Prediction device, control device, manufacturing method, and program

Abstract

To provide prediction devices or the like capable of predicting the concentration of an oil as a substrate.SOLUTION: A prediction device according to an aspect of the present invention is a prediction device in a culture system for producing a biodegradable polymer by culturing microorganisms using an oil as a substrate, comprising: a near-infrared spectroscopic analysis unit that analyzes components contained in a culture solution; an acquisition unit that acquires variables related to a culture by the culture system; and a prediction unit that predicts the concentration of the substrate based on the analysis result by the near-infrared spectroscopic analysis unit and the variables acquired by the acquisition unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a prediction device, a control device, a manufacturing method, and a program. [Background technology]

[0002] Biodegradable polymers that are produced by microorganisms using vegetable oils as raw materials and that are biodegradable, for example, even in seawater, have been known for some time. One example of such a biodegradable polymer is PHBH (Kaneka Biodegradable Polymer, registered trademark). The production process for biodegradable polymers includes, for example, a culturing step, a refining step, and a post-treatment step. The culturing step includes, for example, a seed culture step and a main culture step, and the main culture step includes a medium preparation step, an inoculation step, a carbon source (oil) feeding step, and a culturing step.

[0003] A known technology for culturing cells is, for example, that disclosed in Patent Document 1. The cell culture control system described in Patent Document 1 measures metabolite concentrations in a culture medium, generates time-series data, and controls the physical and chemical variables of the culture medium based on feature points of the time-series data. Furthermore, the cell culture control system has a simulation unit 7 that measures nutrient source concentrations, metabolite concentrations, pH, temperature, dissolved oxygen concentration, and osmotic pressure of the culture medium, calculates predicted values ​​of the time-series data, and extracts feature points of the predicted values.

[0004] A state detection technique using a near-infrared spectrophotometer in a technique for culturing microorganisms is described in, for example, Non-Patent Document 1.

[0005] Furthermore, techniques using a near-infrared spectroscopic analyzer are known, for example, from Patent Documents 2 and 3. Patent Document 2 describes a method for producing an aromatic petroleum resin, in which a near-infrared spectroscopic analyzer is used to measure the absorption spectrum of a sample in a reactor in a polymerization step at wavelengths of 800 to 2500 nm, the physical properties of the aromatic petroleum resin obtained in the final step are predicted based on the measured values, and the production process is controlled based on the predicted values.

[0006] Patent Document 3 describes a method for producing aliphatic polyesters, in which a measuring device including a near-infrared spectrometer having an analyzer capable of performing multivariate analysis using chemometrics is used to measure the near-infrared absorption spectrum of a test substance during a dehydration condensation reaction, and then, based on the measurement data, at least one physical property value selected from the number of terminal groups (or terminal group concentration), moisture, concentration, and molecular weight is calculated, and from these calculated values, a computing device is used to obtain equipment control information, and this information is used to remotely operate the instrumentation of the reactor to control specific reaction conditions and reaction time. [Prior art documents] [Patent documents]

[0007] [Patent Document 1] Japanese Patent Application Laid-Open No. 2015-216886 [Patent Document 2] Japanese Patent Application Laid-Open No. 2002-145966 [Patent Document 3] Japanese Patent Application Publication No. 11-60711 [Non-patent literature]

[0008] [Non-Patent Document 1] MV Cruz et al., “Online monitoring of P(3HB) produced from used cooking oil with near-infrared spectroscopy”, Journal of Biotechnology 194 (2015) 1-9 Summary of the Invention [Problem to be solved by the invention]

[0009] In the above-mentioned fed-batch culture process using oil as a substrate, the inventors have found that it is important to appropriately control the substrate concentration in the culture system, taking productivity and other factors into consideration. A small amount of oil reduces the assimilation rate, while an excessive amount of oil fed into the culture medium causes foaming, making stable culture difficult. However, with the techniques described in Non-Patent Document 1 and Patent Documents 2-3, the absorption positions of the functional groups (e.g., methyl groups, carbonyl groups) in the PHBH skeleton and the functional groups (e.g., methyl groups, carbonyl groups) derived from the oil appear close to each other in near-infrared spectrophotometers, making it difficult to obtain a good calibration curve. In this case, obtaining a good calibration curve in a near-infrared spectrophotometer requires, for example, a large amount of data.

[0010] Furthermore, errors in oil concentration measurements using a near-infrared spectrophotometer can occur due to factors such as the degree of polymerization of the polymer, its concentration in the culture system, the influence of oil immiscibility, and the influence of foaming. Furthermore, errors in oil concentration measurements using a near-infrared spectrophotometer are influenced not only by physical and chemical influences of NIR, such as the temperature in the culture system, the particle size and pH of the bacterial cells, and the absorption of near-infrared light due to general molecular vibration and rotation, but also by electronic transitions and scattering of near-infrared light. Figure 13 shows an example of the relationship between measured NIR intensity and wavenumber.

