Microbial fermentation optimization method based on data analysis model
By deploying a variety of sensors and data processing units in microbial fermentation tanks, building growth environment and dynamic models, and adjusting operating parameters using particle swarm optimization algorithms, the problem of microbial fermentation optimization in traditional methods is solved, and efficient and stable microbial fermentation is achieved. Improved process and product quality.
Patent Information
- Application Number
- CN202411065848.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-05
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-08-05
AI Technical Summary
Traditional microbial fermentation optimization methods rely on experience accumulation and trial and error exploration, making it difficult to accurately control fermentation conditions and maximize microbial growth rate, resulting in difficult to stably improve production efficiency and product quality.
Using a microbial fermentation optimization method based on data analysis model, the fermentation parameters are monitored in real time by deploying temperature sensors, pH sensors, oxygen concentration monitors and nutrient concentration monitors, and the growth environment simulation field and growth rate dynamics are constructed using data processing units. Field, establish an environmental constraint-growth and metabolism data analysis model, and use particle swarm optimization algorithm to adjust operating parameters to optimize the fermentation process.
Accurate control of the microbial fermentation process is achieved, production efficiency and product quality are improved, resource waste and production costs are reduced, and the stability of the fermentation process and output optimization are ensured.
Smart Images

Figure CN119028423A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of microbial data analysis, and in particular to a microbial fermentation optimization method based on a data analysis model. Background Art
[0002] With the development of data science and artificial intelligence technology, data analysis models based on new technologies have become key tools for realizing the intelligence and optimization of microbial fermentation processes, thus bringing important innovations and progress to improving fermentation efficiency and product quality. By introducing online monitoring and sensor equipment to monitor the parameters of microbial fermentation tanks in real time, key parameters in the fermentation process, such as temperature, pH value, dissolved oxygen content, nutrient concentration, etc., can be collected in real time. These data are transmitted to the central database and optimized by building corresponding data analysis models. The dynamic changes of the fermentation process can be monitored in real time, so that potential optimization space and risk factors can be identified. In addition, by combining machine learning and optimization algorithms to train and build models for the fermentation parameter data obtained from real-time monitoring, the optimal operating conditions in the fermentation process can be predicted and optimized. Optimization algorithms (such as genetic algorithms, particle swarm algorithms, etc.) can automatically adjust fermentation parameters through iterative optimization to achieve maximum yield, optimal energy efficiency and stable product quality. However, traditional microbial fermentation optimization methods rely on experience accumulation and trial and error exploration, and it is difficult to accurately control fermentation conditions and maximize microbial growth rate. Summary of the invention
[0003] Based on this, it is necessary for the present invention to provide a microbial fermentation optimization method based on a data analysis model to solve at least one of the above technical problems.
[0004] To achieve the above object, a microbial fermentation optimization method based on a data analysis model comprises the following steps:
[0005] Step S1: deploying a temperature sensor, a pH sensor, an oxygen concentration monitor, a nutrient concentration monitor and a data processing unit in a microbial fermentation tank, and using the temperature sensor, the pH sensor, the oxygen concentration monitor and the nutrient concentration monitor to monitor the fermentation parameters of the microbial fermentation process in the microbial fermentation tank in real time, so as to obtain real-time temperature data of microbial fermentation, real-time pH data of microbial fermentation, real-time oxygen concentration data of microbial fermentation and real-time nutrient concentration data of microbial fermentation; transmitting the real-time temperature data of microbial fermentation, the real-time pH data of microbial fermentation, the real-time oxygen concentration data of microbial fermentation and the real-time nutrient concentration data of microbial fermentation to the data processing unit through a network connection;
[0006] Step S2: performing fermentation growth environment simulation analysis on the real-time temperature data of microbial fermentation and the real-time pH value data of microbial fermentation through a data processing unit to generate a real-time growth environment simulation field of microbial fermentation; performing fermentation growth dynamic field setting on the real-time oxygen concentration data of microbial fermentation and the real-time nutrient concentration data of microbial fermentation to generate a real-time growth rate dynamic field of microbial fermentation;
[0007] Step S3: performing fermentation growth metabolism analysis modeling on the microbial fermentation process in the microbial fermentation tank based on the microbial fermentation real-time growth environment simulation field and the microbial fermentation real-time growth rate dynamic field, so as to construct a microbial fermentation environment constraint-growth metabolism data analysis model;
[0008] Step S4: Based on the microbial fermentation environmental constraint-growth metabolism data analysis model, the microbial fermentation process in the microbial fermentation tank is subjected to microbial fermentation optimization processing to obtain a microbial fermentation growth metabolism target optimization result.
[0009] Further, step S1 includes the following steps:
[0010] Step S11: designing a sensor network layout scheme in the microbial fermentation tank according to the network monitoring coverage corresponding to the temperature sensor, the pH sensor, the oxygen concentration monitor, the nutrient concentration monitor, and the data processing unit, and deploying the temperature sensor, the pH sensor, the oxygen concentration monitor, the nutrient concentration monitor, and the data processing unit in the microbial fermentation tank based on the sensor network layout scheme;
[0011] Step S12: using a temperature sensor to monitor the fermentation temperature of the microbial fermentation process in the microbial fermentation tank in real time to obtain real-time temperature data of the microbial fermentation;
[0012] Step S13: using a pH sensor to monitor the fermentation pH value of the microbial fermentation process in the microbial fermentation tank in real time to obtain real-time pH value data of the microbial fermentation;
[0013] Step S14: using an oxygen concentration monitor to monitor the fermentation oxygen concentration of the microbial fermentation process in the microbial fermentation tank in real time to obtain real-time oxygen concentration data of the microbial fermentation;
[0014] Step S15: using a nutrient concentration monitor to monitor the fermentation nutrient concentration of the microbial fermentation process in the microbial fermentation tank in real time, so as to obtain real-time nutrient concentration data of the microbial fermentation;
[0015] Step S16: transmitting the real-time temperature data of microbial fermentation, the real-time pH value data of microbial fermentation, the real-time oxygen concentration data of microbial fermentation and the real-time nutrient concentration data of microbial fermentation to the data processing unit via a network connection.
[0016] Further, step S2 includes the following steps:
[0017] Step S21: performing time series synchronization processing on the real-time temperature data of microbial fermentation and the real-time pH value data of microbial fermentation by a data processing unit to obtain time series synchronization data of microbial fermentation temperature and time series synchronization data of microbial fermentation pH value;
[0018] Step S22: performing microbial environment temperature modeling analysis on the microbial fermentation temperature time series synchronization data to generate a microbial fermentation environment temperature time series change simulation field;
[0019] Step S23: performing a microbial environment pH dynamic simulation analysis on the microbial fermentation pH value time series synchronization data to generate a microbial fermentation environment pH value time series change simulation field;
[0020] Step S24: performing a coupled analysis of the rhythmic influence of the growth environment according to the microbial fermentation environment temperature time series variation simulation field and the microbial fermentation environment pH value time series variation simulation field to generate a microbial fermentation real-time growth environment simulation field;
[0021] Step S25: setting the fermentation growth dynamic field for the real-time oxygen concentration data of microbial fermentation and the real-time nutrient concentration data of microbial fermentation to generate the real-time growth rate dynamic field of microbial fermentation.
[0022] Further, step S24 includes the following steps:
[0023] Step S241: performing frequency domain change conversion processing on the microbial fermentation environment temperature time series change simulation field and the microbial fermentation environment pH value time series change simulation field to obtain the microbial fermentation temperature frequency domain change simulation field and the microbial fermentation pH value frequency domain change simulation field;
[0024] Step S242: performing rhythmic frequency analysis on the microbial fermentation temperature frequency domain variation simulation field and the microbial fermentation pH value frequency domain variation simulation field to obtain the microbial fermentation temperature rhythmic frequency and the microbial fermentation pH value rhythmic frequency;
[0025] Step S243: performing a temperature frequency domain rhythmic fluctuation analysis on the microbial fermentation temperature frequency domain change simulation field based on the microbial fermentation temperature rhythmic frequency to obtain a microbial fermentation temperature frequency domain rhythmic fluctuation change relationship;
[0026] Step S244: performing a pH value frequency domain rhythmic fluctuation analysis on the pH value frequency domain change simulation field of the microbial fermentation based on the pH value rhythmic frequency of the microbial fermentation to obtain a pH value frequency domain rhythmic fluctuation change relationship of the microbial fermentation;
[0027] Step S245: Based on the relationship between the rhythmic fluctuations in the frequency domain of microbial fermentation temperature and the rhythmic fluctuations in the frequency domain of microbial fermentation pH value, a coupling analysis of the rhythmic influence of the growth environment is performed on the simulation field of the frequency domain change of microbial fermentation temperature and the simulation field of the frequency domain change of microbial fermentation pH value to generate a real-time growth environment simulation field for microbial fermentation.
[0028] Further, step S245 includes the following steps:
[0029] The frequency domain rhythmic fluctuation relationship of microbial fermentation temperature and the frequency domain rhythmic fluctuation relationship of microbial fermentation pH value were analyzed by frequency domain rhythmic synchronization interaction mining, and the frequency domain rhythmic synchronization interaction relationship of microbial temperature-pH was obtained.
[0030] The frequency domain rhythmic interaction effect pattern recognition analysis was performed on the frequency domain rhythmic synchronization interaction relationship of microbial temperature and pH to obtain the frequency domain rhythmic change interaction effect pattern of microbial temperature and pH.
[0031] Based on the interactive effect model of microbial temperature-pH frequency domain rhythmic changes, the rhythmic phase influence constraint analysis of the microbial fermentation temperature frequency domain change simulation field and the microbial fermentation pH value frequency domain change simulation field is performed to generate the microbial fermentation temperature frequency domain rhythmic phase influence constraint and the microbial fermentation pH value frequency domain rhythmic phase influence constraint;
[0032] According to the frequency domain rhythmic phase influence constraint of the microbial fermentation temperature, the temperature frequency domain phase of the microbial fermentation temperature frequency domain change simulation field is dynamically adjusted to obtain the microbial temperature frequency domain phase dynamic adjustment simulation field; according to the frequency domain rhythmic phase influence constraint of the microbial fermentation pH value, the pH frequency domain phase of the microbial fermentation pH value frequency domain change simulation field is dynamically adjusted to obtain the microbial pH value frequency domain phase dynamic adjustment simulation field;
[0033] The real-time growth environment simulation coupling processing is performed on the microbial temperature frequency domain phase dynamic adjustment simulation field and the microbial pH value frequency domain phase dynamic adjustment simulation field to generate a real-time growth environment simulation field for microbial fermentation.
[0034] Further, step S25 includes the following steps:
[0035] Step S251: plotting concentration change curves for the real-time oxygen concentration data of microbial fermentation and the real-time nutrient concentration data of microbial fermentation to generate a microbial fermentation oxygen concentration change curve and a microbial fermentation nutrient concentration change curve;
[0036] Step S252: performing a statistical analysis of dissolved oxygen on the oxygen concentration variation curve of the microbial fermentation to obtain the real-time dissolved oxygen in the microbial fermentation process; performing a statistical analysis of nutrient consumption on the nutrient concentration variation curve of the microbial fermentation to obtain the real-time nutrient consumption in the microbial fermentation process;
[0037] Step S253: performing a microbial growth rate prediction analysis on the corresponding microbial fermentation process according to the real-time dissolved oxygen amount and the real-time consumption of nutrients in the microbial fermentation process, so as to obtain the real-time growth rate of the microbial fermentation process;
[0038] Step S254: performing a growth rate mass transfer kinetic analysis on the real-time growth rate of the microbial fermentation process to obtain the real-time growth rate mass transfer kinetic parameters of the microbial fermentation;
[0039] Step S255: Based on the mass transfer kinetic parameters of the real-time growth rate of microbial fermentation, the fermentation growth kinetic field of the corresponding microbial fermentation process is set to generate the real-time growth rate kinetic field of microbial fermentation.
[0040] Further, step S255 includes the following steps:
[0041] The microbial fermentation process is divided into growth stages to obtain the fermentation process of microorganisms in different growth stages;
[0042] Based on the real-time growth rate mass transfer kinetic parameters of microbial fermentation, the fermentation mass transfer dynamic process of microorganisms in different growth stages is simulated and analyzed to obtain the biomass transfer kinetic simulation process of microbial fermentation in different growth stages;
[0043] The mass transfer dynamics field fusion setting is performed on the biomass transfer dynamics simulation process in different growth stages of the microbial fermentation process to generate the real-time mass transfer dynamics field of microbial fermentation;
[0044] Based on the real-time mass transfer dynamic field of microbial fermentation, the growth rate dynamic response simulation of the corresponding microbial fermentation process is carried out to generate the real-time growth rate dynamic field of microbial fermentation.
