A pressure regulation method for separating tea components

Abstract

The present invention discloses a pressure adjustment method for tea component separation, which relates to the technical field of tea processing. It includes obtaining a first extraction adjustment coefficient according to the relationship between the extraction pressure and the extraction target amount; determining a second extraction adjustment coefficient by measuring the concentration of the extract through a sensor; comparing the two extraction adjustment coefficients with a preset target value to judge whether pressure adjustment is required; if the extraction adjustment coefficient is not within the preset range, combining a multi-index comprehensive scoring model, automatically adjusting the extraction pressure through a pressure adjustment algorithm; the present invention can automatically adjust the extraction pressure to meet the requirements of different types of tea and extraction targets, thereby improving the extraction efficiency of the target component and the product quality. The present invention solves the limitations of traditional fixed pressure settings. By real-time monitoring and automatically adjusting the extraction pressure, the extraction efficiency and product quality are improved, enabling the extraction process to automatically adjust process parameters according to the characteristics of different teas and extraction targets.

Description

Technical Field

[0001] The present invention relates to the technical field of tea processing, and in particular, to a pressure adjustment method for tea component separation. Background Art

[0002] Tea component separation is an important link in the deep processing of tea, which involves extracting specific active ingredients from tea, such as tea polyphenols, caffeine, etc. In this process, pressure is a key control parameter, which directly affects the extraction efficiency and product quality. Traditional methods often adopt fixed pressure settings, but this method is difficult to meet the requirements of different types of tea and different extraction targets. Summary of the Invention

[0003] The purpose of the present invention is to provide a pressure adjustment method for tea component separation, which brings technological progress and economic benefits to the field of tea deep processing through precise process control, intelligent automatic adjustment, and the application of a comprehensive scoring model, and realizes the efficient, intelligent, and high-quality production of tea component separation.

[0004] The purpose of the present invention can be achieved through the following technical solutions:

[0005] The present application provides a pressure adjustment method for tea component separation, including the following steps:

[0006] A pressure adjustment method for tea component separation, including the following steps:

[0007] In a tea component separation device, according to the required tea components such as phenols or alkaloids, etc., determine the extraction target and set the process parameters of the extraction process;

[0008] Wherein, the process parameters include any one of extraction temperature, extraction pressure, extraction time, and solvent concentration;

[0009] Calculate the first extraction adjustment coefficient according to the relationship between the extraction pressure and the extraction target amount;

[0010] Measure the concentration of the extract through a sensor to determine the second extraction adjustment coefficient and quantify the deviation between the extract concentration and the expected target;

[0011] Wherein, after obtaining the second extraction adjustment coefficient, combine it with the first extraction adjustment coefficient to establish a multi-index comprehensive scoring model, and combine different extraction targets to evaluate the contribution of tea quality and efficacy;

[0012] Real-time detect the pressure change during the extraction process in the tea component separation device;

[0013] Compare the two extraction adjustment coefficients with the preset target value to determine whether pressure adjustment is required; if the extraction adjustment coefficient is not within the preset range, combine the multi-index comprehensive scoring model and automatically adjust the extraction pressure through the pressure adjustment algorithm to optimize the extraction effect.

[0014] Furthermore, according to the extraction target, design experiments and optimize the extraction process parameters by the response surface method. The specific content includes:

[0015] Determine the main active ingredients to be extracted according to the type and expected use of the tea leaves, and select the factors affecting the extraction efficiency;

[0016] Use the experimental data to construct a multiple quadratic regression model to describe the relationship between each extraction component and the extraction efficiency;

[0017] Specifically, the multiple quadratic regression model is expressed as:

[0018] ;

[0019] Among them, represents the extraction efficiency, and are the extraction components, i is used to represent each independent extraction process parameter in the model, j represents the interaction between each parameter in the model. In the multiple quadratic regression model, j and i are used to represent the interaction between two different parameters, is the intercept, and are the regression coefficients, is the error term;

[0020] Test the significance of the model through analysis of variance, and analyze the main effects, quadratic effects and interactions of each factor;

[0021] Use the optimization function of statistical software to set the objective function to maximize the content of specific components. After finding the optimal process conditions, conduct verification experiments;

[0022] Among them, the objective function is expressed as:

[0023] , where Z represents the content of the specific component, T, t, C and P respectively represent the extraction temperature, time, solvent concentration and pressure, which are used to reflect the maximum content of components during the extraction process.