[0011] Therefore, an object of the present invention is to provide a prediction device, a control device, a manufacturing method, and a program that can predict the concentration of oil as a substrate. [Means for solving the problem]

[0012] The prediction device according to one aspect of the present invention is a device for predicting the occurrence of a disease by culturing microorganisms using oil as a substrate. Copolymer of 3HB (3-hydroxybutyrate) and 3HH (3-hydroxyhexanoate)a near-infrared spectroscopic analysis unit that analyzes components contained in a culture solution; an acquisition unit that acquires variables related to the culture by the culture system; and a prediction unit that predicts the concentration of the substrate based on the analysis results by the near-infrared spectroscopic analysis unit and the variables acquired by the acquisition unit, wherein the analysis results by the near-infrared spectroscopic analysis unit include an oil concentration and a dry cell weight, and the variables related to the culture include an integrated value of the amount of ammonia water fed, the amount of oil fed, and strain information. The prediction device according to one aspect of the present invention is a device for predicting the occurrence of a disease by culturing microorganisms using oil as a substrate. Copolymer of 3HB (3-hydroxybutyrate) and 3HH (3-hydroxyhexanoate) a prediction device for a culture system for producing a substance comprising: a near-infrared spectroscopic analysis unit that analyzes components contained in a culture solution; an acquisition unit that acquires variables related to the culture by the culture system; and a prediction unit that predicts the concentration of the substrate based on the analysis results by the near-infrared spectroscopic analysis unit and the variables acquired by the acquisition unit, wherein the analysis results by the near-infrared spectroscopic analysis unit include an oil concentration and a copolymer ratio, and the variables related to the culture include an oil feed amount, an ammonia water feed amount, a culture time, strain information, and an OUR (oxygen consumption rate).

[0013] The control device according to one aspect of the present invention is a device for cultivating microorganisms using oil as a substrate. Copolymer of 3HB (3-hydroxybutyrate) and 3HH (3-hydroxyhexanoate) a control device for a culture system for producing a compound, the control device comprising: a near-infrared spectroscopic analysis unit that analyzes components contained in a culture solution; an acquisition unit that acquires variables related to the culture by the culture system; a prediction unit that predicts a concentration related to the substrate based on the analysis results by the near-infrared spectroscopic analysis unit and the variables acquired by the acquisition unit; and a control unit that controls the culture system based on the prediction results by the prediction unit, wherein the analysis results by the near-infrared spectroscopic analysis unit include an oil concentration and a dry cell weight, and the variables related to the culture include an integrated value of the amount of ammonia water fed, the amount of oil fed, and strain information. The control device according to one aspect of the present invention is a device for cultivating microorganisms using oil as a substrate. Copolymer of 3HB (3-hydroxybutyrate) and 3HH (3-hydroxyhexanoate)a control device for a culture system for producing a compound, the control device comprising: a near-infrared spectroscopic analysis unit that analyzes components contained in the culture solution; an acquisition unit that acquires variables related to the culture by the culture system; a prediction unit that predicts the concentration of the substrate based on the analysis results by the near-infrared spectroscopic analysis unit and the variables acquired by the acquisition unit; and a control unit that controls the culture system based on the prediction results by the prediction unit, wherein the analysis results by the near-infrared spectroscopic analysis unit include an oil concentration and a copolymer ratio, and the variables related to the culture include an oil feed rate, an ammonia water feed rate, a culture time, strain information, and an OUR (oxygen consumption rate).

[0014] The production method according to one aspect of the present invention is a method for culturing a microorganism using oil as a substrate. Copolymer of 3HB (3-hydroxybutyrate) and 3HH (3-hydroxyhexanoate) The method for producing a compound in a culture system includes the steps of: analyzing components contained in a culture solution by near-infrared spectroscopy; acquiring variables related to the culture in the culture system; and predicting the concentration of the substrate based on the analysis results of the components and the variables, wherein the analysis results of the components contained in the culture solution include an oil concentration and a dry cell weight, and the variables related to the culture include an integrated value of the amount of ammonia water fed, the amount of oil fed, and strain information. The production method according to one aspect of the present invention is a method for culturing a microorganism using oil as a substrate. Copolymer of 3HB (3-hydroxybutyrate) and 3HH (3-hydroxyhexanoate) The method for producing a substrate in a culture system includes the steps of: analyzing components contained in a culture solution by near-infrared spectroscopy; acquiring variables related to the culture in the culture system; and predicting the concentration of the substrate based on the analysis results of the components and the variables, wherein the analysis results of the components contained in the culture solution include an oil concentration and a copolymer ratio, and the variables related to the culture include an oil feed rate, an ammonia water feed rate, a culture time, strain information, and an OUR (oxygen consumption rate).

[0015] A program according to one aspect of the present invention is a method for culturing microorganisms using oil as a substrate. Copolymer of 3HB (3-hydroxybutyrate) and 3HH (3-hydroxyhexanoate)a step of analyzing components contained in the culture solution by near-infrared spectroscopy; a step of acquiring variables related to the culture by the culture system; and a step of predicting the concentration of the substrate based on the analysis results of the components and the variables, wherein the analysis results of the components contained in the culture solution include an oil concentration and a dry cell weight, and the variables related to the culture include an integrated value of the amount of ammonia water fed, the amount of oil fed, and strain information. A program according to one aspect of the present invention is a method for culturing microorganisms using oil as a substrate. Copolymer of 3HB (3-hydroxybutyrate) and 3HH (3-hydroxyhexanoate) a step of analyzing components contained in the culture solution by near-infrared spectroscopy; a step of acquiring variables related to the culture by the culture system; and a step of predicting the concentration of the substrate based on the analysis results of the components and the variables, wherein the analysis results of the components contained in the culture solution include an oil concentration and a dry cell weight, and the variables related to the culture include an integrated value of the amount of ammonia water fed, the amount of oil fed, and strain information. [Effects of the Invention]

