A method and system for intelligently controlling the internal environment of a microbial fermentation tank

Abstract

The present invention discloses a method and system for intelligent control of the environment in a microbial fermentation tank, and relates to the field of intelligent control technology. The method includes: extracting key control indicators based on multivariate environmental indicators; performing interaction analysis of key control indicators to generate multiple sets of correlation functions; obtaining real-time environmental indicators and growth stages in the tank through a monitoring module, combining multiple optimal culture indicator ranges, calculating and obtaining real-time environmental deviations, and performing index adjustment optimization in combination with multiple sets of correlation functions to obtain multiple index adjustment vectors, and performing tank environment control based on multiple index adjustment vectors and corresponding index adjustment speeds. The present invention solves the technical problem in the prior art that the accuracy of environmental optimization control is low due to the nonlinear mutual influence between environmental factors in the fermentation tank, and achieves the technical effect of improving the accuracy of environmental optimization control in the microbial fermentation tank through the correlation influence adjustment of multivariate environmental indicators.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to an intelligent control method and system for the internal environment of a microbial fermentation tank. Background Art

[0002] Microbial fermentation technology is a technology that uses the specific functions of microorganisms to convert raw materials into products needed by humans. During the fermentation process, the growth and metabolism of microorganisms are affected by a variety of environmental factors, including temperature, pH value, dissolved oxygen concentration, nutrient concentration, etc. Environmental control in microbial fermentation tanks is a key link in microbial fermentation technology, which directly affects the growth and metabolism of microorganisms and the quality and yield of the final product.

[0003] Existing environmental control methods in fermentation tanks are mostly used to adjust independent indicators, but there are nonlinear interactions between environmental factors in actual fermentation tanks. For example, as the temperature increases, the rate of certain chemical reactions will accelerate, which may cause the pH value of the fermentation liquid to decrease. At higher temperatures, the dissolved oxygen concentration of the fermentation liquid may decrease because high temperature accelerates the consumption and escape of oxygen. The correlation between multiple indicators leads to low accuracy of environmental control. Summary of the invention

[0004] The present application provides a method and system for intelligently controlling the environment in a microbial fermentation tank, which is used to solve the technical problem in the prior art of low accuracy of environmental optimization control due to nonlinear mutual influence between environmental factors in the fermentation tank.

[0005] The first aspect of the present application provides a method for intelligent control of the environment in a microbial fermentation tank, the method comprising: obtaining multiple environmental indicators, combining the survival characteristics of the target microorganisms, analyzing and ranking the indicator importance, and extracting key control indicators; based on the key control indicators, performing interaction analysis of the key control indicators through control variable analysis, and generating multiple sets of correlation functions; obtaining multiple optimal culture indicator ranges for each growth stage of the target microorganism; obtaining real-time environmental indicators and growth stages in the tank through a monitoring module, and calculating and obtaining real-time environmental deviations in combination with the multiple optimal culture indicator ranges; based on the real-time environmental deviations, performing indicator adjustment optimization in combination with the multiple sets of correlation functions to obtain multiple indicator adjustment vectors; calculating the indicator adjustment speeds for the multiple indicator adjustment vectors, and controlling the environment in the tank according to the multiple indicator adjustment vectors and the corresponding indicator adjustment speeds.

[0006] According to a second aspect of the present application, there is provided an intelligent control system for the environment in a microbial fermentation tank, the system comprising: a key control indicator extraction module, the key control indicator extraction module is used to obtain multiple environmental indicators, combine the survival characteristics of target microorganisms, perform indicator importance analysis and ranking, and extract key control indicators; an indicator correlation analysis module, the indicator correlation analysis module is used to perform interaction analysis of key control indicators based on the key control indicators through control variable analysis, and generate multiple groups of correlation functions; an optimal culture indicator range acquisition module, the optimal culture indicator range acquisition module is used to obtain multiple optimal culture indicator ranges for each growth stage of the target microorganism; a real-time environment deviation calculation module, the real-time environment deviation calculation module is used to obtain the real-time environment indicators and growth stages in the tank through a monitoring module, and calculate and obtain the real-time environment deviation in combination with the multiple optimal culture indicator ranges; an indicator adjustment optimization module, the indicator adjustment optimization module is used to perform indicator adjustment optimization based on the real-time environment deviation and in combination with the multiple groups of correlation functions to obtain multiple indicator adjustment vectors; and an in-tank environment control module, the in-tank environment control module is used to perform indicator adjustment speed calculations for the multiple indicator adjustment vectors, and perform in-tank environment control according to the multiple indicator adjustment vectors and the corresponding indicator adjustment speeds.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] The present application provides an intelligent control method for the environment inside a microbial fermentation tank, which relates to the field of intelligent control technology. The method extracts key control indicators based on multiple environmental indicators, performs interaction analysis, generates multiple sets of correlation functions, obtains real-time environmental indicators and growth stages inside the tank, calculates and obtains real-time environmental deviations in combination with multiple optimal culture indicator ranges, and performs indicator adjustment optimization in combination with multiple sets of correlation functions to obtain multiple indicator adjustment vectors. The method controls the environment inside the tank in combination with corresponding indicator adjustment speeds, solves the technical problem in the prior art of low precision of environmental optimization control due to nonlinear mutual influence between environmental factors in the fermentation tank, and achieves the technical effect of improving the precision of environmental optimization control inside the microbial fermentation tank through adjustment of the correlation influence of multiple environmental indicators. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1A schematic diagram of a process flow of an intelligent control method for the internal environment of a microbial fermentation tank provided in an embodiment of the present application;

[0011] Figure 2 A schematic diagram of a process for optimizing an index adjustment vector in a method for intelligently controlling an internal environment of a microbial fermentation tank provided in an embodiment of the present application;

[0012] Figure 3 A schematic diagram of the structure of an intelligent control system for the internal environment of a microbial fermentation tank provided in an embodiment of the present application.