[0045] Further, step S3 includes the following steps:
[0046] Step S31: performing population growth environment condition optimization analysis on the corresponding microbial fermentation process in the microbial fermentation tank based on the microbial fermentation real-time growth environment simulation field to obtain the optimal growth environment conditions of different microbial populations in the microbial fermentation process;
[0047] Step S32: performing growth environment metabolic impact constraint analysis on the optimal growth environment conditions of different microbial populations during the microbial fermentation process to obtain growth environment metabolic impact constraint targets of different microbial populations;
[0048] Step S33: performing population growth metabolic kinetics characteristic analysis on the corresponding microbial fermentation process in the microbial fermentation tank based on the real-time growth rate kinetics field of microbial fermentation to obtain growth metabolic kinetics characteristic data of different microbial populations;
[0049] Step S34: establishing an environmental constraint analysis mathematical equation for the growth metabolic kinetic characteristic data of different microbial populations based on the growth environment metabolic impact constraint targets of different microbial populations, so as to generate a microbial population fermentation environment constraint-growth metabolic data analysis mathematical equation;
[0050] Step S35: Perform fermentation growth metabolism analysis modeling processing according to the microbial population fermentation environment constraint-growth metabolism data analysis mathematical equation to construct a microbial fermentation environment constraint-growth metabolism data analysis model.
[0051] Further, step S31 includes the following steps:
[0052] Based on the real-time growth environment simulation field of microbial fermentation, the population growth environment conditions of the corresponding microbial fermentation process in the microbial fermentation tank are simulated and set to obtain different initial simulation conditions for the growth environment set for each microbial population;
[0053] Perform spatial distribution analysis of microbial populations on the corresponding microbial fermentation process in the microbial fermentation tank to obtain the growth spatial distribution position of each microbial population;
[0054] By performing population growth position distribution density analysis on the growth space distribution position corresponding to each microbial population under different growth environment initial simulation conditions set for each microbial population, the microbial distribution density at the corresponding growth space position of each microbial population under different growth environment conditions is obtained;
[0055] Based on the microbial distribution density at the corresponding growth space position of each microbial population under different growth environment conditions, the corresponding initial simulation conditions of the growth environment are quantitatively calculated to obtain the growth environment preference value of each microbial population under different growth environment conditions;
[0056] According to the growth environment preference value of each microbial population under different growth environment conditions, the different growth environment initial simulation conditions set for each microbial population are subjected to optimal screening of growth environment conditions to obtain the optimal growth environment conditions for different microbial populations during the microbial fermentation process.
[0057] Further, step S4 includes the following steps:
[0058] Step S41: Based on the microbial fermentation environment constraint-growth metabolism data analysis model, a particle swarm optimization algorithm is used to optimize and analyze the growth environment parameters of the microbial fermentation process in the microbial fermentation tank to obtain the best optimization results of the microbial fermentation growth environment parameters;
[0059] Step S42: performing fermentation growth and metabolic target analysis on the microbial fermentation process in the microbial fermentation tank to obtain the growth and metabolic target of the microbial fermentation process;
[0060] Step S43: Based on the optimal optimization result of the microbial fermentation growth environment parameters, the nutrient supplementation strategy and metabolic pathway optimization analysis of the microbial fermentation process in the microbial fermentation tank are performed to generate a microbial fermentation nutrient supplementation strategy optimization plan and a microbial fermentation metabolic pathway optimization plan;
[0061] Step S44: performing microbial fermentation optimization processing on the growth metabolic target of the microbial fermentation process according to the microbial fermentation nutrient supplementation strategy optimization scheme and the microbial fermentation metabolic pathway optimization scheme to obtain the microbial fermentation growth metabolic target optimization result.
[0062] Beneficial effects of the present invention:
[0063] Compared with the prior art, the microbial fermentation optimization method based on the data analysis model proposed in the present invention has the beneficial effect of comprehensively monitoring and controlling the key parameters in the microbial fermentation process by deploying multiple sensors in the microbial fermentation tank and designing a reasonable network monitoring layout, wherein the temperature sensor is responsible for real-time monitoring of the temperature changes in the fermentation tank to ensure the maintenance of suitable biological reaction conditions; the pH sensor monitors the acidity and alkalinity of the solution, which is key to controlling the stability of the microbial growth environment; the oxygen concentration monitor is used to track the oxygen level in the fermentation liquid, affecting the metabolic process of the microorganism; the nutrient concentration monitor monitors the concentration changes of nutrients in the fermentation liquid to ensure that the microorganisms have sufficient nutrients to proliferate and produce target products. These sensors, through the joint action of the data processing unit, construct a comprehensive monitoring network, aiming to improve production efficiency and product quality, and reduce resource waste and production costs. At the same time, the real-time temperature data, pH value data, oxygen concentration data and nutrient concentration data of the microbial fermentation obtained above are transmitted to the data processing unit through a network connection. The data processing unit is responsible for analyzing and processing these data, and can provide the operator with real-time fermentation process status and trend analysis. Through the monitoring and analysis of real-time data, potential problems can be discovered in time and necessary measures can be taken to ensure the stability of the fermentation process and the optimization of production. Secondly, the real-time temperature data and the real-time pH value data of microbial fermentation are simulated and analyzed by the data processing unit. This process aims to use statistical analysis and mathematical modeling to couple the time series data of environmental temperature and pH value with the growth environment, and explore their interaction in time and space. Through this coupled simulation analysis, the relationship between temperature and pH changes in the fermentation process and their impact on the growth rhythm of microorganisms can be revealed, and the corresponding growth environment simulation field can be coupled to generate, thereby providing a scientific basis for optimizing fermentation conditions and increasing production. The fermentation growth dynamic field is also set by setting the real-time oxygen concentration data and real-time nutrient concentration data of microbial fermentation. This step involves establishing the growth rate dynamic field of microbial fermentation based on the real-time monitored oxygen concentration and nutrient concentration data. The precise setting of these data can directly affect the growth rate of microorganisms and the output of the final product, providing important operational guidance and precise fermentation condition control means for achieving efficient fermentation process. Then, the corresponding microbial fermentation process in the microbial fermentation tank is modeled and processed based on the real-time growth environment simulation field of microbial fermentation and the real-time growth rate dynamic field of microbial fermentation to construct a comprehensive microbial fermentation environmental constraint-growth metabolism data analysis model. This model can not only predict the growth behavior of microorganisms under different environmental conditions, but also optimize the control strategy of the fermentation process to ensure that microorganisms operate efficiently and produce target products in complex environments.Through these steps, more precise microbial fermentation process control can be achieved in microbial fermentation production, thereby improving production efficiency and economic benefits, and promoting the further development and application of bioprocess technology. Finally, the microbial fermentation process in the microbial fermentation tank is optimized based on the microbial fermentation environmental constraint-growth metabolism data analysis model, which includes using the previously constructed data analysis model to adjust the operating parameters and control strategies in the microbial fermentation process to achieve the expected growth and metabolic goals. Through this step, the microbial fermentation process can achieve the maximum microbial growth rate and the best quality product production, thereby improving the efficiency and economic benefits of microbial fermentation industrial production. BRIEF DESCRIPTION OF THE DRAWINGS
[0064] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:
[0065] Figure 1 It is a schematic diagram of the steps of the microbial fermentation optimization method based on the data analysis model of the present invention;
[0066] Figure 2 for Figure 1 Detailed step flow diagram of step S1;
[0067] Figure 3 for Figure 1 Detailed step flow chart of step S2 in FIG. DETAILED DESCRIPTION
[0068] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.
[0069] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.
[0070] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.
[0071] To achieve this, please refer to Figures 1 to 3 The present invention provides a method for optimizing microbial fermentation based on a data analysis model. In the embodiments of the present invention, please refer to Figure 1 FIG. 1 is a schematic diagram of the steps of the microbial fermentation optimization method based on the data analysis model of the present invention, and the microbial fermentation optimization method based on the data analysis model comprises the following steps:
[0072] Step S1: deploying a temperature sensor, a pH sensor, an oxygen concentration monitor, a nutrient concentration monitor and a data processing unit in a microbial fermentation tank, and using the temperature sensor, the pH sensor, the oxygen concentration monitor and the nutrient concentration monitor to monitor the fermentation parameters of the microbial fermentation process in the microbial fermentation tank in real time, so as to obtain real-time temperature data of microbial fermentation, real-time pH data of microbial fermentation, real-time oxygen concentration data of microbial fermentation and real-time nutrient concentration data of microbial fermentation; transmitting the real-time temperature data of microbial fermentation, the real-time pH data of microbial fermentation, the real-time oxygen concentration data of microbial fermentation and the real-time nutrient concentration data of microbial fermentation to the data processing unit through a network connection;
[0073] In an embodiment of the present invention, an effective sensor network layout scheme is designed according to the specific size, shape and expected monitoring requirements of the microbial fermentation tank. This scheme needs to take into account the monitoring range, sensitivity and possibility of mutual interference of different sensors, so as to determine the optimal layout position of the sensor to deploy the corresponding temperature sensor, pH sensor, oxygen concentration monitor, nutrient concentration monitor and data processing unit. For example, the temperature sensor can be installed at the top and bottom of the tank to capture the temperature gradient of the fermentation liquid; the pH sensor is installed at the center of the liquid to ensure uniform monitoring of the pH value change of the fermentation liquid; the oxygen concentration monitor is installed next to the vent to ensure accurate measurement of the oxygen supply during the fermentation process; the nutrient concentration monitor is arranged according to the input point of the nutrient to fully understand the changes in the nutrients in the fermentation liquid. At the same time, the data processing unit is deployed on the surface of the microbial fermentation tank, and the temperature sensor, pH sensor, oxygen concentration monitor and nutrient concentration monitor are electrically connected to the data processing unit so that the data processing unit analyzes and processes the microbial fermentation process parameters obtained by real-time monitoring. The temperature of the corresponding microbial fermentation process in the microbial fermentation tank is also monitored in real time by using the previously deployed temperature sensor to monitor the temperature change in the microbial fermentation tank in real time, the pH sensor monitors the pH change in the microbial fermentation tank in real time, the oxygen concentration monitor accurately measures the concentration of dissolved oxygen in the microbial fermentation liquid in real time, and the nutrient concentration monitor (for example, a sensor for specific nutrients (such as sugars, nitrogen sources, minerals, etc.)) measures the concentration of target nutrients in the fermentation liquid in real time, thereby obtaining real-time temperature data of microbial fermentation, real-time pH data of microbial fermentation, real-time oxygen concentration data of microbial fermentation, and real-time nutrient concentration data of microbial fermentation. Then, the real-time temperature data of microbial fermentation, real-time pH data of microbial fermentation, real-time oxygen concentration data of microbial fermentation, and real-time nutrient concentration data of microbial fermentation obtained by the previous real-time monitoring of each sensor are transmitted to the data processing unit on the microbial fermentation tank by using a network connection method, so as to optimize the setting of microbial fermentation parameters.
[0074] Step S2: performing fermentation growth environment simulation analysis on the real-time temperature data of microbial fermentation and the real-time pH value data of microbial fermentation through a data processing unit to generate a real-time growth environment simulation field of microbial fermentation; performing fermentation growth dynamic field setting on the real-time oxygen concentration data of microbial fermentation and the real-time nutrient concentration data of microbial fermentation to generate a real-time growth rate dynamic field of microbial fermentation;
[0075] In an embodiment of the present invention, a data processing unit is used to simulate and analyze the growth environment of the transmitted real-time temperature data of microbial fermentation and the real-time pH data of microbial fermentation, so as to integrate and compare the temporal changes of temperature and pH value, and analyze the interaction and influence of temperature and pH value changes on the microbial growth process, thereby coupling and simulating the corresponding real-time growth environment simulation field of microbial fermentation. Then, by using the corresponding data visualization tools, the previously collected real-time oxygen concentration data of microbial fermentation and the real-time nutrient concentration data of microbial fermentation are plotted to draw the corresponding concentration change curves. These curves usually take time as the horizontal axis and concentration as the vertical axis to show the changing trends of relevant parameters in different stages, and by using mathematical statistical methods to statistically calculate the dissolved oxygen amount and the real-time consumption of nutrients in the microbial fermentation process, and at the same time, by combining the previously statistically calculated real-time dissolved oxygen amount and real-time consumption of nutrients, the growth rate of microorganisms under current environmental conditions is inferred, so as to describe the growth rate of microorganisms by selecting appropriate mathematical models. Commonly used models include Monod model, Logistic model, etc. These models can predict the growth rate of microorganisms according to the changes in dissolved oxygen amount and nutrient consumption. The real-time growth rate of the microbial fermentation process previously predicted in real time is also analyzed by selecting an appropriate mass transfer kinetic model to dynamically simulate and establish the corresponding mass transfer dynamic field, and perform real-time dynamic response simulation of the microbial fermentation process, which includes predicting the growth curve of microorganisms, the accumulation of metabolites and the influence of reaction conditions on microbial growth at different time points and operating conditions, and finally simulating and generating the corresponding real-time growth rate kinetic field of microbial fermentation.
