Flow detection method for manufacturing process of chicory preparation

Abstract

The invention relates to the technical field of data processing, in particular to a process detection method for a manufacturing process of a chicory preparation, which comprises the following steps: acquiring a concentrated solution concentration data sequence and a corresponding chicoric acid yield data sequence in the manufacturing process of the chicory preparation under each ethanol concentration; dividing each concentrated solution concentration data sequence into at least two stage sequences according to data change characteristics in each concentrated solution concentration data sequence; each concentrated solution concentration data sequence is divided into at least two subsequences, and according to the data difference of the subsequences contained in each stage sequence in each concentrated solution concentration data sequence and the fluctuation characteristics of the concentrated solution concentration data in each stage sequence, the concentrated solution concentration data in each stage sequence is obtained; according to the method, the stage influence weight of each stage sequence in each concentrated solution concentration data sequence is obtained according to the concentration data sequence of each concentrated solution and the similarity between each concentrated solution concentration data sequence and the corresponding chicoric acid yield data sequence, a regression analysis model is constructed, and the accuracy of a regression analysis result is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a process detection method for a chicory preparation manufacturing process. BACKGROUND

[0002] Modern pharmacological studies have shown that chicory is rich in active ingredients such as phenolic acids (e.g., chicoric acid), coumarins (e.g., juglone), sesquiterpenes (e.g., lactucerin), polysaccharides, and alkaloids, and has multiple pharmacological effects such as reducing blood sugar, reducing blood lipids, reducing uric acid, protecting the liver, and regulating immunity. Based on its homoeopathy characteristics, chicory has been developed into various types of preparations. However, as market demand grows, quality control problems of chicory preparations have become increasingly prominent. Existing detection methods have technical bottlenecks in active ingredient quantification, process stability evaluation, and impurity control, and there is an urgent need to develop a systematic process detection method to ensure product quality.

[0003] In the process of the chicory preparation manufacturing process, the extraction process directly affects the manufacturing result. The main extraction process is ethanol reflux extraction, in which the ethanol concentration, extraction temperature, time, and solid-liquid ratio have an impact on the extraction rate of active ingredients such as chicoric acid and chlorogenic acid. Therefore, a mathematical model between process parameters and product quality indicators can be established by regression analysis to optimize the extraction conditions (parameter settings during ethanol reflux extraction). However, regression analysis is suitable for steady-state processes. In ethanol reflux extraction, the concentration of the concentrated solution changes dynamically over time due to solvent evaporation, solute enrichment, dynamic adjustment of component solubility equilibrium, and degradation of heat-sensitive components, resulting in poor adaptability of regression analysis to dynamic changes in continuous production, which may lead to inaccurate analysis results.

[0004] Therefore, how to improve the adaptability of regression analysis to dynamic changes in continuous production and improve the accuracy of the analysis results has become a problem to be solved. SUMMARY

[0005] Therefore, the present application provides a process detection method for a chicory preparation manufacturing process to solve the problem of how to improve the adaptability of regression analysis to dynamic changes in continuous production and improve the accuracy of the analysis results.

[0006] The process detection method for a chicory preparation manufacturing process provided in the present application includes the following steps: During the manufacturing process of chicory preparations under at least two ethanol concentrations, the concentration of the concentrated solution and the chicoric acid yield are detected in real time according to a preset detection frequency, and at least two concentrated solution concentration data sequences and their corresponding chicoric acid yield data sequences are obtained. Based on the data change characteristics in each concentrate concentration data sequence, obtain the stage coefficient of each concentrate concentration data in each concentrate concentration data sequence, and divide each concentrate concentration data sequence into at least two stage sequences based on the stage coefficient of each concentrate concentration data in each concentrate concentration data sequence. Each concentrated solution concentration data sequence is divided into at least two subsequences. Based on the data differences of the subsequences contained in each stage sequence of each concentrated solution concentration data sequence, the fluctuation characteristics of the concentrated solution concentration data in each stage sequence, and the similarity between each concentrated solution concentration data sequence and its corresponding chicoric acid yield data sequence, the stage influence weight of each stage sequence in each concentrated solution concentration data sequence is obtained. Based on the stage influence weight of each stage sequence in each concentrate concentration data sequence, a regression analysis model for chicory preparations in the manufacturing process is constructed to detect and adjust the process parameters of chicory preparations in the manufacturing process.

[0007] Preferably, the step of obtaining the stage coefficient of each concentrate concentration data in each concentrate concentration data sequence based on the data change characteristics in each concentrate concentration data sequence includes: The formula for calculating the stage coefficient of the b-th concentrate concentration data in any concentrate concentration data sequence is as follows: ; in, The stage coefficient for the b-th concentrate concentration data; For the first The stage coefficient of the concentrate concentration data; This represents the number of concentrate concentration data points preceding the b-th concentrate concentration data point. This is the first preset quantity; This represents the difference between the concentration data of the b-th concentrate and its left adjacent concentrate concentration data. The concentration difference between the b-th concentrate data and its right adjacent concentrate data; N is the second preset quantity; Let be the variance of the data sequence consisting of the b-th concentrate concentration data and the previous n concentrate concentration data; Let be the variance of the data sequence consisting of the b-th concentrate concentration data and the preceding n-1 concentrate concentration data. This represents the number of concentrate concentration data points following the b-th concentrate concentration data point. This is the third preset quantity; The stage coefficient for the left adjacent concentrate concentration data of the last concentrate concentration data; It is the absolute value symbol; This is the normalization function.