[0013] Explanation of the accompanying drawings: key control indicator extraction module 11, indicator correlation analysis module 12, optimal cultivation indicator range acquisition module 13, real-time environmental deviation calculation module 14, indicator adjustment optimization module 15, tank environment control module 16. DETAILED DESCRIPTION

[0014] The present application provides a method for intelligently controlling the environment in a microbial fermentation tank, which is used to solve the technical problem in the prior art of low accuracy of environmental optimization control due to nonlinear mutual influence between environmental factors in the fermentation tank.

[0015] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0016] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Embodiment 1

[0017] like Figure 1 As shown, the present application provides a method for intelligently controlling the internal environment of a microbial fermentation tank, the method comprising:

[0018] P10: Obtain multiple environmental indicators, combine them with the survival characteristics of target microorganisms, analyze and sort the indicator importance, and extract key control indicators;

[0019] Furthermore, step P10 of the embodiment of the present application further includes:

[0020] P11: Based on the basic growth environment requirements of the target microorganisms, obtain the multi-environmental indicators of the fermentation tank;

[0021] P12: Based on the historical culture records of the target microorganism, analyze and extract the survival characteristics of the target microorganism, wherein the survival characteristics of the target microorganism include the survival status and growth rate data of the target microorganism under different environmental conditions;

[0022] P13: According to the survival characteristics of the target microorganisms, the multiple environmental indicators are analyzed and ranked in terms of their importance, and key control indicators are extracted based on the ranking results. The key control indicators include ambient temperature, ambient oxygen concentration, and ambient pH.

[0023] Optionally, the basic growth environment requirements of the target microorganisms are clarified, and based on these requirements, the multi-environmental indicators of the microbial fermentation tank are set, including environmental temperature, environmental humidity, environmental oxygen concentration, environmental acidity (pH value), environmental pressure, environmental light, etc. Further, the historical culture records of the target microorganisms are collected, and by analyzing the historical culture records, the growth performance data of the target microorganisms under different temperature, humidity, oxygen concentration and other conditions are used to obtain the survival characteristics of the target microorganisms, including the survival status and growth rate of the target microorganisms under different environmental conditions.

[0024] Furthermore, according to the survival characteristics of the target microorganisms, the importance of the multivariate environmental indicators is analyzed. Through statistical analysis, the degree of influence of changes in different environmental indicators on the survival status and growth rate of microorganisms is quantified. The importance of each environmental indicator is configured according to the degree of influence, and the environmental indicators are sorted according to the importance. According to the sorting results, the indicators with greater influence are screened out as key control indicators. The key control indicators include ambient temperature, ambient oxygen concentration and ambient pH. These indicators will serve as the main focus of subsequent environmental control.

[0025] P20: Based on the key control indicators, through control variable analysis, interaction analysis of key control indicators is performed to generate multiple groups of correlation functions;

[0026] Furthermore, step P20 of the embodiment of the present application further includes:

[0027] P21: extracting a first control variable based on the key control indicator;

[0028] P22: According to the first control variable, multiple variable adjustments are performed based on a preset step size to obtain multiple environmental indicator change sets, wherein each environmental indicator change set includes changes in other environmental indicators except the first control variable;

[0029] P23: Performing indicator correlation analysis based on the multiple environmental indicator change sets to generate a first correlation function;

[0030] P24: Similarly, based on the key control indicators, the second control variable and the third control variable are extracted respectively, and control variable analysis is performed to generate multiple sets of correlation functions, which include temperature correlation functions, oxygen concentration correlation functions and pH correlation functions.

[0031] It should be understood that, for the key control indicators, the interaction analysis of the key control indicators is performed through the control variable analysis method. First, an indicator is randomly selected from the key control indicators as the first control variable, for example, the ambient temperature is selected as the first control variable. Furthermore, for the first control variable, multiple variable adjustments are performed based on a preset step size, and the preset step size can be set according to the adjustment range and control accuracy requirements of the environmental indicator. For example, if the first control variable is the ambient temperature, the preset step size can be increased or decreased based on the current temperature, such as 1°C, and then the changes in other environmental indicators such as oxygen concentration and pH value after each adjustment are recorded.

[0032] After multiple adjustments, multiple environmental indicator change sets are obtained, each of which corresponds to a specific first control variable value and includes changes in other environmental indicators except the first control variable. Further, multiple environmental indicator change sets are analyzed through machine learning to obtain the indicator correlation relationship between the first control variable and other environmental indicators, and based on the indicator correlation relationship, a first correlation function is generated, which can describe the influence relationship between the first control variable and other environmental indicators.

[0033] By analogy, referring to the above method, the second control variable and the third control variable are extracted from the key control indicators respectively to perform control variable analysis. For example, after analyzing the ambient temperature as the first control variable, the ambient oxygen concentration can be selected as the second control variable, and a similar analysis can be performed to generate a second correlation function. Thus, multiple groups of correlation functions are generated, including temperature correlation functions, oxygen concentration correlation functions, and pH correlation functions, which can be used for subsequent correlation influence calculations.

