Intelligent detection system and method for traditional Chinese medicine purification components

Abstract

The invention relates to the technical field of intelligent detection, in particular to an intelligent detection system and method for traditional Chinese medicine purification components, and the system comprises a component extraction module, a concentration distribution correction module, a dynamic matching optimization module, a fluctuation suppression control module and an execution path adaptation module. According to the invention, through intelligent analysis and optimization of concentration distribution, temperature and pressure factors in a traditional Chinese medicine purification process, accurate control of target component concentration and impurity distribution is realized, concentration gradient data is extracted, a related model is established, change of component extraction and concentration distribution is effectively corrected, accurate separation of target components and impurities is ensured, and the purity of the traditional Chinese medicine is improved. Aiming at the fluctuation influence, the fluctuation influence in the purification process is reduced and the purification efficiency and stability are improved through dynamic optimization and adjustment of the distribution sequence and the fluctuation suppression strategy, so that the purification quality of the target component is continuously optimized, and accurate component control and high-quality purification results in the traditional Chinese medicine purification process are ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent detection, in particular to a traditional Chinese medicine purification component intelligent detection system and method. BACKGROUND

[0002] The technical field of intelligent detection refers to a technical system that realizes intelligent and automated detection of various product or substance components by combining sensors, detection devices, and data analysis methods. The core tasks of this technical field include obtaining the physical properties and chemical components of the detection object, automatically collecting and analyzing detection data, and real-time controlling and feeding back the detection process. It is widely used in fields such as food safety, drug quality, and environmental monitoring, aiming to improve detection efficiency and the accuracy of detection data, reduce human intervention and operational errors, and promote the intelligent development of detection methods. Among them, the traditional Chinese medicine purification component intelligent detection system refers to the detection of effective component content and impurity content involved in the traditional Chinese medicine purification process. It is usually completed by manual sampling combined with laboratory detection methods such as high-performance liquid chromatography, gas chromatography, and mass spectrometry. This method generally uses traditional Chinese medicine samples taken from different stages of the purification process to perform qualitative and quantitative analysis of components using the above instruments, and evaluates the purification effect and product quality based on the analysis results.

[0003] The existing technology uses manual sampling and traditional laboratory detection methods, which rely on manual operation and sample stage selection, making it difficult to monitor and adjust various parameters in the purification process in real time. This results in unstable control of component concentration and impurities, low purification efficiency, and the inability of traditional methods to consider the comprehensive influence of factors such as temperature and pressure during component extraction. There is a lack of effective correction means for concentration changes and error accumulation, leading to large fluctuations and errors in the purification process. Traditional technology relies on manual judgment for impurity control and separation, lacks an automated fluctuation control mechanism, and is difficult to ensure precise and efficient purification results throughout the entire process, thereby affecting the stability and consistency of traditional Chinese medicine purification quality. SUMMARY

[0004] To solve the technical problems existing in the prior art, the present application provides a traditional Chinese medicine purification component intelligent detection system and method. The technical solution is as follows: On the one hand, a traditional Chinese medicine purification component intelligent detection system is provided, which includes: The component extraction module extracts target component concentration parameters according to the concentration gradient distribution curve of the target component in the traditional Chinese medicine purification process, analyzes the influence of temperature and pressure on component extraction efficiency, organizes the component extraction and concentration distribution relationship model, and obtains the component extraction adaptation table. The concentration distribution correction module extracts the real-time concentration value and target concentration deviation based on the component extraction adaptation table, identifies the concentration change rate and response time, quantifies the concentration error accumulation effect, induces the concentration correction weight, and obtains a concentration distribution correction dataset; The dynamic matching optimization module extracts the impurity distribution frequency and peak node based on the concentration distribution correction dataset, performs hierarchical weighted analysis combined with the pressure fluctuation characteristics and concentration change law in the purification process, and obtains an impurity distribution matching table. The fluctuation suppression control module sorts the fluctuation distribution relationship between the purification and the target component according to the impurity priority and concentration demand ratio, adjusts and allocates the order through the fluctuation node characteristics, and constructs a reference fluctuation suppression scheme.

[0005] As a further scheme of the present application, the component extraction adaptation table includes a concentration gradient interval, an extraction efficiency range, a temperature and pressure compensation factor, and a concentration coupling factor. The concentration distribution correction dataset includes a concentration error factor, a response delay index, a change rate weight, and a correction coefficient. The impurity distribution matching table includes a graded impurity interval, a demand priority level, a fluctuation threshold, and a matching weight. The reference fluctuation suppression scheme includes a fluctuation distribution structure, a node adjustment order, a fluctuation correction factor, and a concentration allocation factor.

[0006] As a further scheme of the present application, the component extraction module includes: The concentration parameter extraction submodule extracts the target component concentration parameters according to the concentration gradient distribution curve of the target component in the traditional Chinese medicine purification process, classifies the temperature and pressure influence factors, and generates a concentration gradient distribution table. The extraction efficiency analysis submodule analyzes the influence of temperature and pressure on the extraction efficiency of the component based on the concentration gradient distribution table, calculates the extraction efficiency adaptation value under different working conditions, and generates a component extraction and concentration distribution relationship model. The adaptation table generation submodule sorts the component extraction parameters based on the component extraction and concentration distribution relationship model, analyzes the corresponding relationship with the target component concentration value, and generates a component extraction adaptation table.

[0007] As a further scheme of the present application, the extraction efficiency adaptation value under different working conditions uses the formula: ; Wherein, represents the extraction efficiency adaptation value under different working conditions, represents the pressure under the i-th working condition, represents the reference pressure value, represents the temperature under the i-th working condition, represents the reference temperature value, is the pressure influence index on efficiency, is the index of temperature's influence on efficiency, and n is the total number of operating conditions.

[0008] As a further solution of the present invention, the concentration distribution correction module includes: The concentration deviation extraction submodule extracts the deviation between the real-time concentration value and the target concentration based on the component extraction adaptation table, records the concentration change rate and response time data, and generates a concentration deviation data table; The error accumulation quantification submodule quantifies the concentration error accumulation effect based on the concentration deviation data table, analyzes the difference between the concentration distribution and the demand ratio, and generates a concentration error accumulation effect table; The correction weight summarization submodule extracts the concentration deviation magnitude and correction frequency based on the concentration error cumulative effect table, filters the high-frequency error segments and marks the deviation direction, summarizes the concentration correction weights, and generates a concentration distribution correction data set.