[0016] According to the present invention, it is possible to predict the concentration of oil as a substrate. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a diagram showing an example of a culture system 1 according to an embodiment. [Figure 2] FIG. 2 is a block diagram showing an example of a learning device 400 according to an embodiment. [Figure 3] FIG. 1 is a diagram illustrating the relationship between explanatory variables, a prediction model, and a response variable in an embodiment. [Figure 4] FIG. 10 is a diagram showing the results of evaluating a prediction model through a learning process in an embodiment. [Figure 5] FIG. 10 is a diagram showing an evaluation of the results of oil concentration prediction using a prediction model in an embodiment. [Figure 6]FIG. 10 is a diagram showing the relationship between the oil concentration predicted according to the embodiment and the measured oil concentration as a comparative example. [Figure 7] FIG. 1A is a diagram showing the relationship between the oil concentration measured by a gas chromatography (GC) device and the oil concentration measured by NIR, and FIG. 1B is a diagram showing the relationship between the oil concentration measured by a gas chromatography (GC) device and the oil concentration predicted by the prediction model of the embodiment. [Figure 8] FIG. 10 is a diagram showing the results of evaluating a prediction model through a learning process in an embodiment. [Figure 9] FIG. 10 is a diagram showing an evaluation of the results of oil concentration prediction using a prediction model in an embodiment. [Figure 10] FIG. 10 is a diagram showing the relationship between the oil concentration predicted according to the embodiment and the measured oil concentration as a comparative example. [Figure 11] FIG. 1A is a diagram showing the relationship between the oil concentration measured by a gas chromatography (GC) device and the oil concentration measured by NIR, and FIG. 1B is a diagram showing the relationship between the oil concentration measured by a gas chromatography (GC) device and the oil concentration predicted by the prediction model of the embodiment. [Figure 12] (A) is a histogram showing the residual between the oil concentration measured by a gas chromatography (GC) device and the oil concentration measured by NIR, and (B) is a histogram showing the residual between the oil concentration measured by a gas chromatography (GC) device and the oil concentration predicted by the prediction model of the embodiment. [Figure 13] FIG. 1 is a diagram showing an example of the relationship between the measured intensity of NIR and the wave number. DETAILED DESCRIPTION OF THE INVENTION

[0018] A prediction device, a control device, a manufacturing method, and a program to which the present invention is applied will be described below with reference to the drawings.

[0019] [Overview of Culture System 1] FIG. 1 is a diagram showing an example of a culture system 1 according to an embodiment. The culture system 1 according to an embodiment is a system for culturing microorganisms in a process for producing a biodegradable polymer by culturing the microorganisms using oil as a substrate. The biodegradable polymer is, for example, PHBH (Kaneka Biodegradable Polymer) (registered trademark), which is a type of PHA (polyhydroxyalkanoate) and is a copolymer of 3HB (3-hydroxybutyrate) and 3HH (3-hydroxyhexanoate). PHBH is a raw material for biodegradable plastics. However, the object of production in this embodiment is not limited to PHBH, and may be other copolymers such as PHA. In an embodiment, the PHA may be P(3HB), a homopolymer of 3-hydroxybutanoic acid (3HB), P(3HB-co-3HV), a copolymer of 3HB and 3-hydroxyvaleric acid (3HV), P(3HB-co-3HH) (abbreviation: PHBH), a copolymer of 3HB and 3-hydroxyhexanoic acid (3HH), or a copolymer of 3HB and 4-hydroxybutanoic acid (4HB).

[0020] The PHBH production process is carried out, for example, in the order of a culture process, a purification process, and a post-treatment process. The culture process includes, for example, a process called a seed culture process and a main culture process, which includes a medium preparation process, an inoculation process, a process of feeding oil as a substrate, and a culture process. In the oil feeding process, phosphoric acid and aqueous ammonia are fed as other substrates. In the oil feeding process, the culture system 1 of the embodiment predicts the oil concentration in the culture solution to manage the oil flow rate. As a result, the culture system 1 can, for example, display the predicted oil concentration in real time, allowing a manager to be aware of the oil concentration. Furthermore, the culture system 1 of the embodiment may automatically control the oil flow rate based on the predicted oil concentration in the culture solution.

[0021] In an embodiment, the PHA microbial culture substrate is, for example, oil. Oils include fats and oils, fatty acids, and glycerin. Fat and oil are esters of fatty acids and glycerin. However, the substrate for PHA microbial culture is not limited to oil, and may be a fatty acid, a carbon source such as glucose, or a combination thereof. In an embodiment, fats and oils used in the culture are, for example, triacylglycerol, diacylglycerol, monoacylglycerol, etc. In an embodiment, fatty acids used in the culture are, for example, palmitic acid, oleic acid, linoleic acid, stearic acid, etc.

[0022] [Configuration of Culture System 1] As shown in FIG. 1, the culture system 1 includes a culture device 100. The culture device 100 includes, for example, a culture tank 110, an agitator 120, a pump system 130, and a group of sensors (140, 142, 144, 146, and 148). A culture solution is stored in the culture tank 110. The agitator 120 includes, for example, a motor and a motor drive unit (not shown), a stirrer 112, and the like, and agitates the culture solution stored in the culture tank 110. The pump system 130 includes a pump, a pump drive unit (not shown), and a flow path connected to the pump, and supplies materials necessary for culture, such as oil, NH4OH, and H3PO4, into the culture tank 110. The exhaust gas sensor 140 outputs a signal based on the oxygen concentration and a signal based on the CO2 concentration in the gas discharged from the culture tank 110. The dissolved oxygen (DO) sensor 142 outputs a signal based on the concentration of oxygen dissolved in the culture solution. The temperature sensor 144 outputs a signal based on the temperature of the culture solution. The pH sensor 146 outputs a signal related to the pH of the culture solution. The NIR (near-infrared) sensor 148 includes, for example, a light source that emits near-infrared light and a light detection unit that detects reflected light or transmitted light from the culture solution. The NIR sensor 148 outputs a signal based on the reflected light.

