A method, apparatus, storage medium, and electronic device for predicting CO2 information in a bioreactor.

Abstract

The application discloses a CO2 information prediction method and device in a bioreactor, a storage medium and an electronic device. The method comprises the following steps: obtaining influence parameters of CO2 in the bioreactor, wherein the influence parameters comprise one or more of the following: a CO2 input rate, O2 concentration information in the bioreactor, an O2 input rate, an air input rate, a PH adjusting material input rate and a preset metabolite generation rate in a biological reaction process; performing CO2 concentration prediction based on the influence parameters of CO2 in the bioreactor by using a pre-created CO2 prediction model to obtain CO2 concentration information of the bioreactor; and determining CO2 partial pressure information of the bioreactor based on the CO2 concentration information of the bioreactor. By setting the CO2 prediction model, the influence parameters of CO2 in the bioreactor are predicted and processed, and the prediction efficiency and prediction accuracy of the CO2 information can be improved.

Description

Technical Field

[0001] This invention relates to the field of bioreactor technology, and in particular to a method, apparatus, storage medium, and electronic device for predicting CO2 information in a bioreactor. Background Technology

[0002] The research and development and production of biopharmaceuticals largely rely on cell culture. Stable control of key parameters in the cell culture process is crucial for ensuring process success and consistent yield and quality across different scales. Core parameters in cell culture include temperature, pH, and dissolved oxygen, which are relatively easy to control and show little variation across different cell culture scales. However, the partial pressure of CO2 often differs significantly across cell culture scales. This is because at large scales, the higher liquid level leads to increased hydrostatic pressure, resulting in higher gas solubility. Furthermore, the longer upward path of gas bubbles allows for greater mass transfer time within the bubbles, ultimately leading to better oxygen mass transfer capabilities at large scales. This difference in oxygen mass transfer capabilities means that the aeration rate per unit volume per unit time is lower at large scales than at smaller scales, resulting in reduced carbon dioxide escape and consequently higher pCO2 levels. Differences in pCO2 levels across different scales can significantly impact cell culture performance, such as inconsistencies in cell growth and metabolism, and yield and quality.

[0003] Therefore, controlling the appropriate pCO2 level is crucial when culturing cells in bioreactors, as excessively high or low pCO2 levels can adversely affect cell growth, metabolism, yield, and quality. However, current pCO2 prediction methods have limitations in accuracy and applicability. Summary of the Invention

[0004] This invention provides a method, apparatus, storage medium, and electronic device for predicting CO2 information in a bioreactor, in order to improve the accuracy of CO2 partial pressure prediction.

[0005] According to one aspect of the present invention, a method for predicting CO2 information in a bioreactor is provided, comprising:

[0006] Obtain the parameters affecting CO2 in the bioreactor, including one or more of the following: CO2 introduction rate, O2 concentration information in the bioreactor, O2 introduction rate, air introduction rate, pH adjustment substance input rate, and the production rate of preset metabolites during the biological reaction.

[0007] By using a pre-created CO2 prediction model, the CO2 concentration is predicted based on the parameters affecting CO2 in the bioreactor, thus obtaining the CO2 concentration information of the bioreactor.

[0008] The CO2 partial pressure information of the bioreactor is determined based on the CO2 concentration information of the bioreactor.

[0009] According to another aspect of the present invention, a device for predicting CO2 information in a bioreactor is provided, comprising:

[0010] The parameter acquisition module is used to acquire the influence parameters of CO2 in the bioreactor. The influence parameters include one or more of the following: CO2 introduction rate, O2 concentration information in the bioreactor, O2 introduction rate, air introduction rate, pH adjustment substance input rate, and the production rate of preset metabolites during the biological reaction.

[0011] The CO2 concentration information prediction module is used to predict the CO2 concentration based on the parameters affecting CO2 in the bioreactor using a pre-created CO2 prediction model, thereby obtaining the CO2 concentration information of the bioreactor.

[0012] The CO2 partial pressure information determination module is used to determine the CO2 partial pressure information of the bioreactor based on the CO2 concentration information of the bioreactor.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the method for predicting CO2 information in a bioreactor according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the method for predicting CO2 information in a bioreactor as described in any embodiment of the present invention.

[0018] The technical solution of this invention improves the comprehensiveness of CO2 influence parameters within the bioreactor by acquiring CO2 introduction rate, O2 concentration information within the bioreactor, O2 introduction rate, air introduction rate, pH adjustment substance input rate, and the pre-set metabolite production rate during the biological reaction as CO2 influence parameters. By setting a CO2 prediction model to predict these CO2 influence parameters, the prediction efficiency and accuracy of CO2 information can be improved.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart of a method for predicting CO2 information in a bioreactor provided by an embodiment of the present invention;

[0022] Figure 2 This is a schematic diagram illustrating the source of CO2 in the bioreactor provided in this embodiment of the invention;

[0023] Figure 3 This is a schematic diagram of the CO2 removal method in the bioreactor provided in the embodiments of the invention;

[0024] Figure 4 This is a flowchart of a method for predicting CO2 information in a bioreactor provided by an embodiment of the present invention;

[0025] Figure 5 This is a schematic diagram of the structure of a CO2 information prediction device in a bioreactor provided in an embodiment of the present invention;

[0026] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0027] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0029] Example 1

[0030] Figure 1 This is a flowchart illustrating a method for predicting CO2 information in a bioreactor according to an embodiment of the present invention. This embodiment is applicable to predicting the partial pressure of CO2 in a bioreactor during cell culture using bioreactors. The method can be executed by a device for predicting CO2 information in a bioreactor, which can be implemented in hardware and / or software. This device can be configured in an electronic device, which may include, but is not limited to, a server, computer, mobile terminal, or bioreactor control equipment. Mobile terminals include, but are not limited to, mobile phones and tablets. Figure 1 As shown, the method includes:

[0031] S110. Obtain the influence parameters of CO2 in the bioreactor, including one or more of the following: CO2 introduction rate, O2 concentration information in the bioreactor, O2 introduction rate, air introduction rate, pH adjustment substance input rate, and the production rate of preset metabolites during the biological reaction.

