A method for predicting the content of an index component in a traditional Chinese medicine extraction process, a storage medium and an electronic device

Abstract

The application discloses a kind of traditional Chinese medicine extraction process index component content prediction method, storage medium and electronic device, belong to traditional Chinese medicine extraction technical field, comprising: (1) collect traditional Chinese medicine raw material parameters, change the parameter of traditional Chinese medicine extraction process, collect the sample of traditional Chinese medicine extraction liquid obtained under different extraction conditions at different extraction times, record information, determine the content of index component in traditional Chinese medicine extraction liquid sample, obtain data set after data cleaning;(2) establish extraction process heat transfer model and extraction process mass transfer model, screen extraction process mass transfer model, train extraction process heat transfer model and extraction process mass transfer model using the sample in data set, optimize prediction model parameter;(3) the extraction process heat transfer model and extraction process mass transfer model after using parameter optimization predict the content of index component in traditional Chinese medicine extraction process.This method is suitable for a variety of Chinese herbal medicines, and can be used for extraction process prediction in actual production.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of traditional Chinese medicine extraction, and particularly relates to a method for predicting the content of index components in a traditional Chinese medicine extraction process, a storage medium and an electronic device. BACKGROUND

[0002] The extraction of effective components of traditional Chinese medicine is an important link in the production process of traditional Chinese medicine. If abnormal conditions occur in the extraction process, it may cause fluctuations in the quality of the traditional Chinese medicine extract, thereby affecting the consistency of the quality of traditional Chinese medicine intermediates and finished products. The traditional Chinese medicine extraction process is complex and difficult to control. There are often quality differences between different batches of medicinal materials, resulting in inconsistent quality of extraction liquid in different batches. Even under the same medicinal materials, the heating curve of the extraction process under different working conditions is inconsistent, which will also cause large differences in the quality of the extraction liquid of different batches of medicinal materials. The traditional Chinese medicine industry extraction tank often has a large time lag, so it is necessary to adopt a suitable feedforward control strategy to set the appropriate heating temperature before extraction. For some traditional Chinese medicines with degradable index components, it is also necessary to control the appropriate extraction time to reduce the loss of index components while ensuring sufficient extraction. Therefore, in order to strengthen the control level of the traditional Chinese medicine extraction process, it is necessary to adopt a mathematical modeling method to study the kinetic curve of the traditional Chinese medicine extraction process under different parameter changes, and then help to predict the extraction amount and extraction endpoint, so as to better control the traditional Chinese medicine extraction process.

[0003] Some modeling research methods for traditional Chinese medicine extraction process have also been reported in the prior art. For example, Chinese patent document CN111665716A discloses a mathematical modeling method for traditional Chinese medicine / natural plant extraction. Based on the existing steam heating method, the system model of the tank body from the initial temperature to the equilibrium temperature is first established, then the system model of the temperature reduction process in the tank body is established, and then the system model of the pressure change in the temperature rising process in the tank body until stable is established, the system model of the pressure change process in the temperature reduction process in the tank body is established, and the mathematical model of the dynamic characteristics of the input and output in the traditional Chinese medicine / natural plant extraction process is established. Finally, the mathematical model of the dynamic characteristics of the input and output is decoupled, and the multivariable coupled control is changed into single-input and single-output control. The invention reduces the problems of errors caused by human factors and the decrease of the quality of the extract by optimizing the steam heating extraction method.

[0004] Chinese patent document CN112964690A discloses a method for real-time monitoring of the extraction process of traditional Chinese medicine formula granules based on Raman spectrum. Taking licorice formula granules as an example, the sample of the licorice formula granule extraction process is first taken to obtain a sample, then the Raman spectrum of the sample is collected, the actual values of the contents of glycyrrhizin and glycyrrhizic acid in the sample are determined, and finally a content prediction model is established to predict the contents of glycyrrhizin and glycyrrhizic acid in the actual extraction process.

[0005] However, some studies including the above invention still have the following problems: (1) The existing research on the kinetics of traditional Chinese medicine extraction process mainly focuses on the constant temperature extraction stage, and the established model is mostly an ideal model. In industrial production, the extraction time and extraction temperature of the constant temperature stage are mostly required, but the actual traditional Chinese medicine extraction process includes soaking, heating, constant temperature extraction and liquid discharge, and the dissolution of chemical components in traditional Chinese medicinal materials exists in the four stages, which leads to the deviation between the ideal extraction process and the actual extraction process. (2) The kinetic model of the modeling research on the extraction process is mostly described by first-order kinetic model and second-order kinetic model equations. These equations can fit relatively simple kinetic curves, but the fitting is often poor in industrial production process. Most models use a single kinetic curve to fit, and the prediction ability is poor under different parameter changes (temperature change, medicinal material batch change, etc.), which is difficult to be used for feedforward control of actual extraction process. (3) Different types of traditional Chinese medicine extraction processes have significant differences. For example, some are only simple component dissolution processes, and some components have chemical conversion (such as degradation or generation). (4) Some studies use spectroscopy and other technologies for online monitoring, and use spectroscopy technology to calculate the content of index components in real time to model the content of index components in the extraction process. The advantage of this method is that it can better determine the end point, and the disadvantage is that the device cost is high, and the model is often difficult to adapt to the extraction process under material or parameter changes.

[0006] In summary, it is necessary to develop a universal method for fitting and predicting the traditional Chinese medicine extraction process as the basis for implementing advanced control of industrial extraction process. SUMMARY

[0007] The present application provides a method for predicting the content of index components in traditional Chinese medicine extraction process, which is suitable for various traditional Chinese medicinal materials and can be used for extraction process prediction in actual production, solving the defect that the prior art is difficult to simulate and predict the complex extraction process of traditional Chinese medicine.

[0008] The specific technical solutions adopted are as follows:

[0009] A method for predicting the content of index components in traditional Chinese medicine extraction process, comprising the following steps:

[0010] (1) First, collect the parameters of traditional Chinese medicine raw materials, then change the parameters of traditional Chinese medicine extraction process, collect traditional Chinese medicine extraction liquid samples obtained under different extraction conditions and different extraction times, and record the information, measure the content of index components in traditional Chinese medicine extraction liquid samples, and obtain data set after data cleaning;

[0011] The traditional Chinese medicine extraction process includes soaking, heating and constant temperature process, and the recorded information includes extraction liquid temperature data and heating medium temperature data;

[0012] (2) establishing an extraction process heat transfer model and an extraction process mass transfer model, screening the extraction process mass transfer model, and using samples in the data set to train the extraction process heat transfer model and the extraction process mass transfer model to optimize the prediction model parameters; the extraction process mass transfer model is a dissolution model or a chemical reaction model, the dissolution model includes a single solvent extraction model or a mixed solvent extraction model, and the chemical reaction model includes a degradation extraction model or a generation extraction model;

[0013] (3) Use the parameter-optimized heat transfer model of the extraction process and the mass transfer model of the extraction process to predict the content of index components in the traditional Chinese medicine extraction process.

