Beer fermentation multi-parameter prediction method and system

Abstract

The invention provides a beer fermentation multi-parameter prediction method and system, and belongs to the technical field of beer fermention.The method comprises the steps that the beer fermentation time is obtained, the current fermentation stage of beer is determined, and each beer fermentation stage comprises a plurality of fermentation sub-time periods; obtaining a parameter value of a first target parameter corresponding to the beer in the current fermentation sub-time period; determining a second target parameter corresponding to the beer in the current fermentation stage; determining a temperature influence factor value according to the temperature interval of the fermentation stage; determining a parameter value of a second target parameter corresponding to the current fermentation sub-time period according to the temperature influence factor value and a parameter value of a first target parameter corresponding to the current fermentation sub-time period, and predicting the parameter value of the second target parameter in the next fermentation sub-time period according to the parameter value of the second target parameter corresponding to the current fermentation sub-time period. According to the beer fermentation multi-parameter prediction method and system provided by the invention, the quality of beer can be improved.

Description

Technical Field

[0001] This application belongs to the field of beer fermentation technology, and more specifically, relates to a method and system for predicting multiple parameters of beer fermentation. Background Technology

[0002] As a widely consumed beverage worldwide, beer's fermentation process is a complex biochemical reaction involving multiple interconnected biochemical reactions such as yeast growth, sugar metabolism, alcohol production, and the diacetyl cycle. This process determines beer quality, flavor, and yield, and plays a crucial role in the development of the beer industry.

[0003] Currently, existing technologies have attempted to monitor parameters during beer fermentation, but they have significant shortcomings in parameter prediction. Existing technologies focus on real-time monitoring of key parameters during fermentation using sensors and other devices, lacking the ability to effectively monitor future trends in these parameters. Consequently, they cannot predict changes in key parameters during fermentation. By the time sensors and other devices detect abnormal parameters, the beer fermentation process may have already deviated. Adjusting the abnormal parameters at this point can cause losses, reduce beer quality, and negatively impact beer standards. Summary of the Invention

[0004] The purpose of this application is to provide a method and system for predicting multiple parameters in beer fermentation, so as to achieve accurate prediction of key parameters in the beer fermentation process and improve the quality of beer.

[0005] A first aspect of this application provides a method for predicting multiple parameters of beer fermentation, including: The fermentation time of the beer is obtained, and based on the fermentation time, the current fermentation stage of the beer is determined. There is a corresponding relationship between the fermentation stage of the beer and the fermentation time of the beer. The fermentation stages of beer include: yeast free reproduction stage, main fermentation stage, heating stage, diacetyl reduction stage and cooling stage. Each fermentation stage of beer contains multiple fermentation sub-time periods. Obtain the parameter value of the first target parameter corresponding to the current fermentation sub-time period of the beer. There is a mapping relationship between the current fermentation sub-time period of the beer and the parameter value of the first target parameter. Determine the second target parameter corresponding to the current fermentation stage of the beer; Determine the temperature range corresponding to the current fermentation stage of the beer, and determine the temperature influence factor value corresponding to this fermentation stage based on the temperature range; The parameter value of the second target parameter corresponding to the current fermentation sub-time period is determined based on the temperature influence factor value corresponding to the fermentation stage and the parameter value of the first target parameter corresponding to the current fermentation sub-time period. The parameter value of the second target parameter in the next fermentation sub-time period is predicted based on the parameter value of the second target parameter corresponding to the current fermentation sub-time period.

[0006] A second aspect of this application provides a multi-parameter prediction system for beer fermentation, comprising: The fermentation stage determination module is used to obtain the fermentation time of the beer and determine the current fermentation stage of the beer based on the fermentation time. There is a corresponding relationship between the fermentation stage of the beer and the fermentation time of the beer. The fermentation stages of beer include: yeast free reproduction stage, main fermentation stage, heating stage, diacetyl reduction stage and cooling stage. Each fermentation stage of beer contains multiple fermentation sub-time periods. The target parameter value determination module is used to obtain the parameter value of the first target parameter corresponding to the current fermentation sub-time period of beer. There is a mapping relationship between the current fermentation sub-time period of beer and the parameter value of the first target parameter. The second target parameter determination module is used to determine the second target parameter corresponding to the current fermentation stage of the beer; The temperature influence factor value determination module is used to determine the temperature range corresponding to the current fermentation stage of the beer, and to determine the temperature influence factor value corresponding to the fermentation stage based on the temperature range. The parameter prediction module is used to determine the parameter value of the second target parameter corresponding to the current fermentation sub-time period based on the temperature influence factor value corresponding to the fermentation stage and the parameter value of the first target parameter corresponding to the current fermentation sub-time period, and to predict the parameter value of the second target parameter in the next fermentation sub-time period based on the parameter value of the second target parameter corresponding to the current fermentation sub-time period.

