Prediction methods and manufacturing methods

Abstract

To predict OUR (Oxygen Uptake Rate).SOLUTION: Provided is a prediction method for predicting OUR (oxygen uptake rate) at time B based on parameters related to the nutrient source of a culture from time A, which is one or more past time points, to time B, which is a time point after time A, and the OUR actually measured from time A to time C, which is a time point after time A but before time B.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] In culturing, the occurrence of contamination is judged by humans, so there is a possibility of misjudgment due to human error. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2019-129726 [Patent Document 2] Special Publication No. 2017-521080 Summary of the Invention [Problem to be solved by the invention]

[0004] An object of the present invention is to provide a prediction method and a manufacturing method that can predict OUR (oxygen uptake rate). [Means for solving the problem]

[0005] One aspect of the present invention is a prediction method for predicting OUR at time B based on parameters related to the nutrient source of culture from time A, which is one or more past time points, to time B, which is a time point after time A, and the OUR (oxygen uptake rate) actually measured from time A to time C, which is a time point after time A but before time B. [Effects of the Invention]

[0006] According to the present invention, OUR (oxygen uptake rate) can be predicted. [Brief explanation of the drawings]

[0007] [Figure 1]FIG. 1 is a diagram illustrating an outline of a culture system according to an embodiment of the present invention. [Figure 2] FIG. 1 shows an example of changes in OUR in a culture tank. [Figure 3] FIG. 1 shows an example of parameters related to the nutrient source of the culture from time A to time B. [Figure 4] FIG. 1 shows an example of parameters related to the nutrient source of the culture from time A to time B. [Figure 5] FIG. 1 illustrates the input and output of a trained model. [Figure 6] FIG. 2 is a diagram illustrating an example of a hardware configuration of a prediction device according to the present embodiment. [Figure 7] 10 is a flowchart illustrating an example of a flow of processing executed by the prediction device of the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0008] (Culture system) Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. 1 is a diagram illustrating an overview of a culture system 1 of this embodiment. The culture system 1 of this embodiment includes a prediction device 10, a culture measurement device 20, and a culture device 30.

[0009] The culture device 30 performs culture. The culture device 30 includes, for example, a culture tank, and produces a material by culturing in the culture tank. The material produced by the culture device 30 is, for example, polyhydroxyalkanoate. The culture measuring device 20 measures parameters related to the nutrient source for culture and the OUR (oxygen uptake rate) of the culture tank in which culture is performed in the culture device 30. The culture measuring device 20 is attached to, for example, the culture device 30, and measures the parameters related to the nutrient source for culture and the OUR of the culture tank. The parameters related to the nutrient source for the culture include, for example, the flow rate of a carbon source into the culture tank where the culture is performed. The carbon source includes, for example, oil. The parameters related to the nutrient source for the culture include, for example, the flow rate of a nitrogen source into the culture tank where the culture is performed. The parameters related to the nutrient source for the culture may further include at least one selected from the concentration of the carbon source in the culture tank where the culture is performed, the concentration of the nitrogen source in the culture tank, the flow rate of the phosphorus source into the culture tank, and the concentration of the phosphorus source in the culture tank.

[0010] The prediction device 10 includes a control unit 11 including a processor 91, such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit) or an NPU (Neural Network Processing Unit), and a memory 92, which are connected via a bus. The control unit 11 executes, for example, an information acquisition process and a prediction process.

[0011] (Information acquisition processing) The information acquisition process is a process of acquiring information used in the prediction process from the culture measuring device 20. The prediction process is a process of predicting the OUR based on the information acquired by the information acquisition process.

[0012] Figure 2 shows an example of the change in OUR in a culture tank. The following explanation will be given by defining the time points as A, C, and B in order of oldest to newest. The time between A and C and the time between C and B are determined arbitrarily.

[0013] The information acquired by the information acquisition process includes parameters related to the nutrient source of the culture from time point A to time point B. The parameters related to the nutrient source of the culture from time point A to time point B may be parameters related to the nutrient source of the culture at one or more time points from time point A to time point B.

[0014] When the parameter related to the nutrient source for the culture is the flow rate of a carbon source, a nitrogen source, or a phosphorus source, the parameter related to the nutrient source for the culture from time A to time B may be the integrated amount of flow rate from each of one or more time points from time A to time B to a predetermined time before. The parameters related to the nutrient source of the culture from time A to time B are, for example, parameters related to the nutrient source of the culture obtained at regular time intervals from time A to time B. The regular time interval is preferably 1 minute or more and 30 minutes or less, and more preferably 5 minutes or more and 10 minutes or less.