[0076] Step S3: performing fermentation growth metabolism analysis modeling on the microbial fermentation process in the microbial fermentation tank based on the microbial fermentation real-time growth environment simulation field and the microbial fermentation real-time growth rate dynamic field, so as to construct a microbial fermentation environment constraint-growth metabolism data analysis model;
[0077] In an embodiment of the present invention, the optimal growth environment conditions of different microbial populations are determined by combining the real-time growth environment simulation field of microbial fermentation obtained by previous simulation analysis, and the optimal growth environment conditions of different microbial populations in the microbial fermentation process are subjected to influence constraint analysis of growth environment metabolism by using the influence constraint analysis method, so as to further analyze the metabolic characteristics and metabolite formation process of different microbial populations under these conditions according to the previously determined optimal conditions, which involves the understanding of microbial metabolic pathways and the modeling of biochemical reactions, and then determines the target of growth environment metabolic influence constraint, and secondly, the corresponding microbial fermentation process in the microbial fermentation tank is subjected to statistical analysis of growth metabolic kinetic characteristics by combining the real-time growth rate kinetic field of microbial fermentation obtained by previous setting, so as to statistically analyze the growth metabolic kinetic characteristics of the corresponding microbial fermentation process in the microbial fermentation tank, so as to statistically analyze the growth metabolic kinetic characteristics of the corresponding microbial fermentation process in the microbial fermentation tank, and ... The growth metabolic kinetic characteristic data corresponding to each microbial population in the microbial fermentation tank are analyzed and obtained, including the microbial growth rate, the metabolite production rate and the response parameters of the relevant environmental conditions such as temperature, pH value and nutrient concentration. At the same time, the mathematical equation for environmental constraint data analysis of the growth metabolic kinetic characteristic data of the corresponding microbial population is established by combining the growth environment metabolic impact constraint targets of different microbial populations determined previously, so as to integrate the growth environment metabolic impact constraints and growth metabolic kinetic characteristic data corresponding to the microbial population, thereby associating the growth metabolic kinetic characteristic data of the microbial population with the constraint targets of the environmental conditions, so as to establish the corresponding environmental constraint-growth metabolism mathematical equation. For example, the mathematical equation can be: Where X(t) is the microbial growth yield (biovolume or cell number) of the microbial population at time t, S(t) is the metabolic substrate or nutrient concentration of the microbial population at time t, μ(X(t), S(t), t) is the growth rate of the microbial population over time, that is, the growth rate of the microbial population, k(t-τ) represents the microbial growth yield decay or dissipation function associated with time t-τ, which is related to the natural decay or resource depletion in the environment, which reflects the impact of microbial growth yield in the past on the current growth state. Then, by using the previously established environmental constraint-growth generation The mathematical equations are integrated with the data from the actual microbial fermentation process, which includes inputting the microbial growth rate, metabolite production rate and environmental conditions such as temperature and pH value measured in the laboratory or on-site into the mathematical equations. This allows a dynamic model to be established to describe the changes in lactic acid production and growth rate of the strains under different environmental constraints. Finally, the corresponding microbial fermentation environmental constraint-growth metabolism data analysis model is constructed. This data analysis model can be used to explore the optimal fermentation strategy under different operating conditions, such as adjusting the feed concentration, controlling the temperature and pH value, etc., to maximize the microbial growth and product production efficiency.
[0078] Step S4: Based on the microbial fermentation environmental constraint-growth metabolism data analysis model, the microbial fermentation process in the microbial fermentation tank is subjected to microbial fermentation optimization processing to obtain a microbial fermentation growth metabolism target optimization result.
[0079] In an embodiment of the present invention, the corresponding microbial fermentation process is intelligently analyzed by combining the previously constructed microbial fermentation environment constraint-growth metabolism data analysis model, and the corresponding microbial fermentation process in the microbial fermentation tank is optimized by introducing the corresponding particle swarm optimization algorithm to search for the growth environment parameters, so that the growth environment parameters in the microbial fermentation process are regarded as variables of the optimization problem, and the goal is to maximize the yield of the fermentation product or maximize the growth rate of the fermentation process. The particle swarm optimization algorithm iterates the potential solutions in the search space and continuously adjusts the parameter values until the optimal combination of microbial growth environment parameters is found (that is, the optimal temperature and pH value parameter conditions are determined), and the corresponding microbial fermentation process in the microbial fermentation tank is optimized by using the corresponding target recognition method. The long-term metabolic goals are defined and set, including the yield of biological products, the concentration of specific metabolites, or the microbial growth rate, etc. Then, the corresponding microbial fermentation process growth metabolic goals are optimized by combining the best optimization results of the growth environment parameters obtained by the previous intelligent optimization analysis to adjust and optimize the growth metabolic goals in the microbial fermentation process to achieve the expected biological product production efficiency and quality. This involves laboratory small-scale fermentation experiments or pilot-scale fermentation reactor operations, which includes further fine-tuning the added concentration of nutrients and adjusting the operating conditions of the fermentation reactor (such as temperature, stirring rate, etc.) to optimize the growth and metabolic performance of microorganisms until the best fermentation production effect is achieved, and finally the optimization results of the microbial fermentation growth metabolic goals are obtained.
[0080] Further, as an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S1 in FIG. 1 , in this embodiment, step S1 includes the following steps:
[0081] Step S11: designing a sensor network layout scheme in the microbial fermentation tank according to the network monitoring coverage corresponding to the temperature sensor, the pH sensor, the oxygen concentration monitor, the nutrient concentration monitor, and the data processing unit, and deploying the temperature sensor, the pH sensor, the oxygen concentration monitor, the nutrient concentration monitor, and the data processing unit in the microbial fermentation tank based on the sensor network layout scheme;
[0082] In an embodiment of the present invention, an effective sensor network layout scheme is designed according to the specific size, shape and expected monitoring requirements of the microbial fermentation tank. This scheme needs to take into account the monitoring range, sensitivity and possibility of mutual interference of different sensors to ensure that the key parameters in the microbial fermentation tank can be fully covered. This involves measuring key parameters such as the diameter, height, inlet and outlet positions of the microbial fermentation tank in order to determine the optimal layout position of the sensor. For example, if the microbial fermentation tank is cylindrical, sensors can be installed on the top, bottom and sides to cover the entire fermentation liquid volume. By considering the monitoring characteristics of different sensors, temperature sensors can be installed at the top and bottom of the tank to capture the temperature gradient of the fermentation liquid; the pH sensor is installed in the center of the liquid to ensure uniform monitoring of the pH value changes of the fermentation liquid; the oxygen concentration monitor is installed next to the vent to ensure accurate measurement during the fermentation process. The supply of oxygen; the nutrient concentration monitors are arranged according to the input points of the nutrients to fully understand the changes in the nutrients in the fermentation liquid. In addition, the mutual interference and signal shielding problems between the sensors are considered to avoid installing sensors that affect each other near each other, and to ensure that the signal of each sensor can be stably transmitted to the data processing unit on the microbial fermentation tank, so as to design and generate the corresponding sensor network layout scheme. At the same time, by using the sensor network layout scheme obtained by the previous design, temperature sensors, pH sensors, oxygen concentration monitors, nutrient concentration monitors and data processing units are deployed at corresponding positions in the microbial fermentation tank, and the temperature sensors, pH sensors, oxygen concentration monitors and nutrient concentration monitors are electrically connected to the data processing unit, so that the data processing unit can analyze and process the microbial fermentation process parameters obtained by real-time monitoring.
[0083] Step S12: using a temperature sensor to monitor the fermentation temperature of the microbial fermentation process in the microbial fermentation tank in real time to obtain real-time temperature data of the microbial fermentation;
[0084] In an embodiment of the present invention, the temperature of the corresponding microbial fermentation process in the microbial fermentation tank is monitored in real time by using a previously deployed temperature sensor to monitor the temperature changes in the microbial fermentation tank in real time, and ensure that the measured temperature can represent the situation of the entire fermentation process, and finally obtain the real-time temperature data of the microbial fermentation.
[0085] Step S13: using a pH sensor to monitor the fermentation pH value of the microbial fermentation process in the microbial fermentation tank in real time to obtain real-time pH value data of the microbial fermentation;
[0086] In an embodiment of the present invention, the pH value of the corresponding microbial fermentation process in the microbial fermentation tank is monitored in real time by using a previously deployed pH sensor to take into account its stability and accuracy in the microbial fermentation liquid. The pH sensor is usually installed in the inner part of the tank, for example, through an opening on the tank wall or directly inserted into the fermentation liquid through a sterile joint. After installation, calibration is required to ensure that the measurement results are accurate and reliable, and the calibrated pH sensor is started to monitor the pH value changes in the microbial fermentation tank in real time, and finally obtain the real-time pH value data of the microbial fermentation.
[0087] Step S14: using an oxygen concentration monitor to monitor the fermentation oxygen concentration of the microbial fermentation process in the microbial fermentation tank in real time to obtain real-time oxygen concentration data of the microbial fermentation;
[0088] In an embodiment of the present invention, the oxygen concentration of the corresponding microbial fermentation process in the microbial fermentation tank is monitored in real time by using a previously deployed oxygen concentration monitor, so as to accurately measure the concentration of dissolved oxygen in the microbial fermentation liquid in real time, and ensure that the changes in the oxygen concentration in the fermentation liquid can be accurately reflected, and finally obtain the real-time oxygen concentration data of the microbial fermentation.
[0089] Step S15: using a nutrient concentration monitor to monitor the fermentation nutrient concentration of the microbial fermentation process in the microbial fermentation tank in real time, so as to obtain real-time nutrient concentration data of the microbial fermentation;
[0090] In an embodiment of the present invention, by using a previously deployed nutrient concentration monitor (for example, a sensor for specific nutrients (such as sugars, nitrogen sources, minerals, etc.)), the real-time monitoring of the nutrient concentration of the corresponding microbial fermentation process in the microbial fermentation tank is performed. These sensors are usually based on chemical sensing technology or optical sensing technology, and can accurately measure the concentration of target nutrients in the fermentation liquid. The installation location should take into account the mixing degree of the fermentation liquid and the convenience of sampling. It is usually selected to be inside the tank or directly connected to the fermentation liquid through a sterile connector. After installation, starting the corresponding nutrient monitor will measure the concentration of the target nutrient in the fermentation liquid in real time, which can help determine the nutritional needs and metabolic activity levels of the microorganisms at a specific moment, and ultimately obtain real-time nutrient concentration data of microbial fermentation.
[0091] Step S16: transmitting the real-time temperature data of microbial fermentation, the real-time pH value data of microbial fermentation, the real-time oxygen concentration data of microbial fermentation and the real-time nutrient concentration data of microbial fermentation to the data processing unit via a network connection.
[0092] In an embodiment of the present invention, the real-time temperature data of microbial fermentation, the real-time pH data of microbial fermentation, the real-time oxygen concentration data of microbial fermentation and the real-time nutrient concentration data of microbial fermentation obtained by real-time monitoring of each sensor are transmitted to the data processing unit on the microbial fermentation tank by using a network connection, so as to optimize the setting of microbial fermentation parameters.
[0093] Further, as an embodiment of the present invention, refer to Figure 3 As shown, Figure 1 Detailed step flow diagram of step S2 in FIG. 1 , in this embodiment, step S2 includes the following steps:
[0094] Step S21: performing time series synchronization processing on the real-time temperature data of microbial fermentation and the real-time pH value data of microbial fermentation by a data processing unit to obtain time series synchronization data of microbial fermentation temperature and time series synchronization data of microbial fermentation pH value;
[0095] In an embodiment of the present invention, a data processing unit uses a timing synchronization method to perform timing synchronization processing on the transmitted real-time temperature data of microbial fermentation and the real-time pH value data of microbial fermentation to receive real-time data from the temperature sensor and pH sensor inside the microbial fermentation tank. These data are collected at different frequencies and timestamps, and need to be time-synchronized to ensure that the temperature and pH data are aligned in time. This usually involves data interpolation, timestamp calibration or other time series processing techniques to ensure data consistency and comparability, thereby ensuring that the temperature and pH data obtained from different sensors are consistent with time. For example, if the data shows that the temperature and pH value in the fermentation tank fluctuate abnormally at a specific stage, the operator can immediately intervene to adjust the control, such as adjusting the heating or cooling system to stabilize the temperature, or adjusting the added acidity and alkalinity chemicals to maintain the ideal pH range, and finally obtaining the microbial fermentation temperature time-series synchronization data and the microbial fermentation pH time-series synchronization data.
[0096] Step S22: performing microbial environment temperature modeling analysis on the microbial fermentation temperature time series synchronization data to generate a microbial fermentation environment temperature time series change simulation field;
[0097] In an embodiment of the present invention, after data cleaning and preprocessing of the microbial fermentation temperature time series synchronization data that has previously undergone time series synchronization, statistical and mathematical modeling methods, such as time series analysis, regression analysis or neural network models, are used to model the microbial fermentation temperature time series synchronization data to help understand the trend, periodicity and influencing factors of temperature changes, thereby constructing a simulation scenario of the environmental temperature change process in microbial fermentation. Taking yeast fermentation as an example, the temperature changes in the fermentation tank can be simulated and displayed in real time through modeling and analysis, so that the fermentation conditions can be adjusted in real time according to the simulated temperature changes, and finally a simulation field of the time series changes in the environmental temperature of microbial fermentation is generated.