[0032] S120. Using a pre-created CO2 prediction model, CO2 concentration is predicted based on parameters affecting CO2 in the bioreactor, thereby obtaining CO2 concentration information of the bioreactor.

[0033] S130. Determine the CO2 partial pressure information of the bioreactor based on the CO2 concentration information of the bioreactor.

[0034] A bioreactor is a container used for cell culture. The bioreactor includes a cell culture medium containing cells, and the cell type is not limited here. For example, it may include, but is not limited to, mammalian cells.

[0035] In cell culture within a bioreactor, the CO2 concentration in the culture medium is affected by multiple factors. See also... Figure 2 , Figure 2 This is a schematic diagram illustrating the source of CO2 in the bioreactor provided in this embodiment of the invention. The factors influencing CO2 in the culture medium include aerobic respiration of cells. Aerobic respiration consumes one molecule of glucose and six molecules of O2, producing water and six molecules of CO2 simultaneously. In other words, the aerobic respiration process leads to CO2 production, and the number of moles of CO2 produced is the same as the number of moles of O2 consumed. Other factors influencing CO2 in the culture medium include metabolites produced during cell culture. These metabolites can include, but are not limited to, organic acids, including but not limited to, lactic acid and ammonium ions. According to the chemical equilibrium equation for CO2 in solution, when acid is added to the culture medium in the bioreactor, the reaction equilibrium shifts towards CO2 production, promoting CO2 generation. Finally, factors influencing CO2 in the culture medium also include pH-adjusting substances, which can include acidic and alkaline substances, and can be added according to the needs of cell culture. pH-adjusting substances can include a primary substance that generates CO2 and / or a secondary substance that consumes CO2. Taking an alkaline pH-adjusting substance as an example, it can include NaHCO3 and Na2CO3. Adding NaHCO3 to a bioreactor will result in CO2 production, while adding Na2CO3 will result in the consumption of CO2 in the bioreactor. Factors affecting CO2 in the culture medium also include the direct introduction of CO2 into the bioreactor, which can adjust the pH of the culture medium.

[0036] See Figure 3 , Figure 3 This is a schematic diagram illustrating the CO2 removal method in the bioreactor provided in the embodiments of the invention. CO2 is mainly removed from the culture medium through gas exchange via oxygen or air bubbles introduced from the bottom, and then discharged from the liquid surface with the bubbles. It is understood that although air may sometimes be introduced to the liquid surface, its impact is small and can be directly ignored.

[0037] In this embodiment, a CO2 prediction model is created based on the CO2 generation and removal processes in a bioreactor. This model is used to predict the CO2 concentration in the bioreactor, and based on the CO2 concentration information, the CO2 partial pressure in the bioreactor can be determined, thus achieving the prediction of the CO2 partial pressure in the bioreactor. The size of the bioreactor is not limited here, enabling the prediction of CO2 partial pressure in cell culture scenarios with bioreactors of different sizes.

[0038] Based on the processes of CO2 generation and removal in a bioreactor, the influencing factors of CO2 within the bioreactor can be identified as one or more of the following: cellular aerobic respiration, the reaction process of pH-regulating substances, the reaction process of metabolites, and the direct introduction of CO2. Correspondingly, the parameters affecting CO2 within the bioreactor include one or more of the following: CO2 introduction rate, O2 concentration information within the bioreactor, O2 introduction rate, air introduction rate, pH-regulating substance input rate, and the rate of pre-set metabolite production during the biological reaction.

[0039] In this embodiment, a CO2 prediction model is created based on the equilibrium state of CO2 generation and CO2 removal rates within the bioreactor. Influence parameters of CO2 within the bioreactor are obtained, and the prediction model is used to predict CO2 information within the bioreactor based on these parameters. This CO2 information can be CO2 concentration information and / or CO2 partial pressure information.

[0040] In some embodiments, CO2 impact parameters within the bioreactor can be acquired periodically according to a prediction cycle to achieve periodic prediction of CO2 information within the bioreactor. In some embodiments, a prediction task is preset, which may include prediction time information, such as time information corresponding to different stages of cell culture. When prediction time information that meets the prediction task is detected, CO2 impact parameters within the bioreactor are acquired, and CO2 information within the bioreactor is predicted. In some embodiments, a prediction command input by a user is received, and in response to the prediction command, CO2 impact parameters within the bioreactor are acquired, and CO2 information within the bioreactor is predicted.

[0041] Optionally, the bioreactor may be equipped with a control console that controls the feeding and gas introduction into the bioreactor, specifically controlling the type of feed and the feed rate; or, controlling the type and rate of gas introduction, etc. For example, adding pH adjusting substances into the bioreactor, or introducing one or more gases such as air, O2, and CO2 into the bioreactor. The control console may include control buttons. In response to user operation of the control buttons, the control console receives and executes control commands. These control buttons may include, but are not limited to, buttons for selecting the type of feed and the type of gas introduced, buttons for adjusting the gas introduction rate, and buttons for adjusting the feed rate of materials. The control console can also be connected to other electronic devices (e.g., wired or wireless connection) to receive and execute control commands transmitted from other electronic devices.

[0042] The console can record feeding information and gas introduction information. For example, feeding information may include the type of substance and its feeding rate; gas introduction information may include the type of gas and its introduction rate. This feeding and gas introduction information can be timestamped and stored in a preset file or database. The feeding and gas introduction information can be read from the preset file or database. For example, the feeding rate of the pH adjusting substance, the CO2 introduction rate, the O2 introduction rate, and the air introduction rate can be read from the console's database.

[0043] Optionally, the console can also be configured with a display component, such as a display screen or a touch screen, to display feeding information and gas inlet information through the display interface of the display component, so that the user can read the displayed feeding information and gas inlet information.