[0014] The method of the present invention is based on Fick's mass transfer law and Fourier's heat transfer law, and establishes a complex functional relationship between the temperature of the heating medium and the temperature of the extract, the content of the index component and multiple extraction process parameters. After screening and obtaining a suitable model, the optimization algorithm and known experimental data are used to perform global parameter fitting and parameter tuning on the model to achieve the purpose of training the model. After the model training is completed, the heat transfer model of the extraction process and the mass transfer model of the extraction process after parameter optimization are used to predict the content of the index component in the traditional Chinese medicine extraction process.

[0015] The parameters of Chinese medicine raw materials include the particle size of medicinal material particles, the specific surface area of ​​medicinal material particles, the content of index components, the volume of wet medicinal materials or the volume of extract. The specific surface area of ​​medicinal material particles is obtained in the following way: for Chinese medicinal materials that have been pulverized, they are regarded as spherical particles, and the particle size is calculated by the average of the sieve aperture that can retain the powder after screening and the aperture of the sieve that is one size larger than the sieve aperture (for example, if the powder is retained on the No. 3 sieve, then the particle size of the powder is the average of the apertures of the No. 3 sieve and the No. 2 sieve), and then the specific surface area is calculated based on the particle size; for medicinal materials that have not been pulverized, an approximate conversion can be made depending on the situation. The content of index components is detected by the method recorded in the literature or pharmacopoeia. The volume of wet medicinal materials and the volume of extract are specifically determined by filtering and measuring the volume of wet medicinal materials and extract after soaking under different conditions, and are determined by soaking experiments or obtained by the following formula:

[0016] V M =αM1+κM1 Formula (1)

[0017]

[0018] κ=β r+ γ Formula (3)

[0019] Among them, V M Represents the volume of wet medicinal materials, V w Represents the volume of the extract, M1 represents the mass of the medicinal materials fed, where r is the particle size of the medicinal material, and a, b, g and k are the parameters of the extraction process, which are determined by the extraction experiment. In the modeling process, it is assumed that the volume is unchanged before and after extraction, the medicinal material absorbs part of the solvent volume and becomes larger, and the volume of the extracted liquid decreases. The volume of the absorbed solvent is related to the mass of the medicinal material and the particle size of the medicinal material.

[0020] Specifically, the recorded information further includes the particle size of the medicinal material, the batch of the medicinal material, the extraction solvent, the ratio of solid to liquid, or the extraction time; and the content of the index component in the traditional Chinese medicine extraction liquid sample is determined by liquid chromatography.

[0021] Specifically, the data cleaning includes abnormal data rejection or data format conversion.

[0022] In step (2), the heat balance of the traditional Chinese medicine extraction process is calculated, and an extraction process heat transfer model is established to represent the heat transfer of the heating medium, the extraction container and the extraction liquid. The extraction process heat transfer model is represented as:

[0023]

[0024] where H is the overall heat transfer coefficient, A w is the heat transfer area between the heater and the extraction container, T w is the temperature of the heating medium in the heater, ∑MC p = M1C p,1 + M2C p,2 + M3C p,3 , M1 is the mass of the medicinal material, C p,1 is the specific heat capacity of the medicinal material particles, M2 is the mass of the extraction container, C p,2 is the specific heat capacity of the extraction container, M3 is the mass of the extraction solvent, C p,3 is the specific heat capacity of the extraction solvent, A is the heat dissipation area in contact with the air, h is the heat transfer coefficient between the extraction solution and the outside, T is the temperature of the extraction liquid, T0 is the ambient temperature, and t is the time.

[0025] In the above equation, the overall heat transfer coefficient H and the heat transfer coefficient h are to be fitted parameters. Since T w is not a constant value, it changes with time in the actual extraction process, so the differential equation is a variable coefficient differential equation, which is solved by the variable coefficient Runge-Kutta numerical solution method.

[0026] In step (2), the extraction process mass transfer model is used to represent the change of the content of the index component with different extraction conditions and different extraction times. According to the properties of the index component and different extraction solvents, the corresponding extraction process mass transfer model is selected.

[0027] The quality transfer model of the screening extraction process is specifically as follows: when the index component extraction process is a component dissolution process, and the extraction solvent is a pure solvent, a single solvent extraction model is selected; when the index component extraction process is a component dissolution process, and the extraction solvent is a mixed solvent, a mixed solvent extraction model is selected; when the index component extraction process involves conversion or degradation of the index component, for the degraded index component, a degradation extraction model is selected, and for the converted index component, a generation extraction model is selected.

[0028] The single solvent extraction model is expressed as:

[0029]

[0030]

[0031] wherein M1 is the mass of the medicinal material for feeding, is the initial content of the index component in the medicinal material, t is time, k is a mass transfer coefficient, the mass transfer coefficient is related to the extraction liquid temperature T, the relationship is shown in formula (S4), a is the specific surface area of the medicinal material particles, C M is the content of the index component in the medicinal material in the extraction process, C W is the content of the index component in the extraction liquid, K is a proportionality coefficient of the index component in the medicinal material and the index component in the extraction liquid, the relationship with the temperature is shown in formula (S5), V M and V W have the same meanings as formulae (1) and (2), x1, x2, x3 and x4 are all to-be-fitted parameters (x1 and x2 are related to the mass transfer coefficient, and x3 and x4 are related to the distribution coefficient), if the experimental results show that the content of the index component is not related to the temperature, x4 can be set to 0 to simplify the model.

[0032] In step (2), the mixed solvent extraction model is expressed as:

[0033]

[0034] wherein, is the solvent proportion of one component in the mixed solvent, and the meanings of the remaining parameters are the same as those in formulae (S1)-(S5), x1, x2, x3, x4, x5, x6, x7, x8 and x9 are all to-be-fitted parameters (x1, x2, x3 and x4 are related to the mass transfer coefficient, and x5, x6, x7, x8 and x9 are related to the distribution coefficient), if the content of the index component at the extraction endpoint is not related to part of the parameters, the related parameters can be set to 0 to simplify the model, if it is not related to the temperature, that is, there is no obvious difference in the extraction amount under different temperature changes, x6 can be set to 0; if it is not related to the solvent proportion, that is, there is no obvious difference in the extraction amount under different solvent proportion changes, x7 can be set to 0; wherein x9 can be expressed as That is, assuming that it is the specific surface area of ​​spherical particles, r is the particle size of the medicinal material particles. If it is independent of the particle size of the medicinal material particles, that is, there is no obvious difference in the extraction amount under different medicinal material particle sizes, then x9 can be set to 1.