[0024] Furthermore, calculate the first extraction adjustment coefficient according to the relationship between the extraction pressure and the extraction target amount. Specifically, obtain the first extraction adjustment coefficient through the gradient ascent method, including:

[0025] Initialize the parameters. According to the experimental data collection, record the extraction target amounts obtained under different extraction pressures, and select the initial extraction pressure;

[0026] Calculate the gradient. Describe the relationship between the extraction pressure and the extraction target amount through a multivariate quadratic regression model, and calculate the gradient of the objective function Y with respect to the extraction pressure P.

[0027] Update the parameters. Update the extraction pressure along the positive direction of the gradient, which is expressed as:

[0028] where is the learning rate, which controls the step size of each update;

[0029] Keep repeating the above calculation of the gradient and parameter update until the gradient reaches the preset maximum number of iterations;

[0030] Calculate the first extraction adjustment coefficient according to the preset maximum number of iterations, which is specifically expressed as: where is the optimal extraction pressure obtained by the gradient ascent method.

[0031] Specifically, the gradient of the objective function Y with respect to the extraction pressure P is expressed as:

[0032] where is the regression coefficient of the model, represents the sensitivity of the objective function with respect to the extraction pressure.

[0033] Furthermore, determine the second extraction adjustment coefficient, which specifically includes:

[0034] Measure the concentration of the extract in real time through a sensor, set the target concentration, calculate the concentration deviation value, and input the measured concentration deviation value into a fuzzy logic controller for analysis to generate a control output for adjusting the parameters of the extraction process;

[0035] Use a reinforcement learning algorithm to adjust the extraction parameters based on the current extraction performance and feedback;

[0036] where the goal of reinforcement learning is to maximize the cumulative reward R, which is expressed as: ; where is the immediate reward at the current moment, is the discount factor, which is used to consider future rewards;

[0037] Perform weighted synthesis on the control outputs of fuzzy logic control and reinforcement learning to obtain a comprehensive control output; the comprehensive control output is expressed as: , where is the control output from fuzzy logic control, is the control output from reinforcement learning, a weight coefficient between 0 and 1.

[0038] According to the comprehensive control output, the second extraction adjustment coefficient is calculated, where the second extraction adjustment coefficient is expressed as: ; where represents the actual measured concentration, represents the target concentration, represents the comprehensive control output.

[0039] Furthermore, a multi-index comprehensive scoring model is established, and the specific content includes:

[0040] A weight coefficient is determined for each extraction target to reflect the relative importance of each extraction target in the quality and efficacy of tea;

[0041] For each extraction target, the extraction score is calculated according to the actual performance and target value during the extraction process, and the extraction score is expressed as: , where, is the weight coefficient of the i th extraction target, indicating the relative importance of this target in the overall evaluation;

[0042] The scores of all extraction targets are weighted and synthesized to obtain the final comprehensive score, and the specific comprehensive score is expressed as: ; where m is the total number of extraction targets.

[0043] Furthermore, the extraction pressure is automatically adjusted through a pressure adjustment algorithm, and the specific content includes:

[0044] The extraction pressure value is measured in real time, and a preset target range is set for each extraction adjustment coefficient;

[0045] According to the currently calculated extraction adjustment coefficient, multi-index comprehensive score, and preset target range, calculate the pressure adjustment amount that needs to be adjusted;

[0046] According to the calculated pressure adjustment amount, automatically adjust the extraction pressure to make the extraction process gradually approach the optimal state;

[0047] Among them, the current extraction pressure is updated according to the calculated pressure adjustment amount, which is expressed as:

[0048] where

[0049] represents the minimum safety value of the extraction pressure, represents the maximum safety value of the extraction pressure.

[0050] The process of continuously repeating real-time measurement, calculation, and adjustment is used for the automatic regulation of the extraction pressure.

[0051] Furthermore, calculate the pressure adjustment amount that needs to be adjusted. Specifically, according to and determine the direction of pressure regulation based on the deviation direction, and then use a PID controller to calculate the pressure adjustment amount.

[0052] where the pressure adjustment amount is expressed as:

[0053] , is the error term, are the proportional, integral, and differential coefficients respectively.

[0054] Furthermore, use the BP neural network - genetic algorithm to optimize the parameters of the multi-index comprehensive scoring model, improve the prediction accuracy of the model and the efficiency of the adjustment algorithm, specifically expressed as:

[0055] ,

[0056] where, represents the comprehensive score of the optimized tea extract. T, t, C, and P represent the extraction temperature, time, solvent concentration, and pressure respectively, which are the input variables of the model. represents the parameter set of the BP neural network, which is adjusted through the BP algorithm. BPNN is the BP neural network model used to predict the initial score of the extract based on the input variables. GA is the genetic algorithm model used to optimize the parameters of the BP neural network. .