[0034] Furthermore, step P23 of the embodiment of the present application also includes:

[0035] P23-1: Based on the first control variable, construct a multidimensional space coordinate;

[0036] P23-2: writing the multiple environmental indicator change sets into the multidimensional space coordinates to form multiple coordinate scatter point sets;

[0037] P23-3: Draw a plurality of indicator change curves respectively according to the plurality of coordinate scatter point sets;

[0038] P23-4: Perform curvature characteristic analysis based on the multiple indicator change curves to generate a first correlation function.

[0039] Specifically, a multidimensional space coordinate is constructed according to the first control variable, such as ambient temperature, and other environmental indicators, such as oxygen concentration, pH, etc., and the number of dimensions of the multidimensional space coordinate depends on the number of environmental indicators considered. Further, the multiple environmental indicator change sets are written into the multidimensional space coordinate, and each environmental indicator change set corresponds to a point in the multidimensional space coordinate, thereby forming a coordinate scatter point set.

[0040] Further, according to the plurality of coordinate scatter point sets, a plurality of index change curves are drawn respectively, and the plurality of index change curves can reflect the change trend of other environmental indicators when the first control variable changes. The curvature characteristic analysis is performed on the plurality of index change curves to obtain the change trend and speed of the curves, so as to find the correlation between the first control variable and other environmental indicators, and based on this correlation, a mathematical method such as polynomial fitting, neural network, etc. can be used to generate a function describing the relationship between the first control variable and other environmental indicators, i.e., a first correlation function, for subsequent environmental control optimization and decision support.

[0041] P30: Obtain multiple optimal culture index ranges for each growth stage of the target microorganism;

[0042] Optionally, based on the target microorganism type and historical culture experience data, the optimal growth environment data of the target microorganism at each growth stage is obtained. For example, the optimal growth temperature of most microorganisms is 20°C~40°C, and the temperature change within this range has little effect on the growth of microorganisms. The optimal pH of most bacteria, algae and protozoa is 6.5-7.5, and they can also grow between pH 4-10. Yeast and mold are suitable for an acidic environment of pH 5-6, but the survival range is between pH 1.5-10. For aerobic microorganisms, an environmental dissolved oxygen greater than 0.3 mg / l can meet normal metabolic activities. Therefore, for each growth stage of the target microorganism, multiple culture indicators such as temperature, pH, dissolved oxygen, nutrient ratio and water activity are comprehensively considered, and multiple optimal culture indicator ranges are determined, such as the optimal growth temperature range, etc., as a reference for subsequent environmental indicator adjustment.

[0043] P40: Obtaining the real-time environmental indicators and growth stages in the tank through the monitoring module, and calculating and obtaining the real-time environmental deviation in combination with the multiple optimal cultivation indicator ranges;

[0044] In a possible embodiment of the present application, the real-time environmental indicators in the tank and the growth stage information of the target microorganism are obtained through the monitoring module of the microbial fermentation tank. The monitoring module is composed of a variety of sensors, which are used to monitor the environmental indicators in the culture tank in real time and obtain the growth status data of the target microorganism. The real-time environmental indicator data in the culture tank is continuously obtained through the monitoring module, including the current temperature, pH value, dissolved oxygen concentration, etc., and the growth status data of the target microorganism is obtained, and the growth stage of the target microorganism is obtained in combination with the ecological measurement module. The ecological measurement module can perform ecological measurement by methods such as cell counting and biomass measurement.

[0045] Furthermore, the real-time environmental index is compared and calculated with the optimal cultivation index range of the corresponding growth stage to obtain the real-time environmental deviation. For example, if the current temperature is 27°C and the optimal temperature is 28-30°C, the temperature deviation is -1°C.

[0046] P50: Based on the real-time environmental deviation, the index adjustment optimization is performed in combination with the multiple groups of correlation functions to obtain multiple index adjustment vectors;

[0047] Furthermore, step P50 of the embodiment of the present application also includes:

[0048] P51: The real-time environmental deviation includes environmental temperature deviation, environmental oxygen concentration deviation and environmental pH deviation;

[0049] P52: Obtaining an indicator adjustment direction based on the real-time environmental deviation, and performing environmental deviation adjustment to obtain an initial indicator adjustment vector;

[0050] P53: For the initial indicator adjustment vector, a multi-environment indicator balance calculation is performed based on the multiple groups of correlation functions to obtain multiple indicator adjustment vectors.

[0051] It should be understood that, according to the real-time environmental deviation, the multiple groups of correlation functions are used to adjust the indexes for optimization. Specifically, according to the data provided by the monitoring module, the real-time environmental deviation of the current culture environment is determined, including the environmental temperature deviation, the environmental oxygen concentration deviation, and the environmental pH deviation, etc. Further, according to the numerical value and sign of the real-time environmental deviation, the direction in which each environmental indicator needs to be adjusted is determined. For example, if the temperature deviation is positive, the temperature needs to be lowered, and if the oxygen concentration deviation is negative, the oxygen concentration needs to be increased. According to the indicator adjustment direction, a preliminary environmental deviation adjustment is performed, and the adjustment amount and direction of each environmental indicator are obtained to form an initial indicator adjustment vector, which will serve as the starting point for subsequent multi-environmental indicator balance calculations.

