperature distribution image of the potato root system and the concentration data of each component of the aeroponic nutrient solution, and extract the root system characteristic data and concentration characteristic data; The trend prediction module is used to establish a concentration trend prediction model based on root characteristic data and concentration characteristic data, and use the concentration trend prediction model to predict the concentration change trend of the nutrient solution under different conditions; The trend analysis and control module is used to analyze the trend of changes in nutrient solution concentration under different conditions using a feature analysis algorithm, identify the key factors affecting the stability of nutrient solution concentration, and dynamically adjust the nutrient solution based on the key factors.

Images