[0044] The O2 concentration information in the bioreactor is a set specific value. The O2 concentration in the bubble is determined based on the O2 introduction rate and the air introduction rate. The oxygen content of the introduced air is 21%, and the oxygen content of the introduced oxygen is 100%. Accordingly, the O2 concentration information in the bubble is calculated based on the following formula: 100 / 21*(O2+0.21*air) / (O2+air), where O2 represents the O2 introduction rate and air represents the air introduction rate.

[0045] The production rate of a predetermined metabolite during a bioreactor reaction can be obtained by sampling and detecting the culture medium within the bioreactor. For example, this can be done through periodic sampling at predetermined intervals, recording the detection timestamp and the type and production rate of each detected metabolite. Among these metabolites, those that can affect CO2 information are identified as predetermined metabolites and marked. The production rate of the predetermined metabolite corresponding to the most recent timestamp is obtained for CO2 information prediction. Alternatively, sampling and detecting the culture medium within the bioreactor can be triggered before CO2 information prediction to obtain the production rate of the predetermined metabolite.

[0046] In some embodiments, the CO2 prediction model can be a machine learning model, such as a neural network model. This model is trained using sample data, which includes historical CO2 influence parameters from bioreactors of different sizes and the corresponding actual CO2 information. The CO2 influence parameters within the bioreactor are input into the pre-trained CO2 prediction model to obtain the CO2 information output by the model. This CO2 information can be CO2 concentration information and / or CO2 partial pressure information.

[0047] In some embodiments, the CO2 prediction model can be a mathematical model that characterizes the equilibrium state between the CO2 generation rate and the CO2 removal rate within the bioreactor, i.e., CO2 generation rate = CO2 removal rate. The CO2 generation rate can be understood as the total rate of CO2 production caused by multiple influencing factors within the bioreactor; the CO2 removal rate can be understood as... Figure 3 The rate of CO2 removal process is shown.

[0048] Optionally, the CO2 generation rate is determined based on the rate of change of CO2 caused by the CO2 influence parameters in the bioreactor; the CO2 influence parameters in the bioreactor include the CO2 generation parameters and the CO2 consumption parameters, and correspondingly, the CO2 change rate includes the CO2 generation rate and the CO2 consumption rate, where the CO2 generation rate is the rate of CO2 generation caused by the CO2 generation parameters, and the CO2 consumption rate is the rate of CO2 consumption caused by the CO2 consumption parameters.

[0049] Optionally, the parameters affecting CO2 production include the CO2 injection rate, O2 concentration information within the bioreactor, O2 injection rate, air injection rate, the input rate of the first substance in the pH adjustment medium, and the production rate of a preset metabolite. The CO2 production rate can be determined based on the CO2 sub-production rates corresponding to these parameters. The parameters affecting CO2 consumption include the input rate of the second substance in the pH adjustment medium; correspondingly, the CO2 consumption rate can be determined based on these parameters.

[0050] In this embodiment, the CO2 generation rate is determined by the difference between the CO2 generation rate and the CO2 consumption rate. Optionally, the CO2 consumption rate includes the CO2 consumption rate corresponding to the input rate of the second substance; specifically, based on the reaction process of the second substance generating CO2, the consumption-generation ratio of the second substance and CO2 can be determined. The consumption-generation ratio can be understood as the ratio between the amount of the second substance consumed and the amount of CO2 generated. Based on this ratio and the input rate of the second substance, the CO2 consumption rate can be determined. For example, the quotient of the input rate of the second substance and this ratio can be used as the CO2 consumption rate. Taking Na2CO3 as an example, one part of Na2CO3 can consume one part of CO2, that is, the consumption-generation ratio of Na2CO3 and CO2 is 1:1. Correspondingly, the CO2 consumption rate is the same as the input rate of Na2CO3. It can be understood that the second substance is one or more, and correspondingly, the total CO2 consumption rate is the sum of the CO2 consumption rates corresponding to one or more second substances.

[0051] Optionally, the CO2 production rate includes one or more of the following: a first CO2 production rate corresponding to aerobic respiration in the bioreactor, the first CO2 production rate being determined based on the oxygen mass transfer rate, wherein the oxygen mass transfer rate is determined based on O2 concentration information, O2 inlet rate, and air inlet rate; a second CO2 production rate corresponding to the reaction process of the preset metabolite, the second CO2 production rate being determined based on the production rate of the preset metabolite; a third CO2 production rate corresponding to the reaction process of the first substance, the third CO2 production rate being determined based on the input rate of the first substance; and the CO2 inlet rate.

[0052] The CO2 production rate can be the sum of one or more of the first CO2 production rate, the second CO2 production rate, the third CO2 production rate, and the CO2 introduction rate. It is understood that if no CO2 is introduced into the bioreactor, the CO2 introduction rate is zero; if no first substance is introduced into the bioreactor, the third CO2 production rate is zero, and so on. The CO2 production rate is determined based on the actual conditions of the bioreactor.

[0053] Based on the reaction process of aerobic respiration, the rate of first CO2 production is equal to the rate of oxygen mass transfer, that is, the rate of first CO2 production can be: kla O2 *([O2] * -[O2]), where kla O2 The mass transfer coefficient characterizes oxygen, and [O2] represents the O2 concentration information in the culture medium within the bioreactor. * Information characterizing the O2 concentration in bubbles within the bioreactor. Oxygen mass transfer coefficient Kla. O2 = k2*(P / V) a2 (Qs) b2P / V represents the power per unit volume, where P is the power of the bioreactor, which can be calculated from the stirring speed, and V is the volume of the culture medium in the bioreactor. Optionally, the parameters affecting CO2 also include the volume of the culture medium in the bioreactor and the stirring speed, with the bioreactor's power determined based on the stirring speed. The stirring speed is positively correlated with the bioreactor's power. Qs represents the aeration rate per unit liquid surface area, determined based on the total gas aeration rate. This can be based on the ratio of the total gas aeration rate to the liquid surface area of ​​the culture medium; for example, Qs could be the ratio of the sum of the aeration rates of air, CO2, and O2 to the liquid surface area of ​​the culture medium. k2, a2, and b2 are the second set of coefficients corresponding to the scale of the bioreactor, and are related to the scale of the bioreactor. Different scales of the bioreactor can correspond to different sets of second coefficients. Optionally, the second set of coefficients corresponding to any scale of the bioreactor can be obtained by fitting multiple sets of data at that scale. By setting different coefficient values ​​corresponding to different scales of bioreactors, CO2 information can be predicted in a targeted manner for bioreactor scenarios of different scales, thereby improving the accuracy of CO2 information prediction in bioreactor scenarios of different scales.