[0023] The culture device 100 further includes an O2 / CO2 acquisition unit 200, a DO acquisition unit 202, a temperature acquisition unit 204, a pH acquisition unit 206, and an NIR analysis unit 208. The O2 / CO2 acquisition unit 200 acquires a signal based on the oxygen concentration in the gas and a signal based on the CO2 concentration from the exhaust gas sensor 140, and supplies the O2 concentration information and CO2 concentration information of the exhaust gas to the prediction device 300. The DO acquisition unit 202 acquires a signal based on the concentration of oxygen dissolved in the culture solution from the dissolved oxygen sensor 142, and supplies the dissolved oxygen concentration information to the prediction device 300. The temperature acquisition unit 204 acquires a signal based on the temperature of the culture solution from the temperature sensor 144, and supplies the culture solution temperature information to the prediction device 300. The pH acquisition unit 206 acquires a signal based on the pH of the culture solution from the pH sensor 146, and supplies the pH information to the prediction device 300. The NIR analysis unit 208 is a near-infrared spectrophotometer that acquires a signal based on reflected light or transmitted light from the NIR sensor 148, analyzes the acquired signal, and supplies the analysis result to the prediction device 300. The NIR analysis unit 208 is an example of a near-infrared spectroscopic analysis unit that analyzes components contained in the culture solution. The O2 / CO2 acquisition unit 200, the DO acquisition unit 202, the temperature acquisition unit 204, and the pH acquisition unit 206 are examples of acquisition units that acquire variables related to culture by the culture system 1.

[0024] The culture device 100 further includes a prediction device 300, a learning device 400, a display device 500, and a control device 600. The prediction device 300 predicts the oil concentration in the culture solution based on the analysis results from the NIR analysis unit 208 and variables related to the culture by executing processing based on the prediction model 304 using the prediction processing unit 302. The prediction processing unit 302 is realized by a processor such as a CPU (Central Processing Unit) executing a program stored in a program memory. The prediction model 304 is, for example, a regression model that receives explanatory variables as variables related to the culture as input and outputs a response variable as the oil concentration in the culture solution. The explanatory variables are, for example, physically acquired information and information stored in the explanatory variable storage unit 310.

[0025] The display device 500 is, for example, a display device that can be viewed by a manager of the culture system 1. The display device 500 displays, for example, information related to the oil concentration predicted by the prediction device 300.

[0026] The control device 600 controls each part of the culture system 1 based on the oil concentration predicted by the prediction device 300. The control device 600 includes a processor such as a CPU, and is realized by the processor executing a program stored in a program memory. For example, the control device 600 calculates a target oil flow rate based on the oil concentration predicted at a predetermined timing in the culture process, and controls the pump system 130 to approach the target oil flow rate. It is desirable to set the predetermined timing to occur continuously, for example, every few minutes, so that the control device 600 continuously obtains the oil concentration and performs control based on the oil concentration.

[0027] Furthermore, it is desirable that the control device 600 controls the pump system 130 so as to optimize the oil flow rate based on the O2 concentration and CO2 concentration in the exhaust gas, and it is desirable that the control device 600 controls so as to optimize the oil flow rate based on foaming in the culture tank 110. In this case, it is desirable that the control device 600 controls the oil flow rate based on the oil concentration predicted by the prediction device 300 so that the oil concentration in the culture solution falls within a predetermined range.

[0028] The learning device 400 trains a prediction model 402 based on the training data stored in the training data storage unit 410. The prediction model 402 trained by the learning device 400 is introduced into the prediction device 300 as a prediction model 304.

[0029] 2 is a block diagram showing an example of a learning device 400 according to an embodiment. The learning device 400 includes, for example, a teacher data acquisition unit 420, a model construction unit 430, a prediction model 402, and a learning result storage unit 440.

[0030] The teacher data acquisition unit 420 acquires an explanatory variable x and a response variable y as teacher data from the teacher data storage unit 410. The explanatory variable x and response variable y in one teacher data have a corresponding relationship. That is, when a culture process is performed using the calculated NIR value and / or culture conditions specified by the explanatory variable x in a certain teacher data, the oil concentration will be specified by the response variable y in the teacher data.

[0031] The model construction unit 430 inputs an explanatory variable x to the prediction model 402 and learns a function f or processing parameters that specify the prediction model 402 so that the prediction model 402 outputs a response variable y corresponding to the explanatory variable x. The model construction unit 430 recursively calculates (updates) the function f or processing parameters so that, for example, the difference between the response variable y corresponding to the explanatory variable x and the output of the prediction model 402 becomes smaller. The prediction model 402 is, for example, a regression model before being trained. The function f in the prediction model 402 is, for example, an arithmetic expression that calculates the explanatory variable x, and the processing parameters are, for example, weighting coefficients in the arithmetic expression. The model construction unit 430 stores the calculated (updated) function f and processing parameters in the learning result storage unit 440.

[0032] FIG. 3 is a diagram illustrating the relationship between explanatory variables, a prediction model, and a response variable in an embodiment. The explanatory variable storage unit 310 is a storage device including, for example, a hard disk drive or a database management device. The explanatory variable storage unit 310 stores explanatory variables including calculated NIR values ​​(analysis results), culture conditions, polymer information, substrate information, process parameters, and microbial information. The information stored in the explanatory variable storage unit 310 may be information acquired by the acquisition units (200, 202, 204, 206, 208), information based on signals detected by sensors (not shown), or information received by the explanatory variable setting unit 312. The explanatory variable setting unit 312 is, for example, a personal computer used by an administrator of the culture system 1, and stores explanatory variables in the explanatory variable storage unit 310 based on the administrator's operation.