[0015] Fig. 3 is a diagram showing an example of parameters related to the nutrient source for culture from time A to time B. In the parameters related to the nutrient source for culture shown in Fig. 3, time B is used as the reference, and time A is -150 minutes before time B. The parameters related to the nutrient source for culture shown in Fig. 3 are the concentrations of the carbon source in the culture tank where culture is performed at 16 time points at 10-minute intervals from time A to time B.

[0016] FIG. 4 is a diagram showing an example of parameters related to the nutrient source for culture from time A to time B. In the parameters related to the nutrient source for culture shown in FIG. 3, time B is used as the reference, and time A is -150 minutes before time B. The parameters related to the nutrient source for culture shown in FIG. 3 are the integrated amount of flow of the carbon source into the culture tank where culture is performed from each of 16 time points at 10-minute intervals from time A to time B to 30 minutes before. For example, at time B, the integrated amount of flow of the carbon source from time B to 30 minutes before time B is calculated.

[0017] The information acquired by the information acquisition process includes the OUR measured at time C. The OUR measured at time C may be the OUR measured at one or more time points between time A and time B. The OUR measured at time C is, for example, the OUR measured at regular time intervals during the time period between time A and time B.

[0018] The control unit 11 may acquire the parameters related to the nutrient source of the culture and the OUR at multiple points in time from the culture measurement device 20, or may acquire the parameters related to the nutrient source of the culture and the OUR from the culture measurement device 20 at the time when the OUR is measured.

[0019] (Prediction processing) The prediction process predicts the OUR at time B based on parameters related to the nutrient source for culture from time A to time B and the OUR actually measured at time C. In the prediction process, the OUR is predicted using, for example, a trained model. The trained model used is a model trained to output the OUR at time B by inputting parameters related to the nutrient source for culture from time A to time B and the OUR at time C. The prediction process predicts the OUR at time B, for example, by inputting parameters related to the nutrient source for cultivation from time A to time B and the OUR actually measured at time C into the trained model and outputting the OUR at time B. The trained model is, for example, a nonlinear regression model, such as Random Forest, XGBoost, ExtraRandomTrees, or LightGBM. FIG. 5 is a diagram illustrating the input and output of the trained model.

[0020] The control unit 11 can predict the OUR at each point in time in the future by performing the prediction process at regular intervals.

[0021] The control unit 11 may perform a process for determining whether an abnormality has occurred during culture. When performing the abnormality determination process, the control unit 11 acquires the OUR actually measured at time B. The abnormality determination process is a process for determining whether an abnormality has occurred in the culture based on the difference between the predicted OUR at time B and the actually measured OUR. The abnormality determination process is a process for determining whether an abnormality has occurred in the culture when, for example, the difference between the predicted OUR at time B and the actually measured OUR is greater than a predetermined value. An abnormal occurrence in the culture is, for example, the occurrence of contamination in the culture.

[0022] The time between time points A and C and the time between time points C and B are arbitrary, but the time between time points A and B is preferably determined by the delay time Td from when the flow rate of the nutrient source added to the culture tank of the culture device 30 is changed until the change in the flow rate of the nutrient source added appears in the OUR. The time between time points A and B is preferably equal to or greater than Td and equal to or less than Td × 3 / 2.

[0023] The time between time points C and B is preferably 20 minutes or more, and preferably 90 minutes or less. If the time between time points C and B is short, the contribution of the OUR measured at time point C becomes greater among the parameters related to the nutrient source of culture from time points A to B, which are explanatory variables for predicting the OUR at time point B, and the OUR measured at time point C, improving the prediction accuracy of the OUR at time point B, but making it difficult to detect abnormalities. Furthermore, if the time between time points C and B is long, the correlation between the OUR at time point C and the OUR at time point B becomes weaker, reducing the prediction accuracy.

[0024] <Example of Hardware Configuration of Prediction Device 10> 6 is a diagram showing an example of the hardware configuration of the prediction device 10 according to this embodiment. The prediction device 10 includes a control unit 11 having a processor 91 and a memory 92 connected via a bus, and executes a program. By executing the program, the prediction device 10 functions as a device including the control unit 11, an interface unit 12, and a storage unit 13.

[0025] More specifically, the processor 91 reads out a program stored in the storage unit 13 and stores the read out program in the memory 92. The processor 91 executes the program stored in the memory 92, whereby the prediction device 10 functions as a device including the control unit 11, the interface unit 12, and the storage unit 13.