[0008] Preferably, the stage coefficient of each concentrated liquid concentration data in each concentrated liquid concentration data sequence is used to divide each concentrated liquid concentration data sequence into at least two stage sequences, including: The stage coefficients of each concentrated liquid concentration data in all concentrated liquid data sequences are formed into a stage coefficient set, the peak value in the stage coefficient set is obtained, the peak value in the stage coefficient set is eliminated to obtain a first stage coefficient set, the average value of the stage coefficients in the first stage coefficient set is obtained, the stage coefficients greater than the average value of the stage coefficients in the first stage coefficient set are eliminated to obtain a second stage coefficient set, and the peak value in the second stage coefficient set is obtained to correspondingly obtain the average value of the peak value; For any concentrated liquid concentration data sequence, the average value of the peak value is used to divide the any concentrated liquid concentration data sequence into at least two stage sequences.

[0009] Preferably, the stage influence weight of each stage sequence in each concentrated liquid concentration data sequence is obtained according to the data difference of the subsequence contained in each stage sequence in each concentrated liquid concentration data sequence, the fluctuation characteristics of the concentrated liquid concentration data in each stage sequence, and the similarity between each concentrated liquid concentration data sequence and its corresponding chrysin yield data sequence, including: For any concentrated liquid concentration data sequence, the dynamic lag influence coefficient of each subsequence is obtained according to the data difference of the concentrated liquid concentration data in each subsequence in the any concentrated liquid concentration data sequence; The influence coefficient importance of each stage sequence is obtained according to the dynamic lag influence coefficient of the subsequence contained in each stage sequence in the any concentrated liquid concentration data sequence, and the fluctuation characteristics of the concentrated liquid concentration data in each stage sequence; The influence coefficient importance of each stage sequence in the any concentrated liquid concentration data sequence is accumulated to obtain an influence coefficient importance accumulation value, and the ratio of the influence coefficient importance of each stage sequence in the any concentrated liquid concentration data sequence to the influence coefficient importance accumulation value is obtained to obtain the stage weight of each stage sequence; The stage influence weight of each stage sequence is obtained according to the stage weight of each stage sequence in the any concentrated liquid concentration data sequence, and the similarity between the any concentrated liquid concentration data sequence and its corresponding chrysin yield data sequence.

[0010] Preferably, the dynamic lag influence coefficient of each subsequence is obtained according to the data difference of the concentrated liquid concentration data in each subsequence in the any concentrated liquid concentration data sequence, including: According to the concentrated liquid concentration data in the any sub-sequence except the last concentrated liquid concentration data, a prediction value of the last concentrated liquid concentration data in the any sub-sequence is obtained by using an ARIMA algorithm, an absolute value of a difference between the last concentrated liquid concentration data and the prediction value is obtained, a prediction difference value is obtained, the prediction difference value is normalized to obtain a dynamic lag influence coefficient of the any sub-sequence.

[0011] Preferably, the dynamic lag influence coefficient of the sub-sequence contained in each stage sequence in the any concentrated liquid concentration data sequence and the fluctuation feature of the concentrated liquid concentration data in each stage sequence are used to obtain an influence coefficient importance degree of each stage sequence, including: The average value of the dynamic lag influence coefficient of the sub-sequence contained in the any stage sequence in the any concentrated liquid concentration data sequence is obtained, and is recorded as a dynamic lag influence coefficient average value; The reciprocal of the addition result of the variance of the any stage sequence and a constant 1 is obtained to obtain a stability degree, and the difference between the constant 1 and the stability degree is obtained to obtain a fluctuation degree; The product of the dynamic lag influence coefficient average value and the fluctuation degree is obtained to obtain the influence coefficient importance degree of the any stage sequence.

[0012] Preferably, the stage weight of each stage sequence in the any concentrated liquid concentration data sequence and the similarity degree between the any concentrated liquid concentration data sequence and the corresponding chrysin yield data sequence are used to obtain a stage influence weight of each stage sequence, including: The first-order difference data sequence of the any concentrated liquid concentration data sequence is obtained to obtain a concentrated liquid concentration difference sequence, the first-order difference data sequence of the chrysin yield data sequence corresponding to the any concentrated liquid concentration data sequence is obtained to obtain a chrysin yield difference sequence, the similarity degree between the concentrated liquid concentration difference sequence and the chrysin yield difference sequence is calculated by using a DTW algorithm, the product of the stage weight of the any stage sequence and the similarity degree is obtained to obtain the stage influence weight of the any stage sequence.

[0013] Compared with the prior art, the embodiment of the application has the beneficial effects that: In the present application, the acquisition stage coefficient is used to divide each concentrate concentration data sequence into at least two stage sequences, i.e., at least two stages according to the change of the concentrate concentration in the ethanol reflux extraction process, so that the stage dynamic change characteristics of the concentrate concentration data can be better captured; then the stage influence weight of each stage sequence in each concentrate concentration data sequence is acquired, so that the influence of the concentrate concentration change on the chrysanthemum acid yield in different stages of the ethanol reflux extraction process can be better analyzed in combination with the dynamic lag and stage change characteristics of the concentrate concentration data; and finally, a regression analysis model of the chrysanthemum preparation in the manufacturing process is constructed, the dynamic change adaptability of the regression analysis to the concentrate concentration change in the continuous production is improved, and the accuracy of the analysis result is improved. BRIEF DESCRIPTION OF DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0015] Figure 1 is a method flow chart of a chrysanthemum preparation manufacturing process flow detection method provided by the first embodiment of the present application. DETAILED DESCRIPTION

[0016] The embodiments of the present disclosure will be described in detail below, and examples of the embodiments are shown in the drawings. The embodiments described below by referring to the drawings are exemplary and are intended to explain the present disclosure, and cannot be understood as a limitation of the present disclosure.