[0098] Step S23: performing a microbial environment pH dynamic simulation analysis on the microbial fermentation pH value time series synchronization data to generate a microbial fermentation environment pH value time series change simulation field;
[0099] In an embodiment of the present invention, similarly, after data cleaning and preprocessing of the microbial fermentation pH time series synchronization data previously obtained after time series synchronization, the microbial fermentation pH time series synchronization data is modeled using a corresponding mathematical scenario modeling method, such as time series analysis, regression analysis or a neural network model, so as to model and generate a simulation scenario of the time series changes of pH value in the corresponding microbial fermentation environment. For example, taking lactic acid bacteria fermentation as an example, the growth and fermentation activity of lactic acid bacteria are significantly affected by the environmental pH value. By dynamically simulating and analyzing the pH changes in the microbial fermentation environment, factors that may cause pH fluctuations can be detected, such as the lactic acid production rate in the fermentation tank, the amount of added acid and alkali substances, or the influence of other chemical reactions during the fermentation process, thereby ensuring the stability of the lactic acid bacteria growth environment and the high efficiency of lactic acid production, and finally simulating and generating a simulation field of the time series changes of pH value in the microbial fermentation environment.
[0100] Step S24: performing a coupled analysis of the rhythmic influence of the growth environment according to the microbial fermentation environment temperature time series variation simulation field and the microbial fermentation environment pH value time series variation simulation field to generate a microbial fermentation real-time growth environment simulation field;
[0101] In an embodiment of the present invention, a simulation coupling analysis of the influence of the rhythm of the growth environment is performed on the previously simulated and generated microbial fermentation environment temperature time-series change simulation field and the microbial fermentation environment pH time-series change simulation field in the data processing unit, so as to integrate and compare the two time-series change simulation fields, and analyze the interaction and influence of temperature and pH value changes on the microbial growth process, so as to couple and simulate the corresponding growth environment simulation field. For example, in the yeast fermentation process, the changing rhythm of temperature and pH value will affect the fermentation rate and wine production quality. This step can determine the key environmental conditions affecting yeast growth through coupling analysis, and finally couple to generate a real-time growth environment simulation field for microbial fermentation.
[0102] Step S25: setting the fermentation growth dynamic field for the real-time oxygen concentration data of microbial fermentation and the real-time nutrient concentration data of microbial fermentation to generate the real-time growth rate dynamic field of microbial fermentation.
[0103] In an embodiment of the present invention, a corresponding data visualization tool is used to draw a change curve of the previously collected real-time oxygen concentration data of microbial fermentation and the real-time nutrient concentration data of microbial fermentation, so as to draw a corresponding concentration change curve. These curves usually take time as the horizontal axis and concentration as the vertical axis, so as to show the change trend of relevant parameters in different stages, and use mathematical statistical methods to statistically calculate the dissolved oxygen amount in the microbial fermentation process and the real-time consumption of nutrients in the microbial fermentation process. At the same time, the growth rate of the microorganism under the current environmental conditions is inferred by combining the previously statistically calculated real-time dissolved oxygen amount and real-time consumption of nutrients, so as to describe the growth rate of the microorganism by selecting an appropriate mathematical model. Commonly used models include Monod model, Logistic model, etc. These models can predict the growth rate of the microorganism according to the changes in the dissolved oxygen amount and the nutrient consumption. The mass transfer kinetic model performs a dynamic analysis of the real-time growth rate of the microbial fermentation process predicted in real time, and establishes the corresponding mass transfer dynamic field through dynamic simulation, which helps to predict and optimize the growth dynamics of microorganisms to achieve real-time process control and adjustment. For example, based on the microbial growth rate obtained in the previous analysis, a growth rate kinetic model of microorganisms in the mass transfer process is established. This model takes into account the impact of the mass transfer process on microbial growth and metabolic activities, such as the supply rate of nutrients, the accumulation rate of metabolites, etc. The establishment of this model can adopt dynamic system equations or computer simulation-based methods, and use the established growth rate kinetic model to simulate the real-time dynamic response of the microbial fermentation process, which includes predicting the growth curve of the microorganism, the accumulation of metabolites and the impact of reaction conditions on microbial growth at different time points and operating conditions, and finally simulating and generating the corresponding real-time growth rate kinetic field of microbial fermentation.
[0104] Further, step S24 includes the following steps:
[0105] Step S241: performing frequency domain change conversion processing on the microbial fermentation environment temperature time series change simulation field and the microbial fermentation environment pH value time series change simulation field to obtain the microbial fermentation temperature frequency domain change simulation field and the microbial fermentation pH value frequency domain change simulation field;
[0106] In an embodiment of the present invention, the previously simulated microbial fermentation environment temperature time-series change simulation field and the microbial fermentation environment pH time-series change simulation field in the time domain are converted into the frequency domain by using Fourier transform or related frequency domain analysis methods, so as to convert the temperature and pH time-series change simulation field into a frequency domain change simulation field, and allow the decomposition of the components of temperature and pH at different frequencies, so as to identify the influence of frequency characteristics on the microbial fermentation process, and finally generate a microbial fermentation temperature frequency domain change simulation field and a microbial fermentation pH frequency domain change simulation field, wherein the temperature frequency domain change simulation field reflects the amplitude and phase information of temperature changes at different frequencies, while the pH value frequency domain change simulation field reveals the amplitude and phase information of pH changes at different frequencies.
[0107] Step S242: performing rhythmic frequency analysis on the microbial fermentation temperature frequency domain variation simulation field and the microbial fermentation pH value frequency domain variation simulation field to obtain the microbial fermentation temperature rhythmic frequency and the microbial fermentation pH value rhythmic frequency;
[0108] In an embodiment of the present invention, by using a suitable frequency domain analysis method, such as Fourier analysis or wavelet analysis, the rhythmic frequency is statistically calculated for the microbial fermentation temperature frequency domain change simulation field and the microbial fermentation pH value frequency domain change simulation field obtained after the frequency domain conversion, so as to analyze the microbial fermentation temperature frequency domain change simulation field according to the selected method. This analysis will reveal the periodic change frequency values of temperature changes in different frequency ranges. Then, similarly, the rhythmic frequency analysis of the microbial fermentation pH value frequency domain change simulation field is performed. This analysis will also reveal the periodic change frequency values of pH value changes in different frequency ranges, and finally the rhythmic frequency of microbial fermentation temperature and the rhythmic frequency of microbial fermentation pH value are obtained.
[0109] Step S243: performing a temperature frequency domain rhythmic fluctuation analysis on the microbial fermentation temperature frequency domain change simulation field based on the microbial fermentation temperature rhythmic frequency to obtain a microbial fermentation temperature frequency domain rhythmic fluctuation change relationship;
[0110] In an embodiment of the present invention, the rhythmic fluctuation changes of the corresponding microbial fermentation temperature frequency domain change simulation field are identified and analyzed by combining the rhythmic frequency of the microbial fermentation temperature obtained by the previous statistical analysis, so as to understand the influence of temperature on the frequency domain fluctuation in the microbial fermentation process and establish the corresponding fluctuation change relationship. First, the key temperature range and its change pattern in the fermentation process need to be determined. Next, the microbial fermentation process under each temperature condition is monitored and data recorded in detail, which includes real-time measurement of the temperature changes in the fermentation tank, and the use of sensors and data acquisition systems to record the frequency and fluctuation properties, so as to analyze and determine the changing law of the rhythmic fluctuation of the temperature frequency domain in the microbial fermentation process. For example, within a certain frequency range, the temperature fluctuation will show periodic increase and decrease or stable state, and finally the relationship of the rhythmic fluctuation of the microbial fermentation temperature frequency domain is obtained by analysis.
[0111] Step S244: performing a pH value frequency domain rhythmic fluctuation analysis on the pH value frequency domain change simulation field of the microbial fermentation based on the pH value rhythmic frequency of the microbial fermentation to obtain a pH value frequency domain rhythmic fluctuation change relationship of the microbial fermentation;
[0112] In an embodiment of the present invention, the rhythmic fluctuation change of the corresponding microbial fermentation pH value frequency domain change simulation field is similarly identified and analyzed by combining the rhythmic frequency of the microbial fermentation pH value obtained by previous statistical analysis, so as to explore the fluctuation characteristics of the pH value in the frequency domain during the microbial fermentation process, and establish a fluctuation change relationship, thereby revealing the change relationship of the fluctuation characteristics of pH at different frequencies, and finally obtaining the rhythmic fluctuation change relationship of the microbial fermentation pH value frequency domain.
[0113] Step S245: Based on the relationship between the rhythmic fluctuations in the frequency domain of microbial fermentation temperature and the rhythmic fluctuations in the frequency domain of microbial fermentation pH value, a coupling analysis of the rhythmic influence of the growth environment is performed on the simulation field of the frequency domain change of microbial fermentation temperature and the simulation field of the frequency domain change of microbial fermentation pH value to generate a real-time growth environment simulation field for microbial fermentation.
[0114] In an embodiment of the present invention, a data mining method is used to perform a rhythmic synchronous interaction mining analysis on the previously analyzed relationship between the rhythmic fluctuation changes in the frequency domain of the microbial fermentation temperature and the rhythmic fluctuation changes in the frequency domain of the microbial fermentation pH value, so as to mine and explore the frequency domain synchronous interaction relationship between them, and realize the synchronous interaction mining analysis of the frequency domain rhythmic fluctuation changes of the temperature and pH value, which includes calculating their correlation and interaction in the frequency domain, and by using an appropriate frequency domain interaction pattern recognition method, common methods include principal component analysis (PCA), wavelet packet analysis, etc., and using a selected method to perform pattern recognition and feature extraction on the previously analyzed microbial temperature-pH frequency domain rhythmic synchronous interaction relationship, which includes identifying in which frequency ranges the change patterns of temperature and pH value are significantly correlated with microbial growth or product generation, so as to analyze and describe how the changes in temperature and pH value in the frequency domain jointly affect the dynamic change pattern of the microbial fermentation process, and establish the rhythmic phase influence constraints of temperature and pH value in the frequency domain based on the dynamic change pattern obtained by the previous analysis, that is, understanding how the rhythmic changes of temperature and pH value in the frequency domain affect each other, and at the same time, according to The temperature rhythmic phase influence constraint dynamically adjusts the temperature frequency domain change simulation field, which includes frequency domain phase shift, phase correction or phase locking techniques to ensure that the phase relationship of the temperature in the key frequency range meets the requirements of the optimized fermentation conditions, so that the phase of the temperature is most consistent with the optimized fermentation effect within the key frequency range. Similarly, by combining the pH rhythmic phase influence constraint obtained by the previous analysis, the phase of the corresponding microbial fermentation pH frequency domain change simulation field is dynamically adjusted to optimize the frequency domain change mode of the pH value in the microbial fermentation process according to the rhythmic phase influence constraint, so that within the key frequency range, the phase adjustment of the pH value can maximize the stability and yield of the microbial fermentation process. Then, by using the simulation coupling method, the temperature dynamic adjustment simulation field and the pH dynamic adjustment simulation field obtained after the influence constraint adjustment are simulated and coupled with the growth environment, so as to couple the frequency domain phase dynamic adjustment simulation fields of the temperature and pH values, and generate a comprehensive simulation scene reflecting the real-time microbial growth environment, thereby ensuring that the simulation field can reflect the dynamic changes of the temperature and pH phase relationship at different times, and finally generate a real-time growth environment simulation field of microbial fermentation.
[0115] Further, step S245 includes the following steps:
[0116] The frequency domain rhythmic fluctuation relationship of microbial fermentation temperature and the frequency domain rhythmic fluctuation relationship of microbial fermentation pH value were analyzed by frequency domain rhythmic synchronization interaction mining, and the frequency domain rhythmic synchronization interaction relationship of microbial temperature-pH was obtained.
[0117] In an embodiment of the present invention, a data mining method is used to perform a rhythmic synchronization interaction mining analysis on the previously analyzed relationship between the frequency domain rhythmic fluctuation changes in the microbial fermentation temperature and the frequency domain rhythmic fluctuation changes in the microbial fermentation pH value, so as to explore the frequency domain synchronization interaction relationship between them. This analysis aims to reveal the joint influence of temperature and pH value on the microbial fermentation process, and to realize the synchronization interaction mining analysis of the frequency domain rhythmic fluctuation changes in temperature and pH value, which includes calculating their correlation and interaction in the frequency domain, for example, identifying the synchronization effect between them through phase relationship or resonant frequency, including temperature and pH value showing obvious synchronous oscillation in certain frequency ranges, which implies a coupling relationship between microbial growth and metabolic activity at certain frequencies, so that it can be found that in certain frequency ranges, there is an obvious synchronization relationship between the growth rate of the microorganism and the temperature and pH value, and finally the microbial temperature-pH frequency domain rhythmic synchronization interaction relationship is obtained.