[0054] The second CO2 production rate can be understood as the sum of the CO2 generation rates corresponding to the reaction processes of at least one metabolite. Taking a preset metabolite including lactic acid and ammonium ions as an example, the first CO2 generation rate is determined based on the production rate of lactic acid, and the second CO2 generation rate is determined based on the production rate of ammonium ions. The sum of the first and second CO2 generation rates is then determined as the second CO2 production rate. For any metabolite, the ratio of metabolite consumption to CO2 production can be determined based on the reaction formula for CO2 generation from that metabolite. Based on the production rate of the metabolite and the above ratio, the corresponding CO2 generation rate of the metabolite can be determined.

[0055] Similarly, based on the reaction formula for CO2 generation from the first substance in the pH-regulating substance, the ratio of the consumption of the first substance to the CO2 generation can be determined. Based on the input rate of the first substance and the aforementioned ratio, the third CO2 generation rate can be determined. Taking NaHCO3 as the first substance as an example, consuming one part NaHCO3 produces one part CO2. Accordingly, the consumption-generation ratio of NaHCO3 to CO2 is 1:1, and the CO2 consumption rate is the same as the input rate of NaHCO3. It can be understood that the first substance can include one or more substances; correspondingly, the third CO2 generation rate can be the sum of the CO2 generation rates corresponding to one or more first substances.

[0056] During CO2 removal, the CO2 removal rate is based on the product of the CO2 mass transfer coefficient and the driving force. The driving force is the difference between the CO2 concentration in the culture medium of the bioreactor and the CO2 concentration inside the bubbles. Since the partial pressure of CO2 in the bubbles is approximately zero, the CO2 concentration inside the bubbles is ignored here. Accordingly, the CO2 removal rate is determined based on the CO2 concentration information and the CO2 mass transfer coefficient, i.e.:

[0057] kla CO2 *([CO2]-[CO2] * )=kla CO2 *[CO2], where kla CO2 The CO2 mass transfer coefficient is used to characterize CO2, and [CO2] represents the CO2 concentration information in the culture medium within the bioreactor. * This characterizes the CO2 concentration information within the bubbles. The CO2 mass transfer coefficient is determined based on a first set of coefficients corresponding to the total gas flow rate, power per unit volume, and the scale of the bioreactor, such as Kla. co2 =k1*(P / V) a1 (Qs) b1 Wherein, k1, a1, and b1 are the first set of coefficients corresponding to the scale of the bioreactor, which are related to the scale of the bioreactor; different scales of the bioreactor can correspond to different first sets of coefficients. Optionally, the first set of coefficients corresponding to any scale of the bioreactor can be obtained by fitting multiple sets of data at that scale.

[0058] The equilibrium state between CO2 generation rate and CO2 removal rate in a bioreactor, i.e., CO2 generation rate = CO2 removal rate, can be further characterized by CO2 generation rate = CO2 concentration information * CO2 mass transfer coefficient. A CO2 prediction model can be created based on the above equilibrium state.

[0059] Optionally, the CO2 prediction model includes the ratio between the CO2 generation rate and the CO2 mass transfer coefficient within the bioreactor.

[0060] In the above embodiments, CO2 concentration information of the bioreactor is obtained by predicting CO2 concentration based on the CO2 influence parameters in the bioreactor using a pre-created CO2 prediction model. This includes: determining the CO2 production rate and CO2 consumption rate based on the CO2 influence parameters in the bioreactor using the pre-created CO2 prediction model; determining the CO2 generation rate based on the difference between the CO2 production rate and the CO2 consumption rate; and determining the CO2 concentration information of the bioreactor based on the CO2 generation rate and the CO2 mass transfer coefficient.

[0061] Here, the CO2 generation rate includes multiple calculation items, which are CO2 change rate calculation items corresponding to the CO2 influence parameters within the bioreactor, i.e., at least one CO2 generation rate calculation item and / or at least one CO2 consumption rate calculation item. For example, the multiple calculation items for the CO2 generation rate include a CO2 consumption rate calculation item based on a second substance, a first CO2 generation rate calculation item, a second CO2 generation rate calculation item, a third CO2 generation rate calculation item, and a CO2 introduction rate calculation item.

[0062] The parameters affecting CO2 within the bioreactor are input into a CO2 prediction model. The CO2 generation rate is obtained through multiple calculation terms in the CO2 prediction model. The total gas aeration rate is acquired, and the aeration rate per unit liquid surface area is determined based on this rate. This aeration rate is then input into the CO2 mass transfer coefficient calculation term in the CO2 prediction model to obtain the CO2 mass transfer coefficient. The CO2 concentration in the culture medium within the bioreactor can be determined based on the ratio of the CO2 generation rate to the CO2 mass transfer coefficient. The CO2 partial pressure information can be determined based on the conversion relationship between CO2 concentration and CO2 partial pressure information; that is, the CO2 partial pressure information can be determined by comparing the CO2 concentration information with the Henry's coefficient. The Henry's coefficient is related to the temperature of the culture medium within the bioreactor; it is positively correlated with temperature, with a larger coefficient at higher temperatures. Optionally, the temperature of the culture medium within the bioreactor can also be included as a parameter affecting CO2. A pre-defined correspondence between temperature and the Henry's coefficient is established, and the Henry's coefficient is determined based on this correspondence. For example, the correspondence between temperature and the Henry's coefficient can be a curve showing the Henry's coefficient changing with temperature. The Henry's coefficient corresponding to the temperature of the culture medium within the bioreactor is determined from this curve. Alternatively, the correspondence can be a list of temperature and Henry's coefficients, containing multiple sets of temperature-Henry's coefficient data. The Henry's coefficient corresponding to the temperature of the culture medium within the bioreactor is read from this list. If the temperature of the culture medium within the bioreactor fails to match in the list, two neighboring temperatures are determined. These neighboring temperatures can include a first temperature greater than the temperature of the culture medium within the bioreactor and a second temperature less than the temperature of the culture medium within the bioreactor. The difference between the Henry's coefficients corresponding to the first and second temperatures is then calculated to obtain the Henry's coefficient corresponding to the temperature of the culture medium within the bioreactor.