[0035] In step (2), for the extraction model with chemical reaction transformation, assuming that both the index component A and the index component B are present in the medicinal material, part of the index component A will be transformed into the index component B during the extraction process, then for the index component A, it belongs to the degradation extraction model;

[0036] The degradation extraction model is expressed as:

[0037]

[0038] Among them, k d,A is the degradation rate constant of the index component A, k A is the mass transfer coefficient of the index component A, K A The ratio coefficient of the index component A in the medicinal material to the index component A in the extract, C M,A is the content of the index component A in the medicinal material during the extraction process, C W,A is the content of index component A in the extract, the meanings of the other parameters are the same as those in formulas (S1)-(S5), x1, x2, x3, x4, x5, and x6 are all parameters to be fitted (x1 and x2 are related to the mass transfer coefficient, x3 and x4 are related to the degradation coefficient, and x5 and x6 are related to the distribution coefficient);

[0039] For the index component B, it belongs to the generation and extraction model:

[0040]

[0041] Among them, k d,B is the generation rate constant of the index component B, k B is the mass transfer coefficient of the index component B, K B The ratio coefficient of the index component B in the medicinal material and the index component B in the extract, C M,B is the content of the index component B in the medicinal material, C W,B is the content of index component B in the extract, and the meanings of the other parameters are the same as in formulas (S11)-(S15). x1, x2, x3, x4, x5, and x6 are all parameters to be fitted (x1 and x2 are related to the mass transfer coefficient, x3 and x4 are related to the generation coefficient, and x5 and x6 are related to the distribution coefficient).

[0042] Specifically, different samples of multiple groups in the data set are used as a training set, the training set is used to train the extraction process heat transfer model and the extraction process mass transfer model, to fit the appropriate parameters while meeting the extraction process data obtained under different extraction conditions and at different extraction times, in order to improve the fitting effect of the fitted parameter values, a target function is defined, and an optimization algorithm is used to optimize the parameters to be fitted, so that the actual data and the calculated data are minimized.

[0043] The optimization algorithm is set to one of a genetic algorithm, a grey wolf optimization algorithm and a Markov-Monte Carlo optimization algorithm, further, the optimization algorithm is set to a genetic algorithm, the target function is a determination coefficient, a mean square error, a root mean square error or a mean absolute error, further, the target function is a mean square error, and more further, the target function is the sum of determination coefficients, the sum of mean square errors, the sum of root mean square errors or the sum of mean absolute errors of the training set, and most preferably, the target function is the sum of mean square errors of the training set.

[0044] Further, the target function F is defined as a mean square error:

[0045]

[0046] Wherein, m is the number of groups, n is the number of experimental data points, y i,j is the measured value of the actual data point of the jth point of the ith group, is the predicted value of the extraction process corresponding to the time point calculated by the model under the parameter combination X of the jth point of the ith group, and the parameter combination is X=[x1, x2…x m ], wherein m is the number of parameters to be fitted.

[0047] The samples in the prediction set except the training set in the data set are used as a prediction set, the extraction process heat transfer model and the extraction process mass transfer model after parameter optimization are used to predict the samples in the prediction set, and the determination coefficient (R 2 ), the mean square error (MSE), the root mean square error (RMSE) and the mean absolute error (MAE) of the calculation results and the experimental results are compared to evaluate the prediction effect of the model.

[0048] The application also provides a storage medium, wherein the storage medium stores a program, and the program executes the prediction method of the content of the index component in the traditional Chinese medicine extraction process when running.

[0049] The application also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, and the processor executes the prediction method of the content of the index component in the traditional Chinese medicine extraction process through the computer program.

[0050] Compared with the prior art, the present application has the beneficial effects that:

[0051] (1) The method of the present application establishes a process prediction method for index components in traditional Chinese medicine under complex extraction conditions, can fully utilize the known data in the experimental stage for model screening and model training, and the model after parameter optimization can be used for prediction of the extraction process kinetics curve (content change curve with time) in actual production, solving the defects that the prior art is difficult to simulate and predict the complex extraction process of traditional Chinese medicine.

[0052] (2) The method of the present application can predict the content and extraction rate of index components under different extraction parameter changes according to the temperature rise curve in the industrial extraction process, and judge the extraction endpoint, so as to achieve the purpose of improving the quality and efficiency of the industrial extraction process of traditional Chinese medicine.

[0053] (3) The method of the present application has good applicability and can be applied to the prediction of the content of various index components in the extraction process of various traditional Chinese medicines including ginkgo leaves, panax notoginseng, and radix scrophulariae. BRIEF DESCRIPTION OF DRAWINGS

[0054] Figure 1 The flow chart of the method for predicting the content of index components in the extraction process of traditional Chinese medicine.

[0055] Figure 2 The flow chart of screening the quality transfer model of the extraction process.

[0056] Figure 3 The temperature curve of ginkgo leaf extraction process under different conditions, wherein the scattered points are experimental values, and the curve is the prediction curve of the heat transfer model of the extraction process.

[0057] Figure 4 The content curve of ginkgo leaf extraction process under different conditions, wherein the scattered points are experimental values, and the curve is the prediction curve of the heat transfer model of the extraction process.

[0058] Figure 5 The effect diagram of predicting the content of total flavonoid glycoside in the extraction process of ginkgo leaves by using the method of the present application.

[0059] Figure 6 The effect diagram of predicting the content of panax notoginseng saponin R1, ginsenoside Rg1 and ginsenoside Rb1 in the extraction process of panax notoginseng by using the method of the present application.

[0060] Figure 7 The effect diagram of predicting the content of baicalin in the extraction process of radix scrophulariae by using the method of the present application.

[0061] Figure 8The effect diagram for predicting the content of chlorogenic acid, cryptochlorogenic acid, neochlorogenic acid, caffeic acid, isochlorogenic acid A, isochlorogenic acid B and isochlorogenic acid C in the extraction process of honeysuckle by using the method of the present application. DETAILED DESCRIPTION

[0062] The present application will be further illustrated by the following examples and drawings. It should be understood that these examples are only used to illustrate the present application, and are not used to limit the scope of the present application.

[0063] The flow chart of the prediction method of the content of index components in the extraction process of traditional Chinese medicine is shown in Figure 1

[0064] (1) Specifically, in the following examples, the heat transfer model of the extraction process is shown in formula (4).

[0065] (2) Specifically, in the following examples, the quality transfer model of the extraction process is established, and the screening of the quality transfer model of the extraction process is shown in Figure 2 . The method is as follows: if it is a simple component dissolution process, i.e. the index component is contained in the medicinal material and the extraction liquid, and there is no literature research report recording the formation of component degradation or component transformation in the extraction process, it is classified as a dissolution component modeling, and a single solvent extraction model or a mixed solvent extraction model is selected according to the type of extraction solvent. The single solvent extraction model is shown in formulas (S1)-(S5), and the mixed solvent extraction model is shown in formulas (S6)-(S10). If the component has chemical component transformation and degradation in the extraction process, it is classified as an extraction model with chemical reaction. For the extraction model with chemical reaction transformation, it is assumed that the index component A and the index component B exist in the medicinal material, and part of the index component A will be transformed into the index component B in the extraction process. Therefore, for the index component A, it belongs to the degradation extraction model, and the degradation extraction model is shown in formulas (S11)-(S15). For the component B, it belongs to the generation extraction model, and the generation extraction model is shown in formulas (S16)-(S20). After selecting the model, the numerical solution is carried out according to the improved variable coefficient Runge-Kutta method.