[0118] Preferably, the frequency domain rhythmic interaction effect pattern recognition analysis is performed on the frequency domain rhythmic synchronization interaction relationship of microbial temperature and pH to obtain the frequency domain rhythmic change interaction effect pattern of microbial temperature and pH;
[0119] In an embodiment of the present invention, by using appropriate frequency domain interaction pattern recognition methods, common methods include principal component analysis (PCA), wavelet packet analysis, etc., these methods can help extract key patterns and features in frequency domain data, and use the selected method to perform pattern recognition and feature extraction on the microbial temperature-pH frequency domain rhythmic synchronous interaction relationship obtained by previous analysis, which includes identifying in which frequency ranges the change patterns of temperature and pH values are significantly correlated with microbial growth or product production. This can deeply analyze the interaction patterns of temperature and pH values at different frequencies, thereby revealing how these parameters jointly affect the fermentation effect during the microbial fermentation process, and help to establish a mathematical or statistical model to describe how changes in temperature and pH values in the frequency domain jointly affect the dynamic changes of the microbial fermentation process, and finally obtain the interaction effect pattern of microbial temperature-pH frequency domain rhythmic changes.
[0120] Preferably, a rhythmic phase influence constraint analysis is performed on the microbial fermentation temperature frequency domain change simulation field and the microbial fermentation pH value frequency domain change simulation field based on the microbial temperature-pH frequency domain rhythmic change interaction effect mode to generate the microbial fermentation temperature frequency domain rhythmic phase influence constraint and the microbial fermentation pH value frequency domain rhythmic phase influence constraint;
[0121] In an embodiment of the present invention, the frequency domain phase influence constraint analysis is performed on the corresponding microbial fermentation temperature frequency domain change simulation field and the microbial fermentation pH value frequency domain change simulation field by combining the analysis of the interaction effect pattern of the microbial temperature-pH frequency domain rhythmic change, so as to collect and prepare the frequency domain change simulation field data of the temperature and pH value in the microbial fermentation process. These data are generated by mathematical models or simulation software, which can reflect the change pattern of temperature and pH value at different frequencies, and select appropriate analysis methods to explore the phase influence constraint relationship of temperature and pH value in the frequency domain, which involves complex time-frequency analysis techniques, such as wavelet analysis or phase spectrum analysis, to reveal in which frequency range the phase change of temperature and pH value has the most significant effect on the microbial fermentation process, so as to analyze their phase relationship at different frequencies, such as phase delay or phase difference, and how these phase relationships affect the dynamic changes of microbial growth and metabolic activities, and establish the rhythmic phase influence constraint of temperature and pH value in the frequency domain, that is, to understand how the rhythmic changes of temperature and pH value in the frequency domain affect each other, and finally generate the rhythmic phase influence constraint of microbial fermentation temperature in the frequency domain and the rhythmic phase influence constraint of microbial fermentation pH value in the frequency domain.
[0122] Preferably, the temperature frequency domain phase of the microbial fermentation temperature frequency domain change simulation field is dynamically adjusted according to the frequency domain rhythmic phase influence constraint of the microbial fermentation temperature to obtain the microbial temperature frequency domain phase dynamic adjustment simulation field; the pH value frequency domain phase of the microbial fermentation pH value frequency domain change simulation field is dynamically adjusted according to the frequency domain rhythmic phase influence constraint of the microbial fermentation pH value to obtain the microbial pH value frequency domain phase dynamic adjustment simulation field;
[0123] In an embodiment of the present invention, the phase of the corresponding microbial fermentation temperature frequency domain change simulation field is dynamically adjusted by combining the rhythmic phase influence constraints of the microbial fermentation temperature frequency domain obtained by previous analysis, so as to optimize the frequency domain change pattern of temperature in the microbial fermentation process according to the rhythmic phase influence constraints, and use the previously determined microbial fermentation temperature frequency domain rhythmic phase influence constraints as the basis for adjustment, and select a suitable adjustment method to dynamically adjust the temperature frequency domain change simulation field according to the phase influence constraints, including frequency domain phase shifting, phase correction or phase locking and other technologies, to ensure that the phase relationship of the temperature within the critical frequency range meets the requirements of the optimized fermentation conditions, so that within the critical frequency range, the phase of the temperature is most consistent with the optimized fermentation effect, thereby obtaining a microbial temperature frequency domain phase dynamic adjustment simulation field. At the same time, the phase of the corresponding microbial fermentation pH value frequency domain change simulation field is dynamically adjusted by combining the rhythmic phase influence constraints of the microbial fermentation pH value obtained in the previous analysis, so as to optimize the frequency domain change pattern of the pH value in the microbial fermentation process according to the rhythmic phase influence constraints, so as to ensure that its phase relationship within the critical frequency range meets the requirements of the optimized fermentation conditions, and select a suitable phase dynamic adjustment method by combining the previous influence constraints, which involves phase shifting, phase correction or phase locking technologies, to ensure that the phase of the pH value within the critical frequency range is consistent with the optimized fermentation effect, so that within the critical frequency range, the phase adjustment of the pH value can maximize the stability and yield of the microbial fermentation process, and ensure that the phase dynamic adjustment of the pH value at the critical frequency reaches the optimal state, and finally obtain the microbial pH value frequency domain phase dynamic adjustment simulation field.
[0124] Preferably, the microbial temperature frequency domain phase dynamic adjustment simulation field and the microbial pH value frequency domain phase dynamic adjustment simulation field are coupled with real-time growth environment simulation to generate a microbial fermentation real-time growth environment simulation field.
[0125] In an embodiment of the present invention, a simulation coupling method is used to simulate the growth environment of the microbial temperature frequency domain phase dynamic adjustment simulation field and the microbial pH value frequency domain phase dynamic adjustment simulation field obtained after the influence constraint adjustment, so as to couple the frequency domain phase dynamic adjustment simulation fields of temperature and pH value, and generate a comprehensive simulation scene reflecting the real-time microbial growth environment. For example, by preparing the data integration of the microbial temperature frequency domain phase dynamic adjustment simulation field and the microbial pH value frequency domain phase dynamic adjustment simulation field generated in the previous step, ensuring that these data contain the phase relationship between temperature and pH value within the critical frequency range, and selecting a suitable real-time coupling processing method to couple the frequency domain phase dynamic adjustment simulation field of temperature and pH value, which involves the conversion between time domain simulation and frequency domain regulation to ensure that the simulation field can reflect the dynamic changes in the phase relationship between temperature and pH value at different times, thereby generating a comprehensive simulation scene reflecting the real-time growth environment of the microorganisms, and finally generating a real-time growth environment simulation field of microbial fermentation.
[0126] Further, step S25 includes the following steps:
[0127] Step S251: plotting concentration change curves for the real-time oxygen concentration data of microbial fermentation and the real-time nutrient concentration data of microbial fermentation to generate a microbial fermentation oxygen concentration change curve and a microbial fermentation nutrient concentration change curve;
[0128] In an embodiment of the present invention, the real-time oxygen concentration data of microbial fermentation and the real-time nutrient concentration data of microbial fermentation previously collected are plotted as change curves by using corresponding data visualization tools to draw corresponding concentration change curves. These curves not only reflect the dynamic changes of key parameters in the fermentation process, but this step uses data processing and visualization tools based on the collected real-time data to draw change curves of oxygen concentration and nutrient concentration in the microbial fermentation process. These curves usually use time as the horizontal axis and concentration as the vertical axis to show the change trends of related parameters in different stages. For example, the rapid drop in oxygen concentration in the early stage of fermentation and the consumption curve of carbon source concentration over time can be plotted, and finally the corresponding microbial fermentation oxygen concentration change curve and microbial fermentation nutrient concentration change curve are generated.
[0129] Step S252: performing a statistical analysis of dissolved oxygen on the oxygen concentration variation curve of the microbial fermentation to obtain the real-time dissolved oxygen in the microbial fermentation process; performing a statistical analysis of nutrient consumption on the nutrient concentration variation curve of the microbial fermentation to obtain the real-time nutrient consumption in the microbial fermentation process;
[0130] In an embodiment of the present invention, a mathematical statistical method is used to perform a statistical analysis of the amount of dissolved oxygen on the previously generated microbial fermentation oxygen concentration change curve, so as to statistically calculate the amount of dissolved oxygen in the microbial fermentation process. This usually involves converting the concentration curve into the amount of dissolved oxygen in the corresponding mass or volume unit, and performing a statistical analysis based on the change trend within a time period. These data can help determine the supplementary demand and optimal control range of oxygen in the fermentation process, thereby obtaining the real-time amount of dissolved oxygen in the microbial fermentation process. At the same time, a mathematical statistical method is also used to perform a statistical analysis of the consumption of the previously drawn microbial fermentation nutrient concentration change curve, so as to achieve integration or change rate analysis of the nutrient concentration change curve, thereby statistically calculating the real-time consumption of nutrients in the microbial fermentation process. This analysis can reveal the changes in the demand for different nutrients by microorganisms at different growth stages, thereby obtaining the amount of nitrogen source consumed by microorganisms in a specific stage, and finally obtaining the real-time consumption of nutrients in the microbial fermentation process.
[0131] Step S253: performing a microbial growth rate prediction analysis on the corresponding microbial fermentation process according to the real-time dissolved oxygen amount and the real-time consumption of nutrients in the microbial fermentation process, so as to obtain the real-time growth rate of the microbial fermentation process;
[0132] In an embodiment of the present invention, mathematical modeling and statistical analysis are used to predict the microbial growth rate of the corresponding microbial fermentation process by combining the real-time dissolved oxygen amount in the microbial fermentation process and the real-time consumption of nutrients in the microbial fermentation process obtained by previous statistical calculations, so as to use the monitored key parameters, infer the growth rate of the microorganism under the current environmental conditions through mathematical modeling and statistical analysis, and describe the growth rate of the microorganism by selecting an appropriate mathematical model. Commonly used models include Monod model, Logistic model, etc. These models can predict the growth rate of the microorganism according to the changes in the dissolved oxygen amount and the consumption of nutrients. For example, the Monod model is usually used to describe the growth of microorganisms to a single limiting factor (such as a carbon source), and is suitable for predicting the change in the growth rate of microorganisms under different nutrient concentrations. According to the selected model, the dissolved oxygen amount and the nutrient consumption obtained by statistical analysis are used to estimate the parameters, which includes adjusting the growth kinetic parameters in the model to best fit the experimental data. For example, in the Monod model, it is necessary to estimate the maximum growth rate and the half-saturation constant. These parameters directly affect the prediction results of the growth rate, and finally the real-time growth rate of the microbial fermentation process is predicted.
[0133] Step S254: performing a growth rate mass transfer kinetic analysis on the real-time growth rate of the microbial fermentation process to obtain the real-time growth rate mass transfer kinetic parameters of the microbial fermentation;
[0134] In an embodiment of the present invention, a dynamic analysis of the real-time growth rate of the microbial fermentation process previously predicted in real time is performed by selecting an appropriate mass transfer kinetic model to describe the relationship between the growth rate and the concentration of key resources. For example, the Michaelis-Menten model or other derivative models can be used to express the utilization rate of oxygen and nutrients by microorganisms. These models can help understand the degree of influence of different resource concentrations on the growth rate, and estimate and analyze the model parameters based on the selected mass transfer kinetic model using real-time monitoring data. These parameters generally include mass transfer coefficients, diffusion rates, and mass transfer limitations, which directly affect the growth efficiency and rate of microorganisms under specific resource conditions, and ultimately obtain the real-time growth rate mass transfer kinetic parameters of microbial fermentation.
[0135] Step S255: Based on the mass transfer kinetic parameters of the real-time growth rate of microbial fermentation, the fermentation growth kinetic field of the corresponding microbial fermentation process is set to generate the real-time growth rate kinetic field of microbial fermentation.
[0136] In an embodiment of the present invention, by combining the previously determined real-time growth rate mass transfer kinetic parameters of microbial fermentation (such as mass transfer coefficient, diffusion rate and mass transfer limit, etc.), the fermentation process of the corresponding microorganism in different growth stages (including lag phase (adaptation period), exponential growth period, stable period and decay period, etc.) is simulated and analyzed to understand the influence of the transfer rate of nutrients in different stages on the growth and metabolic activity of microorganisms, and based on the determined mass transfer kinetic parameters, a mass transfer model of the microbial fermentation process is established. At the same time, by fusion setting of the mass transfer dynamic field of the biomass transfer kinetic simulation process at different growth stages generated by the previous simulation, a comprehensive description of various mass transfer phenomena in the fermentation process is established by integrating the mass transfer kinetic parameters and real-time monitoring data, and the entire mass transfer model is established based on the previously simulated transfer process between microorganisms and nutrients in different growth stages. The mass transfer dynamics field of the microbial fermentation process includes the distribution of nutrients, concentration gradients and the growth status of the microbial population. Then, the dynamic response simulation of the growth rate of the corresponding microbial fermentation process is performed by combining the real-time mass transfer dynamics field of microbial fermentation obtained by the previous fusion, so as to use the previously established mass transfer dynamics field to predict and optimize the growth dynamics of microorganisms and realize real-time process control and adjustment. For example, a microbial growth rate model is established based on the real-time mass transfer dynamics field of microbial fermentation generated by the previous fusion. The establishment of this model can adopt dynamic system equations or computer simulation-based methods, and the established growth rate model is used to simulate the real-time dynamic response of the microbial fermentation process, which includes predicting the growth curve of the microorganism, the accumulation of metabolites and the influence of reaction conditions on the growth of microorganisms at different time points and operating conditions, and finally simulating and generating the corresponding real-time growth rate dynamics field of microbial fermentation.