[0017] It should be noted that the terms "first", "second" and the like in the specification of the present disclosure and the above drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all the embodiments consistent with the present disclosure. On the contrary, they are only examples of devices and methods consistent with some aspects of the present disclosure.

[0018] In order to illustrate the technical solutions of the present application, the following will be described by specific embodiments.

[0019] Reference Figure 1 is a method flow chart of a chrysanthemum preparation manufacturing process flow detection method provided by the first embodiment of the present application, as shown in Figure 1 The method can include: Step S101, during the preparation process of chicory preparations at least two ethanol concentrations, the concentration of concentrated liquid and the yield of chicoric acid are detected in real time according to the preset detection frequency, and at least two concentrated liquid concentration data sequences and their corresponding chicoric acid yield data sequences are obtained.

[0020] In the process of chicory preparation process, the extraction process directly affects the manufacturing results, the main extraction process is ethanol reflux extraction, the ethanol reflux extraction process is to crush the chicory root or leaf for drying treatment, add chicory powder and ethanol solution according to the set material liquid ratio, control the temperature for heating reflux extraction, after extraction, filter separation, reduce pressure concentration to dry, recover ethanol (can be recycled), obtain extract, then further separate target components by macroporous resin adsorption, column chromatography and other methods, vacuum drying or spray drying to obtain powder extract. Among them, the ethanol concentration, extraction temperature, time, material liquid ratio and other parameters have influence on the extraction rate of active ingredients such as chicoric acid and chlorogenic acid, therefore, the mathematical model between process parameters and product quality index can be established by regression analysis, and the extraction conditions (parameter setting during ethanol reflux extraction) are optimized.

[0021] But regression analysis is suitable for steady-state process, in ethanol reflux extraction, there are dynamic changes of concentrated liquid concentration with time, such as dynamic adjustment of component dissolution equilibrium, degradation of heat sensitive components, etc., which leads to poor adaptability of regression analysis to dynamic changes in continuous production, so that the analysis result may deviate, and then the result is inaccurate.

[0022] Because ethanol concentration is one of the key factors affecting the concentration of concentrated liquid, and the concentration of concentrated liquid is one of the key factors affecting the purity of purified product, therefore, in this embodiment, ethanol concentration is taken as an example for analysis, ethanol with different concentrations is added to chicory powder and ethanol solution according to the commonly used material liquid ratio (1:10-1:20), the temperature is controlled near the boiling point of ethanol (78-80℃), the reflux time is usually 1-3 hours, the concentration of concentrated liquid (i.e. concentrated extract after removing ethanol solution from the extract liquid by rotary evaporation) and the yield of chicoric acid in the process are detected in real time according to the preset detection frequency, and the concentrated liquid concentration data sequence and its corresponding chicoric acid yield data sequence are obtained, that is, a concentrated liquid concentration data sequence and its corresponding chicoric acid yield data sequence are obtained in the ethanol reflux extraction process at each ethanol concentration, which is used to analyze the dynamic change of the concentration of concentrated liquid in the ethanol reflux extraction process. In this embodiment, the preset detection frequency is set to once every 2 minutes, which is not limited here and can be set according to the specific implementation scene, the concentration of concentrated liquid is obtained by direct weighing method or drying residue method, and the yield of chicoric acid is obtained by HPLC method to obtain the content of chicoric acid, and then the yield of chicoric acid is calculated by dividing the mass of the extract liquid by the mass of the raw material.

[0023] In step S102, a stage coefficient of each concentrated liquid concentration data in each concentrated liquid concentration data sequence is obtained according to the data variation characteristics in each concentrated liquid concentration data sequence, and each concentrated liquid concentration data sequence is divided into at least two stage sequences according to the stage coefficient of each concentrated liquid concentration data in each concentrated liquid concentration data sequence.

[0024] During the ethanol reflux extraction process, the concentration of the concentrated liquid changes dynamically over time, which is affected by multiple factors such as solvent evaporation, component dissolution equilibrium, and degradation of heat-sensitive components. For example, during the ethanol reflux process, ethanol continuously vaporizes and condenses back to flow, and part of the ethanol is lost due to evaporation or leakage, resulting in a decrease in the total amount of solvent. As the solvent decreases, the concentration of solutes (such as chicoric acid and polysaccharides) in the remaining solvent gradually increases, forming a concentration effect. In different stages, such as the initial stage, the solvent is sufficient and the solute is quickly dissolved, so the concentration rises quickly; in the middle stage, the dissolution approaches equilibrium, and the concentration growth slows down; in the later stage, the solvent is close to exhaustion, and the concentration reaches saturation or supersaturation state, that is, the concentration of the concentrated liquid changes in stages.

[0025] Therefore, according to the data variation characteristics in each concentrated liquid concentration data sequence, the stage coefficient of each concentrated liquid concentration data in each concentrated liquid concentration data sequence can be obtained, and then each concentrated liquid concentration data sequence can be divided into at least two stage sequences according to the stage coefficient of each concentrated liquid concentration data in each concentrated liquid concentration data sequence.