[0033] In the embodiments, the prediction model is described as a model using a regression equation. However, the regression equation for realizing the prediction model may be, but is not limited to, multiple regression, sparse regression, or partial least squares (PLS) regression in linear regression. Known regression equations that input explanatory variables and output a response variable for predicting oil concentration, as well as various regression equations applicable to predicting future oil concentrations, may also be used. The model construction unit 430 can construct a prediction model by selecting, for example, one of multiple regression, sparse regression, or PLS regression, and selecting a combination of explanatory variables that can predict oil concentration with high accuracy using the selected regression equation. Furthermore, the model construction unit 430 may predict oil concentration using an optimal combination of explanatory variables for each regression equation, or may adopt an optimal regression equation based on a combination of explanatory variables that can be obtained (measured) in the culture system 1.

[0034] The NIR calculation value (analysis result) information includes, for example, at least one of the following: the oil concentration in the culture medium, information about copolymers in the culture medium, weight-average molecular weight (Mw) information for each component contained in the culture medium, and information about the dry cell weight (DCW) in the culture medium. The NIR calculation value (analysis result) information as an explanatory variable is information that can be output by the NIR analysis unit 208 and may be information that is correlated with the oil concentration that is the prediction target. The NIR calculation value information is the analysis result of the NIR analysis unit 208, but is not limited to this, and may be information based on the analysis result of the NIR analysis unit 208, such as a value obtained by processing the analysis result of the NIR analysis unit 208. The processed value of the analysis result of the NIR analysis unit 208 may be, for example, the average value of the analysis result, a normalized value, or a data group from which anomalous data has been removed.

[0035] The culture condition information includes, for example, at least one of the following: the amount of oil (substrate) fed per unit time, the integrated value of the amount of oil (substrate) fed, the amount of alkaline solution (e.g., NH4OH) fed per unit time, the integrated value of the amount of alkaline solution (e.g., NH4OH) fed, the amount of acid solution (e.g., H3PO4) fed per unit time, the integrated value of the amount of acid solution (e.g., H3PO4) fed, the culture time information, the stirring rate information, the stirring power information, the internal pressure information of the culture vessel 110, the aeration rate information in the culture vessel 110, the temperature information of the culture medium, the pH information of the culture medium, the liquid volume information of the culture medium, and the inoculation amount information. The internal pressure information of the culture vessel 110 and the aeration rate information in the culture vessel 110 may be detected by a sensor (not shown) and may be predetermined values ​​such as target values ​​or empirical values. Note that the culture condition information as an explanatory variable may be any information of the culture conditions that is correlated with the oil concentration to be predicted. The culture condition information may also be a processed value of the culture conditions. Processed values ​​of culture conditions include, for example, average values ​​of culture conditions, normalized values, and data groups from which anomalous data has been excluded.

[0036] Polymer information is an example of information related to biodegradable polymers. The polymer information includes at least one of the concentration of the polymer (biodegradable polymer) in the culture medium, copolymer ratio information as the primary structure, and inter- and intramolecular composition distribution information in the polymer. The primary structure is, for example, a structure that indicates the state before the polymer (biodegradable polymer) is formed (e.g., copolymer, comonomer (e.g., 3HH)), and the copolymer ratio indicates the ratio of copolymer to polymer in the culture medium, and the comonomer ratio indicates the ratio of comonomer to polymer in the culture medium. The copolymer ratio and comonomer ratio are examples of information related to the primary structure of a biodegradable polymer.

[0037] The polymer information may be a measured value obtained by sampling and analyzing the culture solution, or a predetermined value such as a target value or an empirical value may be input. The polymer information as an explanatory variable may also include other information about the polymer to which the embodiment is applicable, as long as the information about the polymer is correlated with the oil concentration to be predicted. The polymer information may also be a value obtained by processing the polymer information. Examples of the processed value of the polymer information include an average value of values ​​related to the polymer, a normalized value, and a data group from which anomalous data has been removed.

[0038] The substrate information includes, for example, at least one of the following: the state of decomposition of the substrate, the types and composition ratios of fats and oils contained in the culture medium, the types and composition ratios of fatty acids contained in the culture medium, and the rate of substrate consumption. In the embodiment, fats and oils used in the culture are, for example, triacylglycerol, diacylglycerol, monoacylglycerol, etc. In the embodiment, fatty acids used in the culture are, for example, palmitic acid, oleic acid, linoleic acid, stearic acid, etc. The substrate information may be a measured value obtained by sampling and analyzing the culture medium, or a predetermined value such as a target value or an empirical value may be input. The substrate information as an explanatory variable may also include other information related to the substrate to which the embodiment is applicable, as long as the information correlates with the oil concentration to be predicted. The substrate information may be a processed value related to the substrate. The processed value related to the substrate may be, for example, the average value of the substrate values, a normalized value, or a data group from which anomalous data has been removed.

[0039] The process parameters are an example of information relating to the state of the culture system 1. The process parameters include, for example, at least one of the following: the amount of oxygen in the culture solution (dissolved oxygen concentration; DO), the O2 concentration and CO2 concentration in the exhaust gas, the oxygen uptake rate (OUR), the respiratory quotient (RQ) during culture, and parameters relating to the foaming state. Parameters relating to the foaming state include, for example, information on the position of the foaming liquid surface, changes in position, and the duration of foaming. The process parameters may be measured values, target values, empirical values, or other predetermined values. The process parameters as explanatory variables may include other information relating to the process parameters to which the embodiments are applicable, as long as the information correlates with the oil concentration to be predicted. The process parameters may be processed values ​​relating to the process parameters. Examples of processed values ​​relating to the process parameters include the average values ​​of the process parameters, normalized values, and data sets from which anomalous data has been removed.