[0009] As a further solution of the present invention, the dynamic matching optimization module includes: The impurity distribution extraction submodule extracts the impurity distribution frequency and peak nodes based on the concentration distribution correction data set, classifies the impurity distribution priority data, and generates an impurity distribution frequency table; The pressure fluctuation analysis submodule calculates the pressure node fluctuation state value based on the impurity distribution frequency table and combines the pressure fluctuation characteristics and concentration change rules during the purification process to generate a pressure fluctuation state table; The hierarchical weighted analysis submodule performs a multi-dimensional comparison between the impurity distribution and the pressure fluctuation based on the pressure fluctuation state table, screens the impurity distribution adaptation relationship, and generates an impurity distribution matching table.

[0010] As a further solution of the present invention, the fluctuation suppression control module includes: The priority sorting submodule extracts the impurity peak position and concentration difference threshold based on the impurity distribution matching table, analyzes the impurity contribution under unit concentration difference, and generates an impurity priority sorting table; The fluctuation distribution identification submodule extracts the fluctuation change trajectory of the main channel node based on the impurity priority ranking table, identifies the fluctuation balance point and offset direction, and generates a fluctuation distribution relationship table; The fluctuation adjustment submodule is based on the fluctuation distribution relationship table, adjusts the allocation order according to the fluctuation node characteristics, extracts the node fluctuation change frequency and amplitude sequence, counts the offset amplitude and duration of the fluctuation exceeding the limit node, divides the stable interval and the fluctuation transition section, and generates a benchmark fluctuation suppression plan.

[0011] As a further solution of the present invention, the system further includes an execution path adaptation module: The execution path adaptation module monitors the purification pressure state and target component concentration execution based on the reference fluctuation suppression scheme, compares the unsatisfied concentration requirement and the remaining capacity in real time, fills in the fluctuation gap by adjusting the concentration distribution and impurity separation matching order, and generates a purification process global optimization execution scheme; The purification process global optimization execution scheme includes residual adjustment parameters, execution order configuration, remaining capacity utilization rate, and adjustment completion criterion.

[0012] As a further scheme of the present application, the execution path adaptation module includes: The state monitoring submodule collects pressure node values and target component concentration feedback based on the reference fluctuation suppression scheme, records the jump time and deviation amplitude, and generates a state monitoring data table; The demand comparison submodule extracts the corresponding time point of the unsatisfied concentration based on the state monitoring data table, identifies the remaining capacity and instantaneous gap, matches the target gap and capacity segment, and generates a demand comparison result table; The dynamic adjustment submodule fills in the fluctuation gap by adjusting the concentration distribution and impurity separation matching order based on the demand comparison result table, identifies the capacity gap node and response lag segment, updates the concentration output timing and impurity separation curve, and generates a purification process global optimization execution scheme.

[0013] On the other hand, an intelligent detection method for Chinese medicine purification components is based on the above-mentioned intelligent detection system for Chinese medicine purification components, which includes the following steps: S1: According to the concentration gradient distribution curve of the target component in the Chinese medicine purification process, extract the target component concentration parameter and purification target value, normalize the temperature and pressure influence factor, match the component extraction and target concentration relationship, and generate a component extraction adaptation table; S2: Based on the component extraction adaptation table, extract the target and real-time concentration deviation value, calculate the offset amplitude and response duration, select the concentration change rate and response time data, and generate a concentration distribution correction data set; S3: Based on the concentration distribution correction data set, extract the impurity distribution frequency and peak node in unit time, associate the concentration response value to identify abnormal transition points and stable recovery points, extract the echo time and jump boundary in the fluctuation interval, and generate an impurity distribution matching table; S4: Based on the impurity distribution matching table, analyze the high-frequency impurity priority section and fluctuation peak position, identify the step change node and reconstruct the main channel and compensation path, and construct a reference fluctuation suppression scheme; S5: Based on the reference fluctuation suppression scheme, screen the unsatisfied concentration requirement parameters and key node fluctuation state values, extract the offset frequency peak and correct the concentration adjustment logic, and generate a purification process global optimization execution scheme.

[0014] The technical scheme provided by the embodiment of the present application has at least the following beneficial effects: By intelligently analyzing and optimizing factors such as concentration distribution, temperature, and pressure in the purification process of traditional Chinese medicine, the precise control and adjustment of the concentration of target components and the distribution of impurities can be realized. During the execution process, by extracting the concentration gradient data of target components and establishing a related model, combined with real-time concentration deviation and error accumulation analysis, the changes in component extraction and concentration distribution are effectively corrected, ensuring the separation precision of target components and impurities. In view of the influence of fluctuations, dynamic optimization is implemented, and by adjusting the distribution sequence and fluctuation suppression strategy, the influence of fluctuations in the purification process is effectively reduced, improving the purification efficiency and stability, thereby realizing the continuous optimization of the purification quality of target components, and ensuring the precise control of components and high-quality purification results in the purification process of traditional Chinese medicine. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical scheme in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0016] Figure 1 is a schematic diagram of a traditional Chinese medicine purification component intelligent detection system provided by the embodiment of the present application; Figure 2 is a system framework schematic diagram of the present application; Figure 3 is a component extraction module flowchart in the present application; Figure 4 is a concentration distribution correction module flowchart in the present application; Figure 5 is a dynamic matching optimization module flowchart in the present application; Figure 6 is a fluctuation suppression control module flowchart in the present application; Figure 7 is an execution path adaptation module flowchart in the present application; Figure 8 is a flowchart of a traditional Chinese medicine purification component intelligent detection method provided by the embodiment of the present application. DETAILED DESCRIPTION

[0017] The technical scheme in the present application will be described below in conjunction with the drawings.

[0018] In the embodiments of the present application, the words such as "exemplary", "for example", etc. are used to represent an example, illustration, or description. Any embodiment or design scheme described as "exemplary" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the word "exemplary" is intended to present the concept in a specific manner. In addition, in the embodiments of the present application, the meaning expressed by "and / or" can be both, or can be one of the two.

[0019] In the embodiments of the present application, "image" and "picture" can be used interchangeably at times, and it should be pointed out that the meanings expressed are consistent when the distinction is not emphasized. "Of", "corresponding" and "relevant" can be used interchangeably at times, and it should be pointed out that the meanings expressed are consistent when the distinction is not emphasized.

[0020] In the embodiments of the present application, sometimes the subscript such as W1 can be written in the form of non-subscript such as W1, and the meanings expressed are consistent when the distinction is not emphasized.