[0052] Furthermore, the initial indicator adjustment vector is substituted into the multiple groups of correlation functions respectively to perform multi-environmental indicator balance calculation, that is, the influence of each adjustment indicator on other indicators is calculated respectively. For example, the initial indicator adjustment vector of the ambient temperature is substituted into the temperature correlation function for calculation to obtain the influence value of temperature adjustment on oxygen concentration and environmental pH, and then the influence value is balanced and corrected so that the final sum of the indicator adjustment vector and the influence value approaches the optimal cultivation indicator range infinitely, thereby improving the control accuracy of environmental indicators.

[0053] Furthermore, step P53 of the embodiment of the present application also includes:

[0054] P53-1: The initial index adjustment vector includes an initial temperature adjustment vector, an initial oxygen concentration adjustment vector and an initial pH adjustment vector;

[0055] P53-2: Based on the temperature correlation function, the oxygen concentration correlation function and the pH correlation function, the correlation index influence calculation is performed for the initial temperature adjustment vector, the initial oxygen concentration adjustment vector and the initial pH adjustment vector, respectively, to obtain a plurality of correlation changes, including a correlation temperature change, a correlation oxygen concentration change and a correlation pH change;

[0056] P53-3: Based on the associated temperature change, the associated oxygen concentration change, and the associated pH change, the initial index adjustment vector is updated in reverse, and the associated index impact calculation is performed according to the updated index adjustment vector;

[0057] P53-4: Perform multiple iterative adjustments until the sum of the associated change amount and the updated indicator adjustment vector meets the optimal cultivation indicator range, and obtain the multiple indicator adjustment vectors.

[0058] Optionally, the initial indicator adjustment vector includes an initial temperature adjustment vector, an initial oxygen concentration adjustment vector and an initial pH adjustment vector, which respectively represent preliminary adjustment plans for three key environmental indicators: temperature, oxygen concentration and pH.

[0059] Furthermore, the temperature correlation function is used to analyze the possible impact of the initial temperature adjustment vector on other environmental indicators, such as oxygen concentration and pH, to obtain the first oxygen concentration associated change and the first pH associated change. The oxygen concentration correlation function is used to evaluate the impact of the initial oxygen concentration adjustment vector on temperature and pH, to obtain the first temperature associated change and the second pH associated change. Based on the pH correlation function, the impact of the initial pH adjustment vector on temperature and oxygen concentration is calculated to obtain the second temperature associated change and the second oxygen concentration associated change. The associated change categories are accumulated to obtain the associated temperature change, the associated oxygen concentration change, and the associated pH change.

[0060] Further, based on the associated temperature change, the associated oxygen concentration change, and the associated pH change, the initial index adjustment vector is adjusted in the opposite direction to offset the impact of the associated change on the target environmental index, and the updated index adjustment vector is used to perform the associated index impact calculation again to evaluate whether the new index adjustment vector is closer to the optimal cultivation index range, and an optimization decision is made based on the evaluation result. Multiple iterative adjustments are performed in this way until the sum of the associated change and the updated index adjustment vector meets the optimal cultivation index range, that is, a sufficiently accurate environmental index adjustment scheme is found, and the updated index adjustment vector obtained in the last iteration is used as the final index adjustment vector.

[0061] Further, such as Figure 2 As shown, step P53-4 of the embodiment of the present application also includes:

[0062] P53-41: Randomly select the ambient temperature as the first optimization indicator, and configure an optimization step table for the first optimization indicator;

[0063] P53-42: for the first optimization index, selecting a first step length based on the optimization step length table, and adjusting the initial temperature adjustment vector according to the first step length to obtain a first optimized temperature adjustment vector;

[0064] P53-43: According to the first optimized temperature adjustment vector, using the temperature correlation function, calculate and obtain a first associated oxygen concentration change amount and a first associated pH change amount;

[0065] P53-44: Determine whether the first associated oxygen concentration change and the first associated pH change are less than the associated oxygen concentration change and the associated pH change; if so, continue to perform iterative optimization with the first optimization index and the first step length; if not, select a second step length based on the optimization step length table, and adjust the initial temperature adjustment vector according to the second step length;

[0066] P53-45: By analogy, if after traversing the optimization step table, the first associated oxygen concentration change and the first associated pH change still do not meet the requirements, then switch the oxygen concentration or the environmental pH as the first optimization indicator, and continue to update the adjustment vector until the sum of the associated change and the update indicator adjustment vector meets the optimal cultivation indicator range.

[0067] The specific optimization process may be to randomly select any key indicator, such as ambient temperature, oxygen concentration and ambient pH, as the first optimization indicator for the three key indicators of ambient temperature, oxygen concentration and ambient pH, and configure an optimization step table for the indicator, wherein the optimization step table contains a series of predefined step values, such as 0.1°C, 0.2°C, 0.1°C and other temperature adjustment steps.

[0068] Furthermore, the indicator adjustment amount is first optimized for the first optimization indicator, the first step length is selected from the optimization step length table, and the initial temperature adjustment vector is adjusted according to this step length to obtain the first optimized temperature adjustment vector. For example, if the first step length is 0.1°C and the initial temperature adjustment vector is 27°C, the adjusted first optimized temperature adjustment vector is 26.9°C.