[0063] Taking the pH-regulating substances introduced into the bioreactor, including NaHCO3 and Na2CO3, and the metabolites produced during cell culture, including lactic acid and ammonium ions, as an example, the equilibrium state between the CO2 generation rate and the CO2 elimination rate can be expressed as:

[0064] klaO2 *([O2] * -[O2])+NaHCO3(in)-Na2CO3(in)+H + (Lac+NH4 + )+CO2(in)=kla CO2 *[CO2]

[0065] Wherein, NaHCO3(in) represents the induction rate of NaHCO3, Na2CO3(in) represents the induction rate of Na2CO3, and H... + (Lac+NH4 + The rate of hydrogen ion production in a preset metabolite is represented by CO2(in), and the rate of CO2 introduction is represented by CO2(in). The rate of hydrogen ion production in a preset metabolite can be the sum of the rates of hydrogen ion production corresponding to at least one metabolite.

[0066] Accordingly, the CO2 prediction model can be expressed as: (k2*(P / V)) a2 (Qs) b2 ([O2)) * -[O2])+NaHCO3(in)-Na2CO3(in)+H + (Lac+NH4 + )+CO2(in)) / k1*(P / V) a1 (Qs) b1

[0067] It is known that the coefficients (k1, a1, b1, k2, a2, and b2) configured in the CO2 prediction model are determined based on the scale of the bioreactor. Optionally, these coefficients can be dynamically set during the CO2 prediction process for bioreactors of different scales; alternatively, different CO2 prediction models can be set for different bioreactor scales. Correspondingly, the corresponding CO2 prediction model is called based on the scale of the bioreactor, thus achieving accurate prediction of CO2 information for bioreactors of different scales.

[0068] The technical solution of this embodiment improves the comprehensiveness of CO2 influence parameters within the bioreactor by acquiring CO2 introduction rate, O2 concentration information within the bioreactor, O2 introduction rate, air introduction rate, pH adjustment substance input rate, and the pre-set metabolite production rate during the biological reaction as CO2 influence parameters. By setting a CO2 prediction model to predict these CO2 influence parameters, the prediction efficiency and accuracy of CO2 information can be improved.

[0069] Example 2

[0070] Figure 4This is a flowchart of a method for predicting CO2 information in a bioreactor according to an embodiment of the present invention. Based on the above embodiment, the bioreactor is controlled based on the predicted CO2 partial pressure information to adjust the CO2 partial pressure information in the bioreactor to meet the requirements of cell culture, i.e., preset CO2 partial pressure information. Figure 4 As shown, the method includes:

[0071] S210. Obtain the influence parameters of CO2 in the bioreactor, wherein the influence parameters include one or more of the following: CO2 introduction rate, O2 concentration information in the bioreactor, O2 introduction rate, air introduction rate, pH adjustment substance input rate, and the production rate of preset metabolites during the biological reaction.

[0072] S220. Using a pre-created CO2 prediction model, CO2 concentration is predicted based on parameters affecting CO2 in the bioreactor, thereby obtaining CO2 concentration information of the bioreactor.

[0073] S230. Determine the CO2 partial pressure information of the bioreactor based on the CO2 concentration information of the bioreactor.

[0074] S240. If the CO2 partial pressure information of the bioreactor does not meet the preset CO2 partial pressure information, adjust the aeration information of the bioreactor based on the preset CO2 partial pressure information. The aeration information includes one or more of the gas type introduced into the bioreactor and the introduction rate of the gas type.

[0075] In this embodiment, the preset CO2 partial pressure information can be understood as the standard CO2 partial pressure information required for cell culture within the bioreactor. Optionally, the preset CO2 partial pressure information required for bioreactors of different sizes can be different; alternatively, the preset CO2 partial pressure information required for different stages of cell culture within the bioreactor can be different.

[0076] The CO2 partial pressure information of the bioreactor is determined by setting a preset CO2 partial pressure information. If the CO2 partial pressure information of the bioreactor differs from the preset CO2 partial pressure information, it can be determined that the CO2 partial pressure information in the bioreactor needs to be adjusted. Alternatively, the difference between the CO2 partial pressure information of the bioreactor and the preset CO2 partial pressure information is determined. If the difference is greater than a preset threshold, it can be determined that the CO2 partial pressure information in the bioreactor needs to be adjusted.

[0077] If the CO2 partial pressure in the bioreactor is lower than the preset CO2 partial pressure, it indicates insufficient CO2 in the bioreactor, and the CO2 inlet rate can be increased for adjustment. For example, the CO2 inlet rate can be increased sequentially by a unit adjustment amount, and the CO2 partial pressure in the bioreactor can be predicted during the adjustment process until the CO2 partial pressure in the bioreactor meets the preset CO2 partial pressure, at which point the adjustment of the CO2 inlet rate can be stopped. Alternatively, a target CO2 inlet rate can be determined based on the preset CO2 partial pressure, and the bioreactor can be adjusted based on this target CO2 inlet rate. For example, an adjustment command carrying the target CO2 inlet rate can be generated and sent to the bioreactor or its control console to adjust the CO2 inlet rate.