[0057] The beneficial effects of the present invention are as follows:

[0058] By real-time monitoring of key parameters in the extraction process, such as temperature, pressure, time, and solvent concentration, and establishing a multiple quadratic regression model, the present invention realizes precise control of the extraction process. Using the response surface method and the gradient ascent method, the present invention can automatically adjust the extraction pressure to meet the requirements of different types of tea and extraction targets, thereby significantly improving the extraction efficiency of target components (such as tea polyphenols and caffeine) and product quality. The present invention solves the limitations of traditional fixed pressure settings. By real-time monitoring and automatic adjustment of the extraction pressure, the extraction efficiency and product quality are improved, making the extraction process more flexible and efficient, and capable of automatically adjusting process parameters according to the characteristics of different teas and extraction targets.

[0059] By combining a fuzzy logic controller and a reinforcement learning algorithm, the present invention realizes the automatic adjustment of extraction pressure. The fuzzy logic controller generates a control output based on the concentration deviation value, while the reinforcement learning algorithm dynamically adjusts the extraction parameters based on the current extraction performance and feedback to maximize the cumulative reward. This intelligent control strategy not only improves the automation level of the extraction process but also ensures optimal extraction effects under different extraction conditions;

[0060] By establishing a multi-index comprehensive scoring model, weight coefficients are assigned to each target component in the tea extraction process to reflect its contribution to the quality and efficacy of tea. Then, through weighted comprehensive scoring, weight coefficients are assigned to each target component to ensure the efficient extraction of target components. By optimizing the model parameters using the BP neural network and genetic algorithm, the prediction accuracy of the model and the efficiency of the adjustment algorithm are improved, significantly enhancing the consistency and market competitiveness of tea products. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] For better understanding and implementation, the technical solutions of the present application will be described in detail below with reference to the drawings.

[0062] Figure 1 It is a schematic flowchart of a method for adjusting the pressure of tea component separation provided by an embodiment of the present application;

[0063] Figure 2 It is a schematic flowchart of a method for adjusting the pressure of tea component separation provided by an embodiment of the present application to design experiments and optimize extraction process parameters through the response surface method;

[0064] Figure 3 It is a schematic flowchart of a method for adjusting the pressure of tea component separation provided by an embodiment of the present application to obtain the first extraction adjustment coefficient through the gradient ascent method;

[0065] Figure 4 It is a schematic flowchart of a method for adjusting the pressure of tea component separation provided by an embodiment of the present application to determine the second extraction adjustment coefficient;

[0066] Figure 5 It is a schematic flowchart of a method for adjusting the pressure of tea component separation provided by an embodiment of the present application to automatically adjust the extraction pressure through a pressure adjustment algorithm. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0067] To further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, exemplary embodiments will be described in detail herein, and their examples are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of methods and systems consistent with some aspects of the present application as detailed in the appended claims.

[0068] The terms used in the present application are for the purpose of describing specific embodiments only and are not intended to limit the present application. The singular forms "a", "the", and "said" used in the present application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0069] The following, in conjunction with the accompanying drawings and preferred embodiments, details the specific embodiments, features, and their effects according to the present invention.

[0070] Please refer to Figures 1 - 5 , this embodiment provides a pressure regulation method for tea component separation, which brings technological progress and economic benefits to the field of tea deep processing through precise process control, intelligent automatic regulation, and the application of a comprehensive scoring model, achieving efficient, intelligent, and high-quality production of tea component separation.

[0071] The present invention provides a pressure regulation method for tea component separation, including the following steps:

[0072] S1. In the tea component separation device, according to the required tea components such as phenols or alkaloids, etc., determine the extraction target, and set process parameters such as temperature, pressure, and time during the extraction process;

[0073] Among them, the extraction target generally includes various bioactive components in tea, such as tea polyphenols, caffeine, amino acids, vitamins, and minerals, etc. These components are highly regarded for their potential health benefits, such as antioxidant, refreshing, anti-inflammatory, and antibacterial effects, etc. When determining the extraction target, a specific group of components will be selected according to the intended use of the final product and market demand, so as to maximize the extraction efficiency and yield of these components by optimizing the extraction process.

[0074] The process parameters include any one of extraction temperature, extraction pressure, extraction time, and solvent concentration.