[0026] The method for obtaining the stage coefficient of each concentrated liquid concentration data in each concentrated liquid concentration data sequence according to the data variation characteristics in each concentrated liquid concentration data sequence is as follows: The calculation formula of the stage coefficient of the bth concentrated liquid concentration data in any concentrated liquid concentration data sequence is as follows:

[0027] Wherein, is the stage coefficient of the bth concentrated liquid concentration data; is the stage coefficient of the bth concentrated liquid concentration data; is the stage coefficient of the bth concentrated liquid concentration data; is the number of concentrated liquid concentration data before the bth concentrated liquid concentration data; is the first preset number; is the difference between the bth concentrated liquid concentration data and its left adjacent concentrated liquid concentration data; is the difference between the bth concentrated liquid concentration data and its right adjacent concentrated liquid concentration data; N is the second preset number; is the variance of the data sequence composed of the bth concentrated liquid concentration data and its previous n concentrated liquid concentration data; a variance of a data sequence composed of the bth concentrated liquid concentration data and n-1 concentrated liquid concentration data before the bth concentrated liquid concentration data; a number of concentrated liquid concentration data after the bth concentrated liquid concentration data; a third preset number; a stage coefficient of a left adjacent concentrated liquid concentration data of the last concentrated liquid concentration data; an absolute value symbol; a normalization function.

[0028] It should be noted that in the embodiment, the third preset number is set to 3, which is not limited here and can be set according to a specific implementation scenario. When the number of concentrated liquid concentration data after the bth concentrated liquid concentration data is less than 3, it indicates that the bth concentrated liquid concentration data is not enough to analyze the data change characteristics, and a stage change does not occur at the beginning, so the stage coefficient of the first three concentrated liquid concentration data is set to be the same as the stage coefficient of the fourth concentrated liquid concentration data. When the number of concentrated liquid concentration data after the bth concentrated liquid concentration data is greater than 3, it indicates that the bth concentrated liquid concentration data is enough to analyze the data change characteristics, and a stage change occurs at the beginning, so the stage coefficient of the first three concentrated liquid concentration data is set to be different from the stage coefficient of the fourth concentrated liquid concentration data. When the number of concentrated liquid concentration data after the bth concentrated liquid concentration data is greater than 3, it indicates that the bth concentrated liquid concentration data is enough to analyze the data change characteristics, and a stage change occurs at the beginning, so the stage coefficient of the first three concentrated liquid concentration data is set to be different from the stage coefficient of the fourth concentrated liquid concentration data. When the number of concentrated liquid concentration data after the bth concentrated liquid concentration data is greater than 3, it indicates that the bth concentrated liquid concentration data is enough to analyze the data change characteristics, and a stage change occurs at the beginning, so the stage coefficient of the first three concentrated liquid concentration data is set to be different from the stage coefficient of the fourth concentrated liquid concentration data. When the number of concentrated liquid concentration data after the bth concentrated liquid concentration data is greater than 3, it indicates that the bth concentrated liquid concentration data is enough to analyze the data change characteristics, and a stage change occurs at the beginning, so the stage coefficient of the first three concentrated liquid concentration data is set to be different from the stage coefficient of the fourth concentrated liquid concentration data. The greater the value is, the greater the difference between the concentration of the bth concentrated liquid concentration data and the concentration of the previous concentrated liquid concentration data is, and the greater the probability that the bth concentrated liquid concentration data is a stage point is. The greater the value is, the greater the difference between the concentration of the bth concentrated liquid concentration data and the concentration of the previous concentrated liquid concentration data is, and the greater the probability that the bth concentrated liquid concentration data is a stage point is. The greater the value is, the greater the difference between the concentration of the bth concentrated liquid concentration data and the concentration of the previous concentrated liquid concentration data is, and the greater the probability that the bth concentrated liquid concentration data is a stage point is. The greater the value is, the greater the difference between the concentration of the bth concentrated liquid concentration data and the concentration of the previous concentrated liquid concentration data is, and the greater the probability that the bth concentrated liquid concentration data is a stage point is. The greater the value is, the greater the difference between the concentration of the bth concentrated liquid concentration data and the concentration of the previous concentrated liquid concentration data is, and the greater the probability that the bth concentrated liquid concentration data is a stage point is. In the embodiment, the number N is set to 10, which is not limited here and can be set according to a specific implementation scenario. If the number of concentrated liquid concentration data before the bth concentrated liquid concentration data is less than 10, N is processed according to the number of the bth concentrated liquid concentration data. The greater the value is, the greater the difference between the concentration of the bth concentrated liquid concentration data and the concentration of the previous concentrated liquid concentration data is, and the greater the probability that the bth concentrated liquid concentration data is a stage point is. The greater the value is, the greater the difference between the concentration of the bth concentrated liquid concentration data and the concentration of the previous concentrated liquid concentration data is, and the greater the probability that the bth concentrated liquid concentration data is a stage point is. In the embodiment, the number N is set to 10, which is not limited here and can be set according to a specific implementation scenario. If the number of concentrated liquid concentration data before the bth concentrated liquid concentration data is less than 10, N is processed according to the number of the bth concentrated liquid concentration data. When the number of concentrated liquid concentration data after the bth concentrated liquid concentration data is greater than 3, it indicates that the bth concentrated liquid concentration data is enough to analyze the data change characteristics, and a stage change occurs at the beginning, so the stage coefficient of the first three concentrated liquid concentration data is set to be different from the stage coefficient of the fourth concentrated liquid concentration data.

[0029] ​According to the stage coefficient acquisition method of the bth concentrated liquid concentration data in any concentrated liquid concentration data sequence, the stage coefficient of each concentrated liquid concentration data in any concentrated liquid concentration data sequence is acquired, and the stage coefficient of each concentrated liquid concentration data in each concentrated liquid concentration data sequence is obtained.