[0021] In order to make the technical problems, technical schemes and advantages to be solved by the present application more clear, the following will be described in detail in conjunction with the drawings and specific embodiments.

[0022] The embodiments of the present application provide a traditional Chinese medicine purification component intelligent detection system, as shown in a traditional Chinese medicine purification component intelligent detection system schematic diagram, the system comprises: Figures 1-2 A component extraction module extracts target component concentration parameters according to the concentration gradient distribution curve of the target component in the traditional Chinese medicine purification process, analyzes the influence of temperature and pressure on component extraction efficiency, sorts the component extraction and concentration distribution relationship model, and obtains a component extraction adaptation table. A concentration distribution correction module extracts real-time concentration value and target concentration deviation based on the component extraction adaptation table, identifies concentration change rate and response time, quantifies concentration error accumulation effect, induces concentration correction weight, and obtains a concentration distribution correction data set. A dynamic matching optimization module extracts impurity distribution frequency and peak node based on the concentration distribution correction data set, performs hierarchical weighted analysis combined with pressure fluctuation characteristics and concentration change law in the purification process, and obtains an impurity distribution matching table. A fluctuation suppression control module sorts the fluctuation distribution relationship between purification and target components according to impurity priority and concentration demand ratio based on the impurity distribution matching table, identifies fluctuation distribution relationship between purification and target components, adjusts distribution order through fluctuation node characteristics, and constructs a reference fluctuation suppression scheme. A fluctuation suppression control module sorts the fluctuation distribution relationship between purification and target components according to impurity priority and concentration demand ratio based on the impurity distribution matching table, identifies fluctuation distribution relationship between purification and target components, adjusts distribution order through fluctuation node characteristics, and constructs a reference fluctuation suppression scheme. The execution path adaptation module monitors the execution of the target component concentration and the purification pressure state based on the benchmark fluctuation suppression scheme, compares the unsatisfied concentration requirement and the remaining capacity in real time, fills in the fluctuation gap by adjusting the concentration distribution and the impurity separation matching order, and generates a global optimization execution scheme for the purification process.

[0023] The component extraction adaptation table includes a concentration gradient interval, an extraction efficiency range, a temperature and pressure compensation factor, and a concentration coupling factor. The concentration distribution correction data set includes a concentration error factor, a response delay indicator, a change rate weight, and a correction coefficient. The impurity distribution matching table includes a graded impurity interval, a demand priority level, a fluctuation threshold, and a matching weight. The benchmark fluctuation suppression scheme includes a fluctuation distribution structure, a node adjustment order, a fluctuation correction factor, and a concentration distribution factor. The global optimization execution scheme for the purification process includes a residual adjustment parameter, an execution order configuration, a remaining capacity utilization rate, and an adjustment completion criterion.

[0024] Specifically, as shown in Figure 2 , 3 The component extraction module includes: The concentration parameter extraction submodule extracts the concentration parameters of the target component according to the concentration gradient distribution curve of the target component in the traditional Chinese medicine purification process, classifies the temperature and pressure influence factors, and generates a concentration gradient distribution table. According to the concentration gradient distribution curve of the target component in the traditional Chinese medicine purification process, a series of pre-set temperature and pressure conditions are collected and analyzed to obtain the concentration value of the target component under different purification conditions. For example, the extraction process of chlorogenic acid in honeysuckle is monitored. When the temperature is set to 70℃ and the pressure is set to 0.1MPa, the concentration of chlorogenic acid is 1.2mg / mL. When the temperature is set to 80℃ and the pressure is set to 0.15MPa, the concentration of chlorogenic acid is 1.5mg / mL. When the temperature is set to 90℃ and the pressure is set to 0.2MPa, the concentration of chlorogenic acid is 1.8mg / mL. The data is used to construct a concentration gradient distribution curve. Then, the temperature and pressure parameters that affect the concentration change are identified, and the temperature value and pressure value are classified as influence factors, respectively. For example, 70℃, 80℃, 90℃, etc. temperature values are classified as a set of temperature influence factors, and 0.1MPa, 0.15MPa, 0.2MPa, etc. pressure values are classified as a set of pressure influence factors. Finally, the classified temperature and pressure influence factors are associated with the corresponding target component concentration values, and the concentration gradient distribution table is formed. The table records the concentration distribution of the target component under different temperature and pressure combinations in detail, such as the fields of “temperature (℃)”, “pressure (MPa)”, and “chlorogenic acid concentration (mg / mL)”. Each row represents a specific working condition and its corresponding concentration data.