[0069] Further, according to the first optimized temperature adjustment vector, the temperature correlation function is used to calculate the correlation change again, and the first correlation oxygen concentration change and the first correlation pH change are calculated to obtain the first correlation oxygen concentration change and the first correlation pH change. It is determined whether the first correlation oxygen concentration change and the first correlation pH change are less than the correlation oxygen concentration change and the correlation pH change. If they are less than, it means that the current optimization index and the adjustment step are valid, and iterative optimization is continued with the first optimization index and the first step as the direction. If they are not less than, the second step is selected based on the optimization step table, and the initial temperature adjustment vector is adjusted according to the second step to see whether a better optimization direction can be found.

[0070] Furthermore, if after traversing the optimization step table of the ambient temperature index, the first associated oxygen concentration change and the first associated pH change still do not meet the requirements, other parameters need to be considered as new optimization indicators, by switching the oxygen concentration or the ambient pH as the first optimization indicator, and updating the adjustment vector according to the optimization step table corresponding to the oxygen concentration or the ambient pH, repeat the above optimization process until the sum of the associated change and the updated indicator adjustment vector meets the optimal cultivation indicator range, that is, the comprehensive adjustment value of all key indicators reaches the range of the optimal cultivation indicator.

[0071] P60: Calculate the index adjustment speeds for each of the multiple index adjustment vectors, and control the environment inside the tank based on the multiple index adjustment vectors and the corresponding index adjustment speeds.

[0072] Furthermore, step P60 of the embodiment of the present application further includes:

[0073] P61: Based on the key control indicators, obtain the indicator adjustment records of each growth stage, including the growth status of the target microorganisms at different indicator adjustment amounts and different adjustment speeds;

[0074] P62: Based on the indicator adjustment record, training the adjustment rate calculation model;

[0075] P63: Obtain the real-time growth stage of the target microorganism, combine the multiple indicator adjustment vectors, use the adjustment rate calculation model, calculate the indicator adjustment speeds respectively, and obtain multiple indicator adjustment speeds.

[0076] It should be understood that if the index adjustment speed is too fast or too slow, it will affect the environmental adjustment effect. For example, a sudden change in temperature may affect the survival rate of the target microorganism. Therefore, for the multiple index adjustment vectors, the adjustment speed of each index is calculated separately. First, the key control index obtains the index adjustment records of the target microorganism at different growth stages, including the growth status of the target microorganism under different index adjustment amounts and different adjustment speeds of each environmental index. Further, the index adjustment records are used in combination with machine learning algorithms such as neural networks, decision trees, etc. for supervised training to generate an adjustment rate calculation model.

[0077] Furthermore, by real-time monitoring of growth parameters, the real-time growth stage of the target microorganism is obtained, and the multiple index adjustment vectors are combined, input into the adjustment rate calculation model, and the index adjustment speed of each environmental index is calculated respectively. Then, the multiple index adjustment vectors and the corresponding index adjustment speeds are combined to perform environmental adjustment control in the microbial fermentation tank to improve the accuracy and efficiency of control, adapt to the growth requirements of microorganisms under different growth stages and conditions, and thus achieve a more efficient and economical production process.

[0078] In summary, the embodiments of the present application have at least the following technical effects:

[0079] The present application extracts key control indicators based on multivariate environmental indicators, performs interaction analysis, generates multiple sets of correlation functions, obtains real-time environmental indicators and growth stages in the tank, combines multiple optimal cultivation indicator ranges, calculates and obtains real-time environmental deviations, and combines multiple sets of correlation functions to adjust and optimize indicators, obtains multiple indicator adjustment vectors, and controls the environment in the tank in combination with the corresponding indicator adjustment speeds.

[0080] The technical effect of improving the accuracy of environmental optimization control in microbial fermentation tanks by regulating the correlation influence of multiple environmental indicators has been achieved. Embodiment 2

[0081] Based on the same inventive concept as the method for intelligently controlling the internal environment of a microbial fermentation tank in the aforementioned embodiment, Figure 3 As shown, the present application provides an intelligent control system for the internal environment of a microbial fermentation tank, and the system and method embodiments in the embodiments of the present application are based on the same inventive concept. The system includes:

[0082] A key control indicator extraction module 11 is used to obtain multiple environmental indicators, analyze and sort the indicator importance in combination with the survival characteristics of target microorganisms, and extract key control indicators;

[0083] An indicator correlation analysis module 12, the indicator correlation analysis module 12 is used to perform interaction analysis of key control indicators based on the key control indicators through control variable analysis, and generate multiple groups of correlation functions;

[0084] An optimal culture index range acquisition module 13, wherein the optimal culture index range acquisition module 13 is used to acquire multiple optimal culture index ranges for each growth stage of the target microorganism;

[0085] A real-time environmental deviation calculation module 14, which is used to obtain the real-time environmental index and growth stage in the tank through the monitoring module, and calculate the real-time environmental deviation in combination with the multiple optimal cultivation index ranges;

[0086] An index adjustment optimization module 15, wherein the index adjustment optimization module 15 is used to perform index adjustment optimization based on the real-time environment deviation and in combination with the multiple groups of correlation functions to obtain multiple index adjustment vectors;

[0087] The in-tank environment control module 16 is used to calculate the index adjustment speeds for the multiple index adjustment vectors respectively, and to control the in-tank environment according to the multiple index adjustment vectors and the corresponding index adjustment speeds.