[0075] Furthermore, according to the extraction target, design experiments and optimize the extraction process parameters by the response surface method. The specific content includes:

[0076] S11. Determine the main active ingredients to be extracted, such as tea polyphenols, caffeine, etc., according to the type and intended use of the tea, and select the factors affecting the extraction efficiency, such as extraction temperature (T), time (t), solvent concentration (C), etc.;

[0077] S12. Use the experimental data to construct a multiple quadratic regression model to describe the relationship between each extracted component and the extraction efficiency;

[0078] Specifically, the multiple quadratic regression model is expressed as:

[0079] ;

[0080] where, represents the extraction efficiency, and are the extracted components, i is used to represent each independent extraction process parameter in the model, such as extraction temperature (T), time (t), solvent concentration (C), and pressure (P). In the model, i is used to traverse all extraction parameters to consider the individual effect of each parameter on the extraction efficiency (linear term) and the effect of the square of each parameter on the extraction efficiency, representing the interaction between parameters in the model. In the multiple quadratic regression model, the interaction term represents the combined effect of two different parameters on the extraction efficiency, j and i are used together to represent the interaction between two different parameters, is the intercept, and are the regression coefficients, is the error term;

[0081] S13. Test the significance of the model through analysis of variance, and analyze the main effects, quadratic effects, and interactions of each factor;

[0082] S14. Use the optimization function of statistical software to set the objective function to maximize the content of a specific component, find the optimal process conditions, and then conduct verification experiments to ensure that the prediction of the model is consistent with the actual results.

[0083] where, the objective function is expressed as:

[0084] , where Z represents the content of the specific component, and T, t, C, and P represent the extraction temperature, time, solvent concentration, and pressure respectively, which are used to reflect the component content to be maximized during the extraction process.

[0085] Among them, the Response Surface Methodology (RSM) is a statistical method for optimizing extraction processes by establishing a mathematical model, used to study the influence of multiple variables on one or more response variables. In the process of tea component extraction, the RSM can be used to determine the optimal process parameters such as temperature, time, and pressure to achieve the maximum extraction efficiency of specific components. First, based on single-factor experiments, key factors affecting extraction efficiency are selected, such as temperature, time, and solvent concentration. Then, through experimental design methods such as central composite design, a series of experiments are systematically arranged to collect data to construct a multiple quadratic regression model, which reveals the relationship between various factors and extraction efficiency. Next, analysis of variance is used to verify the accuracy of the model, and an optimization algorithm is used to find the combination of factors that can maximize extraction efficiency. Finally, the optimal conditions are confirmed through verification experiments and applied to actual production to improve the extraction efficiency of target components in tea and product quality.

[0086] S2. Calculate the first extraction adjustment coefficient according to the relationship between the extraction pressure and the extraction target quantity;

[0087] Furthermore, the first extraction adjustment coefficient is calculated according to the relationship between the extraction pressure and the extraction target quantity. Specifically, the first extraction adjustment coefficient is obtained through the gradient ascent method, including:

[0088] S21. Initialize the parameters. According to the experimental data collection, record the extraction target quantities obtained under different extraction pressures, and select the initial extraction pressure;

[0089] S22. Calculate the gradient. Describe the relationship between the extraction pressure and the extraction target quantity through a multiple quadratic regression model, and calculate the gradient of the objective function Y with respect to the extraction pressure P.

[0090] Specifically, the gradient of the objective function Y with respect to the extraction pressure P is expressed as:

[0091] where is the regression coefficient of the model, represents the sensitivity of the objective function with respect to the extraction pressure.

[0092] S23. Update the parameters. Update the extraction pressure along the positive direction of the gradient, expressed as:

[0093] where is the learning rate, which controls the step size of each update;

[0094] S24. Keep repeating the above calculation of the gradient and updating of the parameters until the gradient reaches the preset maximum number of iterations;

[0095] S25. Calculate the first extraction adjustment coefficient according to the preset maximum number of iterations, specifically expressed as: Among them, is the optimal extraction pressure obtained by the gradient ascent method.

[0096] S3. Measure the concentration of the extract through a sensor, determine the second extraction adjustment coefficient, and quantify the deviation between the extract concentration and the expected target;

[0097] Among them, after obtaining the second extraction adjustment coefficient, combined with the first extraction adjustment coefficient, a multi-index comprehensive scoring model is established. The multi-index comprehensive scoring model combines different extraction targets and the contributions to the quality and efficacy of the tea;

[0098] Furthermore, determining the second extraction adjustment coefficient specifically includes:

[0099] S31. Measure the concentration of the extract in real time through a sensor, set the target concentration, calculate the concentration deviation value, and input the measured concentration deviation value into a fuzzy logic controller for analysis to generate a control output for adjusting the parameters of the extraction process;

[0100] S32. Use a reinforcement learning algorithm (such as Q-learning or deep Q-network) to adjust the extraction parameters based on the current extraction performance and feedback;

[0101] Among them, the goal of reinforcement learning is to maximize the cumulative reward R, expressed as: ; where is the immediate reward at the current moment, is the discount factor, used to consider future rewards;

[0102] S33. Perform weighted integration on the control outputs of fuzzy logic control and reinforcement learning to obtain a comprehensive control output; the comprehensive control output is expressed as: where is the control output from fuzzy logic control, is the control output from reinforcement learning, is a weight coefficient between 0 and 1.