[0066] (3) In the parameter fitting process, the objective function is defined as the mean square error, which is shown in formula (5).

[0067] Example 1

[0068] (1.1) Collection of parameters of traditional Chinese medicine raw materials

[0069] ​Ginkgo biloba L. was crushed and sieved to obtain coarsest powder, coarse powder and medium powder. The average particle size of the coarsest powder was 1.425 mm, the average particle size of the coarse powder was 0.6025 mm, and the average particle size of the medium powder was 0.3025 mm. According to the specific surface area formula of spherical particles, the specific surface areas were 2.105 mm -1 , 4.979 mm -1 and 9.917 mm -1 , respectively.

[0070] The formula for determining the volume of Ginkgo biloba L. and the volume of the extraction liquid through different soaking experiments was:

[0071] V M = 0.2M1+1.8M1 formula (1.1)

[0072]

[0073] wherein the unit of mass was (g), the unit of volume was (mL), V M represented the volume of wet medicinal materials, V w represented the volume of the extraction liquid, M1 represented the mass of the medicinal materials, and M2 represented the volume of the initial extraction solvent. The initial content of total flavonoid glycosides in Ginkgo biloba L. in three batches was determined according to the literature method.

[0074] (1.2) Data set establishment

[0075] Different groups of traditional Chinese medicine extraction experiments were designed. The factors investigated during the extraction process included the heating medium temperature, the proportion of ethanol in the ethanol-water mixed solvent (v / v), the solid-liquid ratio, the particle size of the medicinal materials, and the batch of medicinal materials. The extraction experiment conditions of different groups are shown in Table 1. The extraction process included soaking for 1 h, then heating for 3 h in a heating tank. Samples were collected at different time points during the extraction process and information was recorded. The recorded information included the particle size of the medicinal materials, the batch of medicinal materials, the extraction solvent, the solid-liquid ratio, the temperature data of the extraction liquid, and the temperature data of the heating medium.

[0076] Table 1 Ginkgo biloba L. extraction experiment table

[0077]

[0078] The collected samples were analyzed by liquid chromatography to determine the content of the index components in the traditional Chinese medicine extraction liquid samples. After data cleaning, the data set was obtained.

[0079] (1.3) Extraction model screening

[0080] ​Considering that the index component flavonoid glycoside does not degrade, the solvent for extraction is a mixed solvent, and the solvent ratio parameter for extraction is taken as a factor for investigation, a mixed solvent extraction model is selected.

[0081] (1.4) Establishing a heat transfer model for the extraction process

[0082] The temperature data of the extraction liquid at different times and the temperature data of the heating tank obtained in each extraction experiment are T = [T1, T2…Tn], and the temperature data of the heating tank is T = [T1, T2…Tn], which satisfies formula (4). Specifically, the extraction container is an extraction tank, the heating area A is the jacket heating area, A is the heat dissipation area in contact with air, and the surface area of the extraction tank minus the jacket heating area can be obtained, and all data in ∑MC can be obtained by literature query or actual extraction process. That is, the parameters to be solved are h and H. In the solving equation, first, the temperature T vector and the heating tank temperature data T are interpolated to generate a larger data matrix, and then the differential equation is differentiated by using a numerical calculation method, and the variable coefficient Runge-Kutta method is used to solve it. In each time advancing process, the different temperatures obtained by interpolation are used for iterative solution. n w w,1 w,2 w,n ] satisfies formula (4). Specifically, the extraction container is an extraction tank, the heating area A is the jacket heating area, A is the heat dissipation area in contact with air, and the surface area of the extraction tank minus the jacket heating area can be obtained, and all data in ∑MC can be obtained by literature query or actual extraction process. That is, the parameters to be solved are h and H. In the solving equation, first, the temperature T vector and the heating tank temperature data T are interpolated to generate a larger data matrix, and then the differential equation is differentiated by using a numerical calculation method, and the variable coefficient Runge-Kutta method is used to solve it. In each time advancing process, the different temperatures obtained by interpolation are used for iterative solution. w p w W

[0083] (1.5) Establishing a mass transfer model for the extraction process

[0084] After the model is screened in step (1.3), whether different parameters have a greater impact on the extraction result is investigated, so as to consider reducing the parameters in the model. In the same batch of medicinal materials, the parameter K that affects the final extraction content in the model is the result, and the parameter K corresponds to the mixed solvent extraction model formula (S6)-(S10). The calculation is t = 0, C = 0, and there are 8 parameters to be fitted. In the solving equation, first, the temperature T vector is interpolated to generate a larger data matrix by using an interpolation algorithm, and then the differential equation is differentiated by using a numerical calculation method, and the variable coefficient Runge-Kutta method is used to solve it. In each time advancing process, the different temperatures obtained by interpolation are used for iterative solution to finally obtain the extraction process curve.

[0085] (1.6) Optimization algorithm for solving temperature parameters

[0086] ​​​​​​​​​​The different samples of the multiple groups of experiments in the data set were used as the training set, the training set was used to train the heat transfer model of the extraction process, to fit the appropriate parameters while meeting the extraction process data obtained under different extraction conditions and different extraction times. In order to improve the fitting effect of the fitting parameter values, the objective function was defined as the sum of squares of errors of all group experiment values and calculated values, the genetic algorithm was used for parameter optimization, the temperature parameters were brought into equation (1.4) to solve the temperature change curve of the extraction tank inside with time of the experimental group, see Figure 3 . The determination coefficients R 2 of the fitting of the temperature change curves of the extraction tank inside in the ginkgo leaf extraction process of the 10 groups were 0.9953, 0.9952, 0.9940, 0.9977, 0.9941, 0.9971, 0.9965, 0.9977, 0.9940, 0.9933 respectively. The average determination coefficient was 0.9955. Overall, the fitting effect was good, which could reflect the temperature change rule of the extraction tank inside in the ginkgo leaf extraction process.