[0088] Furthermore, the key control indicator extraction module 11 is also used to perform the following steps:

[0089] Based on the basic growth environment requirements of the target microorganisms, obtain the multi-environmental indicators of the fermentation tank;

[0090] Based on the historical culture records of the target microorganism, analyzing and extracting the survival characteristics of the target microorganism, the survival characteristics of the target microorganism include the survival status and growth rate data of the target microorganism under different environmental conditions;

[0091] According to the survival characteristics of the target microorganisms, the multiple environmental indicators are analyzed and ranked in terms of their importance, and key control indicators are extracted based on the ranking results. The key control indicators include ambient temperature, ambient oxygen concentration, and ambient pH.

[0092] Furthermore, the indicator association analysis module 12 is also used to perform the following steps:

[0093] Based on the key control indicator, extracting a first control variable;

[0094] According to the first control variable, multiple variable adjustments are performed based on a preset step length to obtain multiple environmental indicator change sets, wherein each environmental indicator change set includes changes in other environmental indicators except the first control variable;

[0095] Performing indicator correlation analysis based on the multiple environmental indicator change sets to generate a first correlation function;

[0096] Similarly, based on the key control indicators, the second control variable and the third control variable are extracted respectively, and control variable analysis is performed to generate multiple groups of correlation functions, which include temperature correlation functions, oxygen concentration correlation functions and pH correlation functions.

[0097] Furthermore, the indicator association analysis module 12 is also used to perform the following steps:

[0098] Based on the first control variable, construct a multidimensional space coordinate;

[0099] Writing the multiple environmental indicator change sets into the multidimensional space coordinates to form multiple coordinate scatter point sets;

[0100] According to the plurality of coordinate scatter point sets, a plurality of indicator change curves are drawn respectively;

[0101] A curvature characteristic analysis is performed based on the multiple indicator change curves to generate a first correlation function.

[0102] Furthermore, the index adjustment optimization module 15 is also used to perform the following steps:

[0103] The real-time environmental deviation includes environmental temperature deviation, environmental oxygen concentration deviation and environmental pH deviation;

[0104] Acquire an indicator adjustment direction based on the real-time environmental deviation, and perform environmental deviation adjustment to obtain an initial indicator adjustment vector;

[0105] For the initial indicator adjustment vector, a multi-environment indicator balance calculation is performed based on the multiple groups of correlation functions to obtain multiple indicator adjustment vectors.

[0106] Furthermore, the index adjustment optimization module 15 is also used to perform the following steps:

[0107] The initial index adjustment vector includes an initial temperature adjustment vector, an initial oxygen concentration adjustment vector and an initial pH adjustment vector;

[0108] Based on the temperature correlation function, the oxygen concentration correlation function and the pH correlation function, the correlation index influence calculation is performed for the initial temperature adjustment vector, the initial oxygen concentration adjustment vector and the initial pH adjustment vector, respectively, to obtain a plurality of correlation changes, including a correlation temperature change, a correlation oxygen concentration change and a correlation pH change;

[0109] Based on the associated temperature change, the associated oxygen concentration change, and the associated pH change, the initial index adjustment vector is updated in reverse, and the associated index impact calculation is performed according to the updated index adjustment vector;

[0110] Perform multiple iterative adjustments until the sum of the associated change amount and the updated indicator adjustment vector meets the optimal cultivation indicator range, thereby obtaining the multiple indicator adjustment vectors.

[0111] Furthermore, the index adjustment optimization module 15 is also used to perform the following steps:

[0112] Randomly select ambient temperature as a first optimization indicator, and configure an optimization step table for the first optimization indicator;

[0113] For the first optimization index, a first step length is selected based on the optimization step length table, and the initial temperature adjustment vector is adjusted according to the first step length to obtain a first optimized temperature adjustment vector;

[0114] According to the first optimized temperature adjustment vector, using the temperature correlation function, calculating and obtaining a first associated oxygen concentration change amount and a first associated pH change amount;

[0115] Determine whether the first associated oxygen concentration change and the first associated pH change are less than the associated oxygen concentration change and the associated pH change; if so, continue to perform iterative optimization with the first optimization index and the first step length; if not, select a second step length based on the optimization step length table, and adjust the initial temperature adjustment vector according to the second step length;

[0116] By analogy, if after traversing the optimization step table, the first associated oxygen concentration change and the first associated pH change still do not meet the requirements, then switch the oxygen concentration or the environmental pH as the first optimization indicator, and continue to update the adjustment vector until the sum of the associated change and the updated indicator adjustment vector meets the optimal cultivation indicator range.

[0117] Furthermore, the tank environment control module 16 is also used to perform the following steps:

[0118] Based on the key control indicators, obtaining indicator adjustment records at each growth stage, including target microbial growth conditions at different indicator adjustment amounts and different adjustment speeds;

[0119] Based on the indicator adjustment record, training an adjustment rate calculation model;

[0120] The real-time growth stage of the target microorganism is obtained, and the index adjustment speed calculation is performed respectively in combination with the multiple index adjustment vectors using the adjustment rate calculation model to obtain multiple index adjustment speeds.