[0103] S34. Calculate the second extraction adjustment coefficient according to the comprehensive control output, where the second extraction adjustment coefficient is expressed as: ; where represents the actually measured concentration, represents the target concentration, represents the comprehensive control output.

[0104] Specifically, in the process of combining the fuzzy logic controller and the reinforcement learning algorithm, first, the FLC analyzes the deviation between the concentration of the extract measured in real time and the target concentration, generating a preliminary adjustment strategy as the control output. This control output is then used as part of the input of the reinforcement learning algorithm. The algorithm updates and optimizes the adjustment strategy of the extraction parameters by evaluating the extraction effect (instantaneous reward) under the current strategy and considering the long-term effect (through the discount factor). In this way, the fuzzy logic controller provides an immediate adjustment method based on the current deviation, while reinforcement learning optimizes these adjustments in the long term to achieve higher extraction efficiency and an extract closer to the target concentration. Finally, these adjustment strategies are translated into specific operations, such as changing the extraction pressure, temperature, or time, etc., to achieve precise control of the extraction process.

[0105] Furthermore, a multi-index comprehensive scoring model is established, and the specific content includes:

[0106] Determine a weight coefficient for each extraction target to reflect the relative importance of each extraction target in the quality and efficacy of tea;

[0107] For each extraction target, calculate the extraction score according to the actual performance and the target value during the extraction process. The extraction score is expressed as: , where is the weight coefficient of the i th extraction target, indicating its relative importance in the overall evaluation;

[0108] Weight and synthesize the scores of all extraction targets to obtain the final comprehensive score. The specific comprehensive score is expressed as: ; where m is the total number of extraction targets.

[0109] Specifically, by establishing a multi-index comprehensive scoring model, weight coefficients are assigned to each target component in the tea extraction process to reflect its contribution to the quality and efficacy of tea, realizing the optimization of the tea extraction process and ensuring the efficient extraction of target components such as tea polyphenols and caffeine; then, according to the actual extraction effect and the expected target of each component, calculate its score; these scores are weighted and synthesized to form a comprehensive score, thus providing a quantitative evaluation index for the tea extraction process. This method not only optimizes the extraction process, ensures the efficient extraction of target components, but ultimately improves the consistency and market competitiveness of tea products.

[0110] S4. Detect the pressure change in real time during the extraction process in the tea component separation device;

[0111] Furthermore, first, use a high-precision pressure sensor to collect data in real time. These data are the key information of the pressure change during the extraction process. Subsequently, condition the original signal through signal processing steps, including amplification to increase the signal strength, filtering to eliminate noise interference, and digitization to convert the analog signal into a digital signal for subsequent analysis. Then, adopt data analysis techniques such as moving average or exponential smoothing methods to deeply analyze the pressure data to identify and track the trends and patterns of pressure changes, thereby understanding the dynamic characteristics of the extraction process. Finally, scan the data for outliers or mutations through an anomaly detection algorithm. These anomalies may be signs of problems during the extraction process, such as equipment failures or operational errors, so as to achieve timely diagnosis and adjustment to ensure the stability of the extraction process and the maximization of extraction efficiency.

[0112] S5. Compare the two extraction adjustment coefficients with the preset target values to determine whether pressure adjustment is required; if the extraction adjustment coefficients are not within the preset range, combine the multi-index comprehensive scoring model and automatically adjust the extraction pressure through the pressure adjustment algorithm to optimize the extraction effect and make the pressure closer to the preset target value.

[0113] Specifically, the multi-index comprehensive scoring model helps to more accurately evaluate the effect of the extraction process and guide pressure adjustment to achieve more efficient and high-quality extraction of tea components. This method can automatically adjust the extraction pressure according to the requirements of different teas and extraction targets, improving the extraction efficiency.

[0114] Furthermore, automatically adjust the extraction pressure through the pressure adjustment algorithm. The specific content includes:

[0115] S51. Measure the extraction pressure value in real time and set a preset target range for each extraction adjustment coefficient.