[0087] (1.7) Optimization algorithm for solving mass transfer parameters

[0088] The different samples of the multiple groups of experiments in the data set were used as the training set, the training set was used to train the mass transfer model of the extraction process, to fit the appropriate parameters while meeting the extraction process data obtained under different extraction conditions and different extraction times. In order to improve the fitting effect of the fitting parameter values, the optimization algorithm was used to fit the parameters, the 8 parameters in (1.5) were fitted, the fitting results were brought into the equation to solve the kinetic curve of the experimental group, see Figure 4 . The determination coefficients R 2 of the fitting curves of the ginkgo leaf extraction process of the 10 groups were 0.9587, 0.9344, 0.9716, 0.9533, 0.9547, 0.9920, 0.9798, 0.9285, 0.9822, 0.9496 respectively. The average determination coefficient was 0.9605. Overall, the fitting effect was good, which could reflect the component change rule of the ginkgo leaf extraction process.

[0089] (1.8) Prediction using the model

[0090] The extraction process heat transfer model and the extraction process mass transfer model after parameter optimization were used for prediction with the 11th group as the prediction group. After knowing the temperature change of the heating medium, the temperature change curve of the extraction tank inside with time was predicted, see Figure 5 . The prediction R 2 of the prediction group was 0.9950. Then the temperature change rule was used to predict the content change of ginkgo leaf flavonoid glycoside, the prediction R 2The value is 0.9862. It shows that the model developed in the application can better fit and predict the temperature and index component changes under different parameter conditions and different extraction processes (soaking extraction, temperature increase extraction, and temperature maintenance extraction).

[0091] Example 2

[0092] (2.1) Collection of Chinese medicine raw material parameters

[0093] The notoginseng medicinal material was crushed and sieved to obtain coarse powder, fine powder, and medium powder. The volume of the notoginseng medicinal material and the volume of the extraction liquid were determined through different soaking experiments, and the initial contents of the three saponins (notoginsenoside R1, ginsenoside Rg1, and ginsenoside Rb1) in the three batches of notoginseng medicinal materials were determined according to the literature method.

[0094] (2.2) Data set establishment

[0095] Different groups of Chinese medicine extraction experiments were designed, and the factors investigated in the extraction process included heating medium temperature, the proportion of ethanol in the mixed solvent (v / v), solid-liquid ratio, particle size of the medicinal material, and medicinal material batch. The extraction experiments of different groups are shown in Table 2. The extraction process included soaking for 1 h, and then heating for 3 h in a heating tank. The samples at different time points in the extraction process were collected and information was recorded. The recorded information included particle size of the medicinal material, medicinal material batch, extraction solvent, solid-liquid ratio, extraction liquid temperature data, and heating medium temperature data.

[0096] Table 2. Notoginseng extraction experiment table

[0097]

[0098] The collected samples were subjected to liquid chromatography detection and analysis to determine the content of the index component in the Chinese medicine extraction liquid sample. After data cleaning, the data set was obtained.

[0099] (2.3) Extraction model screening

[0100] Considering that the index component does not degrade, the extraction solvent is a mixed solvent, and the solvent ratio parameter is an investigation factor, a mixed solvent extraction model is selected.

[0101] (2.4) Establishment of heat transfer model in extraction process

[0102] Same as Example 1.

[0103] (2.5) Establishment of mass transfer model in extraction process

[0104] After the model is screened, the expression form of the parameter K is specifically considered. In the same batch of medicinal materials, the result of the parameter K in the model affects the final extraction content, and the parameter K is The extraction content results are related to temperature, extraction solvent ratio and medicinal material particle size. According to the actual extraction results, whether they are related to these parameters can reduce the complexity of the model.

[0105] Specifically related to three index components: notoginsenoside R1, ginsenoside Rg1 and ginsenoside Rb1. For notoginsenoside R1, the difference under different conditions is very small, so it can be considered that K is a constant, K = x5 simplified model, the initial solution of the equation group is: t = 0, C W = 0, and 5 parameters need to be fitted.

[0106] For ginsenoside Rg1, the difference under different conditions is very small, so it can be considered that K is a constant, K = x5 simplified model, the initial solution of the equation group is: t = 0, C W = 0, and 5 parameters need to be fitted.

[0107] For ginsenoside Rb1, the difference under different conditions is very small, so it can be considered that K is a constant, K = x5 simplified model, the initial solution of the equation group is: t = 0, C W = 0, and 5 parameters need to be fitted.

[0108] In the solution of the equation, first, the temperature T vector is interpolated to generate a larger data matrix using the interpolation algorithm, and then the differential equation is differentiated using the numerical calculation method and solved using the variable coefficient Runge-Kutta method. In each time advancing process, the different temperatures obtained by interpolation are used for iterative solution to finally obtain the extraction process curve.

[0109] (2.6) Optimization algorithm to solve temperature parameters

[0110] The objective function is defined as the sum of the mean square error of all group experimental values and calculated values, and the genetic algorithm is used for parameter optimization. The temperature parameters are brought into the equation to obtain the extraction tank internal temperature curve with time change in the experimental group. The determination coefficients R 2 of the fitting of the internal temperature change curve of the extraction tank in the extraction process of 12 groups of notoginseng are 0.9965, 0.9982, 0.9974, 0.9955, 0.9950, 0.9975, 0.9967, 0.9916, 0.9978, 0.9966, 0.9979, respectively. The average determination coefficient is 0.9964. Overall, the fitting effect is good, which can reflect the temperature change rule of the extraction tank in the extraction process of notoginseng.

[0111] (2.7) Optimization algorithm to solve the mass transfer parameters

[0112] For the index component notoginsenoside Rl, the optimization algorithm is used to fit the parameters, and 5 parameters are obtained by fitting. The fitting results are brought into the equation to solve the kinetic curve of the experimental group. The determination coefficients R 2 of the fitting curve of notoginsenoside Rl extraction process before fitting are 0.9834, 0.9845, 0.9290, 0.9806, 0.9855, 0.9781, 0.9610, 0.9532, 0.8893, 0.9756 and 0.9325 respectively. The average determination coefficient is 0.9577. Overall, the fitting effect is good, which can reflect the component change rule of notoginsenoside Rl extraction process.

[0113] For the index component ginsenoside Rg1, the optimization algorithm is used to fit the parameters, and 5 parameters are obtained by fitting. The fitting results are brought into the equation to solve the kinetic curve of the experimental group. The determination coefficients R 2 of the fitting curve of ginsenoside Rg1 extraction process before fitting are 0.9779, 0.9800, 0.9863, 0.9847, 0.9760, 0.9712, 0.9582, 0.7860, 0.8871, 0.9496 and 0.9296 respectively. The average determination coefficient is 0.9422. Overall, the fitting effect is good, which can reflect the component change rule of ginsenoside Rg1 extraction process.

[0114] For the index component ginsenoside Rb1, the optimization algorithm is used to fit the parameters, and 5 parameters are obtained by fitting. The fitting results are brought into the equation to solve the kinetic curve of the experimental group. The determination coefficients R 2 of the fitting curve of ginsenoside Rb1 extraction process before fitting are 0.9695, 0.9741, 0.9686, 0.9486, 0.9649, 0.9646, 0.9423, 0.8094, 0.8820, 0.9503 and 0.9002 respectively. The average determination coefficient is 0.9340. Overall, the fitting effect is good, which can reflect the component change rule of ginsenoside Rb1 extraction process.