[0078] Optionally, adjusting the aeration rate of the bioreactor based on the preset CO2 partial pressure information includes: when the CO2 partial pressure information of the bioreactor is less than the preset CO2 partial pressure information, determining the expected CO2 concentration information of the CO2 prediction model based on the preset CO2 partial pressure information; determining the target CO2 inlet rate corresponding to the expected CO2 concentration information through the CO2 prediction model; and adjusting the CO2 inlet rate of the bioreactor based on the target CO2 inlet rate.

[0079] In the CO2 prediction model, the CO2 injection rate is taken as the undetermined data, while other influencing parameters are kept. The preset CO2 partial pressure information is used as the expected CO2 concentration information and input into the CO2 prediction model to obtain the target CO2 injection rate corresponding to the preset CO2 partial pressure information.

[0080] For example, the target CO2 injection rate can be expressed as: k1*(P / V) a1 (Qs) b1 [CO2] 期望 -(k2*(P / V) a2 (Qs) b2 ([O2)) * -[O2])+NaHCO3(in)-Na2CO3(in)+H + (Lac+NH4 + ))

[0081] A CO2 partial pressure exceeding a preset CO2 partial pressure in a bioreactor indicates excess CO2 within the reactor, which can be addressed by reducing the CO2 introduction rate and / or accelerating the CO2 removal process. According to... Figure 3The schematic diagram illustrates the CO2 removal process. Increasing the air inlet rate can accelerate the CO2 removal rate. Optionally, the CO2 inlet rate can be decreased and / or the air inlet rate increased by a unit adjustment rate. During the adjustment of the gas inlet rate, the CO2 partial pressure information of the bioreactor is predicted until the CO2 partial pressure information of the bioreactor meets the preset CO2 partial pressure information, at which point the adjustment of the CO2 inlet rate and / or the air inlet rate is stopped. Optionally, the CO2 inlet rate is adjusted to zero, i.e., CO2 is stopped from being introduced into the bioreactor, and the air inlet rate is increased. During the sequential increase of the air inlet rate, the CO2 partial pressure information of the bioreactor is predicted until the CO2 partial pressure information of the bioreactor meets the preset CO2 partial pressure information, at which point the adjustment of the air inlet rate is stopped.

[0082] Optionally, the introduction rates of air, CO2, and O2 are determined based on preset CO2 partial pressure information, where the CO2 introduction rate can be zero. By adjusting the air and O2 introduction rates, the CO2 removal process is accelerated without affecting cellular responses. Specifically, "without affecting cellular responses" can be understood as maintaining a constant O2 mass transfer rate.

[0083] Adjusting the aeration rate of the bioreactor based on the preset CO2 partial pressure information includes: when the CO2 partial pressure information of the bioreactor is greater than the preset CO2 partial pressure information, determining the expected CO2 concentration information of the CO2 prediction model based on the preset CO2 partial pressure information; determining that the gas type introduced into the bioreactor includes air and oxygen, and determining the introduction ratio of the air and oxygen through the CO2 prediction model and the expected CO2 concentration information; controlling the CO2 introduction rate of the bioreactor to zero, and adjusting the air introduction rate and / or O2 introduction rate of the bioreactor based on the air and oxygen introduction ratio.

[0084] The preset CO2 partial pressure information is converted into the desired CO2 concentration information through the Henry coefficient. The CO2 injection rate is set to zero, while keeping other influencing parameters and the O2 mass transfer rate unchanged. The ventilation rate per unit liquid surface area Qs is used as the data to be determined. The desired CO2 concentration information is input into the CO2 prediction model to obtain the target ventilation rate per unit liquid surface area Qs corresponding to the preset CO2 partial pressure information.

[0085] For example, the process of determining the ventilation rate Qs per unit liquid surface area can be expressed as follows:

[0086] (Qs) 目标 b1 =(k2*(P / V)) a2 (Qs) b2 ([O2))* -[O2])+NaHCO3(in)-Na2CO3(in)+H + (Lac+NH4 + )+CO2(in)) / k1*(P / V) a1 [CO2] 期望

[0087] With the CO2 inlet rate set to zero, the target aeration rate per unit liquid surface area, Qs, is determined based on the introduced air and O2, i.e., Qs = (O2 + air) / S, where air represents the air inlet rate, O2 represents the O2 inlet rate, and S is the liquid surface area of ​​the culture medium in the bioreactor.

[0088] With the mass transfer rate of O2 remaining constant, OTR t0 =OTR t1 = k2*(P / V) a2 (Qs t1 ) b2 *([O2] *t1 -[O2]), where OTR t0 The OTR characterizes the mass transfer rate of O2 at time t0. t1 Qs represents the mass transfer rate of O2 at time t1. t1 Characterized by the aeration rate per unit liquid surface area at time t1, [O2]. *t1 This represents the O2 concentration information inside the bubble at time t1. Here, time t1 can be understood as the adjustment time for the bioreactor.

[0089] Based on the oxygen content of the air introduced into the bioreactor being 21% and the oxygen content being 100%, the O2 concentration information [O2] inside the bubbles is as follows. * =100 / 21*(O2+0.21*air) / (O2+air), where O2 represents the O2 introduction rate and air represents the air introduction rate.

[0090] Based on the constant O2 mass transfer rate and the target aeration rate per unit liquid surface area at time t1, the O2 concentration inside the bubble at time t1 can be determined. Based on the O2 concentration inside the bubble at time t1 and the calculation method of the O2 concentration inside the bubble, the ratio of air to oxygen can be determined.

[0091] Based on the target aeration rate per unit liquid surface area at time t1 and the liquid surface area of ​​the culture medium in the bioreactor, the total air and oxygen inlet rate can be determined. Based on the total air and oxygen inlet rate and the air-to-oxygen ratio, the air inlet rate and O2 inlet rate at time t1 can be determined, i.e., the target air inlet rate and target O2 inlet rate. The bioreactor is then adjusted based on the target air inlet rate and target O2 inlet rate. For example, adjustment commands carrying the target air inlet rate and target O2 inlet rate are generated and sent to the bioreactor or its control console to ensure that the CO2 partial pressure information within the bioreactor meets the preset CO2 partial pressure information.