[0121] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0122] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0123] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for intelligently controlling the internal environment of a microbial fermentation tank, characterized in that: The method comprises: Obtain multiple environmental indicators, combine them with the survival characteristics of target microorganisms, analyze and sort the indicator importance, and extract key control indicators; Based on the key control indicators, through control variable analysis, interaction analysis of key control indicators is performed to generate multiple groups of correlation functions; Obtain multiple optimal culture index ranges for each growth stage of the target microorganism; The real-time environmental index and growth stage in the tank are obtained by the monitoring module, and the real-time environmental deviation is calculated based on the multiple optimal culture index ranges; Based on the real-time environmental deviation, the index adjustment optimization is performed in combination with the multiple groups of correlation functions to obtain multiple index adjustment vectors; Calculating the index adjustment speeds for the multiple index adjustment vectors respectively, and controlling the environment inside the tank according to the multiple index adjustment vectors and the corresponding index adjustment speeds; Combined with the survival characteristics of target microorganisms, the indicator importance analysis and ranking are carried out to extract key control indicators, including: Based on the basic growth environment requirements of the target microorganisms, obtain the multi-environmental indicators of the fermentation tank; Based on the historical culture records of the target microorganism, analyzing and extracting the survival characteristics of the target microorganism, the survival characteristics of the target microorganism include the survival status and growth rate data of the target microorganism under different environmental conditions; According to the survival characteristics of the target microorganisms, the multiple environmental indicators are analyzed and ranked according to their importance, and key control indicators are extracted according to the ranking results, wherein the key control indicators include environmental temperature, environmental oxygen concentration, and environmental pH; Based on the key control indicators, the interaction analysis of the key control indicators is performed through the control variable analysis to generate multiple groups of correlation functions, including: Based on the key control indicator, extracting a first control variable; According to the first control variable, multiple variable adjustments are performed based on a preset step length to obtain multiple environmental indicator change sets, wherein each environmental indicator change set includes changes in other environmental indicators except the first control variable; Performing indicator correlation analysis based on the multiple environmental indicator change sets to generate a first correlation function; Similarly, based on the key control indicators, the second control variable and the third control variable are extracted respectively, and control variable analysis is performed to generate multiple groups of correlation functions, wherein the multiple groups of correlation functions include temperature correlation functions, oxygen concentration correlation functions, and pH correlation functions; Based on the real-time environment deviation, the index adjustment optimization is performed in combination with the multiple groups of correlation functions to obtain multiple index adjustment vectors, including: The real-time environmental deviation includes environmental temperature deviation, environmental oxygen concentration deviation and environmental pH deviation; Acquire an indicator adjustment direction based on the real-time environmental deviation, and perform environmental deviation adjustment to obtain an initial indicator adjustment vector; For the initial indicator adjustment vector, performing a multi-environment indicator balance calculation based on the multiple groups of correlation functions to obtain multiple indicator adjustment vectors; For the initial indicator adjustment vector, a multi-environment indicator balance calculation is performed based on the multiple groups of correlation functions to obtain multiple indicator adjustment vectors, including: The initial index adjustment vector includes an initial temperature adjustment vector, an initial oxygen concentration adjustment vector and an initial pH adjustment vector; Based on the temperature correlation function, the oxygen concentration correlation function and the pH correlation function, the correlation index influence calculation is performed for the initial temperature adjustment vector, the initial oxygen concentration adjustment vector and the initial pH adjustment vector, respectively, to obtain a plurality of correlation changes, including a correlation temperature change, a correlation oxygen concentration change and a correlation pH change; Based on the associated temperature change, the associated oxygen concentration change, and the associated pH change, the initial index adjustment vector is updated in reverse, and the associated index impact calculation is performed according to the updated index adjustment vector; Perform multiple iterative adjustments until the sum of the associated change amount and the updated indicator adjustment vector meets the optimal cultivation indicator range, thereby obtaining the multiple indicator adjustment vectors; Perform multiple iterative adjustments until the sum of the associated change amount and the updated indicator adjustment vector meets the optimal training indicator range, and obtain the multiple indicator adjustment vectors, including: Randomly select ambient temperature as a first optimization indicator, and configure an optimization step table for the first optimization indicator; For the first optimization index, a first step length is selected based on the optimization step length table, and the initial temperature adjustment vector is adjusted according to the first step length to obtain a first optimized temperature adjustment vector; According to the first optimized temperature adjustment vector, using the temperature correlation function, calculating and obtaining a first associated oxygen concentration change amount and a first associated pH change amount; Determine whether the first associated oxygen concentration change and the first associated pH change are less than the associated oxygen concentration change and the associated pH change; if so, continue to perform iterative optimization with the first optimization index and the first step length; if not, select a second step length based on the optimization step length table, and adjust the initial temperature adjustment vector according to the second step length; By analogy, if after traversing the optimization step table, the first associated oxygen concentration change and the first associated pH change still do not meet the requirements, then switch the oxygen concentration or the environmental pH as the first optimization indicator, and continue to update the adjustment vector until the sum of the associated change and the updated indicator adjustment vector meets the optimal cultivation indicator range.

2. The method according to claim 1, characterized in that Performing indicator correlation analysis based on the multiple environmental indicator change sets to generate a first correlation function includes: Based on the first control variable, construct a multidimensional space coordinate; Writing the multiple environmental indicator change sets into the multidimensional space coordinates to form multiple coordinate scatter point sets; According to the plurality of coordinate scatter point sets, a plurality of indicator change curves are drawn respectively; A curvature characteristic analysis is performed based on the multiple indicator change curves to generate a first correlation function.