[0115] (2.8) Prediction by model

[0116] The 12th group is used as the prediction group for prediction. After knowing the change of heating medium temperature, the temperature change curve in the extraction tank with time is predicted, as shown in Figure 6 The prediction R 2 of the prediction group is 0.9980. Then the temperature change rule is used to predict the content change of three saponins in panax notoginseng. For notoginsenoside Rl, the prediction R 2was 0.9612; for ginsenoside Rg1, the predicted R 2 was 0.9341; for ginsenoside Rb1, the predicted R 2 was 0.9638. It shows that the model developed in the present application can better fit and predict the temperature and the change of the index component under different parameter conditions, different extraction processes (soaking extraction, temperature rising extraction, temperature keeping extraction).

[0117] Example 3

[0118] (3.1) Collection of Traditional Chinese Medicine Raw Material Parameters

[0119] The Scutellaria baicalensis Georgi was crushed and sieved to obtain coarse powder, fine powder and medium powder, and the extraction liquid volume and the raw material volume were determined by soaking experiment. The content of baicalin in different batches of Scutellaria baicalensis Georgi was determined according to the literature method.

[0120] (3.2) Data set establishment

[0121] Different groups of traditional Chinese medicine extraction experiments were designed, and the factors investigated in the extraction process included heating medium temperature, solid-liquid ratio, particle size of raw material and batch of raw material. The extraction experiments of different groups are shown in Table 3. The extraction process includes soaking for 1 h, then heating for 3 h by opening the heating tank. The traditional Chinese medicine extraction process includes soaking, temperature rising and temperature keeping processes. Samples at different time points of the extraction process were collected and information was recorded. The recorded information includes particle size of raw material, batch of raw material, solid-liquid ratio, temperature data of extraction liquid and temperature data of heating medium;

[0122] Table 3 Scutellaria baicalensis Georgi extraction experiment table

[0123]

[0124] The collected samples were detected and analyzed by liquid chromatography to determine the content of index components in traditional Chinese medicine extraction liquid samples. After data cleaning, the data set was obtained.

[0125] (3.3) Extraction model screening

[0126] Considering that the index components do not degrade and the solvent for extraction is pure water, a single solvent extraction model is selected.

[0127] (3.4) Establishment of heat transfer model of extraction process

[0128] The same as Example 1.

[0129] (3.5) Establishment of mass transfer model of extraction process

[0130] In the same batch of raw material, the result of the parameter K in the model affecting the final extraction content is the parameter K, wherein the parameter K is the product of the parameters K and K. The extraction content results are related to temperature, extraction solvent ratio and medicinal material particle size, and according to the actual extraction results, whether the parameters are related can reduce the complexity of the model. For baicalin, the model formula (S1)-(S5) corresponding to single solvent extraction model, according to the experimental results, the model parameters can be appropriately simplified, K=x3, the initial solution of the equation group is t=0, C W =0, and the parameters to be fitted are 3.

[0131] (3.6) Optimization algorithm for solving temperature parameters

[0132] The objective function is defined as the sum of the mean square error of all group experimental values and calculated values, the genetic algorithm is used for parameter optimization, the temperature parameters are brought into the equation to obtain the extraction tank internal temperature change curve with time of the experimental groups. The determination coefficients R 2 of the fitting of the extraction tank internal temperature change curves of 8 groups of scutellaria extraction processes are 0.9914, 0.9955, 0.9934, 0.9746, 0.9965, 0.9966, 0.9944 and 0.9979 respectively. The average determination coefficient is 0.9925. Overall, the fitting effect is good, which can reflect the temperature change rule of the extraction tank in the scutellaria extraction process.

[0133] (3.7) Optimization algorithm for solving mass transfer parameters

[0134] The parameters are fitted by using the optimization algorithm, 3 parameters in the equation are fitted, the fitting results are brought into the equation to obtain the kinetic curves of the experimental groups. The determination coefficients R 2 of the fitting curves of 10 groups of scutellaria extraction processes are 0.7221, 0.8984, 0.9437, 0.9897, 0.9613, 0.9934, 0.9206 and 0.9656 respectively. The average determination coefficient is 0.9243. Overall, the fitting effect is good, which can reflect the component change rule of the scutellaria extraction process.

[0135] (3.8) Prediction by using the model

[0136] Another group is used as a prediction group for prediction. After knowing the heating medium temperature change, the temperature change curve with time in the extraction tank is predicted, as shown in Figure 7 . The prediction R 2 of the prediction group is 0.9985. Then the baicalin content change in scutellaria is predicted by using the temperature change rule, and the prediction R 2 is 0.9645. It is shown that the model developed in the application can better fit and predict the temperature and index component change under different parameter conditions and different extraction processes (soaking extraction, temperature rising extraction and temperature keeping extraction).

[0137] Example 4

[0138] (4.1) Collection of Traditional Chinese Medicine Raw Material Parameters

[0139] The extraction liquid volume and the volume of medicinal material of honeysuckle were determined by soaking experiment. The contents of index components in different batches of honeysuckle medicinal materials were determined according to the literature method, and the index components were chlorogenic acid, cryptochlorogenic acid, neochlorogenic acid, caffeic acid, isochlorogenic acid A, isochlorogenic acid B and isochlorogenic acid C.

[0140] (4.2) Data set establishment

[0141] Traditional Chinese medicine extraction experiments in different groups were designed. The factors investigated in the extraction process included heating medium temperature, solid-liquid ratio, soaking time and medicinal material batch. The extraction experiments in different groups are shown in Table 4. A total of 7 groups of experiments, with another batch of honeysuckle extraction experiment in the seventh group as the prediction set. The extraction process was that the medicinal material was first soaked for 1 h, and then the heating tank was started to heat for 3 h. The traditional Chinese medicine extraction process included soaking, heating and holding processes. Samples at different time points in the extraction process were collected and information was recorded. The recorded information included medicinal material batch, soaking time, solid-liquid ratio, extraction liquid temperature data and heating medium temperature data.

[0142] Table 4 Honeysuckle extraction experiment table

[0143]

[0144] The samples collected were detected and analyzed by liquid chromatography to determine the content of index components in traditional Chinese medicine extraction liquid samples. After data cleaning, the data set was obtained.

[0145] (4.3) Extraction model screening

[0146] The conversion rule of components in honeysuckle is complex. According to the related literature, appropriate assumptions are made: chlorogenic acid is partially degraded in the extraction process, and the degradation products are cryptochlorogenic acid and neochlorogenic acid; isochlorogenic acid A is partially degraded in the extraction process, and the degradation products are caffeic acid, isochlorogenic acid B and isochlorogenic acid C. Therefore, chlorogenic acid and isochlorogenic acid A are degradation models, and cryptochlorogenic acid, neochlorogenic acid, caffeic acid, isochlorogenic acid B and isochlorogenic acid C are generation models.