[0092] The technical solution of this embodiment predicts the CO2 partial pressure information in the bioreactor and adjusts the aeration information of the bioreactor when the CO2 partial pressure information in the bioreactor does not meet the preset CO2 partial pressure information, so as to ensure that the CO2 partial pressure information in the bioreactor meets the preset CO2 partial pressure information, thereby ensuring that the CO2 partial pressure information in the bioreactor meets the requirements of cell culture and avoiding the adverse effects of CO2 partial pressure information on the cell culture process.

[0093] Example 3

[0094] Figure 5 This is a schematic diagram of the structure of a CO2 information prediction device in a bioreactor provided in an embodiment of the present invention. Figure 5 As shown, the device includes:

[0095] The parameter acquisition module 310 is used to acquire the influence parameters of CO2 in the bioreactor. The influence parameters include one or more of the following: CO2 introduction rate, O2 introduction rate, air introduction rate, pH adjustment substance input rate, and the production rate of preset metabolites during the biological reaction.

[0096] The CO2 concentration prediction module 320 is used to predict the CO2 concentration based on the influence parameters of CO2 in the bioreactor using a pre-created CO2 prediction model, and to obtain the CO2 concentration information of the bioreactor.

[0097] The CO2 partial pressure information determination module 330 is used to determine the CO2 partial pressure information of the bioreactor based on the CO2 concentration information of the bioreactor.

[0098] The technical solution of this embodiment improves the comprehensiveness of CO2 influence parameters within the bioreactor by acquiring CO2 introduction rate, O2 concentration information within the bioreactor, O2 introduction rate, air introduction rate, pH adjustment substance input rate, and the pre-set metabolite production rate during the biological reaction as CO2 influence parameters. By setting a CO2 prediction model to predict these CO2 influence parameters, the prediction efficiency and accuracy of CO2 information can be improved.

[0099] Based on the above embodiments, optionally, the CO2 prediction model characterizes the equilibrium state of CO2 generation rate and CO2 removal rate in the bioreactor; the CO2 generation rate is determined based on the rate of change of CO2 caused by the CO2 influence parameters in the bioreactor; the CO2 removal rate is determined based on the CO2 concentration information and the CO2 mass transfer coefficient.

[0100] Optionally, the CO2 prediction model includes the ratio between the CO2 generation rate and the CO2 mass transfer coefficient within the bioreactor.

[0101] Optionally, the rate of change of CO2 caused by the influencing parameters includes the CO2 production rate and the CO2 consumption rate;

[0102] The CO2 concentration information prediction module 320 is used to: determine the CO2 production rate and CO2 consumption rate based on the CO2 influence parameters in the bioreactor using the pre-created CO2 prediction model; determine the CO2 generation rate based on the difference between the CO2 production rate and the CO2 consumption rate; and determine the CO2 concentration information of the bioreactor based on the CO2 generation rate and the CO2 mass transfer coefficient.

[0103] Optionally, the pH adjusting substance includes a first substance that generates CO2 and / or a second substance that consumes CO2; the preset metabolite includes a CO2-consuming metabolite; and the CO2 consumption rate includes the CO2 consumption rate corresponding to the input rate of the second substance.

[0104] The CO2 production rate includes one or more of the following: a first CO2 production rate corresponding to aerobic respiration in the bioreactor, the first CO2 production rate being determined based on the O2 introduction rate, the air introduction rate, and the O2 concentration information in the bioreactor; a second CO2 production rate corresponding to the reaction process of the preset metabolite, the second CO2 production rate being determined based on the production rate of the preset metabolite; a third CO2 production rate corresponding to the reaction process of the first substance, the third CO2 production rate being determined based on the input rate of the first substance; and the CO2 introduction rate.

[0105] Optionally, the CO2 mass transfer coefficient is determined based on a first set of coefficients corresponding to the total gas flow rate, power per unit volume, and the scale of the bioreactor.

[0106] Based on the above embodiments, optionally, the device includes an adjustment module for adjusting the aeration rate information of the bioreactor based on the preset CO2 partial pressure information when the CO2 partial pressure information of the bioreactor does not meet the preset CO2 partial pressure information. The aeration rate information includes one or more of the gas type introduced into the bioreactor and the introduction rate of the gas type.

[0107] Optionally, the adjustment module is further configured to, when the CO2 partial pressure information of the bioreactor is less than the preset CO2 partial pressure information, determine the expected CO2 concentration information of the CO2 prediction model based on the preset CO2 partial pressure information; determine the target CO2 inlet rate corresponding to the expected CO2 concentration information through the CO2 prediction model; and adjust the CO2 inlet rate of the bioreactor based on the target CO2 inlet rate.

[0108] Optionally, the adjustment module is further configured to, when the CO2 partial pressure information of the bioreactor is greater than the preset CO2 partial pressure information, determine the expected CO2 concentration information of the CO2 prediction model based on the preset CO2 partial pressure information; determine that the gas type introduced into the bioreactor includes air and oxygen, and determine the introduction ratio of the air and the oxygen through the CO2 prediction model and the expected CO2 concentration information; control the CO2 introduction rate of the bioreactor to zero, and adjust the air introduction rate and / or O2 introduction rate of the bioreactor based on the air and oxygen introduction ratio.

[0109] The CO2 information prediction device in the bioreactor provided in the embodiments of the present invention can execute the CO2 information prediction method in the bioreactor provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0110] Example 4

[0111] Figure 6This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0112] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0113] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0114] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing unit (CPU), graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as methods for predicting CO2 information in a bioreactor.

[0115] In some embodiments, the method for predicting CO2 information in a bioreactor may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for predicting CO2 information in a bioreactor described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the method for predicting CO2 information in a bioreactor by any other suitable means (e.g., by means of firmware).