[0030] Further, according to the stage coefficient of each concentrated liquid concentration data in each concentrated liquid concentration data sequence, each concentrated liquid concentration data sequence is divided into at least two stage sequences, and the specific method is as follows: The stage coefficients of each concentrated liquid concentration data in all concentrated liquid data sequences form a stage coefficient set, a statistical histogram of the stage coefficient set is acquired, the abscissa of the statistical histogram is the stage coefficient, the ordinate is the frequency corresponding to the stage coefficient, the peak value in the statistical histogram is acquired, since the stage coefficient of the stage point is large and the stage coefficients of the remaining data points are small, and the number of the remaining data points is much larger than the frequency distribution of the stage points, the peak value is more likely to be the stage coefficient of the non-stage point, so the peak value is removed from the stage coefficient set to obtain a first stage coefficient set; since the stage coefficient of the stage point is large, the average value of the stage coefficient of the first stage coefficient set is acquired, and the stage coefficient greater than the average value of the stage coefficient in the first stage coefficient set is removed to obtain a second stage coefficient set; meanwhile, since the stage of the change of the concentrated liquid concentration data has regularity and exists in the extraction of different ethanol concentrations, the peak value of the second stage coefficient set is acquired, and the average value of the peak value is obtained as a reference threshold value of the stage point; For any concentrated liquid concentration data sequence, the concentrated liquid concentration data with the stage coefficient greater than the reference threshold value is regarded as the stage point of any concentrated liquid concentration data sequence, and the any concentrated liquid concentration data sequence is divided into at least two stage sequences. For example, the concentrated liquid concentration data sequence (1, 2, 3, 4, 5, 6, 7, 8, 9, 10), assuming that the concentrated liquid concentration data 3 and 7 are stage points, the concentrated liquid concentration data sequence is divided into three stage sequences (1, 2), (3, 4, 5, 6), (7, 8, 9, 10).

[0031] Similarly, each concentrated liquid concentration data sequence is divided into at least two stage sequences.

[0032] In step S103, each concentrated liquid concentration data sequence is divided into at least two sub-sequences, the stage influence weight of each stage sequence in each concentrated liquid concentration data sequence is acquired according to the data difference of the sub-sequences contained in each stage sequence in each concentrated liquid concentration data sequence, the fluctuation characteristics of the concentrated liquid concentration data in each stage sequence, and the similarity degree between each concentrated liquid concentration data sequence and the corresponding chrysin acid yield data sequence.

[0033] Since the dynamics of the concentrated liquid concentration data mainly reflects the different changes in different stages, the stage influence weight of each stage sequence in each concentrated liquid concentration data sequence can be obtained to establish a regression model and enhance the dynamic adaptability of the regression model.

[0034] Since the concentrated liquid concentration data has time-varying characteristics, and the traditional regression model has the limitations of static hypothesis and lag effect neglect, according to the sliding window with a length of 10 and a step of 1, which is not limited here and can be set according to the specific implementation scenario, each concentrated liquid concentration data sequence is divided into at least two subsequences starting from the first concentrated liquid concentration data in each concentrated liquid concentration data sequence. According to the data difference of the subsequence contained in each stage sequence in each concentrated liquid concentration data sequence, the dynamic lag influence coefficient of each subsequence in each concentrated liquid concentration data sequence is obtained.

[0035] Among them, the method for obtaining the dynamic lag influence coefficient of each subsequence in each concentrated liquid concentration data sequence according to the data difference of the subsequence contained in each stage sequence in each concentrated liquid concentration data sequence is as follows: For any subsequence in any concentrated liquid concentration data sequence, according to the concentrated liquid concentration data in the subsequence except the last concentrated liquid concentration data, the predicted value of the last concentrated liquid concentration data in the subsequence is obtained by using the ARIMA algorithm. The ARIMA algorithm belongs to the prior art and will not be described here. The absolute value of the difference between the last concentrated liquid concentration data in the subsequence and its predicted value is obtained to obtain the prediction difference value. The prediction difference value is normalized to obtain the dynamic lag influence coefficient of the subsequence.

[0036] In an embodiment, taking the a-th subsequence in any concentrated liquid concentration data sequence as an example, the calculation formula of the dynamic lag influence coefficient of the a-th subsequence is:

[0037] Among them, is the dynamic lag influence coefficient of the a-th subsequence; is the last concentrated liquid concentration data in the a-th subsequence; is the predicted value of the last concentrated liquid concentration data in the a-th subsequence; is the absolute value symbol; is the normalization function.

[0038] It should be noted that, The larger the value is, the more the data in the a-th subsequence has dynamic lag and is not fully captured, that is, the last concentrated liquid concentration data in the a-th subsequence may be affected by more historical concentrated liquid concentration data, and the influence period is longer, The greater the more.

[0039] Further, since the concentration data of the concentrated solution has stages, that is, each stage corresponds to an extraction result (chicory acid yield) of a concentration of the concentrated solution, if the dynamic lag influence coefficient of the sub-sequence contained in each stage sequence changes greatly, the regression model may underestimate the real influence of the process parameters, and when the concentration data of the concentrated solution changes greatly, the influence on the extraction result is also great. Therefore, according to the dynamic lag influence coefficient of the sub-sequence contained in each stage sequence in each concentrated solution concentration data sequence, the fluctuation characteristics of the concentrated solution concentration data in each stage sequence, and the similarity between each concentrated solution concentration data sequence and its corresponding chicory acid yield data sequence, the stage influence weight of each stage sequence in each concentrated solution concentration data sequence can be obtained.