[0147] (4.4) Establishment of heat transfer model in extraction process

[0148] The same as Example 1.

[0149] (4.5) Establishment of mass transfer model in extraction process

[0150] For chlorogenic acid and isochlorogenic acid A in honeysuckle, the degradation extraction model formula (S11)-(S15) is used. According to the experimental results, the model parameters can be appropriately simplified, K=x5, and the initial solution of the equation group is: t=0, CW = 0, and 5 parameters need to be fitted for each component.

[0151] For cryptochlorogenic acid and neochlorogenic acid, the extraction model equations (S16)-(S20) were generated accordingly. According to the experimental results, the model parameters can be appropriately simplified, K = x5, C W,A is the chlorogenic acid content at different times, and the initial solution of the equation group is: t = 0, C W = 0, and 5 parameters need to be fitted for each component.

[0152] For caffeic acid, isochlorogenic acid B and isochlorogenic acid C, the extraction model equations (S16)-(S20) were generated accordingly. According to the experimental results, the model parameters can be appropriately simplified, K = x5, C W,A is the isochlorogenic acid A content at different times, and the initial solution of the equation group is: t = 0, C W = 0, and 5 parameters need to be fitted for each component.

[0153] (4.6) Optimization algorithm to solve temperature parameters

[0154] The objective function is defined as the sum of the mean square error of all experimental values and calculated values. Genetic algorithm is used for parameter optimization, and the temperature parameters are brought into the equation to obtain the temperature change curve of the extraction tank inside the experimental group over time. The determination coefficients R 2 of the fitting of the temperature change curve of the extraction tank inside the extraction process of 7 groups of honeysuckle are 0.9986, 0.9981, 0.9970, 0.9970, 0.9958, 0.9947, 0.9970, respectively. The average determination coefficient is 0.9969. Overall, the fitting effect is good, which can reflect the temperature change rule of the extraction tank inside the extraction process of honeysuckle.

[0155] (4.7) Optimization algorithm to solve mass transfer parameters

[0156] For the index component chlorogenic acid, the optimization algorithm is used to fit the parameters, and the fitting results are brought into the equation to obtain the kinetic curve of the experimental group. The determination coefficients R 2 of the fitting curve of chlorogenic acid in the extraction process of 7 groups of honeysuckle are 0.9399, 0.9405, 0.9689, 0.9429, 0.9810, 0.9889, 0.9831, respectively. The average determination coefficient is 0.9636. Overall, the fitting effect is good, which can reflect the component change rule of the extraction process of chlorogenic acid.

[0157] For the index component of the new green acid, the optimization algorithm is used to fit the parameters, and the five parameters are obtained. The fitting results are brought into the equation to solve the kinetic curve of the experimental group. The determination coefficients R of the new green acid fitting curve in the extraction process of 7 groups of honeysuckle are 0.9522, 0.9474, 0.9799, 0.9436, 0.9891, 0.9885, 0.9758 respectively. The average determination coefficient is 0.9681. Overall, the fitting effect is good, which can reflect the component change rule of the new green acid in the extraction process. 2

[0158] For the index component of the new green acid, the optimization algorithm is used to fit the parameters, and the five parameters are obtained. The fitting results are brought into the equation to solve the kinetic curve of the experimental group. The determination coefficients R of the new green acid fitting curve in the extraction process of 7 groups of honeysuckle are 0.9522, 0.9474, 0.9799, 0.9436, 0.9891, 0.9885, 0.9758 respectively. The average determination coefficient is 0.9681. Overall, the fitting effect is good, which can reflect the component change rule of the new green acid in the extraction process. 2

[0159] For the index component of the new green acid, the optimization algorithm is used to fit the parameters, and the five parameters are obtained. The fitting results are brought into the equation to solve the kinetic curve of the experimental group. The determination coefficients R of the new green acid fitting curve in the extraction process of 7 groups of honeysuckle are 0.9522, 0.9474, 0.9799, 0.9436, 0.9891, 0.9885, 0.9758 respectively. The average determination coefficient is 0.9681. Overall, the fitting effect is good, which can reflect the component change rule of the new green acid in the extraction process. 2

[0160] For the index component of the new green acid, the optimization algorithm is used to fit the parameters, and the five parameters are obtained. The fitting results are brought into the equation to solve the kinetic curve of the experimental group. The determination coefficients R of the new green acid fitting curve in the extraction process of 7 groups of honeysuckle are 0.9522, 0.9474, 0.9799, 0.9436, 0.9891, 0.9885, 0.9758 respectively. The average determination coefficient is 0.9681. Overall, the fitting effect is good, which can reflect the component change rule of the new green acid in the extraction process. 2

[0161] For the index component of the new green acid, the optimization algorithm is used to fit the parameters, and the five parameters are obtained. The fitting results are brought into the equation to solve the kinetic curve of the experimental group. The determination coefficients R of the new green acid fitting curve in the extraction process of 7 groups of honeysuckle are 0.9522, 0.9474, 0.9799, 0.9436, 0.9891, 0.9885, 0.9758 respectively. The average determination coefficient is 0.9681. Overall, the fitting effect is good, which can reflect the component change rule of the new green acid in the extraction process. 2 ​​​​0.9808, 0.9806, 0.9856, 0.9462, 0.9882, 0.9738, 0.9433. The average determination coefficient is 0.9712. Overall, the fitting effect is good, and the component change rule in the extraction process of isochlorogenic acid C can be reflected.

[0162] For the index component caffeic acid, the optimized algorithm is used to fit the parameters, 7 parameters are obtained by fitting, and the fitting results are brought into the equation to obtain the kinetic curve of the experimental group. The determination coefficients R 2 of the fitting curves of caffeic acid in the extraction process of 7 groups of honeysuckle are 0.8834, 0.9525, 0.9328, 0.8294, 0.9304, 0.9656, and 0.9649. The average determination coefficient is 0.9227. Overall, the fitting effect is good, and the component change rule in the extraction process of caffeic acid can be reflected.

[0163] (4.8) Prediction by using the model

[0164] The extraction process of another batch of medicinal materials is used as a prediction group to predict the temperature change curve in the extraction tank with time after knowing the change of the heating medium temperature, as shown in Figure 8 The prediction R 2 of the prediction group is 0.9961. Then, the content change of different components in honeysuckle is predicted by using the temperature change rule, wherein the prediction R 2 of chlorogenic acid is 0.9501, the prediction R 2 of cryptochlorogenic acid is 0.9538, the prediction R 2 of neochlorogenic acid is 0.9404, the prediction R 2 of isochlorogenic acid A is 0.9325, the prediction R 2 of isochlorogenic acid B is 0.9831, the prediction R 2 of isochlorogenic acid C is 0.9714, and the prediction R 2 of caffeic acid is 0.8996. It is shown that the model developed in the present application can better fit and predict the temperature and index component change under different parameter conditions and different extraction processes (soaking extraction, temperature rising extraction, and temperature keeping extraction).