[0137] Further, step S255 includes the following steps:
[0138] The microbial fermentation process is divided into growth stages to obtain the fermentation process of microorganisms in different growth stages;
[0139] In an embodiment of the present invention, the fermentation process is divided into growth stages by combining the growth characteristics of microorganisms and key indicators (such as biomass, product concentration, nutrient consumption rate, etc.) during the microbial fermentation process, so that the microbial fermentation process is divided into lag phase (adaptation period), exponential growth period, stable period and decline period. The basis for the division of these stages involves specific physiological and biochemical parameters such as growth rate, metabolite accumulation rate or nutrient consumption rate, and finally the fermentation process of microorganisms in different growth stages is obtained.
[0140] Preferably, based on the real-time growth rate mass transfer kinetic parameters of microbial fermentation, the fermentation mass transfer kinetic process of the microorganism in different growth stages is simulated and analyzed to obtain the biomass transfer kinetic simulation process of the microbial fermentation process in different growth stages;
[0141] In an embodiment of the present invention, by combining the previously determined real-time growth rate mass transfer kinetic parameters of microbial fermentation (such as mass transfer coefficient, diffusion rate and mass transfer limit, etc.), these parameters reflect the transfer efficiency and rate of nutrients and metabolites in different growth stages, and the fermentation process of the corresponding microorganisms in different growth stages is simulated and analyzed by mass transfer kinetics to understand the influence of the transfer rate of nutrients in different stages on the growth and metabolic activities of microorganisms, and based on the determined mass transfer kinetic parameters, a mass transfer model of the microbial fermentation process is established. The mass transfer model can be a simplified mathematical model, such as a diffusion equation or a mass conservation equation, which is used to describe the transfer of nutrients in the fermentation tank. Distribution and transport process. The establishment of this model needs to take into account the fluid mechanics conditions in the fermentation tank and the growth dynamics of the microbial population. Taking lactic acid bacteria fermentation as an example, lactic acid bacteria require a large amount of carbon source for growth and lactic acid production during the stable period. Through the implementation of this step, a carbon source transport model for lactic acid bacteria during the stable period can be established to analyze the diffusion rate and utilization efficiency of nutrients in the fermentation broth. If the simulation shows that the carbon source transport rate is low or there is diffusion limitation during the stable period, the operator can increase the stirring rate or adjust the mixing method of the fermentation broth to increase the growth rate of lactic acid bacteria and the production of lactic acid, and finally simulate the biomass transport kinetics simulation process of the microbial fermentation process at different growth stages.
[0142] Preferably, the mass transfer dynamics field fusion setting is performed on the biomass transfer dynamics simulation process in different growth stages of the microbial fermentation process to generate a real-time mass transfer dynamics field of the microbial fermentation;
[0143] In an embodiment of the present invention, a fusion setting of the mass transfer dynamics field is performed by simulating the biomass transfer kinetics simulation process of the microbial fermentation process in different growth stages previously generated by simulation, so as to establish a comprehensive description of various mass transfer phenomena in the fermentation process by integrating mass transfer kinetic parameters and real-time monitoring data, and establish a mass transfer dynamics field of the entire microbial fermentation process based on the previously simulated transfer process between microorganisms and nutrients in different growth stages. The mass transfer dynamics field describes the material transfer state in different areas and time points inside the fermenter, including the distribution of nutrients, concentration gradients and the growth state of the microbial population. Taking the protein expression fermentation of Escherichia coli as an example, Escherichia coli requires a large amount of nitrogen source to support protein synthesis during the exponential growth period. Through the implementation of this step, the mass transfer dynamics field in the fermenter can be set, and the diffusion rate and utilization efficiency of the nitrogen source in the liquid can be accurately described, and finally a real-time mass transfer dynamics field of microbial fermentation can be generated.
[0144] Preferably, based on the real-time mass transfer dynamic field of microbial fermentation, a dynamic response simulation of the growth rate of the corresponding microbial fermentation process is performed to generate a real-time growth rate dynamic field of microbial fermentation.
[0145] In an embodiment of the present invention, the dynamic response simulation of the growth rate of the corresponding microbial fermentation process is performed by combining the real-time mass transfer dynamic field of microbial fermentation obtained by previous fusion, so as to use the previously established mass transfer dynamic field to predict and optimize the growth dynamics of microorganisms and realize real-time process control and adjustment. For example, based on the real-time mass transfer dynamic field of microbial fermentation generated by previous fusion, a microbial growth rate model is established. This model takes into account the influence of the mass transfer process on the growth and metabolic activities of microorganisms, such as the supply rate of nutrients, the accumulation rate of metabolites, etc. The establishment of the model can adopt dynamic system equations or computer simulation-based methods, and use the established growth rate model to perform real-time dynamic response simulation of the microbial fermentation process, which includes predicting the growth curve of the microorganism, the accumulation of metabolites and the influence of reaction conditions on the growth of microorganisms at different time points and operating conditions, so that the real-time simulation can help the operator to adjust the control parameters in time, thereby optimizing the efficiency of the fermentation process and the quality of the product, and finally simulating and generating the corresponding real-time growth rate dynamic field of microbial fermentation.
[0146] Further, step S3 includes the following steps:
[0147] Step S31: performing population growth environment condition optimization analysis on the corresponding microbial fermentation process in the microbial fermentation tank based on the microbial fermentation real-time growth environment simulation field to obtain the optimal growth environment conditions of different microbial populations in the microbial fermentation process;
[0148] In an embodiment of the present invention, the population growth environment conditions of the corresponding microbial fermentation process in the microbial fermentation tank are optimized and analyzed by combining the real-time growth environment simulation field of microbial fermentation obtained by previous simulation analysis. First, various environmental parameter data related to microbial fermentation are collected and sorted, such as temperature, pH value, oxygen content, nutrient concentration, etc. These parameters have a direct impact on the growth and metabolic activity of different microbial populations. For example, for the fermentation of lactic acid bacteria, the environmental conditions in the fermentation tank will be optimized, such as setting the temperature at about 35 degrees Celsius, controlling the pH value between 6.0 and 6.5, and maintaining the oxygen content within 0.5%. At the same time, sufficient lactose and amino acids are supplied as nutrient sources. These optimization conditions can be processed and analyzed by using modern bioinformatics and data analysis tools. For example, numerical simulation software or optimization algorithms can be used to simulate the growth dynamics of microorganisms under different environmental conditions to predict the degree of influence of different parameters on the microbial population, and then determine the optimal growth environment conditions, and finally obtain the optimal growth environment conditions for different microbial populations in the microbial fermentation process.
[0149] Step S32: performing growth environment metabolic impact constraint analysis on the optimal growth environment conditions of different microbial populations during the microbial fermentation process to obtain growth environment metabolic impact constraint targets of different microbial populations;
[0150] In an embodiment of the present invention, an impact constraint analysis method is used to perform an impact constraint analysis on the optimal conditions of the growth environment metabolism of different microbial populations during microbial fermentation, so as to further analyze the metabolic characteristics and metabolite formation process of different microbial populations under these conditions based on the previously determined optimal conditions. This involves the understanding of microbial metabolic pathways and the modeling of biochemical reactions. For example, in the fermentation process of yeast, the sugar metabolic pathway of yeast and the amount of ethanol and carbon dioxide produced under the optimal temperature, pH value and nutrient conditions can be analyzed. These analyses need to be combined with experimental data and computational models to evaluate the effects of different growth conditions on microbial metabolic activity, and then determine the targets of the growth environment metabolic impact constraints. These targets can help optimize the operating strategies in the fermentation process, such as adjusting the temperature and nutrient supply method in the fermentation tank to maximize the growth and product formation efficiency of the microorganisms, and ultimately obtain the growth environment metabolic impact constraint targets of different microbial populations.
[0151] Step S33: performing population growth metabolic kinetics characteristic analysis on the corresponding microbial fermentation process in the microbial fermentation tank based on the real-time growth rate kinetics field of microbial fermentation to obtain growth metabolic kinetics characteristic data of different microbial populations;
[0152] In an embodiment of the present invention, a statistical analysis of the growth metabolic kinetic characteristics of the corresponding microbial fermentation process in the microbial fermentation tank is performed by combining the previously set real-time growth rate kinetic field of microbial fermentation, and the growth metabolic kinetic characteristic data corresponding to each microbial population in the microbial fermentation tank are obtained by statistical analysis, including the microbial growth rate, the metabolite production rate and the response parameters of the related environmental condition changes such as temperature, pH value and nutrient concentration. For example, for yeast in the ethanol fermentation process, the real-time growth metabolic kinetic characteristics can be obtained by monitoring the dissolved oxygen content, carbon dioxide release rate and ethanol concentration in the fermentation tank. These data can reveal the changes in the growth rate of yeast at different stages, the ethanol production rate and the response to changes in environmental conditions, thereby revealing the advantages and limiting factors of the microbial population under specific conditions, which is helpful to identify the most suitable environmental conditions for microbial growth and product production, and finally obtain the growth metabolic kinetic characteristic data of different microbial populations.
[0153] Step S34: establishing an environmental constraint analysis mathematical equation for the growth metabolic kinetic characteristic data of different microbial populations based on the growth environment metabolic impact constraint targets of different microbial populations, so as to generate a microbial population fermentation environment constraint-growth metabolic data analysis mathematical equation;
[0154] In an embodiment of the present invention, a mathematical equation for environmental constraint data analysis of the growth metabolic kinetic characteristic data of the corresponding microbial population is established by combining the growth environment metabolic impact constraint targets of different microbial populations determined previously, so as to integrate the growth environment metabolic impact constraints and growth metabolic kinetic characteristic data corresponding to the microbial population, including the growth rate of the microorganism under optimized environmental conditions, the rate of metabolite production, and the response to environmental factors, and by using mathematical modeling tools, such as optimization algorithms or parameter estimation techniques, the growth metabolic kinetic characteristic data of the microbial population is associated with the constraint targets of the environmental conditions, thereby establishing a corresponding environmental constraint-growth metabolism mathematical equation, which can be used to predict the growth rate and product quality of the microbial population under specific environmental conditions. For example, the mathematical equation can be: Where X(t) is the microbial growth yield (biovolume or cell number) of the microbial population at time t, S(t) is the metabolic substrate or nutrient concentration of the microbial population at time t, μ(X(t), S(t), t) is the growth rate of the growth yield of the microbial population over time, that is, the growth rate of the microbial population, k(t-τ) represents the microbial growth yield decay or dissipation function related to time t-τ, which is related to the natural decay or resource depletion in the environment. This reflects the impact of microbial growth yield in the past on the current growth state. Finally, a mathematical equation for the analysis of the fermentation environment constraints of the microbial population-growth metabolism data is established.
[0155] Step S35: Perform fermentation growth metabolism analysis modeling processing according to the microbial population fermentation environment constraint-growth metabolism data analysis mathematical equation to construct a microbial fermentation environment constraint-growth metabolism data analysis model.
[0156] In an embodiment of the present invention, a previously established mathematical equation for analyzing the fermentation environment constraints of a microbial population - growth and metabolism data is used to integrate the data from the actual microbial fermentation process, which includes inputting the microbial growth rate, metabolite production rate, and environmental conditions such as temperature and pH value measured in the laboratory or on-site into the mathematical equation. For example, in the fermentation process of lactic acid bacteria, the optimal growth conditions and metabolic characteristics obtained by collection are input into the previously established mathematical equation, and a dynamic model can be established to describe the changes in lactic acid production and growth rate of the strain under different environmental constraints. In addition, in the implementation process, it is necessary to select appropriate mathematical modeling tools and techniques to process data and construct models. Commonly used tools include dynamic system simulation software, parameter fitting algorithms and optimization software. These tools can help combine experimental data with mathematical equations to accurately describe the fermentation behavior of microorganisms under complex environmental conditions. For example, a set of differential equations can be used to describe the growth and metabolic dynamics of microbial populations, and numerical solution methods can be used to simulate the fermentation process under different environmental conditions to predict the performance of microorganisms in industrial production. Finally, the corresponding microbial fermentation environmental constraint-growth metabolism data analysis model is constructed. This data analysis model can be used to explore the best fermentation strategy under different operating conditions, such as adjusting feed concentration, controlling temperature and pH value, etc., to maximize microbial growth and product generation efficiency.
[0157] Further, step S31 includes the following steps:
[0158] Based on the real-time growth environment simulation field of microbial fermentation, the population growth environment conditions of the corresponding microbial fermentation process in the microbial fermentation tank are simulated and set to obtain different initial simulation conditions for the growth environment set for each microbial population;
[0159] In an embodiment of the present invention, the population growth environment condition simulation setting is performed on the corresponding microbial fermentation process in the microbial fermentation tank by combining the real-time growth environment simulation field of microbial fermentation obtained by previous simulation analysis, so as to determine and prepare the basic environmental parameters for simulating microbial fermentation according to the corresponding real-time growth environment simulation field of microbial fermentation, such as temperature, pH value, oxygen content, nutrient concentration, etc. These parameters directly affect the growth and product formation of each microbial population in the microbial fermentation process. Taking yeast fermentation in a microbial fermentation tank as an example, a preliminary environmental condition is set: the temperature is between 28 degrees Celsius and 32 degrees Celsius, the pH value is maintained between 5.5 and 6.5, the oxygen content is maintained between 5% and 10%, and an appropriate amount of carbon source and nitrogen source are added as nutrients. In the implementation process, it is necessary to select appropriate experimental equipment and control system to ensure that these environmental parameters can be accurately monitored and adjusted. For example, temperature control equipment and pH meter are used to monitor and adjust temperature and pH value in real time, gas flow meter is used to adjust oxygen content, and specific culture medium is added to adjust nutrient concentration, so as to simulate and set different growth environment conditions for each microbial population, and finally obtain different initial simulation conditions for the growth environment set for each microbial population.