[0116] S52. Calculate the pressure adjustment amount to be adjusted according to the currently calculated extraction adjustment coefficient, multi-index comprehensive score, and preset target range.

[0117] S53. Automatically adjust the extraction pressure according to the calculated pressure adjustment amount to make the extraction process gradually approach the optimal state.

[0118] Among them, update the current extraction pressure according to the calculated pressure adjustment amount, expressed as:

[0119] , where

[0120] represents the minimum safety value of the extraction pressure, represents the maximum safety value of the extraction pressure.

[0121] S54. Continuously repeat the process of real-time measurement, calculation, and adjustment for the automatic regulation of the extraction pressure to achieve an optimized extraction effect.

[0122] Further, calculate the pressure adjustment amount that needs to be adjusted. Specifically, based on and determine the direction of pressure adjustment according to the deviation direction, and then use a PID controller to calculate the pressure adjustment amount.

[0123] The pressure adjustment amount is expressed as:

[0124] , is the error term, are the proportional, integral, and differential coefficients respectively.

[0125] Specifically, during the tea extraction process, precise control of the extraction pressure is achieved through a PID controller: First, set a target pressure value, then use a sensor to measure the current pressure in real time. The controller calculates the error between the target and the current pressure and adjusts this error through three links: proportional (P), integral (I), and differential (D). The proportional link directly amplifies the error, the integral link eliminates long-term deviations, and the differential link predicts the error trend to reduce fluctuations. The outputs of these three links are added together to obtain the pressure adjustment amount, and the controller automatically adjusts the pressure according to this adjustment amount until the error is reduced to an acceptable range. This process is dynamic, and the controller continuously monitors and adjusts the pressure to ensure that the extraction process is always in the best state. By automatically adjusting the extraction pressure, this method can adapt to different types of tea and diverse extraction goals, achieving precise control of the extraction process. This precise pressure regulation significantly improves the extraction efficiency of target components, ensures the quality and consistency of the extract, and also enhances the flexibility of the production process and the ability to respond to market changes, thereby improving the overall production efficiency and product quality.

[0126] Further, use the BP neural network - genetic algorithm to optimize the parameters of the multi-index comprehensive scoring model, improving the prediction accuracy of the model and the efficiency of the adjustment algorithm. Specifically, it is expressed as:

[0127] ,

[0128] Among them, represents the comprehensive score of the optimized tea extract. T, t, C, and P represent the extraction temperature, time, solvent concentration, and pressure respectively, which are the input variables of the model. represents the parameter set of the BP neural network, which is adjusted through the BP algorithm. BPNN is the BP neural network model used to predict the initial score of the extract based on the input variables. GA is the genetic algorithm model used to optimize the parameters of the BP neural network. , to improve the prediction accuracy.

[0129] Specifically, the BP neural network - genetic algorithm is used to optimize the parameters of the multi - index comprehensive scoring model. The principle process includes: First, define the BP neural network (BPNN) model. This model takes the extracted temperature (T), time (t), solvent concentration (C), and pressure (P) as input variables and outputs the initial score of the tea extract. Then, adjust the parameter set of the BPNN model through the BP algorithm to ensure that the model can accurately predict the score of the extract according to the input variables. Next, intervene with the genetic algorithm (GA), use the prediction error of the BPNN model as the fitness function, and search for the optimal solution in the parameter space through selection, crossover, and mutation operations, thereby optimizing the parameters of the BPNN model. This process aims to find the parameter combination that can maximize the prediction accuracy. Through this strategy that combines the learning and prediction capabilities of the BP neural network and the global search ability of the genetic algorithm, the model can more accurately predict the scores of tea extracts under different process parameters, thereby improving the extraction efficiency and product quality. Finally, this optimization process improves the comprehensive score of the tea extract, achieving precise control and optimization of the extraction process. Among them, the BP neural network first predicts the score of the extract according to the input process parameters, and then the genetic algorithm optimizes the parameters of the BP neural network to find the best parameter combination, thereby improving the prediction performance of the model and the comprehensive score of the extract. It combines the learning and prediction capabilities of the BP neural network and the global search ability of the genetic algorithm to optimize the process parameters in the tea extraction process to achieve the maximum extraction efficiency of specific components.