[0165] The above examples have described the technical solutions of the present application in detail, and it should be understood that the above examples are only specific embodiments of the present application, and are not used to limit the present application. Any modification, supplement or similar replacement within the principle range of the present application should be included in the protection range of the present application.

Claims

1. A method for predicting the content of index components in a traditional Chinese medicine extraction process, characterized in that: The following steps are involved: (1) First, the parameters of the Chinese medicine raw materials are collected. Then, by changing the parameters of the Chinese medicine extraction process, samples of Chinese medicine extracts obtained under different extraction conditions and at different extraction times are collected, and the information is recorded. The content of the index components in the Chinese medicine extract samples is measured, and the data is cleaned to obtain the data set; The Chinese medicine extraction process includes soaking, heating and heat preservation processes, and the recorded information includes the temperature data of the extraction liquid and the temperature data of the heating medium; (2) Establishing an extraction process heat transfer model and an extraction process mass transfer model, screening the extraction process mass transfer model, and using samples in the data set to train the extraction process heat transfer model and the extraction process mass transfer model to optimize the prediction model parameters; the extraction process mass transfer model is a dissolution model or a chemical reaction model, the dissolution model includes a single solvent extraction model or a mixed solvent extraction model, and the chemical reaction model includes a degradation extraction model or a generation extraction model; (3) Using the extraction process heat transfer model and the extraction process mass transfer model after parameter optimization to predict the content of the index components in the traditional Chinese medicine extraction process; The mass transfer model for the screening extraction process is as follows: when the index component extraction process is a component dissolution process and the extraction solvent is a pure solvent, the single solvent extraction model is selected; when the index component extraction process is a component dissolution process and the extraction solvent is a mixed solvent, the mixed solvent extraction model is selected; when the index component extraction process involves transformation or degradation of the index component, the degradation extraction model is selected for the index component that undergoes degradation, and the generation extraction model is selected for the index component generated by transformation; The single solvent extraction model is expressed as: Official (S1) Official (S2) Official (S3) Official (S4) Official (S5) In the single solvent extraction model, The quality of the medicinal materials fed, is the initial content of the index component in the medicinal material, For time, is the mass transfer coefficient, which is related to the extraction liquid temperature The correlation is shown in formula (S4). is the specific surface area of ​​the medicinal material particles, It is the index component content in the medicinal materials during the extraction process. is the index component content in the extract, is the ratio coefficient of the index component in the medicinal material to the index component in the extract, and its relationship with temperature is shown in formula (S5). Represents the volume of wet medicinal materials, represents the volume of the extract, are all parameters to be fitted; The mixed solvent extraction model is expressed as: Formula (S6) Formula (S7) Official (S8) Official (S9) Official (S10) In the mixed solvent extraction model, is the solvent ratio of one component in the mixed solvent, and the meanings of the other parameters are the same as those in formulas (S1)-(S5). are all parameters to be fitted; The degradation extraction model is expressed as: Official (S11) Official (S12) Official (S13) Official (S14) Official (S15) In the degradation extraction model, is the degradation rate constant of the index component A, is the mass transfer coefficient of the index component A, is the ratio coefficient of the index component A in the medicinal material to the index component A in the extract, is the content of index component A in the medicinal materials during the extraction process, is the content of index component A in the extract, and the meanings of the other parameters are the same as those in formulas (S1)-(S5). are all parameters to be fitted; The generation and extraction model is expressed as: Formula (S16) Official (S17) Formula (S18) Official (S19) Official (S20) In generating the extraction model, is the generation rate constant of the index component B, is the mass transfer coefficient of the index component B, The ratio coefficient of the index component B in the medicinal material and the index component B in the extract, is the content of the index component B in the medicinal material, is the content of index component B in the extract, and the meanings of the other parameters are the same as those in formulas (S11)-(S15). These are parameters to be fitted.

2. The method for predicting the content of index components in the Chinese medicine extraction process according to claim 1, wherein: The parameters of the Chinese medicine raw materials include the particle size of the medicinal material particles, the specific surface area of ​​the medicinal material particles, the content of the index components, the volume of the wet medicinal material or the volume of the extract.

3. The method for predicting the content of index components in the Chinese medicine extraction process according to claim 1, wherein: The recorded information also includes the particle size of the medicinal material, the batch of medicinal material, the extraction solvent, the material-liquid ratio or the extraction time; the content of the index components in the Chinese medicine extract sample is determined by liquid chromatography.

4. The method for predicting the content of index components in the Chinese medicine extraction process according to claim 1, wherein: Heat balance is performed on the traditional Chinese medicine extraction process, and a heat transfer model of the extraction process is established to characterize the heat transfer of the heating medium, extraction container and extraction liquid.

5. The method for predicting the content of index components in the Chinese medicine extraction process according to claim 1, wherein: The mass transfer model of the extraction process is used to characterize the changes in the content of the index components under different extraction conditions and different extraction times. The corresponding mass transfer model of the extraction process is selected according to the properties of the index components and different extraction solvents.

6. The method for predicting the content of index components in the Chinese medicine extraction process according to claim 1, wherein: Different samples from multiple groups of experiments in the data set are used as training sets, and the heat transfer model of the extraction process and the mass transfer model of the extraction process are trained using the training sets to fit appropriate parameters while satisfying the extraction process data obtained under different extraction conditions and different extraction times. In order to improve the fitting effect of the fitting parameter value, the objective function is defined, and the optimization algorithm is used to optimize the parameters to be fitted so that the deviation between the actual data and the calculated data is minimized.

7. The method for predicting the content of index components in the traditional Chinese medicine extraction process according to claim 6, characterized in that: The optimization algorithm is set to one of the genetic algorithm, gray wolf optimization algorithm, and Markov-Monte Carlo optimization algorithm; the objective function is the coefficient of determination, mean square error, root mean square error, or mean absolute error.

8. The method for predicting the content of index components in the traditional Chinese medicine extraction process according to claim 7, characterized in that: The optimization algorithm is set to genetic algorithm.

9. The method for predicting the content of index components in the traditional Chinese medicine extraction process according to claim 7, characterized in that: The objective function is the mean square error.

10. A storage medium, characterized in that The storage medium stores a program, wherein when the program is run, the method for predicting the content of an indicator component in the traditional Chinese medicine extraction process according to any one of claims 1 to 9 is executed.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: The processor executes the method for predicting the content of index components in the traditional Chinese medicine extraction process according to any one of claims 1 to 9 through the computer program.

Images