[0160] Preferably, a spatial distribution analysis of microbial populations is performed on the corresponding microbial fermentation process in the microbial fermentation tank to obtain the growth spatial distribution position of each microbial population;
[0161] In an embodiment of the present invention, the spatial distribution position of each microbial population corresponding to the microbial fermentation process in the microbial fermentation tank is identified and analyzed, so as to identify and quantify the microbial communities at different positions by utilizing the plate counting method or molecular biology method. For example, the DNA or RNA sequences of the microbial communities in the samples at different positions are sequenced and analyzed by using molecular biology methods to reveal the spatial distribution of the microorganisms in the tank, and the distribution of the microorganisms at different positions is observed and analyzed using a scanning electron microscope or a fluorescence microscope, so as to obtain the actual spatial distribution position of the microbial population in the tank, and finally obtain the growth spatial distribution position of each microbial population.
[0162] Preferably, the population growth position distribution density analysis is performed on the growth space distribution position corresponding to each microbial population under different initial growth environment simulation conditions set for each microbial population, so as to obtain the microbial distribution density at the corresponding growth space position of each microbial population under different growth environment conditions;
[0163] In an embodiment of the present invention, a statistical analysis of the microbial population distribution density is performed on the microbial population at the growth space distribution position corresponding to each microbial population under different initial growth environment simulation conditions. First, it is necessary to analyze the samples under different growth environment conditions based on the spatial distribution data of the microbial population previously obtained. For example, in the case of yeast fermentation, the microbial distribution density of the microbial population at the corresponding position under different temperature, pH value or nutrient concentration conditions will be compared. This involves quantitative and qualitative analysis of the number and population structure of microorganisms in the sample, so as to culture and count the microorganisms in each sample, and then use statistical software to perform statistical calculations on the density distribution to determine the specific distribution density values of the microorganisms at the growth position of the microbial population under different environmental conditions, and finally obtain the microbial distribution density of each microbial population at the corresponding growth space position under different growth environment conditions.
[0164] Preferably, based on the microbial distribution density at the corresponding growth space position of each microbial population under different growth environment conditions, the corresponding initial simulation conditions of the growth environment are quantitatively calculated to obtain the growth environment preference value of each microbial population under different growth environment conditions;
[0165] In an embodiment of the present invention, the microbial distribution density at the corresponding growth space position under different growth environment conditions obtained by combining the previously analyzed microbial populations with the corresponding initial simulation conditions of the growth environment is quantitatively calculated to achieve further analysis and processing of the microbial samples under each growth environment condition. For example, the microbial distribution density data under different conditions can be mathematically modeled or statistically analyzed to derive the degree of preference of each microbial population for various environmental parameters. Multivariate statistical analysis methods, such as principal component analysis (PCA) or cluster analysis, can also be used to identify and quantify key environmental parameter conditions that affect microbial growth preferences. For example, for yeast fermentation processes, the preference metrics of different temperatures, pH values, or oxygen contents for the growth position of yeast during the fermentation process can be analyzed. These analysis methods can help determine which environmental factors have a significant effect on the growth and distribution of microorganisms, thereby optimizing the fermentation conditions, and ultimately obtaining the growth environment preference values of each microbial population under different growth environment conditions. These preference values can be used to determine the most suitable growth environment conditions for each microbial population in the fermentation tank.
[0166] Preferably, the optimal growth environment conditions are screened for the different initial simulation conditions for the growth environments set for each microbial population according to the growth environment preference value of each microbial population under different growth environment conditions, so as to obtain the optimal growth environment conditions for different microbial populations during the microbial fermentation process.
[0167] In an embodiment of the present invention, the optimal conditions are screened for the different initial simulation conditions of the growth environments previously set for each microbial population by combining the growth environment preference values of each microbial population under different growth environment conditions obtained by previous quantitative calculation, so as to screen out the growth environment conditions corresponding to the maximum preference values, thereby determining which growth environment conditions are most conducive to the growth and activity of the corresponding microbial population. For example, by comparing each preference value with the experimental goal (such as increasing yield or reducing growth time), the most suitable combination of environmental conditions in a specific growth stage or a specific application scenario can be determined, and experimental verification and optimization are performed based on the screened optimal growth environment conditions, which involves setting specific experimental conditions, such as in a laboratory or production scale. During fermentation, parameters such as temperature, pH value and nutrient concentration are precisely controlled to confirm whether these conditions can significantly improve the growth efficiency of microorganisms or product quality in practical applications. For example, for a specific yeast variety, batch fermentation experiments are required at a temperature of 30 degrees Celsius, a pH of 6.0 and an oxygen content of 8% to verify its fermentation performance under these optimal conditions, and adjust and optimize the growth environment conditions based on the experimental results, so as to further optimize the operating strategy in the microbial fermentation process, such as adjusting the control parameters in the fermentation tank, optimizing the formula of the fermentation medium, or improving the design of the fermentation tank to achieve more efficient microbial growth and product production, and ultimately obtain the optimal growth environment conditions for different microbial populations in the microbial fermentation process.
[0168] Further, step S4 includes the following steps:
[0169] Step S41: Based on the microbial fermentation environment constraint-growth metabolism data analysis model, a particle swarm optimization algorithm is used to optimize and analyze the growth environment parameters of the microbial fermentation process in the microbial fermentation tank to obtain the best optimization results of the microbial fermentation growth environment parameters;
[0170] In an embodiment of the present invention, the corresponding microbial fermentation process is intelligently analyzed by combining the previously constructed microbial fermentation environment constraint-growth metabolism data analysis model and the corresponding microbial fermentation process in the microbial fermentation tank is optimized by introducing the corresponding particle swarm optimization algorithm to search for the growth environment parameters, so that the growth environment parameters in the microbial fermentation process are regarded as variables of the optimization problem. The goal is to maximize the yield of the fermentation product or maximize the growth rate of the fermentation process. The particle swarm optimization algorithm continuously adjusts the parameter values by iteratively searching for potential solutions in the search space until the optimal combination of microbial growth environment parameters is found (that is, determining the optimal temperature and pH value parameter conditions). At the same time, it also involves the consideration of the limitations and constraints of the parameter space. For example, the range of temperature and pH value will be subject to the physiological limitations of the growth of the fermentation strain. It is necessary to ensure that the optimized parameter combination is feasible and stable in practical applications, and finally optimize the best optimization results of the microbial fermentation growth environment parameters.
[0171] Step S42: performing fermentation growth and metabolic target analysis on the microbial fermentation process in the microbial fermentation tank to obtain the growth and metabolic target of the microbial fermentation process;
[0172] In an embodiment of the present invention, the corresponding target recognition method is used to define and set the growth metabolic target of the corresponding microbial fermentation process in the microbial fermentation tank, including the yield of biological products, the concentration of specific metabolites, or the growth rate of microorganisms, etc. These targets directly affect the efficiency of the fermentation process and the quality of the final product. This analysis process involves dynamic monitoring and analysis of key metabolic pathways and metabolites in the fermentation process. Through biochemical analysis technology, high-throughput analysis instruments or biosensors and other tools, the metabolic activity of microorganisms at different growth stages and the accumulation of metabolites can be obtained and monitored in real time. For example, high-performance liquid chromatography (HPLC) can be used to analyze the concentration changes of specific products in the fermentation broth to determine the achievement of growth metabolic targets in the fermentation process. It also involves the understanding and optimization of metabolic fluxes and regulatory factors. Metabolic flux analysis can help reveal the metabolic path selection and energy utilization patterns of microorganisms under different growth conditions. In addition, the activity or gene expression level of key metabolic enzymes can be regulated by genetic engineering or metabolic engineering strategies to enhance the production capacity of target products or improve the stability of the fermentation process. Finally, the growth metabolic target of the microbial fermentation process is set to achieve the best fermentation production effect.
[0173] Step S43: Based on the optimal optimization result of the microbial fermentation growth environment parameters, the nutrient supplementation strategy and metabolic pathway optimization analysis of the microbial fermentation process in the microbial fermentation tank are performed to generate a microbial fermentation nutrient supplementation strategy optimization plan and a microbial fermentation metabolic pathway optimization plan;
[0174] In an embodiment of the present invention, by combining the optimal optimization results of the microbial fermentation growth environment parameters obtained by the previous intelligent optimization analysis, the nutrient supplementation strategy and metabolic pathway of the corresponding microbial fermentation process in the microbial fermentation tank are optimized, so as to improve the yield and quality stability of the fermentation product by combining the optimized growth environment parameters and optimizing the nutrient supplementation strategy and metabolic pathway in the microbial fermentation process. First, the nutrient supplementation strategy that needs to be optimized in the fermentation process is determined based on the optimal optimization parameter combination of the microbial fermentation growth environment obtained by the previous analysis. This process usually involves analyzing the changes in the demand for nutrients (such as carbon sources, nitrogen sources, minerals, etc.) of microorganisms at different growth stages. For example, for a fermentation strain for certain industrial purposes, the culture medium needs to be adjusted. The proportion and concentration of different nutrients in the fermentation process are adjusted to maximize its growth and metabolic efficiency, and the metabolic pathways in the fermentation process are optimized accordingly. This analysis aims to optimize the operation efficiency of key metabolic pathways in the fermentation process by deeply understanding the structure and function of microbial metabolic pathways. For example, genetic engineering can be used to enhance the activity of certain key enzymes, or to regulate the reaction balance in the metabolic pathway to promote the synthesis of target products or reduce the accumulation of by-products, ensuring that microorganisms can grow and produce target products stably and efficiently in the most suitable nutritional environment, and ultimately generate optimization plans for microbial fermentation nutrient supplementation strategies and microbial fermentation metabolic pathways. These optimization plans include detailed operating procedures, as well as methods and indicators for monitoring and evaluating optimization effects.
[0175] Step S44: performing microbial fermentation optimization processing on the growth metabolic target of the microbial fermentation process according to the microbial fermentation nutrient supplementation strategy optimization scheme and the microbial fermentation metabolic pathway optimization scheme to obtain the microbial fermentation growth metabolic target optimization result.
[0176] In an embodiment of the present invention, the microbial fermentation process is optimized by combining the previously optimized microbial fermentation nutrient supplementation strategy optimization scheme and the microbial fermentation metabolic pathway optimization scheme to optimize the corresponding microbial fermentation process growth metabolic target, so as to adjust and optimize the growth metabolic target in the microbial fermentation process according to the aforementioned optimization scheme, so as to achieve the expected biological product production efficiency and quality, which involves laboratory small-scale fermentation experiments or pilot-scale fermentation reactor operations, which includes regular sampling and analysis of key indicators such as biological product yield, metabolite concentration, and microbial growth rate in the fermentation broth, and through the collection and analysis of experimental data, evaluate the actual impact of the optimization scheme on the fermentation process, and whether the expected growth metabolic target is achieved. Then, according to the experimental results and data analysis, adjust and optimize the operating parameters in the microbial fermentation process, which includes further fine-tuning the added concentration of nutrients, adjusting the operating conditions of the fermentation reactor (such as temperature, stirring rate, etc.), to optimize the growth and metabolic performance of the microorganisms, until the best fermentation production effect is achieved, and finally obtain the optimization result of the microbial fermentation growth metabolic target.
[0177] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.
Claims
1. A microbial fermentation optimization method based on a data analysis model, characterized in that: The following steps are involved: Step S1: deploying a temperature sensor, a pH sensor, an oxygen concentration monitor, a nutrient concentration monitor and a data processing unit in a microbial fermentation tank, and using the temperature sensor, the pH sensor, the oxygen concentration monitor and the nutrient concentration monitor to monitor the fermentation parameters of the microbial fermentation process in the microbial fermentation tank in real time, so as to obtain real-time temperature data of microbial fermentation, real-time pH data of microbial fermentation, real-time oxygen concentration data of microbial fermentation and real-time nutrient concentration data of microbial fermentation; transmitting the real-time temperature data of microbial fermentation, the real-time pH data of microbial fermentation, the real-time oxygen concentration data of microbial fermentation and the real-time nutrient concentration data of microbial fermentation to the data processing unit through a network connection; Step S2: performing fermentation growth environment simulation analysis on the real-time temperature data of microbial fermentation and the real-time pH value data of microbial fermentation through a data processing unit to generate a real-time growth environment simulation field of microbial fermentation; performing fermentation growth dynamic field setting on the real-time oxygen concentration data of microbial fermentation and the real-time nutrient concentration data of microbial fermentation to generate a real-time growth rate dynamic field of microbial fermentation; Step S3: performing fermentation growth metabolism analysis modeling on the microbial fermentation process in the microbial fermentation tank based on the microbial fermentation real-time growth environment simulation field and the microbial fermentation real-time growth rate dynamic field, so as to construct a microbial fermentation environment constraint-growth metabolism data analysis model; Step S4: Based on the microbial fermentation environmental constraint-growth metabolism data analysis model, the microbial fermentation process in the microbial fermentation tank is subjected to microbial fermentation optimization processing to obtain a microbial fermentation growth metabolism target optimization result.