[0025] The extraction efficiency analysis submodule analyzes the effects of temperature and pressure on component extraction efficiency based on the concentration gradient distribution table, calculates the extraction efficiency adaptation value under different chemical conditions, and generates a relationship model between component extraction and concentration distribution; The extraction efficiency adaptation value under different chemical conditions is calculated using the formula: ; in, Represents the extraction efficiency adaptation value under different chemical conditions, represents the pressure under the i-th working condition, Represents the reference pressure value, represents the temperature under the i-th working condition, represents the reference temperature value, is the impact index of pressure on efficiency, is the influence index of temperature on efficiency, n is the total number of working conditions; Based on the concentration gradient distribution table, the target component concentration data under different temperature and pressure conditions in the table are deeply analyzed to calculate the extraction efficiency under each condition. For example, at the reference temperature Set to 80℃, reference pressure When set to 0.15MPa, for the Working conditions, its pressure With reference pressure The absolute difference between the two indicates the degree to which the pressure in the current working condition deviates from the reference pressure. For example, when the pressure in the first working condition is When it is 0.1MPa, the absolute difference between it and the reference pressure of 0.15MPa is MPa, indicating that the pressure deviates from 0.05MPa, then the current working temperature With reference temperature The ratio of is used as the weight factor of the effect of temperature on the extraction efficiency. For example, when the temperature of the first working condition is When the temperature is 70℃, its ratio to the reference temperature of 80℃ is , which represents the proportional relationship between the current temperature and the reference temperature. Then, the pressure difference calculated above is The power of the temperature ratio The influence coefficient of temperature and pressure under the working condition is obtained by multiplying the power, among which the influence index of pressure on efficiency is Set to 2, indicating that the effect of pressure on extraction efficiency is nonlinear, and the effect of temperature on efficiency is exponential. It is set to 1.5, indicating that the effect of temperature on extraction efficiency is also nonlinear. The index is determined by regression analysis based on a large amount of experimental data. For example, by statistically analyzing the extraction experimental data of various Chinese herbal medicine components, when and When , it can best fit the variation trend of the actual extraction efficiency. This result shows that the extraction efficiency adaptation value The calculation method aims to quantify the comprehensive effect of temperature and pressure on extraction efficiency under different working conditions, and by introducing reference values ​​and indices, the evaluation results can better reflect the actual extraction process. The influence coefficients of each working condition are summed up. For example, for the total number of working conditions In the case of , add the influence coefficients of the three working conditions and finally divide the sum by the total number of working conditions , and obtain the extraction efficiency adaptation value under different chemical conditions , for example, when When the influence coefficients of the three working conditions are calculated, the sum of them is divided by 3 to obtain the final extraction efficiency adaptation value. The calculation results are used to generate a component extraction and concentration distribution relationship model. This model describes the quantitative relationship between the extraction efficiency and the concentration of the target component under different temperature and pressure conditions. It can be used to predict and optimize the extraction efficiency in the purification process of traditional Chinese medicine. The following table lists the sample data used to calculate the extraction efficiency adaptation value: Table 1: Parameters for calculating extraction efficiency under different working conditions As shown in Table 1, the table shows the pressure and temperature data under three different working conditions. These data will be substituted into the formula for calculation to obtain the extraction efficiency adaptation value; The parameters in the formula are explained as follows: : represents the extraction efficiency adaptation value under different working conditions and is the comprehensive efficiency measurement index obtained by the final calculation; :Represents The pressure under working conditions, in megapascals (MPa), represents the pressure value measured under the current specific operating conditions; : represents the reference pressure value, the unit is megapascal (MPa), which is a preset benchmark point used for comparison and quantification of pressure; :Represents The temperature under operating conditions is in degrees Celsius (°C), which indicates the temperature value measured under the current specific operating conditions; : represents the reference temperature value, in degrees Celsius (℃), which is a preset benchmark point for comparing and quantifying temperatures; : is the pressure effect index on efficiency, which is a dimensionless index determined by fitting experimental data, reflecting the nonlinear degree of the effect of pressure change on extraction efficiency. ; : is the temperature effect index on efficiency, which is a dimensionless index determined by fitting experimental data, reflecting the nonlinear degree of the effect of temperature change on extraction efficiency. ; : Total number of conditions, representing the total number of different conditions involved in the calculation; By introducing reference values for pressure and temperature, as well as respective influence indices and , the comprehensive influence of pressure and temperature on extraction efficiency under different conditions can be quantified. In actual traditional Chinese medicine purification processes, small fluctuations in temperature and pressure can have a significant impact on the final extraction efficiency. This formula processes the square of pressure deviation and the power of temperature ratio, making the calculation results more accurately reflect these nonlinear influences, thereby improving the accuracy of extraction efficiency evaluation and practical guiding significance; Assuming the reference pressure is 0.15 MPa, the reference temperature is 80℃, the pressure influence index on efficiency is set to 2, the temperature influence index on efficiency is set to 1.5, and the total number of conditions is 3, the data in Table 1 is substituted into the formula for calculation: for condition 1: MPa, ℃; ; ; ; For condition 2: MPa, ℃; ; ; ; For condition 3: MPa, ℃; ; ; ; Total: ; The final calculated extraction efficiency adaptation value : ; The results show that the extraction efficiency fitting value is 0.00168 under the three working conditions evaluated, which reflects the comprehensive extraction efficiency under the current temperature and pressure conditions. The higher the value, the closer the extraction efficiency of the target component under these working conditions to the ideal state. This result is a key input for building the component extraction and concentration distribution relationship model. By correlating this fitting value with other experimental data, the model can be further improved to more accurately predict the extraction efficiency under different working conditions, and ultimately used to generate the component extraction and concentration distribution relationship model.

[0026] The fitting table generation submodule collates the component extraction parameters based on the component extraction and concentration distribution relationship model, and analyzes the corresponding relationship with the target component concentration value to generate a component extraction fitting table. Based on the component extraction and concentration distribution relationship model, key component extraction parameters are extracted from the model, such as temperature, pressure, extraction time, and solvent ratio. The parameters are experimental conditions input during model construction. Then, the internal corresponding relationship between the extraction parameters and the target component concentration value is analyzed, such as determining that the target component concentration increases by 0.05 mg / mL on average for every 1℃ increase in temperature, or the concentration increases by 0.02 mg / mL on average for every 0.01 MPa increase in pressure, and determining that the target component concentration can reach the best under a specific extraction time range and solvent ratio. Then, the analysis results are organized into structured data, such as forming a table containing "extraction parameter combination", "predicted concentration value" and "actual concentration value deviation" fields. Finally, the component extraction fitting table is generated, which lists the expected concentration value of the target component under different extraction parameter combinations and the possible deviation in the actual extraction process. This table provides an important reference for subsequent concentration distribution correction.

[0027] Specifically, as shown in Figure 2 , 4 The concentration distribution correction module includes: The concentration deviation extraction submodule extracts the real-time concentration value and the target concentration deviation based on the component extraction fitting table, records the concentration change rate and response time data, and generates a concentration deviation data table. Based on the component extraction adaptation table, the actual concentration value of the target component in the traditional Chinese medicine purification process is monitored in real time, for example, the concentration data of chlorogenic acid in the purified liquid is collected every 10 seconds by an online spectrum analyzer, and compared with the target concentration value under the corresponding working condition in the adaptation table, for example, when the adaptation table shows that the target concentration is 1.5 mg / mL and the real-time monitoring concentration is 1.4 mg / mL, the deviation between the two is calculated, the deviation value is 1.5 mg / mL-1.4 mg / mL=0.1 mg / mL, at the same time, the system records the rate of change of the concentration with time, for example, if the concentration changes from 1.4 mg / mL to 1.35 mg / mL in the next 10-second period, the concentration change rate is (1.35-1.4) / 10=-0.005 mg / mL / s, and the system response time is recorded, for example, the time interval from detecting the concentration deviation to the system starting to adjust is 5 seconds, finally, the real-time concentration deviation, concentration change rate and response time data are integrated to generate a concentration deviation data table.