[0040] Therefore, for any concentrated solution concentration data sequence, the stage influence weight of each stage sequence in the any concentrated solution concentration data sequence is as follows: (1) According to the dynamic lag influence coefficient of the sub-sequence contained in each stage sequence in the any concentrated solution concentration data sequence, and the fluctuation characteristics of the concentrated solution concentration data in each stage sequence, the influence coefficient importance degree of each stage sequence is obtained.

[0041] Specifically, for any stage sequence in the any concentrated solution concentration data sequence, the average value of the dynamic lag influence coefficient of the sub-sequence contained in the any stage sequence is obtained, denoted as dynamic lag influence coefficient mean; The reciprocal of the addition result of the variance of the any stage sequence and constant 1 is obtained to obtain the stability degree, and the difference between constant 1 and the stability degree is obtained to obtain the fluctuation degree; The product of the dynamic lag influence coefficient mean and the fluctuation degree is obtained to obtain the influence coefficient importance degree of the any stage sequence.

[0042] In an embodiment, taking the vth stage sequence in any concentrated solution concentration data sequence as an example, the calculation formula of the influence coefficient importance degree of the vth stage sequence is:

[0043] Wherein, is the influence coefficient importance degree of the vth stage sequence; M is the number of sub-sequences contained in the vth stage sequence; is the dynamic lag influence coefficient of the mth sub-sequence contained in the vth stage sequence; is the variance of the concentrated solution concentration data in the vth stage sequence.

[0044] It should be noted that, is the dynamic lag influence coefficient mean, The greater, the greater the dynamic coefficient of the sub-sequence contained in the vth stage sequence, The greater, the greater the dynamic coefficient of the sub-sequence contained in the vth stage sequence, The greater, the greater the dynamic coefficient of the sub-sequence contained in the vth stage sequence, The greater, the greater the dynamic coefficient of the sub-sequence contained in the vth stage sequence, The greater, the greater the dynamic coefficient of the sub-sequence contained in the vth stage sequence, The greater, the greater the dynamic coefficient of the sub-sequence contained in the vth stage sequence.

[0045] Similarly, the importance of the influence coefficient of each stage sequence is obtained.

[0046] (2) Obtain the stage weight of each stage sequence.

[0047] Specifically, the importance of the influence coefficient of each stage sequence in the any concentrated liquid concentration data sequence is accumulated to obtain an influence coefficient importance accumulation value, and the ratio of the importance of the influence coefficient of each stage sequence in the any concentrated liquid concentration data sequence to the influence coefficient importance accumulation value is obtained to obtain the stage weight of each stage sequence.

[0048] In an embodiment, taking the vth stage sequence in any concentrated liquid concentration data sequence as an example, the calculation formula of the stage weight of the vth stage sequence is:

[0049] wherein, is the stage weight of the vth stage sequence; is the importance of the influence coefficient of the vth stage sequence; and V is the number of stage sequences in any concentrated liquid concentration data sequence.

[0050] It should be noted that the importance of the influence coefficient of the vth stage sequence The greater, the greater the dynamic coefficient of the sub-sequence contained in the vth stage sequence, The greater, the greater the dynamic coefficient of the sub-sequence contained in the vth stage sequence.

[0051] Similarly, the importance of the influence coefficient of each stage sequence is obtained.

[0052] (3) According to the stage weight of each stage sequence in the any concentrated liquid concentration data sequence, and the similarity between the any concentrated liquid concentration data sequence and its corresponding chicory acid yield data sequence, the stage influence weight of each stage sequence is obtained.

[0053] Specifically, for any stage sequence in the any concentrate concentration data sequence, a first-order difference data sequence of the any concentrate concentration data sequence is obtained to obtain a concentrate concentration difference sequence, a first-order difference data sequence of a chrysin yield data sequence corresponding to the any concentrate concentration data sequence is obtained to obtain a chrysin yield difference sequence, a similarity between the concentrate concentration difference sequence and the chrysin yield difference sequence is calculated by using a DTW algorithm, a product of a stage weight of the any stage sequence and the similarity is obtained to obtain a stage influence weight of the any stage sequence, wherein the DTW algorithm for obtaining the similarity is prior art and will not be described here.

[0054] In an embodiment, taking the vth stage sequence in the any concentrate concentration data sequence as an example, a calculation formula of the stage influence weight of the vth stage sequence is as follows:

[0055] wherein, is the stage influence weight of the vth stage sequence; is the stage weight of the vth stage sequence; is the similarity between the concentrate concentration difference sequence and the chrysin yield difference sequence.

[0056] wherein, The greater the value is, the more important the influence of the change of the concentrate concentration data in the vth stage sequence on the extraction result is, the greater the value is; The greater the value is, the more similar the concentrate concentration difference sequence and the chrysin yield difference sequence are, that is, the more similar the data changes of the any concentrate concentration data sequence and the chrysin yield data sequence corresponding thereto are, and the greater the influence of the change of the concentrate concentration on the change of the chrysin yield is, the greater the value is.

[0057] Similarly, the stage influence weight of each stage sequence in the any concentrate concentration data sequence is obtained.

[0058] According to the method for obtaining the stage influence weight of each stage sequence in the any concentrate concentration data sequence, the stage influence weight of each stage sequence in each concentrate concentration data sequence is obtained.