2. The microbial fermentation optimization method based on the data analysis model according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: designing a sensor network layout scheme in the microbial fermentation tank according to the network monitoring coverage corresponding to the temperature sensor, the pH sensor, the oxygen concentration monitor, the nutrient concentration monitor, and the data processing unit, and deploying the temperature sensor, the pH sensor, the oxygen concentration monitor, the nutrient concentration monitor, and the data processing unit in the microbial fermentation tank based on the sensor network layout scheme; Step S12: using a temperature sensor to monitor the fermentation temperature of the microbial fermentation process in the microbial fermentation tank in real time to obtain real-time temperature data of the microbial fermentation; Step S13: using a pH sensor to monitor the fermentation pH value of the microbial fermentation process in the microbial fermentation tank in real time to obtain real-time pH value data of the microbial fermentation; Step S14: using an oxygen concentration monitor to monitor the fermentation oxygen concentration of the microbial fermentation process in the microbial fermentation tank in real time to obtain real-time oxygen concentration data of the microbial fermentation; Step S15: using a nutrient concentration monitor to monitor the fermentation nutrient concentration of the microbial fermentation process in the microbial fermentation tank in real time, so as to obtain real-time nutrient concentration data of the microbial fermentation; Step S16: transmitting the real-time temperature data of microbial fermentation, the real-time pH value data of microbial fermentation, the real-time oxygen concentration data of microbial fermentation and the real-time nutrient concentration data of microbial fermentation to the data processing unit via a network connection.
3. The microbial fermentation optimization method based on the data analysis model according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: performing time series synchronization processing on the real-time temperature data of microbial fermentation and the real-time pH value data of microbial fermentation by a data processing unit to obtain time series synchronization data of microbial fermentation temperature and time series synchronization data of microbial fermentation pH value; Step S22: performing microbial environment temperature modeling analysis on the microbial fermentation temperature time series synchronization data to generate a microbial fermentation environment temperature time series change simulation field; Step S23: performing a microbial environment pH dynamic simulation analysis on the microbial fermentation pH value time series synchronization data to generate a microbial fermentation environment pH value time series change simulation field; Step S24: performing a coupled analysis of the rhythmic influence of the growth environment according to the microbial fermentation environment temperature time series variation simulation field and the microbial fermentation environment pH value time series variation simulation field to generate a microbial fermentation real-time growth environment simulation field; Step S25: setting the fermentation growth dynamic field for the real-time oxygen concentration data of microbial fermentation and the real-time nutrient concentration data of microbial fermentation to generate the real-time growth rate dynamic field of microbial fermentation.
4. The microbial fermentation optimization method based on the data analysis model according to claim 3, characterized in that: Step S24 includes the following steps: Step S241: performing frequency domain change conversion processing on the microbial fermentation environment temperature time series change simulation field and the microbial fermentation environment pH value time series change simulation field to obtain the microbial fermentation temperature frequency domain change simulation field and the microbial fermentation pH value frequency domain change simulation field; Step S242: performing rhythmic frequency analysis on the microbial fermentation temperature frequency domain variation simulation field and the microbial fermentation pH value frequency domain variation simulation field to obtain the microbial fermentation temperature rhythmic frequency and the microbial fermentation pH value rhythmic frequency; Step S243: performing a temperature frequency domain rhythmic fluctuation analysis on the microbial fermentation temperature frequency domain change simulation field based on the microbial fermentation temperature rhythmic frequency to obtain a microbial fermentation temperature frequency domain rhythmic fluctuation change relationship; Step S244: performing a pH value frequency domain rhythmic fluctuation analysis on the pH value frequency domain change simulation field of the microbial fermentation based on the pH value rhythmic frequency of the microbial fermentation to obtain a pH value frequency domain rhythmic fluctuation change relationship of the microbial fermentation; Step S245: Based on the relationship between the rhythmic fluctuations in the frequency domain of microbial fermentation temperature and the rhythmic fluctuations in the frequency domain of microbial fermentation pH value, a coupling analysis of the rhythmic influence of the growth environment is performed on the simulation field of the frequency domain change of microbial fermentation temperature and the simulation field of the frequency domain change of microbial fermentation pH value to generate a real-time growth environment simulation field for microbial fermentation.
5. The microbial fermentation optimization method based on the data analysis model according to claim 4, characterized in that: Step S245 includes the following steps: The frequency domain rhythmic fluctuation relationship of microbial fermentation temperature and the frequency domain rhythmic fluctuation relationship of microbial fermentation pH value were analyzed by frequency domain rhythmic synchronization interaction mining, and the frequency domain rhythmic synchronization interaction relationship of microbial temperature-pH was obtained. The frequency domain rhythmic interaction effect pattern recognition analysis was performed on the frequency domain rhythmic synchronization interaction relationship of microbial temperature and pH to obtain the frequency domain rhythmic change interaction effect pattern of microbial temperature and pH. Based on the interaction effect model of microbial temperature-pH frequency domain rhythmic changes, the rhythmic phase influence constraint analysis is performed on the microbial fermentation temperature frequency domain change simulation field and the microbial fermentation pH value frequency domain change simulation field to generate the microbial fermentation temperature frequency domain rhythmic phase influence constraint and the microbial fermentation pH value frequency domain rhythmic phase influence constraint; According to the frequency domain rhythmic phase influence constraint of the microbial fermentation temperature, the temperature frequency domain phase of the microbial fermentation temperature frequency domain change simulation field is dynamically adjusted to obtain the microbial temperature frequency domain phase dynamic adjustment simulation field; according to the frequency domain rhythmic phase influence constraint of the microbial fermentation pH value, the pH frequency domain phase of the microbial fermentation pH value frequency domain change simulation field is dynamically adjusted to obtain the microbial pH value frequency domain phase dynamic adjustment simulation field; The real-time growth environment simulation coupling processing is performed on the microbial temperature frequency domain phase dynamic adjustment simulation field and the microbial pH value frequency domain phase dynamic adjustment simulation field to generate a real-time growth environment simulation field for microbial fermentation.
6. The microbial fermentation optimization method based on the data analysis model according to claim 3, characterized in that: Step S25 includes the following steps: Step S251: plotting concentration change curves for the real-time oxygen concentration data of microbial fermentation and the real-time nutrient concentration data of microbial fermentation to generate a microbial fermentation oxygen concentration change curve and a microbial fermentation nutrient concentration change curve; Step S252: performing a statistical analysis of dissolved oxygen on the oxygen concentration variation curve of the microbial fermentation to obtain the real-time dissolved oxygen in the microbial fermentation process; performing a statistical analysis of nutrient consumption on the nutrient concentration variation curve of the microbial fermentation to obtain the real-time nutrient consumption in the microbial fermentation process; Step S253: performing a microbial growth rate prediction analysis on the corresponding microbial fermentation process according to the real-time dissolved oxygen amount and the real-time consumption of nutrients in the microbial fermentation process, so as to obtain the real-time growth rate of the microbial fermentation process; Step S254: performing a growth rate mass transfer kinetic analysis on the real-time growth rate of the microbial fermentation process to obtain the real-time growth rate mass transfer kinetic parameters of the microbial fermentation; Step S255: Based on the mass transfer kinetic parameters of the real-time growth rate of microbial fermentation, the fermentation growth kinetic field of the corresponding microbial fermentation process is set to generate the real-time growth rate kinetic field of microbial fermentation.
7. The microbial fermentation optimization method based on the data analysis model according to claim 6, characterized in that: Step S255 includes the following steps: The microbial fermentation process is divided into growth stages to obtain the fermentation process of microorganisms in different growth stages; Based on the real-time growth rate mass transfer kinetic parameters of microbial fermentation, the fermentation mass transfer dynamic process of microorganisms in different growth stages is simulated and analyzed to obtain the biomass transfer kinetic simulation process of microbial fermentation in different growth stages; The mass transfer dynamics field fusion setting is performed on the biomass transfer dynamics simulation process in different growth stages of the microbial fermentation process to generate the real-time mass transfer dynamics field of microbial fermentation; Based on the real-time mass transfer dynamic field of microbial fermentation, the growth rate dynamic response simulation of the corresponding microbial fermentation process is carried out to generate the real-time growth rate dynamic field of microbial fermentation.
8. The microbial fermentation optimization method based on the data analysis model according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: performing population growth environment condition optimization analysis on the corresponding microbial fermentation process in the microbial fermentation tank based on the microbial fermentation real-time growth environment simulation field to obtain the optimal growth environment conditions of different microbial populations in the microbial fermentation process; Step S32: performing growth environment metabolic impact constraint analysis on the optimal growth environment conditions of different microbial populations during the microbial fermentation process to obtain growth environment metabolic impact constraint targets of different microbial populations; Step S33: performing population growth metabolic kinetics characteristic analysis on the corresponding microbial fermentation process in the microbial fermentation tank based on the real-time growth rate kinetics field of microbial fermentation to obtain growth metabolic kinetics characteristic data of different microbial populations; Step S34: establishing an environmental constraint analysis mathematical equation for the growth metabolic kinetic characteristic data of different microbial populations based on the growth environment metabolic impact constraint targets of different microbial populations, so as to generate a microbial population fermentation environment constraint-growth metabolic data analysis mathematical equation; Step S35: Perform fermentation growth metabolism analysis modeling processing according to the microbial population fermentation environment constraint-growth metabolism data analysis mathematical equation to construct a microbial fermentation environment constraint-growth metabolism data analysis model.
9. The microbial fermentation optimization method based on the data analysis model according to claim 8, characterized in that: Step S31 includes the following steps: Based on the real-time growth environment simulation field of microbial fermentation, the population growth environment conditions of the corresponding microbial fermentation process in the microbial fermentation tank are simulated and set to obtain different initial simulation conditions for the growth environment set for each microbial population; Perform spatial distribution analysis of microbial populations on the corresponding microbial fermentation process in the microbial fermentation tank to obtain the growth spatial distribution position of each microbial population; By performing population growth position distribution density analysis on the growth space distribution position corresponding to each microbial population under different initial growth environment simulation conditions set for each microbial population, the microbial distribution density at the corresponding growth space position of each microbial population under different growth environment conditions is obtained; Based on the microbial distribution density of each microbial population at the corresponding growth space position under different growth environment conditions, the corresponding initial simulation conditions of the growth environment are quantitatively calculated to obtain the growth environment preference value of each microbial population under different growth environment conditions; According to the growth environment preference value of each microbial population under different growth environment conditions, the different growth environment initial simulation conditions set for each microbial population are subjected to optimal screening of growth environment conditions to obtain the optimal growth environment conditions for different microbial populations during the microbial fermentation process.
10. The microbial fermentation optimization method based on the data analysis model according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: Based on the microbial fermentation environment constraint-growth metabolism data analysis model, a particle swarm optimization algorithm is used to optimize and analyze the growth environment parameters of the microbial fermentation process in the microbial fermentation tank to obtain the best optimization results of the microbial fermentation growth environment parameters; Step S42: performing fermentation growth and metabolic target analysis on the microbial fermentation process in the microbial fermentation tank to obtain the growth and metabolic target of the microbial fermentation process; Step S43: Based on the optimal optimization result of the microbial fermentation growth environment parameters, the nutrient supplementation strategy and metabolic pathway optimization analysis of the microbial fermentation process in the microbial fermentation tank are performed to generate a microbial fermentation nutrient supplementation strategy optimization plan and a microbial fermentation metabolic pathway optimization plan; Step S44: performing microbial fermentation optimization processing on the growth metabolic target of the microbial fermentation process according to the microbial fermentation nutrient supplementation strategy optimization scheme and the microbial fermentation metabolic pathway optimization scheme to obtain the microbial fermentation growth metabolic target optimization result.
Citation Information
Patent Citations
Feedback feeding control method and system based on multi-component concentration online detection
CN115730500A
Quantitative relation model and application thereof, and cell state monitoring method, device and system
CN116153388A
Fermentation dissolved oxygen concentration optimization control method based on digital twinborn technology
CN116540533A
Microbial fermentation process management and control system based on soft measurement
CN116656880A
Metabolic flux optimization solving method and system in biological manufacturing process
CN116913391A
Cited By
Real-time monitoring method and system for lactobacillus fermentation process based on block chain
CN119230000A
Bioreactor process optimization system and method thereof
CN119472303A
Stem cell culture information management method and system
CN119694383A
Microbial agent preparation control method based on bacterial strain reproduction characteristic analysis
CN119724368A
Diester oil microbial fermentation method and system based on fermentation process optimization
CN119799810A