[0028] The error accumulation quantification sub-module quantifies the concentration error accumulation effect based on the concentration deviation data table, analyzes the difference between the concentration distribution and the demand ratio, and generates a concentration error accumulation effect table; Based on the concentration deviation data table, the concentration deviation data recorded in the table is accumulated and quantified, for example, for the continuous negative deviation (actual concentration is lower than target concentration), the deviation value is accumulated, for example, in the next 5 monitoring periods, the deviation is 0.1 mg / mL, 0.08 mg / mL, 0.12 mg / mL, 0.09 mg / mL, 0.11 mg / mL, the cumulative error is 0.1+0.08+0.12+0.09+0.11=0.5 mg / mL, then, analyze the difference between the current concentration distribution and the preset demand ratio, for example, when the purity demand of the target component is 95%, and the current real-time purity is only 92%, a 3% purity deviation is identified, and the deviation is associated with the concentration error accumulation, for example, for every 0.1 mg / mL of concentration error accumulation, the purity deviation increases by 0.5%, the cumulative error and the demand ratio difference data are integrated to generate a concentration error accumulation effect table, which contains fields such as "time period", "cumulative concentration error (mg / mL)", "purity demand deviation (%)", etc. The table reveals the law of concentration error accumulation over time and the impact of such accumulation on the purity demand of the final product, providing a quantitative basis for subsequent correction weight induction.

[0029] The correction weight induction sub-module extracts the concentration deviation magnitude and correction frequency based on the concentration error accumulation effect table, filters high-frequency error sections and labels the deviation direction, induces the concentration correction weight, and generates a concentration distribution correction data set; Based on the concentration error accumulation effect table, the magnitude of the concentration deviation recorded in the table is extracted, for example, a deviation less than 0.05 mg / mL is defined as a "low deviation magnitude", a deviation of 0.05 mg / mL to 0.1 mg / mL is defined as a "medium deviation magnitude", and a deviation greater than 0.1 mg / mL is defined as a "high deviation magnitude", and the correction frequency is recorded, for example, a certain high deviation magnitude occurs 10 times in the past one hour, then the high frequency error section is screened out, for example, it is identified that the high deviation magnitude occurs much more frequently in a certain time period of the purification process (for example, 10 minutes to 20 minutes after the start of purification) than in other time periods, for example, the frequency of high deviation magnitude in this time period is 20 times / hour, while the time period is 5 times / hour, and the deviation direction is marked, for example, it is pointed out that the high frequency error section is mainly characterized by low or high concentration deviation, for example, 80% of the deviation in this section is characterized by low concentration deviation, then the concentration correction weight is summarized according to the deviation magnitude, correction frequency and deviation direction, for example, a high correction weight is given to a high deviation magnitude section of low concentration deviation that occurs frequently, for example, set to 0.8, and a low correction weight is given to a low deviation magnitude section of high concentration deviation that occurs infrequently, for example, set to 0.2, the weight is set according to historical data and expert experience, aiming to guide the subsequent correction operation, and a concentration distribution correction data set is generated.

[0030] Specifically, as shown in Figure 2 、 5 The dynamic matching optimization module includes: The impurity distribution extraction sub-module extracts the impurity distribution frequency and peak node based on the concentration distribution correction data set, classifies the impurity distribution priority data, and generates an impurity distribution frequency table; Based on the concentration distribution correction data set, the frequency information related to the impurity distribution in the correction data set is extracted, for example, from the data set, the types of impurities that appear together and their frequencies are identified under a certain concentration deviation magnitude, for example, when the concentration of chlorogenic acid is low by 0.1 mg / mL, the frequency of impurity A is 10 times / hour, and the frequency of impurity B is 5 times / hour, and the peak node of the impurity is extracted, for example, it is identified that the concentration of impurity A reaches a peak at a certain time point (for example, 30 minutes after the start of purification) in the purification process, and the peak value is 0.02 mg / mL, then according to the influence degree of the impurity on the purity of the target component and its frequency, the impurity distribution is prioritized, for example, the impurity (for example, impurity A) with the highest influence on the purity of the target component and the highest frequency is classified as "high priority impurity", and the impurity (for example, impurity C) with lower influence and lower frequency is classified as "low priority impurity", finally, an impurity distribution frequency table is generated, which records in detail the frequency of different impurities, the peak position and its priority, providing important input data for subsequent pressure fluctuation analysis.

[0031] The pressure fluctuation analysis submodule calculates the pressure node fluctuation state value based on the impurity distribution frequency table, combines the pressure fluctuation characteristics and concentration change law in the purification process, and generates a pressure fluctuation state table; Based on the impurity distribution frequency table, combined with the real-time fluctuation characteristics of pressure in the traditional Chinese medicine purification process, for example, monitoring the data of the internal pressure sensor of the purification kettle, recording the real-time fluctuation of the pressure between 0.1 MPa and 0.2 MPa, for example, the pressure fluctuates ± 0.02 MPa around 0.15 MPa, and combined with the concentration change law of the target component, for example, when the pressure suddenly rises, the concentration of the target component may instantaneously decrease, by analyzing the correlation between the data, the pressure node fluctuation state value is calculated, for example, when the pressure jumps from 0.15 MPa to 0.17 MPa instantaneously, according to the distribution characteristics of the corresponding high-priority impurity in the impurity distribution frequency table, the influence of the pressure jump on the separation effect of the impurity is calculated, and quantified as a fluctuation state value, for example, the pressure rise of 0.02 MPa causes the separation efficiency of impurity A to decrease by 5%, and the corresponding fluctuation state value is -0.05, finally, a pressure fluctuation state table is generated, which contains fields such as "time stamp", "real-time pressure (MPa)", "pressure fluctuation amplitude (MPa)", "associated impurity priority", "impurity separation influence (%)" and "pressure node fluctuation state value", etc., providing quantitative pressure fluctuation data for layered weighted analysis.

[0032] The layered weighted analysis submodule performs multi-dimensional comparison of impurity distribution and pressure fluctuation based on the pressure fluctuation state table, selects the impurity distribution adaptation relationship, and generates an impurity distribution matching table; Based on the pressure fluctuation state table, the impurity distribution recorded in the table is compared with the pressure fluctuation data in multiple dimensions, for example, the peak occurrence time of high priority impurities is cross compared with the time period with large pressure fluctuation, to identify whether there is synchronicity or lag correlation between the two, for example, it is found that the peak of impurity A always appears within 5 seconds after the sharp pressure drop, then according to the comparison result, the impurity distribution with significant adaptive relationship is screened out, for example, if the concentration of impurity B changes significantly when the pressure fluctuation amplitude exceeds 0.03 MPa (for example, the concentration of impurity B increases by 0.005 mg / mL for every 0.01 MPa increase in pressure), it is considered that impurity B has an adaptive relationship with pressure fluctuation, the adaptive relationship screened out is analyzed by layering and weighting, for example, according to the influence degree of impurities on the purity of the final product and the correlation strength with pressure fluctuation, different weights are given, for example, impurity A has high correlation strength with pressure fluctuation and has great influence on purity, then it is given a weight of 0.9, impurity C has low correlation strength and small influence, then it is given a weight of 0.3, an impurity distribution matching table is generated, which lists the matching relationship between different impurity types and pressure fluctuation in detail, and the corresponding weighting coefficient, to provide fine impurity control strategy for the fluctuation suppression control module.