[0040] OUR is the amount of oxygen consumed by the bacteria, and is calculated based on the detected values ​​of O2 and CO2 in the exhaust gas. A high OUR indicates a high oil assimilation rate (productivity). An increase in OUR indicates an increase in bacterial activity, while a decrease in OUR indicates at least one of the following: a decrease in bacterial activity, a decrease in oxygen supply rate, or a shortage of oil. A high OUR is desirable for improving productivity.

[0041] DO is the concentration of oxygen remaining dissolved in the culture solution; a high DO indicates that there is excess oxygen in the culture solution, resulting in a low oil assimilation rate and a shortage of oil. A low DO (≒0) indicates that all of the oxygen supplied to the culture solution has been consumed. An increase in DO indicates that there is excess oxygen in the culture solution, resulting in at least one of a decrease in bacterial activity or a shortage of oil, while a decrease in DO indicates that there is sufficient oxygen in the culture solution. A low DO is desirable for improving productivity.

[0042] RQ is the ratio of carbon dioxide (CO2) to consumed oxygen (O2), and a high RQ indicates a state in which oil is being wasted. A state in which oil is being wasted means, for example, a state in which a high proportion of consumed C is converted to CO2. A low RQ indicates a state in which oil is being efficiently converted to polymers. A state in which oil is being efficiently converted to polymers means a low proportion of consumed C is converted to CO2. A low RQ is desirable for improving productivity.

[0043] The microbial information is an example of information about microorganisms such as bacteria, yeast, mold, and archaea that produce biodegradable polymers. The microbial information includes, for example, at least one of the following: the type of strain, the particle size of the microbial cells containing the biodegradable polymer, and the microbial cell weight relative to the dry microbial cell weight of the microbial cells containing the biodegradable polymer. The microbial information may be a measured value, a target value, an empirical value, or other predetermined value. The microbial information as an explanatory variable may be any information about the microorganisms that is correlated with the oil concentration to be predicted. The microbial information may also be a value obtained by processing values ​​related to the microorganisms. Examples of values ​​obtained by processing values ​​related to the microorganisms include the average value of the values ​​related to the microorganisms, normalized values, and a data group from which anomalous data has been removed.

[0044] [Example] FIG. 4 is a diagram showing the results of evaluating the prediction model by the learning process in the above-described embodiment, and shows the MSE (mean squared error), RMSE (root mean squared error), MAE (mean absolute error), and R2 (coefficient of determination) when a partial least squares regression (PLS regression) model and a linear regression model are used as the prediction model. FIG. 5 is a diagram showing the evaluation of the results of predicting oil concentration using the prediction model in the above-described embodiment, and shows the MSE, RMSE, MAE, and R2 when a PLS regression model and a linear regression model are used as the prediction model.

[0045] FIG. 6 is a diagram showing the relationship between the oil concentration predicted by the embodiment and the measured oil concentration as a comparative example. In FIG. 4, the plotted points indicate the predicted oil concentration. The measured oil concentration was measured by sampling the oil concentration in the culture solution and measuring it using a gas chromatography device (gas chromatograph). The prediction model was partial least squares regression. The explanatory variables in the examples were the oil concentration and copolymer ratio (PHBH) as calculated values ​​of NIR. of The parameters are the ratio of 3HH to the oil content (oil feed rate, ammonia water feed rate, and culture time as culture conditions), strain information, and OUR (oxygen consumption rate) as a process parameter. According to the example, the root mean square error (RMSE) of the prediction model was 0.149 and the coefficient of determination (R2) was 0.723. It can also be seen that the predicted oil concentration is highly correlated with the measured oil concentration.

[0046] 7A is a diagram showing the relationship between the oil concentration measured by a gas chromatography (GC) device and the oil concentration measured by NIR, and FIG. 7B is a diagram showing the relationship between the oil concentration measured by a gas chromatography (GC) device and the oil concentration predicted by the prediction model of the embodiment. It can be seen from FIG. 7 that the error between the oil concentration measured by GC and the oil concentration measured by NIR is large, and the error between the oil concentration measured by GC and the oil concentration predicted by the prediction model of the embodiment is small.

[0047] Fig. 8 is a diagram showing the results of evaluating a prediction model using the learning process in the above-described embodiment, showing the MSE, RMSE, MAE, and R2 when a partial least squares regression (PLS regression) model was used as the prediction model. Fig. 9 is a diagram showing the evaluation of the results of predicting oil concentration using the prediction model in the above-described embodiment, showing the MSE, RMSE, MAE, and R2 when a PLS regression model was used as the prediction model. The explanatory variables in the examples were the oil concentration and dry cell weight as calculated NIR values, the integrated value of the ammonia water feed rate and the oil feed rate as culture conditions, and strain information (dummy variables).

[0048] FIG. 10 shows the relationship between the oil concentration predicted by the embodiment and the measured oil concentration as a comparative example. In FIG. 10, the plotted points indicate the predicted oil concentrations. The measured oil concentrations were obtained by sampling the oil concentration in the culture solution and measuring it using a gas chromatography device (gas chromatograph). The prediction model was a partial least squares regression. The explanatory variables in the example were the oil concentration and dry cell weight as calculated NIR values, the integrated value of the ammonia water feed rate and the oil feed rate as culture conditions, and strain information. According to the example, the prediction model had a root mean square error (RMSE) of 0.094 and a coefficient of determination (R2) of 0.924. It was also found that the predicted oil concentration was highly correlated with the measured oil concentration.