3. The method according to claim 1, characterized in that The index adjustment speed calculation is performed respectively for the multiple index adjustment vectors, including: Based on the key control indicators, obtaining indicator adjustment records at each growth stage, including target microbial growth conditions at different indicator adjustment amounts and different adjustment speeds; Based on the indicator adjustment record, training an adjustment rate calculation model; The real-time growth stage of the target microorganism is obtained, and the index adjustment speed calculation is performed respectively in combination with the multiple index adjustment vectors using the adjustment rate calculation model to obtain multiple index adjustment speeds.

4. An intelligent control system for the internal environment of a microbial fermentation tank, characterized in that: The system comprises: A key control indicator extraction module, which is used to obtain multiple environmental indicators, analyze and sort the indicator importance in combination with the survival characteristics of target microorganisms, and extract key control indicators; An indicator correlation analysis module, wherein the indicator correlation analysis module is used to perform interaction analysis of key control indicators based on the key control indicators through control variable analysis to generate multiple groups of correlation functions; An optimal culture index range acquisition module, wherein the optimal culture index range acquisition module is used to obtain multiple optimal culture index ranges for each growth stage of the target microorganism; A real-time environmental deviation calculation module, which is used to obtain the real-time environmental index and growth stage in the tank through the monitoring module, and calculate the real-time environmental deviation in combination with the multiple optimal cultivation index ranges; An indicator adjustment optimization module, the indicator adjustment optimization module is used to perform indicator adjustment optimization based on the real-time environment deviation and in combination with the multiple groups of correlation functions to obtain multiple indicator adjustment vectors; An in-tank environment control module, the in-tank environment control module is used to calculate the index adjustment speeds for the multiple index adjustment vectors, and to control the in-tank environment according to the multiple index adjustment vectors and the corresponding index adjustment speeds; The key control indicator extraction module is also used to perform the following steps: Based on the basic growth environment requirements of the target microorganisms, obtain the multi-environmental indicators of the fermentation tank; Based on the historical culture records of the target microorganism, analyzing and extracting the survival characteristics of the target microorganism, the survival characteristics of the target microorganism include the survival status and growth rate data of the target microorganism under different environmental conditions; According to the survival characteristics of the target microorganisms, the multiple environmental indicators are analyzed and ranked according to their importance, and key control indicators are extracted according to the ranking results, wherein the key control indicators include environmental temperature, environmental oxygen concentration, and environmental pH; The indicator association analysis module is also used to perform the following steps: Based on the key control indicator, extracting a first control variable; According to the first control variable, multiple variable adjustments are performed based on a preset step length to obtain multiple environmental indicator change sets, wherein each environmental indicator change set includes changes in other environmental indicators except the first control variable; Performing indicator correlation analysis based on the multiple environmental indicator change sets to generate a first correlation function; Similarly, based on the key control indicators, the second control variable and the third control variable are extracted respectively, and control variable analysis is performed to generate multiple groups of correlation functions, wherein the multiple groups of correlation functions include temperature correlation functions, oxygen concentration correlation functions, and pH correlation functions; The index adjustment optimization module is also used to perform the following steps: The real-time environmental deviation includes environmental temperature deviation, environmental oxygen concentration deviation and environmental pH deviation; Acquire an indicator adjustment direction based on the real-time environmental deviation, and perform environmental deviation adjustment to obtain an initial indicator adjustment vector; For the initial indicator adjustment vector, performing a multi-environment indicator balance calculation based on the multiple groups of correlation functions to obtain multiple indicator adjustment vectors; The index adjustment optimization module is also used to perform the following steps: The initial index adjustment vector includes an initial temperature adjustment vector, an initial oxygen concentration adjustment vector and an initial pH adjustment vector; Based on the temperature correlation function, the oxygen concentration correlation function and the pH correlation function, the correlation index influence calculation is performed for the initial temperature adjustment vector, the initial oxygen concentration adjustment vector and the initial pH adjustment vector, respectively, to obtain a plurality of correlation changes, including a correlation temperature change, a correlation oxygen concentration change and a correlation pH change; Based on the associated temperature change, the associated oxygen concentration change, and the associated pH change, the initial index adjustment vector is updated in reverse, and the associated index impact calculation is performed according to the updated index adjustment vector; Perform multiple iterative adjustments until the sum of the associated change amount and the updated indicator adjustment vector meets the optimal cultivation indicator range, thereby obtaining the multiple indicator adjustment vectors; The index adjustment optimization module is also used to perform the following steps: Randomly select ambient temperature as a first optimization indicator, and configure an optimization step table for the first optimization indicator; For the first optimization index, a first step length is selected based on the optimization step length table, and the initial temperature adjustment vector is adjusted according to the first step length to obtain a first optimized temperature adjustment vector; According to the first optimized temperature adjustment vector, using the temperature correlation function, calculating and obtaining a first associated oxygen concentration change amount and a first associated pH change amount; Determine whether the first associated oxygen concentration change and the first associated pH change are less than the associated oxygen concentration change and the associated pH change; if so, continue to perform iterative optimization with the first optimization index and the first step length; if not, select a second step length based on the optimization step length table, and adjust the initial temperature adjustment vector according to the second step length; By analogy, if after traversing the optimization step table, the first associated oxygen concentration change and the first associated pH change still do not meet the requirements, then switch the oxygen concentration or the environmental pH as the first optimization indicator, and continue to update the adjustment vector until the sum of the associated change and the updated indicator adjustment vector meets the optimal cultivation indicator range.

Images