[0033] Specifically, as shown in Figure 2 、 6 , the fluctuation suppression control module includes: The priority sorting submodule extracts the impurity peak position and concentration difference threshold based on the impurity distribution matching table, analyzes the impurity contribution degree under unit concentration difference, and generates an impurity priority sorting table; Based on the impurity distribution matching table, the peak position of the impurity is extracted from the matching table, for example, it is identified that the concentration peak of impurity A appears at the 30th minute of the purification time, and the peak of impurity B appears at the 45th minute, and the corresponding concentration difference threshold is extracted, for example, for impurity A, when its concentration exceeds 0.01 mg / mL, it is considered as a threshold that needs to be focused on, for impurity B, the threshold is 0.008 mg / mL, then the contribution degree of the impurity under unit concentration difference is analyzed, for example, when the target component concentration decreases by 0.01 mg / mL, how much purity decrease is caused by impurities A, B and C respectively, for example, impurity A causes 0.5% purity decrease, impurity B causes 0.3% purity decrease, and impurity C causes 0.1% purity decrease, according to the contribution degree data, an impurity priority sorting table is generated, which sorts the impurities according to their influence degree on the purity of the target component, for example, impurity A has the highest priority, followed by impurity B, which provides a clear control direction for subsequent fluctuation distribution identification.

[0034] The fluctuation distribution identification submodule extracts the fluctuation change trajectory of the main channel node based on the impurity priority ranking table, identifies the fluctuation balance point and the offset direction, and generates a fluctuation distribution relationship table; Based on the impurity priority ranking table, the fluctuation change trajectory on the main channel node is extracted, for example, by tracking the pressure, temperature and concentration data of the key monitoring points (such as the inlet, middle of the extraction kettle and outlet) of the main purification channel in real time, a curve of the parameter change with time is drawn, for example, the pressure in the middle of the main channel fluctuates around 0.15 MPa, and a significant peak appears at the 30th minute of purification, then the fluctuation balance point is identified, for example, the long-term stable average pressure value in the pressure fluctuation curve is identified, for example, 0.15 MPa, and the offset direction is identified, for example, when the pressure is continuously higher than 0.15 MPa, it is identified as "positive offset", and when it is lower than 0.15 MPa, it is identified as "negative offset", the balance point and the offset direction are determined based on the average value and the standard deviation calculated from the historical stable operation data, for example, by analyzing the pressure data of the past 100 batches of successful purification, the average value is calculated as the balance point, and the threshold of 2 times the standard deviation is set as the offset, a fluctuation distribution relationship table is generated, which records the fluctuation balance point, offset direction and fluctuation trajectory characteristics of the main channel node in detail, providing quantitative fluctuation information for fluctuation adjustment.

[0035] The fluctuation adjustment submodule adjusts the distribution order based on the fluctuation distribution relationship table, extracts the fluctuation change frequency and amplitude sequence of the node, counts the offset amplitude and duration of the fluctuation overrun node, divides the stable interval and the fluctuation transition section, and generates a reference fluctuation suppression scheme; Based on the wave distribution relationship table, the distribution order is adjusted according to the wave node characteristics. For example, if a certain wave node shows high frequency and large positive pressure deviation, the pressure control strategy of the node is adjusted in priority, for example, the pressure relief valve is immediately started for pressure release, then the frequency of the node wave change is extracted, for example, the number of times that the wave amplitude of a certain pressure node exceeds 0.01 MPa per minute is recorded, for example, 3 times per minute, and the amplitude sequence is extracted, for example, the specific amplitude value of each wave is recorded, for example, 0.012 MPa, 0.015 MPa, 0.009 MPa, the deviation amplitude of the wave out-of-limit node is counted, for example, for the wave exceeding the preset pressure threshold of 0.02 MPa, the actual deviation amplitude is recorded, for example, 0.025 MPa, and the number of continuous times is counted, for example, the out-of-limit wave lasts for 3 monitoring periods, according to the statistical data, the stable interval is divided, for example, the region with a pressure wave amplitude within ±0.005 MPa is divided into a stable interval and a wave transition section, for example, the region with a pressure wave amplitude between ±0.005 MPa and ±0.02 MPa is divided into a wave transition section, and finally, a reference wave suppression scheme is generated, which details the adjustment measures to be taken under different wave conditions, for example, when the pressure wave enters the transition section, the system will suppress the wave by fine-tuning the pump speed, and when it enters the out-of-limit state, it will trigger emergency pressure reduction or increase measures.

[0036] Specifically, as shown in Figure 2 , 7 , the execution path adaptation module includes: The state monitoring submodule generates a state monitoring data table based on the reference wave suppression scheme, collects pressure node values and target component concentration feedback, records jump time and deviation amplitude, and generates a state monitoring data table. Based on the reference wave suppression scheme, the values of the key pressure nodes in the purification process are collected, for example, the inlet pressure, middle pressure and outlet pressure are obtained in real time by pressure sensors installed at different positions of the purification kettle, for example, the inlet pressure is 0.1 MPa, the middle pressure is 0.15 MPa, and the outlet pressure is 0.12 MPa, and the concentration feedback of the target component is collected, for example, the concentration of chlorogenic acid in the purified liquid is monitored in real time by an online concentration sensor, for example, the current concentration is 1.45 mg / mL, at the same time, the accurate time when the pressure or concentration jumps is recorded, for example, when the purification is carried out to 120 seconds, the middle pressure jumps from 0.15 MPa to 0.18 MPa, and the jump amplitude is recorded, for example, the amplitude is 0.03 MPa, then the real-time collected data is integrated to generate a state monitoring data table, which contains fields such as "time stamp", "pressure node (MPa)", "concentration (mg / mL)", "jump time (s)" and "deviation amplitude (MPa / mg / mL)", etc. The table provides comprehensive and accurate operation state data for subsequent demand comparison.