[0116] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0117] Computer programs for implementing the method for predicting CO2 information in a bioreactor according to the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0118] Example 5

[0119] Embodiment 5 of the present invention also provides a computer-readable storage medium storing computer instructions for causing a processor to execute a method for predicting CO2 information in a bioreactor, the method comprising:

[0120] The parameters affecting CO2 in the bioreactor are obtained, including one or more of the following: CO2 introduction rate, O2 concentration information in the bioreactor, pH adjustment substance input rate, and the production rate of preset metabolites during the biological reaction. Based on the parameters affecting CO2 in the bioreactor, a pre-created CO2 prediction model is used to predict the CO2 concentration, thus obtaining the CO2 concentration information of the bioreactor. The CO2 partial pressure information of the bioreactor is then determined based on the CO2 concentration information.

[0121] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0122] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0123] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0124] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0125] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0126] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for predicting CO2 information in a bioreactor, characterized in that, include: Obtain the parameters affecting CO2 in the bioreactor, including one or more of the following: CO2 introduction rate, O2 concentration information in the bioreactor, O2 introduction rate, air introduction rate, pH adjustment substance input rate, and the production rate of preset metabolites during the biological reaction. By using a pre-created CO2 prediction model, the CO2 concentration is predicted based on the parameters affecting CO2 in the bioreactor, thus obtaining the CO2 concentration information of the bioreactor. The CO2 partial pressure information of the bioreactor is determined based on the CO2 concentration information of the bioreactor.

2. The method according to claim 1, characterized in that, The CO2 prediction model characterizes the equilibrium state of CO2 generation rate and CO2 removal rate within the bioreactor; the CO2 generation rate is determined based on the rate of change of CO2 caused by the CO2 influence parameters within the bioreactor; the CO2 removal rate is determined based on the CO2 concentration information and the CO2 mass transfer coefficient.

3. The method according to claim 2, characterized in that, The CO2 prediction model includes the ratio between the CO2 generation rate and the CO2 mass transfer coefficient within the bioreactor.

4. The method according to claim 2, characterized in that, The rate of change of CO2 caused by the influencing parameters includes the CO2 production rate and the CO2 consumption rate; By using a pre-created CO2 prediction model, CO2 concentration is predicted based on parameters affecting CO2 within the bioreactor, resulting in CO2 concentration information for the bioreactor, including: Using the pre-created CO2 prediction model, the CO2 production rate and CO2 consumption rate are determined based on the CO2 influence parameters within the bioreactor. The CO2 generation rate is determined based on the difference between the CO2 production rate and the CO2 consumption rate. The CO2 concentration information of the bioreactor is determined based on the CO2 generation rate and the CO2 mass transfer coefficient.

5. The method according to claim 4, characterized in that, The pH adjusting substance includes a first substance that generates CO2 and / or a second substance that consumes CO2; The CO2 consumption rate includes the CO2 consumption rate corresponding to the input rate of the second substance; The CO2 production rate includes one or more of the following: The first CO2 production rate corresponding to aerobic respiration in the bioreactor is determined by the O2 concentration information, the O2 introduction rate, and the air introduction rate. The second CO2 production rate corresponding to the reaction process of the preset metabolite is determined based on the production rate of the preset metabolite. The third CO2 production rate corresponding to the reaction process of the first substance is determined based on the input rate of the first substance. The CO2 inlet rate.

6. The method according to claim 2, characterized in that, The CO2 mass transfer coefficient is determined based on the total gas flow rate, power per unit volume, and a first set of coefficients corresponding to the size of the bioreactor.

7. The method according to claim 1, characterized in that, The method further includes: If the CO2 partial pressure information of the bioreactor does not meet the preset CO2 partial pressure information, the aeration information of the bioreactor is adjusted based on the preset CO2 partial pressure information. The aeration information includes one or more of the gas type introduced into the bioreactor and the introduction rate of the gas type.

8. The method according to claim 7, characterized in that, Adjusting the aeration rate of the bioreactor based on the preset CO2 partial pressure information includes: If the CO2 partial pressure information of the bioreactor is less than the preset CO2 partial pressure information, the preset CO2 partial pressure information is used to determine the expected CO2 concentration information of the CO2 prediction model; the target CO2 injection rate corresponding to the expected CO2 concentration information is determined by the CO2 prediction model. The CO2 inlet rate of the bioreactor is adjusted based on the target CO2 inlet rate.

9. The method according to claim 7, characterized in that, Adjusting the aeration rate of the bioreactor based on the preset CO2 partial pressure information includes: If the CO2 partial pressure information of the bioreactor is greater than the preset CO2 partial pressure information, the preset CO2 partial pressure information is used to determine the expected CO2 concentration information of the CO2 prediction model. The types of gases introduced into the bioreactor are determined to include air and oxygen. The ratio of air to O2 introduced is determined using the CO2 prediction model and the expected CO2 concentration information. The CO2 inlet rate of the bioreactor is controlled to be zero, and the air inlet rate and / or O2 inlet rate of the bioreactor are adjusted based on the ratio of air to O2.

10. A device for predicting CO2 information in a bioreactor, characterized in that, include: The parameter acquisition module is used to acquire the influence parameters of CO2 in the bioreactor. The influence parameters include one or more of the following: CO2 introduction rate, O2 concentration information in the bioreactor, O2 introduction rate, air introduction rate, pH adjustment substance input rate, and the production rate of preset metabolites during the biological reaction. The CO2 concentration information prediction module is used to predict the CO2 concentration based on the parameters affecting CO2 in the bioreactor using a pre-created CO2 prediction model, thereby obtaining the CO2 concentration information of the bioreactor. The CO2 partial pressure information determination module is used to determine the CO2 partial pressure information of the bioreactor based on the CO2 concentration information of the bioreactor.

11. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, which enables the at least one processor to perform the method for predicting CO2 information in a bioreactor according to any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for predicting CO2 information in a bioreactor as described in any one of claims 1-9.

Images