[0059] In step S104, a regression analysis model of the chrysin preparation in the manufacturing process is constructed according to the stage influence weight of each stage sequence in each concentrate concentration data sequence, which is used for detecting and adjusting the process parameters of the chrysin preparation in the manufacturing process.

[0060] After obtaining the stage influence weight of each stage sequence in each concentrated liquid concentration data sequence, the change of the yield of chicoric acid with different ethanol concentrations and concentrated liquid concentrations is analyzed according to the single factor influence mechanism. The solubility of chicoric acid in the ethanol-water system changes in an inverted U-shaped manner with the increase of the ethanol concentration: in the low concentration area (<40%), chicoric acid exists in the form of salt, and the solubility increases with the increase of the ethanol concentration (because the polarity of the solvent is enhanced); in the high concentration area (>60%), the polarity of the solvent decreases, the solubility of chicoric acid salt decreases, and the co-solvent impurities (such as polysaccharides and proteins) may wrap chicoric acid, further inhibiting the extraction efficiency. Then, the analysis result is obtained: the increase of the concentrated liquid concentration can significantly increase the viscosity of the solution, hinder the diffusion of chicoric acid from the raw material cells to the solvent, the viscosity is low in the low concentration area (1.0-1.2 g / mL), the diffusion resistance is small, the yield of chicoric acid increases with the increase of the concentration (because the total amount of solute is increased), and the viscosity increases sharply in the high concentration area (>1.3 g / mL), the diffusion rate decreases, and the increase of the yield of chicoric acid slows down or even decreases. Therefore, according to the ethanol concentration data of different concentrations, the concentrated liquid concentration data sequence under different ethanol concentrations, and the corresponding chicoric acid yield data sequence, and the stage influence weight of each stage sequence in each concentrated liquid concentration data sequence, an autoregressive distributed lag model is established.

[0061] According to the autoregressive lag model, the lag effect of the adjustment of the ethanol concentration and the concentrated liquid concentration under different conditions is obtained, and the adjustment is made according to the predicted yield of chicoric acid. For example, the autoregressive lag model predicts that when the ethanol concentration is 60%, the concentrated liquid concentration is 1.20 g / mL, and the extraction time is 90 min, the yield of chicoric acid can reach 1.03% (peak value). According to the model prediction, if the ethanol concentration is reduced from 60% to 55% after 60 min of extraction, the yield of chicoric acid will decrease by 5% after 30 min, and at this time, the predicted yield can be maintained by supplementing the ethanol concentration to 60%. Among them, according to the autoregressive lag model, the lag effect of the adjustment of the ethanol concentration and the concentrated liquid concentration under different conditions belongs to the prior art, and will not be repeated here.

[0062] In summary, the stage coefficient obtained by the embodiment of the present application is used to divide each concentrated liquid concentration data sequence into at least two stage sequences, that is, the ethanol reflux extraction process is divided into at least two stages according to the change of the concentrated liquid concentration, which can better capture the dynamic change characteristics of the stage of the concentrated liquid concentration data; then the stage influence weight of each stage sequence in each concentrated liquid concentration data sequence is obtained, which can combine the dynamic lag of the concentrated liquid concentration data, the stage change characteristics, and better analyze the influence of the change of the concentrated liquid concentration on the yield of chicoric acid in different stages of the ethanol reflux extraction process; finally, a regression analysis model of chicoric acid preparation in the manufacturing process is constructed, the dynamic change adaptability of the regression analysis to the change of the concentrated liquid concentration in the continuous production is improved, and the accuracy of the analysis result is improved.

[0063] The above examples are only used to illustrate the technical solutions of the present application, but not to limit the present application; although the present application has been described in detail with reference to the foregoing examples, those ordinarily skilled in the art should understand that the technical solutions recorded in the foregoing examples can be modified, or some technical features can be replaced equivalently; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A process detection method for the manufacturing process of chicory preparations, characterized in that, The process detection method for the manufacturing process of chicory preparations includes: In the manufacturing process of chicory formulations at at least two ethanol concentrations, the concentration of concentrate and the yield of chicoric acid are detected in real time according to a preset detection frequency, so as to obtain at least two concentrate concentration data sequences and their corresponding chicoric acid yield data sequences. Based on the data change characteristics in each concentrate concentration data sequence, obtain the stage coefficient of each concentrate concentration data in each concentrate concentration data sequence, and divide each concentrate concentration data sequence into at least two stage sequences based on the stage coefficient of each concentrate concentration data in each concentrate concentration data sequence. Each concentrated solution concentration data sequence is divided into at least two subsequences. Based on the data differences of the subsequences contained in each stage sequence of each concentrated solution concentration data sequence, the fluctuation characteristics of the concentrated solution concentration data in each stage sequence, and the similarity between each concentrated solution concentration data sequence and its corresponding chicoric acid yield data sequence, the stage influence weight of each stage sequence in each concentrated solution concentration data sequence is obtained. Based on the stage influence weight of each stage sequence in each concentrate concentration data sequence, a regression analysis model for chicory preparations in the manufacturing process is constructed to detect and adjust the process parameters of chicory preparations in the manufacturing process.