[0037] The demand comparison sub-module extracts the time points that do not meet the concentration based on the state monitoring data table, identifies the remaining capacity and the instantaneous gap, matches the target gap and the capacity segment, and generates a demand comparison result table; Based on the state monitoring data table, the corresponding time points that do not meet the target concentration are extracted from the table, for example, during the purification process, when the chlorogenic acid concentration is continuously lower than the target concentration of 1.5 mg / mL for 5 minutes, the time period is identified as the time point of unmet demand, then the remaining capacity possessed by the current purification is identified, for example, the load rate of the current equipment, the maximum flow of the pump and the power of the heating or cooling system and other parameters are analyzed, the extractable capacity under the premise of not affecting the stable operation of the equipment is calculated, for example, under the current working condition, there is still the ability to increase the processing capacity by 10%, and the instantaneous gap is identified, for example, the instantaneous difference between the target concentration and the actual concentration at a certain time point, for example, the instantaneous gap is 0.1 mg / mL, then the target gap and the remaining capacity segment are matched, for example, if the current concentration is short of 0.1 mg / mL, and there is the ability to increase the processing capacity by 10%, and the 10% capacity can make up the concentration gap of 0.1 mg / mL, for example, by calculation, increasing the processing capacity by 10% can increase the concentration by 0.12 mg / mL, then it is considered that the two can be matched, and a demand comparison result table is generated, which lists in detail the time points of unmet demand, instantaneous concentration gap, remaining capacity and matching scheme, providing decision basis for dynamic adjustment.

[0038] The dynamic adjustment sub-module fills the fluctuation gap by adjusting the concentration distribution and impurity separation matching order based on the demand comparison result table, identifies the capacity gap node and response lag segment, updates the concentration output timing and impurity separation curve, and generates a purification process global optimization execution scheme; Based on the demand comparison result table, the fluctuation gap is filled by adjusting the matching order of concentration distribution and impurity separation, for example, if the demand comparison result shows that the concentration is low and the impurity exceeds the standard in a certain time period, the purification parameters will be adjusted to improve the concentration of the target component, for example, the extraction temperature is appropriately increased and the extraction time is prolonged to make up for the concentration gap, and at the same time the impurity separation parameters are adjusted, for example, the flow rate is increased or the amount of adsorbent is increased to ensure that the impurity can be effectively separated, then the ability gap node is identified, for example, when the remaining ability is insufficient to make up for the instantaneous concentration gap, the specific time point or operation link of the insufficient ability is identified, for example, in the later stage of purification, the heating power has reached the upper limit but the concentration still cannot be improved, and the response lag section is identified, for example, the time required for the actual concentration or impurity separation effect to reach the expected value after adjusting the parameters, for example, it takes 5 minutes to see a significant change in concentration after adjusting the temperature, then according to the identification result, the concentration output time sequence is updated, for example, if the expected concentration cannot reach the target in the next 10 minutes, the output time table will be adjusted, the product output will be delayed, and the impurity separation curve will be updated, for example, the expected separation effect curve of the impurity is adjusted according to the new purification parameters, and the global optimization execution scheme of the purification process is generated.

[0039] Please refer to Figure 8 The intelligent detection method of purified components of traditional Chinese medicine is based on the above-mentioned intelligent detection system of purified components of traditional Chinese medicine, comprising the following steps: S1: According to the concentration gradient distribution curve of the target component in the purification process of traditional Chinese medicine, the target component concentration parameter and the target value of purification are extracted, the temperature and pressure influence factors are normalized, the component extraction and target concentration relationship are matched, and the component extraction adaptation table is generated; S2: Based on the component extraction adaptation table, the target and real-time concentration deviation value is extracted, the offset amplitude and response duration are calculated, the concentration change rate and response time data are screened, and the concentration distribution correction data set is generated; S3: Based on the concentration distribution correction data set, the impurity distribution frequency and peak node in unit time are extracted, the abnormal transition point and stable recovery point are associated with the concentration response value, the echo time and jump boundary in the fluctuation interval are extracted, and the impurity distribution matching table is generated; S4: Based on the impurity distribution matching table, the high-frequency impurity priority section and the fluctuation peak position are analyzed, the step change node is identified and the main channel and compensation path are reconstructed, and the reference fluctuation suppression scheme is constructed; S5: Based on the reference fluctuation suppression scheme, the concentration demand parameters and key node fluctuation state values that are not met are screened, the offset frequency peak value is extracted and the concentration adjustment logic is corrected, and the global optimization execution scheme of the purification process is generated.

[0040] The above merely illustrates the specific embodiments of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An intelligent detection system for purified components of traditional Chinese medicine, characterized in that: The system comprises: The component extraction module extracts the target component concentration parameters based on the concentration gradient distribution curve of the target component during the purification process of traditional Chinese medicine, analyzes the influence of temperature and pressure on the component extraction efficiency, organizes the relationship model between component extraction and concentration distribution, and obtains the component extraction adaptation table; The concentration distribution correction module extracts the adaptation table based on the components, extracts the deviation between the real-time concentration value and the target concentration, identifies the concentration change rate and response time, quantifies the cumulative effect of the concentration error, summarizes the concentration correction weight, and obtains a concentration distribution correction data set; The dynamic matching optimization module extracts the impurity distribution frequency and peak nodes based on the concentration distribution correction data set, and performs a hierarchical weighted analysis based on the pressure fluctuation characteristics and concentration change rules during the purification process to obtain an impurity distribution matching table; The fluctuation suppression control module is based on the impurity distribution matching table, sorts the impurities according to their priority and concentration requirement ratio, identifies the fluctuation distribution relationship between the purification and target components, adjusts the allocation order according to the fluctuation node characteristics, and constructs a benchmark fluctuation suppression plan.

2. The intelligent detection system for purified components of traditional Chinese medicine according to claim 1, characterized in that: The component extraction adaptation table includes concentration gradient interval, extraction efficiency range, temperature and pressure compensation factor, and concentration coupling factor; the concentration distribution correction data set includes concentration error factor, response delay index, change rate weight, and correction coefficient; the impurity distribution matching table includes graded impurity interval, demand priority level, fluctuation threshold, and matching weight; the benchmark fluctuation suppression scheme includes fluctuation distribution structure, node adjustment order, fluctuation correction factor, and concentration allocation factor.