[0049] FIG. 11(A) shows the relationship between the oil concentration measured by a gas chromatography (GC) system and the oil concentration measured by NIR, and FIG. 11(B) shows the relationship between the oil concentration measured by the gas chromatography (GC) system and the oil concentration predicted by the prediction model of the embodiment. The lower part of FIG. 11(A) shows MSE, RMSE, MAE, and R2 as accuracy indices for the oil concentration measured by NIR, and the lower part of FIG. 11(B) shows MSE, RMSE, MAE, and R2 as accuracy indices for the oil concentration predicted by the prediction model of the embodiment. It can be seen from FIG. 11(A) that the error in the oil concentration measured by NIR is large compared to the oil concentration measured by GC, while FIG. 11(B) shows that the error in the oil concentration predicted by the prediction model of the embodiment is small compared to the oil concentration measured by GC.

[0050] 12(A) is a histogram showing the residual between the oil concentration measured by a gas chromatography (GC) and the oil concentration measured by NIR, and FIG. 12(B) is a histogram showing the residual between the oil concentration measured by a gas chromatography (GC) and the oil concentration predicted by the prediction model of the embodiment. It can be seen from FIG. 12 that the error in the oil concentration predicted by the prediction model of the embodiment is smaller than the error in the oil concentration measured by NIR.

[0051] [Effects of the embodiment] According to the embodiment, a prediction device 300 in the culture system 1 for producing biodegradable polymers by culturing microorganisms using oil as a substrate can be realized, which includes an NIR analysis unit 208 that analyzes components contained in the culture solution, an acquisition unit (e.g., 200) that acquires variables related to the culture performed by the culture system 1, and a prediction processing unit 302 that predicts the concentration of the substrate based on the analysis results from the NIR analysis unit 208 and the variables acquired by the acquisition unit. The culture system 1 according to the embodiment can predict the oil concentration. As a result, the culture system 1 can eliminate the need to collect culture solution and measure the oil concentration using GC, as in existing methods, thereby reducing the workload. Furthermore, the culture system 1 can continuously predict the oil concentration, thereby controlling the oil concentration in the culture solution with high accuracy and improving the productivity of biodegradable polymers.

[0052] Furthermore, according to the culture system 1 of the embodiment, a prediction model 304 is constructed that is trained using the analysis results by the NIR analysis unit 208, other explanatory variables, and the oil concentration as training data, and during actual prediction, the oil concentration can be predicted based on the output of the prediction model 304 in response to the analysis results by the NIR analysis unit 208 and the variables acquired by the acquisition unit (200, etc.) being input to the prediction model 304. As a result, according to the culture system 1, by repeatedly training the prediction model 304 using the analysis results by the NIR analysis unit 208 and other explanatory variables that are correlated with the oil concentration, it is possible to increase prediction accuracy and further improve productivity.

[0053] Furthermore, according to the culture system 1 of the embodiment, it is possible to realize a control device in the culture system 1 that produces biodegradable polymers by culturing microorganisms using oil as a substrate, the control device including an NIR analysis unit 208 that analyzes components contained in the culture solution, an acquisition unit (200, etc.) that acquires variables related to the culture by the culture system 1, a prediction device 300 that predicts the concentration related to the substrate based on the analysis results by the NIR analysis unit 208 and the variables acquired by the acquisition unit, and a control unit (600) that controls the culture system 1 based on the prediction results of the prediction device 300. As a result, according to the culture system 1, it is possible to continuously predict the oil concentration and control the oil concentration in the culture solution with high accuracy, thereby improving the productivity of biodegradable polymers.

[0054] Furthermore, according to the embodiment of the culture system 1, a production method in the culture system 1 for producing biodegradable polymers by culturing microorganisms using oil as a substrate can be realized, including the steps of analyzing components contained in the culture solution, acquiring variables related to the culture by the culture system 1, and predicting the concentration of the substrate based on the component analysis results and the variables. According to the embodiment of the culture system 1, a program can be realized that causes a computer in the culture system 1 for producing biodegradable polymers by culturing microorganisms using oil as a substrate to execute the steps of analyzing components contained in the culture solution, acquiring variables related to the culture by the culture system 1, and predicting the concentration of the substrate based on the component analysis results and the variables. As a result, the culture system 1 can eliminate the need to collect culture solution and measure the oil concentration using GC, as in existing methods, thereby reducing the workload. Furthermore, according to the culture system 1, by continuously predicting the oil concentration, the oil concentration in the culture solution can be controlled with high accuracy, thereby improving the productivity of biodegradable polymers.

[0055] The above describes the form for carrying out the present invention using an embodiment, but the present invention is not limited to such an embodiment, and various modifications and substitutions can be made within the scope that does not deviate from the gist of the present invention. [Explanation of symbols]

[0056] 1. Culture system 100 Culture equipment 120 Stirring device 130 Pump System 140 Exhaust gas sensor 142 Dissolved oxygen sensor 144 Temperature Sensor 146 pH sensor 148 NIR sensors 200 O2 / CO2 acquisition department 202 DO Acquisition Department 204 Temperature acquisition section 206 pH acquisition section 208 NIR analysis department 300 Prediction Device 302 Prediction processing unit 304 Predictive Model 310 Explanatory variable memory section 312 Explanatory variable setting section 400 Learning Device 410 Teacher data storage unit 430 Model Construction Department 440 Learning result memory unit 500 display device 600 control device

Claims

1. A prediction device for a culture system for producing a copolymer of 3HB (3-hydroxybutyrate) and 3HH (3-hydroxyhexanoate) by culturing a microorganism using oil as a substrate, comprising: a near-infrared spectroscopic analysis unit that analyzes components contained in the culture solution; an acquisition unit that acquires variables related to the culture by the culture system; a prediction unit that predicts a concentration of the substrate based on the analysis result by the near-infrared spectroscopic analysis unit and the variables acquired by the acquisition unit, the analysis results by the near-infrared spectroscopic analysis unit include an oil concentration and a dry cell weight; The variables related to the culture include an integrated value of the amount of aqueous ammonia fed, an amount of oil fed, and strain information.