2. The process detection method for chicory preparation manufacturing according to claim 1, characterized in that, The step of obtaining the stage coefficient of each concentrate concentration data in each concentrate concentration data sequence based on the data change characteristics in each concentrate concentration data sequence includes: The formula for calculating the stage coefficient of the b-th concentrate concentration data in any concentrate concentration data sequence is as follows: ； in, The stage coefficient for the b-th concentrate concentration data; For the first The stage coefficient of the concentrate concentration data; This represents the number of concentrate concentration data points preceding the b-th concentrate concentration data point. This is the first preset quantity; This represents the difference between the concentration data of the b-th concentrate and its left adjacent concentrate concentration data. The concentration difference between the b-th concentrate data and its right adjacent concentrate data; N is the second preset quantity; Let be the variance of the data sequence consisting of the b-th concentrate concentration data and the previous n concentrate concentration data; Let be the variance of the data sequence consisting of the b-th concentrate concentration data and the preceding n-1 concentrate concentration data. This represents the number of concentrate concentration data points following the b-th concentrate concentration data point. This is the third preset quantity; The stage coefficient for the left adjacent concentrate concentration data of the last concentrate concentration data; It is the absolute value symbol; This is the normalization function.

3. The process detection method for chicory preparation manufacturing according to claim 1, characterized in that, The step of dividing each concentrate concentration data sequence into at least two stage sequences based on the stage coefficient of each concentrate concentration data in each concentrate concentration data sequence includes: A set of stage coefficients is formed by combining the stage coefficients of each concentrate concentration data in all concentrate data sequences. The peak values ​​in the set of stage coefficients are obtained. The peak values ​​are removed from the set of stage coefficients to obtain a first set of stage coefficients. The average value of the stage coefficients in the first set of stage coefficients is obtained. Stage coefficients that are greater than the average value of the stage coefficients are removed from the first set of stage coefficients to obtain a second set of stage coefficients. The peak values ​​in the second set of stage coefficients are obtained, and the corresponding average value of the peak values ​​is obtained. For any concentrate concentration data sequence, the peak average value is used to divide the concentrate concentration data sequence into at least two stage sequences.

4. The process detection method for chicory preparation manufacturing according to claim 1, characterized in that, The step-by-step influence weight of each stage sequence in each concentrated solution concentration data sequence is obtained based on the data differences of subsequences contained in each stage sequence in each concentrated solution concentration data sequence, the fluctuation characteristics of concentrated solution concentration data in each stage sequence, and the similarity between each concentrated solution concentration data sequence and its corresponding chicoric acid yield data sequence, including: For any concentrate concentration data sequence, the dynamic hysteresis coefficient of each subsequence is obtained based on the data differences of the concentrate concentration data in each subsequence of the any concentrate concentration data sequence. Based on the dynamic lag influence coefficient of the subsequences contained in each stage sequence of any concentrate concentration data sequence, and the fluctuation characteristics of the concentrate concentration data in each stage sequence, the importance of the influence coefficient of each stage sequence is obtained. The importance of the influence coefficients of each stage sequence in any concentrate concentration data sequence is accumulated to obtain the accumulated value of the importance of the influence coefficients. The ratio of the importance of the influence coefficients of each stage sequence in any concentrate concentration data sequence to the accumulated value of the importance of the influence coefficients is obtained to obtain the stage weight of each stage sequence. Based on the stage weight of each stage sequence in any given concentrate concentration data sequence, and the similarity between any given concentrate concentration data sequence and its corresponding chicoric acid yield data sequence, the stage influence weight of each stage sequence is obtained.

5. The process detection method for chicory preparation manufacturing according to claim 4, characterized in that, The step of obtaining the dynamic hysteresis coefficient of each subsequence based on the data differences of the concentrate concentration data in each subsequence of any concentrate concentration data sequence includes: For any subsequence, based on the concentrate concentration data excluding the last concentrate concentration data in the subsequence, the ARIMA algorithm is used to obtain the predicted value of the last concentrate concentration data in the subsequence. The absolute value of the difference between the last concentrate concentration data and the predicted value in the subsequence is obtained to obtain the predicted difference value. The predicted difference value is normalized to obtain the dynamic lag influence coefficient of the subsequence.

6. The process detection method for chicory preparation manufacturing according to claim 4, characterized in that, The step of obtaining the importance of the influence coefficient of each stage sequence based on the dynamic lag influence coefficient of the subsequences contained in each stage sequence of any concentrate concentration data sequence, and the fluctuation characteristics of the concentrate concentration data in each stage sequence, includes: For any stage sequence in any concentrated solution concentration data sequence, the average value of the dynamic lag influence coefficient of the subsequences contained in any stage sequence is obtained and denoted as the mean dynamic lag influence coefficient. The stability is obtained by taking the reciprocal of the sum of the variance of the sequence at any stage and the constant 1, and the fluctuation is obtained by taking the difference between the constant 1 and the stability. The importance of the influence coefficient of any stage sequence is obtained by multiplying the mean of the dynamic lag influence coefficient by the degree of fluctuation.

7. The process detection method for chicory preparation manufacturing according to claim 4, characterized in that, The step of obtaining the stage influence weight of each stage sequence based on the stage weight of each stage sequence in any concentrate concentration data sequence and the similarity between any concentrate concentration data sequence and its corresponding chicoric acid yield data sequence includes: For any stage sequence in any concentrate concentration data sequence, obtain the first-order difference data sequence of the concentrate concentration data sequence to obtain the concentrate concentration difference sequence. Obtain the first-order difference data sequence of the chicoric acid yield data sequence corresponding to the concentrate concentration data sequence to obtain the chicoric acid yield difference sequence. Calculate the similarity between the concentrate concentration difference sequence and the chicoric acid yield difference sequence using the DTW algorithm. Obtain the product of the stage weight of any stage sequence and the similarity to obtain the stage influence weight of any stage sequence.

Images