[0130] The present invention aims at the problem of optimizing the extraction efficiency and product quality in the process of tea component separation. By real - time monitoring the key parameters in the extraction process, such as temperature, pressure, time, and solvent concentration, a multiple quadratic regression model is constructed using these data. This model can describe the relationship between different extraction parameters and extraction efficiency. Then, the response surface method (RSM) is used for experimental design. Through methods such as central composite design, experiments are systematically arranged and data are collected to further optimize the extraction process parameters to achieve the maximum extraction efficiency of specific components;

[0131] In addition, the present invention also uses a fuzzy logic controller and a reinforcement learning algorithm to adjust the extraction pressure in real - time. The fuzzy logic controller generates a control output based on the concentration deviation value, while the reinforcement learning algorithm dynamically adjusts the extraction parameters based on the current extraction performance and feedback with the goal of maximizing the cumulative reward. The combination of these two methods enables the extraction process to respond more flexibly and precisely to different extraction conditions and goals, achieving automatic regulation of the extraction pressure;

[0132] Through the multi-index comprehensive scoring model, the present invention can comprehensively consider the contents of different components in tea and their contributions to the quality and efficacy of tea, providing a quantitative evaluation index for the tea extraction process. This comprehensive scoring model not only optimizes the extraction process, ensures the efficient extraction of target components, but also improves the consistency and market competitiveness of tea products.

[0133] The present invention introduces a BP neural network to process and learn the complex non-linear relationship between input parameters and extraction efficiency. Through the adaptive learning of the network, the prediction accuracy of the model for extraction efficiency is improved. Then, the parameters of the BP neural network are optimized by a genetic algorithm. The genetic algorithm simulates the process of natural selection, iteratively evolves, and searches for the optimal parameter combination that can maximize the prediction accuracy, thereby further enhancing the prediction performance of the model.

[0134] The present invention successfully solves the limitations of the fixed pressure setting in traditional extraction methods, realizes precise control of the extraction process, significantly improves the extraction efficiency of target components and product quality, and brings significant technological progress and economic benefits to the field of tea deep processing.

[0135] The above are only the preferred embodiments of the present invention and do not impose any form of limitation on the present invention. Although the present invention has been disclosed above with the preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to the equivalent embodiments of equivalent changes within the scope of the technical solution of the present invention. However, as long as it does not depart from the content of the technical solution of the present invention, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A pressure regulation method for tea component separation, characterized in that: In the tea component separation device, the extraction target is determined according to the required tea components, and the process parameters of the extraction process are set; Among them, the process parameters include any one of extraction temperature, extraction pressure, extraction time, and solvent concentration; The first extraction adjustment coefficient is calculated according to the relationship between the extraction pressure and the extraction target amount; The concentration of the extract is measured by a sensor to determine the second extraction adjustment coefficient, and the deviation between the extract concentration and the expected target is quantified; Among them, after obtaining the second extraction adjustment coefficient, combined with the first extraction adjustment coefficient, a multi-index comprehensive scoring model is established, and combined with different extraction targets, the contributions of tea quality and efficacy are evaluated; The pressure change during the extraction process is detected in real time in the tea component separation device; The two extraction adjustment coefficients are compared with the preset target values to determine whether pressure adjustment is required; if the extraction adjustment coefficient is not within the preset range, combined with the multi-index comprehensive scoring model, the extraction pressure is automatically adjusted through the pressure adjustment algorithm; Among them, the first extraction adjustment coefficient is calculated according to the relationship between the extraction pressure and the extraction target amount. Specifically, the first extraction adjustment coefficient is obtained by the gradient ascent method, including: Initialize the parameters. According to the experimental data collection, record the extraction target amounts obtained under different extraction pressures, and select the initial extraction pressure; Calculate the gradient, describe the relationship between the extraction pressure and the extraction target quantity through a multiple quadratic regression model, and calculate the gradient of the objective function Y with respect to the extraction pressure P , Update the parameters, and update the extraction pressure along the positive direction of the gradient, which is expressed as: Among them, is the learning rate, which controls the step size of each update; Keep repeating the above calculation of the gradient and updating the parameters until the gradient reaches the preset maximum number of iterations; Calculate the first extraction adjustment coefficient according to the preset maximum number of iterations, which is specifically expressed as: Among them, is the optimal extraction pressure obtained by the gradient ascent method; Among them, determining the second extraction adjustment coefficient specifically includes: The concentration of the extract is measured in real time by a sensor, and the target concentration is set. The concentration deviation value is calculated. According to the measured concentration deviation value, it is input into the fuzzy logic controller for analysis to generate a control output for adjusting the parameters of the extraction process; Use the reinforcement learning algorithm to adjust the extraction parameters based on the current extraction performance and feedback; Among them, the goal of reinforcement learning is to maximize the cumulative reward R, expressed as: ; where is the immediate reward at the current moment, is the discount factor, used to consider future rewards; The control outputs based on fuzzy logic control and reinforcement learning are weighted and synthesized to obtain a comprehensive control output; the comprehensive control output is expressed as: , where is the control output from fuzzy logic control, is the control output from reinforcement learning, is a weight coefficient between 0 and 1; Calculate the second extraction adjustment coefficient according to the comprehensive control output, The second extraction adjustment coefficient is expressed as: ; where represents the actual measured concentration, represents the target concentration, represents the comprehensive control output.