3. The intelligent detection system for purified components of traditional Chinese medicine according to claim 1, characterized in that: The component extraction module includes: The concentration parameter extraction submodule extracts the target component concentration parameters according to the concentration gradient distribution curve of the target component in the traditional Chinese medicine purification process, classifies the temperature and pressure influencing factors, and generates a concentration gradient distribution table; The extraction efficiency analysis submodule analyzes the effects of temperature and pressure on component extraction efficiency based on the concentration gradient distribution table, calculates the extraction efficiency adaptation value under different processing conditions, and generates a component extraction and concentration distribution relationship model; The adaptation table generation submodule arranges component extraction parameters based on the component extraction and concentration distribution relationship model, analyzes the corresponding relationship with the target component concentration value, and generates a component extraction adaptation table.

4. The intelligent detection system for purified components of traditional Chinese medicine according to claim 3, characterized in that: The extraction efficiency adaptation value under the differentiated working conditions is calculated using the formula: ； in, Represents the extraction efficiency adaptation value under different chemical conditions, represents the pressure under the i-th working condition, Represents the reference pressure value, represents the temperature under the i-th working condition, represents the reference temperature value, is the impact index of pressure on efficiency, is the index of temperature's influence on efficiency, and n is the total number of operating conditions.

5. The intelligent detection system for purified components of traditional Chinese medicine according to claim 3, characterized in that: The concentration distribution correction module includes: The concentration deviation extraction submodule extracts the deviation between the real-time concentration value and the target concentration based on the component extraction adaptation table, records the concentration change rate and response time data, and generates a concentration deviation data table; The error accumulation quantification submodule quantifies the concentration error accumulation effect based on the concentration deviation data table, analyzes the difference between the concentration distribution and the demand ratio, and generates a concentration error accumulation effect table; The correction weight summarization submodule extracts the concentration deviation magnitude and correction frequency based on the concentration error cumulative effect table, filters the high-frequency error segments and marks the deviation direction, summarizes the concentration correction weights, and generates a concentration distribution correction data set.

6. The intelligent detection system for purified components of traditional Chinese medicine according to claim 5, characterized in that: The dynamic matching optimization module includes: The impurity distribution extraction submodule extracts the impurity distribution frequency and peak nodes based on the concentration distribution correction data set, classifies the impurity distribution priority data, and generates an impurity distribution frequency table; The pressure fluctuation analysis submodule calculates the pressure node fluctuation state value based on the impurity distribution frequency table and combines the pressure fluctuation characteristics and concentration change rules during the purification process to generate a pressure fluctuation state table; The hierarchical weighted analysis submodule performs a multi-dimensional comparison between the impurity distribution and the pressure fluctuation based on the pressure fluctuation state table, screens the impurity distribution adaptation relationship, and generates an impurity distribution matching table.

7. The intelligent detection system for purified components of traditional Chinese medicine according to claim 6, characterized in that: The fluctuation suppression control module includes: The priority sorting submodule extracts the impurity peak position and concentration difference threshold based on the impurity distribution matching table, analyzes the impurity contribution under unit concentration difference, and generates an impurity priority sorting table; The fluctuation distribution identification submodule extracts the fluctuation change trajectory of the main channel node based on the impurity priority ranking table, identifies the fluctuation balance point and offset direction, and generates a fluctuation distribution relationship table; The fluctuation adjustment submodule is based on the fluctuation distribution relationship table, adjusts the allocation order according to the fluctuation node characteristics, extracts the node fluctuation change frequency and amplitude sequence, counts the offset amplitude and duration of the fluctuation exceeding the limit node, divides the stable interval and the fluctuation transition section, and generates a benchmark fluctuation suppression plan.

8. The intelligent detection system for purified components of traditional Chinese medicine according to claim 1, characterized in that: The system also includes an execution path adaptation module: The execution path adaptation module monitors the purification pressure status and the execution of the target component concentration based on the baseline fluctuation suppression scheme, compares the unmet concentration requirements with the remaining capacity in real time, fills the fluctuation gaps by adjusting the concentration distribution and the impurity separation matching order, and generates a global optimization execution plan for the purification process; The global optimization execution plan of the purification process includes residual adjustment parameters, execution sequence configuration, remaining capacity utilization, and adjustment completion criteria.

9. The intelligent detection system for purified components of traditional Chinese medicine according to claim 8, characterized in that: The execution path adaptation module includes: The state monitoring submodule collects pressure node values ​​and target component concentration feedback based on the benchmark fluctuation suppression scheme, records the jump time and deviation amplitude, and generates a state monitoring data table; The demand comparison submodule extracts the time points corresponding to the unmet concentrations based on the status monitoring data table, identifies the remaining capacity and the instantaneous gap, matches the target gap with the capacity segment, and generates a demand comparison result table; Based on the demand comparison result table, the dynamic adjustment submodule fills the fluctuation gaps by adjusting the concentration distribution and impurity separation matching order, identifies the capacity gap nodes and response lag segments, updates the concentration output timing and impurity separation curve, and generates a global tuning execution plan for the purification process.

10. An intelligent detection method for purified components of traditional Chinese medicine, characterized in that: The method is used to implement the intelligent detection system for purified components of traditional Chinese medicine according to any one of claims 1 to 9, comprising the following steps: S1: According to the concentration gradient distribution curve of the target component in the purification process of traditional Chinese medicine, the target component concentration parameters and purification target values ​​are extracted, the temperature and pressure influencing factors are normalized, the relationship between component extraction and target concentration is matched, and a component extraction adaptation table is generated; S2: extracting the adaptation table based on the components, extracting the target and real-time concentration deviation values, calculating the offset amplitude and response duration, screening the concentration change rate and response time data, and generating a concentration distribution correction data set; S3: Based on the concentration distribution correction data set, extract the impurity distribution frequency and peak nodes per unit time, associate the concentration response values ​​to identify abnormal transition points and stable recovery points, extract the echo time and jump boundary within the fluctuation range, and generate an impurity distribution matching table; S4: Based on the impurity distribution matching table, analyze the high-frequency impurity priority segments and fluctuation peak positions, identify step change nodes, reconstruct the main channel and compensation path, and build a baseline fluctuation suppression solution; S5: Based on the benchmark fluctuation suppression scheme, the parameters that do not meet the concentration requirements and the fluctuation status values ​​of key nodes are screened, the offset frequency peak is extracted and the concentration adjustment logic is corrected to generate a global tuning execution plan for the purification process.

Images