2. A prediction device for a culture system for producing a copolymer of 3HB (3-hydroxybutyrate) and 3HH (3-hydroxyhexanoate) by culturing a microorganism using oil as a substrate, comprising: a near-infrared spectroscopic analysis unit that analyzes components contained in the culture solution; an acquisition unit that acquires variables related to the culture by the culture system; a prediction unit that predicts a concentration of the substrate based on the analysis result by the near-infrared spectroscopic analysis unit and the variables acquired by the acquisition unit, the analysis results from the near-infrared spectroscopic analysis unit include an oil concentration and a copolymer ratio; The culture variables include the oil feed rate, the ammonia water feed rate, the culture time, strain information, and OUR (oxygen consumption rate). Prediction device.

3. 3. The prediction device according to claim 1, wherein the prediction unit includes a prediction model trained using the analysis results by the near-infrared spectroscopic analysis unit, the variables, and the concentrations of the substrate as training data, and acquires an output of the concentration of the substrate from the prediction model in response to inputting the analysis results by the near-infrared spectroscopic analysis unit and the variables acquired by the acquisition unit into the prediction model.

4. A control device for a culture system for producing a copolymer of 3HB (3-hydroxybutyrate) and 3HH (3-hydroxyhexanoate) by culturing a microorganism using oil as a substrate, comprising: a near-infrared spectroscopic analysis unit that analyzes components contained in the culture solution; an acquisition unit that acquires variables related to the culture by the culture system; a prediction unit that predicts a concentration of the substrate based on the analysis result by the near-infrared spectroscopic analysis unit and the variables acquired by the acquisition unit; a control unit that controls the culture system based on the prediction result of the prediction unit, the analysis results by the near-infrared spectroscopic analysis unit include an oil concentration and a dry cell weight; The variables related to the culture include an integrated value of the amount of aqueous ammonia fed, an amount of oil fed, and strain information.

5. A control device for a culture system for producing a copolymer of 3HB (3-hydroxybutyrate) and 3HH (3-hydroxyhexanoate) by culturing a microorganism using oil as a substrate, comprising: a near-infrared spectroscopic analysis unit that analyzes components contained in the culture solution; an acquisition unit that acquires variables related to the culture by the culture system; a prediction unit that predicts a concentration of the substrate based on the analysis result by the near-infrared spectroscopic analysis unit and the variables acquired by the acquisition unit; a control unit that controls the culture system based on the prediction result of the prediction unit, the analysis results from the near-infrared spectroscopic analysis unit include an oil concentration and a copolymer ratio; A control device, wherein the variables related to the culture include the oil feed rate, the ammonia water feed rate, the culture time, strain information, and OUR (oxygen consumption rate).

6. A method for producing a copolymer of 3HB (3-hydroxybutyrate) and 3HH (3-hydroxyhexanoate) in a culture system by culturing a microorganism using oil as a substrate, comprising: A step of analyzing components contained in the culture solution by near-infrared spectroscopy; acquiring variables related to the culture by the culture system; and predicting a concentration for the substrate based on the analysis of the component and the variable; The analysis results of the components contained in the culture solution include an oil concentration and a dry cell weight, The variables related to the culture include an integrated value of the amount of aqueous ammonia added, an amount of oil added, and strain information.

7. A method for producing a copolymer of 3HB (3-hydroxybutyrate) and 3HH (3-hydroxyhexanoate) in a culture system by culturing a microorganism using oil as a substrate, comprising: A step of analyzing components contained in the culture solution by near-infrared spectroscopy; acquiring variables related to the culture by the culture system; and predicting a concentration for the substrate based on the analysis of the component and the variable; The analysis results of the components contained in the culture solution include an oil concentration and a copolymer ratio, The variables related to the culture include the amount of oil fed, the amount of aqueous ammonia fed, the culture time, strain information, and OUR (oxygen consumption rate).

8. In the step of supplying the substrate to the culture solution by the culture system, the amount of the substrate supplied is controlled based on the predicted concentration of the substrate. The method according to claim 6 or 7.

9. A computer in a culture system for producing a copolymer of 3HB (3-hydroxybutyrate) and 3HH (3-hydroxyhexanoate) by culturing a microorganism using oil as a substrate is installed. A step of analyzing components contained in the culture solution by near-infrared spectroscopy; acquiring variables related to the culture by the culture system; predicting a concentration of the substrate based on the analysis of the component and the variable; The analysis results of the components contained in the culture solution include an oil concentration and a dry cell weight, The variables related to the culture include an integrated value of the amount of aqueous ammonia fed, an amount of oil fed, and strain information.

10. A computer in a culture system for producing a copolymer of 3HB (3-hydroxybutyrate) and 3HH (3-hydroxyhexanoate) by culturing a microorganism using oil as a substrate is installed. A step of analyzing components contained in the culture solution by near-infrared spectroscopy; acquiring variables related to the culture by the culture system; predicting a concentration of the substrate based on the analysis of the component and the variable; The analysis results of the components contained in the culture solution include an oil concentration and a dry cell weight, The variables related to the culture include an integrated value of the amount of aqueous ammonia fed, an amount of oil fed, and strain information.

Images