2. The pressure regulation method for tea ingredient separation according to claim 1, wherein: According to the extraction target, design experiments and optimize the extraction process parameters by the response surface method. The specific content includes: According to the type of tea and the expected use, determine the active ingredients to be extracted and select the factors of extraction efficiency; Use the experimental data to construct a multiple quadratic regression model to describe the relationship between each extracted component and the extraction efficiency; Specifically, the multiple quadratic regression model is expressed as: ； Among them, represents the extraction efficiency, and are the extracted components, i used to represent each independent extraction process parameter in the model, j represents the interaction between each parameter in the model. In the multiple quadratic regression model, j and i are used to represent the interaction between two different parameters, is the intercept, and are the regression coefficients, is the error term; Test the significance of the model through analysis of variance, and analyze the main effects, quadratic effects, and interaction effects of each factor; Using the optimization function of statistical software, set the objective function to maximize the content of specific components, and after finding the optimal process conditions, conduct verification experiments; Among them, the objective function is expressed as: , where Z represents the content of a specific component, and T, t, C, and P represent the extraction temperature, time, solvent concentration, and pressure respectively, which are used to reflect the maximum content of the component during the extraction process.

3. A pressure regulation method for tea component separation according to claim 1, characterized in that: The gradient of the objective function Y with respect to the extraction pressure P is expressed as: Among them, T represents the extraction temperature, t represents the extraction time, C represents the concentration of the extraction solvent, P represents the extraction pressure, are the regression coefficients of the model.

4. A pressure regulation method for tea component separation according to claim 1, characterized in that: Establish a multi-index comprehensive scoring model. The specific content includes: Determine a weight coefficient for each extraction target to reflect the relative importance of each extraction target in tea quality and efficacy; For each extraction target, an extraction score is calculated based on the actual performance and the target value during the extraction process. The extraction score is expressed as: , where is the weight coefficient of the i th extraction target, indicating the relative importance of this target in the overall evaluation, represents the i th extraction target; The scores of all extraction targets are weighted and combined to obtain the final comprehensive score, and the specific comprehensive score is expressed as: ; where m is the total number of extraction targets.

5. A pressure regulation method for separating tea leaf components according to claim 1, characterized in that: Automatically adjust the extraction pressure through the pressure adjustment algorithm. The specific content includes: Measure the extraction pressure value in real time, and set a preset target range for each extraction adjustment coefficient; Calculate the pressure adjustment amount to be adjusted according to the currently calculated extraction adjustment coefficient, multi-index comprehensive score, and preset target range; According to the calculated pressure adjustment amount , automatically adjust the extraction pressure to make the extraction process gradually approach the optimal state; wherein, according to the calculated pressure adjustment amount update the current extraction pressure, expressed as: , where represents the minimum safety value of the extraction pressure, represents the maximum safety value of the extraction pressure; Continuously repeat the process of real-time measurement, calculation, and adjustment for the automatic adjustment of the extraction pressure.

6. A pressure adjustment method for tea ingredient separation according to claim 5, characterized in that: Calculate the pressure adjustment amount that needs to be adjusted, specifically according to and to determine the direction of pressure adjustment based on the deviation direction, and then use the PID controller to calculate the pressure adjustment amount. The pressure adjustment amount is expressed as: , is the error term, are the proportional, integral, and derivative coefficients, respectively.

7. A pressure adjustment method for tea ingredient separation according to claim 6, characterized in that: Use the BP neural network-genetic algorithm to optimize the parameters of the multi-index comprehensive scoring model, specifically expressed as: ， Among them, represents the comprehensive score of the optimized tea extract. T, t, C, and P represent the extraction temperature, time, solvent concentration, and pressure respectively, which are the input variables of the model. represents the parameter set of the BP neural network, which is adjusted by the BP algorithm. BPNN is the BP neural network model used to predict the initial score of the extract according to the input variables. GA is the genetic algorithm model used to optimize the parameters of the BP neural network. .

Images