[0026] The control unit 11 controls the operation of each functional unit included in the prediction device 10. The control unit 11, for example, acquires information stored in the memory unit 13. The process of acquiring information stored in the memory unit 13 is specifically reading. The control unit 11 may, for example, output various information to the memory unit 13. The memory unit 13 records the information output to the memory unit 13. The control unit 11, for example, acquires information acquired by the interface unit 12. The control unit 11 controls, for example, the interface unit 12 to transmit the information to be transmitted to the destination.

[0027] The control unit 11 executes, for example, an information acquisition process and a prediction process.

[0028] The interface unit 12 includes a communication interface for connecting the prediction device 10 to an external device. The interface unit 12 communicates with the external device via wired or wireless communication. The external device is, for example, a device that transmits network information. The interface unit 12 acquires network information by communicating with the device that transmits the network information.

[0029] The interface unit 12 may be configured to include input devices such as a mouse, a keyboard, a touch panel, etc. The interface unit 12 may be configured as an interface that connects these input devices to the prediction device 10. In this way, the input device of the interface unit 12 accepts input of various information to the prediction device 10 via a wired or wireless connection. Note that various information such as network information does not necessarily have to be input to the communication interface of the interface unit 12, and may also be input to the input device of the interface unit 12.

[0030] The interface unit 12 outputs, for example, various types of information. The interface unit 12 includes a display device such as a CRT (Cathode Ray Tube) display, a liquid crystal display, or an organic EL (Electro-Luminescence) display, and a speaker. The interface unit 12 may be configured as an interface that connects these display devices or speakers to the prediction device 10. Therefore, the display device and speaker included in the interface unit 12 output, for example, information input to an input device of the interface unit 12 as an image or sound.

[0031] The control unit 11 may, for example, control the operation of a display device or speaker that constitutes the interface unit 12 to output the predicted OUR or the determination result of the occurrence of an abnormality.

[0032] The storage unit 13 is configured using a computer-readable storage medium (non-transitory computer-readable recording medium) such as a magnetic hard disk drive or a semiconductor storage device. The storage unit 13 stores various information related to the prediction device 10. The storage unit 13 stores various information generated by the operation of the control unit 11, such as predicted OUR. The storage unit 13 may exist on a cloud, for example.

[0033] 7 is a flowchart showing an example of the flow of processing executed by the prediction device 10 of this embodiment. The control unit 11 executes an information acquisition process to acquire information used to predict OUR (step S11). The control unit 11 executes a prediction process to predict OUR (step S12). The control unit 11 outputs the predicted value of OUR to a predetermined output destination (step S13). The predetermined output destination is, for example, a display device or speaker constituting the interface unit 12. When the control unit 11 performs the process of determining whether an abnormality has occurred in the culture, the control unit 11 may output the determination result of the abnormality.

[0034] The above-described method for predicting OUR may be included in the steps of a method for producing a material (for example, polyhydroxyalkanoate) by culturing a production bacterium.

[0035] Other Embodiments One embodiment of the present invention has been described in detail above with reference to the drawings, but the specific configuration is not limited to that described above, and various design changes and the like are possible within the scope that does not deviate from the gist of the present invention. [Explanation of symbols]

[0036] 1... culture system, 10... prediction device, 11... control unit, 12... interface unit, 13... storage unit, 20... culture measurement device

Claims

1. Predicting the OUR at time B based on parameters related to the nutrient source of the culture from time A, which is one or more past time points, to time B, which is a time point after time A, and the OUR (oxygen uptake rate) actually measured from time A to time C, which is a time point after time A but before time B; Forecasting methods.

2. determining whether an abnormality has occurred in the culture based on the difference between the predicted OUR at time B and the actually measured OUR at time B; The prediction method of claim 1 .

3. The parameters related to the nutrient source of the culture include the flow rate of a carbon source to the culture tank in which the culture is performed, or the flow rate of a nitrogen source to the culture tank; The prediction method according to claim 1 or 2.

4. The parameters related to the nutrient source of the culture further include at least one selected from the concentration of the carbon source in the culture tank, the concentration of the nitrogen source in the culture tank, the flow rate of the phosphorus source to the culture tank, and the concentration of the phosphorus source in the culture tank. The prediction method according to claim 3 .

5. The abnormal occurrence in the culture is the occurrence of contamination in the culture. The prediction method according to claim 2 .

6. Random Forest, XGBoost, ExtraRandomTrees, or LightGBM is a nonlinear regression model trained to input parameters related to nutrient sources for culture from time A to time B and the OUR at time C, and output the OUR at time B. By inputting the parameters related to nutrient sources for culture from time A to time B and the OUR at time C, the OUR at time B is output. The prediction method of claim 1 .

7. The prediction method of claim 1 includes the steps: A method for producing polyhydroxyalkanoates.

Images