[0007] A third aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the above-described beer fermentation multi-parameter prediction method.

[0008] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described beer fermentation multi-parameter prediction method.

[0009] The beneficial effects of the beer fermentation multi-parameter prediction method and system provided in this application are as follows: This application determines the current fermentation stage by obtaining the fermentation time of the beer, and then combines the parameter value of the first target parameter corresponding to the fermentation stage with the temperature influence factor value determined by the temperature range to determine the second target parameter value of each fermentation sub-time period of the fermentation stage. The parameter value of the second target parameter of the fermentation sub-time period is used to predict the parameter value of the second target parameter of the next fermentation sub-time period. This embodiment can predict the second target parameter of each fermentation sub-time period in advance during the beer fermentation process, thereby predicting possible parameter deviations in advance and adjusting the corresponding parameters in time, thereby reducing the losses in the beer fermentation process caused by untimely parameter adjustment, and thus ensuring the quality of the beer and improving the beer quality. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 A flowchart illustrating a multi-parameter prediction method for beer fermentation provided in an embodiment of this application; Figure 2 A schematic diagram showing the concentration of the first target parameter at each fermentation stage, as provided in an embodiment of this application; Figure 3 A flowchart for determining the second target parameter of the yeast free reproduction stage provided in an embodiment of this application; Figure 4 A flowchart for determining the second target parameter of the main fermentation stage is provided as an embodiment of this application; Figure 5 A flowchart illustrating the determination of a second target parameter during the heating stage, provided as an embodiment of this application; Figure 6 A flowchart illustrating the determination of the second target parameter in the diacetyl reduction stage, provided as an embodiment of this application; Figure 7 A flowchart illustrating the second target parameter for the cooling stage provided in an embodiment of this application; Figure 8 This application provides a structural block diagram of a multi-parameter prediction system for beer fermentation according to an embodiment of the present application. Figure 9 This is a schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0012] In the following description, specific details such as specific system architectures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should be aware that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0013] To make the objectives, technical solutions, and advantages of the present application clearer, the following will be described through specific embodiments in conjunction with the accompanying drawings.

[0014] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of a multi-parameter prediction method for beer fermentation provided in an embodiment of the present application. The method may include: S101: Obtain the time for which the beer has been fermented, and based on the time for which the beer has been fermented, determine the current fermentation stage of the beer. There is a corresponding relationship between the fermentation stage of the beer and the time for which the beer has been fermented, and each fermentation stage of the beer includes multiple fermentation sub-time periods.

[0015] In this embodiment, according to the microbial metabolism law and process objectives of beer fermentation, the entire fermentation process of the beer is divided into 5 fermentation stages. The fermentation stages of the beer include the yeast free propagation stage, the main fermentation stage, the temperature rise stage, the diacetyl reduction stage, and the temperature drop stage. According to the current fermentation stage of the beer, in combination with the beer fermentation process standard or historical fermentation data, determine the start time and end time corresponding to this fermentation stage, so as to obtain the time period corresponding to this fermentation stage. Determine multiple fermentation sub-time periods according to this time period.

[0016] The starting point of the time for which the beer has been fermented is the moment when yeast is inoculated into the wort (inoculation) in the fermenter and starts active metabolism. Automatically record the inoculation time of yeast, the start time of fermentation, and the current time according to the temperature control system, liquid level sensor, or fermentation monitoring software supporting the fermenter, and determine the fermented time according to the difference between the current time and the inoculation time of yeast.

[0017] There is a corresponding relationship between the fermentation stage of the beer and the time for which the beer has been fermented. According to the time for which the beer has been fermented, the current fermentation stage of the beer can be determined, and each fermentation stage includes multiple fermentation sub-time periods.

[0018] S102: For the current fermentation sub-time period, obtain the parameter value of the first target parameter corresponding to the current fermentation sub-time period of the beer. There is a mapping relationship between the current fermentation sub-time period of the beer and the parameter value of the first target parameter.

[0019] In this embodiment, the first target parameter is a process parameter that is directly monitored or set during the current fermentation sub-time period, which may include pH value, dissolved oxygen level, yeast concentration, etc. A sensor corresponding to the first target parameter is deployed in the fermentation tank and connected to an IoT platform to obtain the value of the first target parameter corresponding to the current fermentation sub-time period in real time, thus determining the mapping relationship between the current fermentation sub-time period and the first target parameter.

[0020] S103: Determine the second target parameter corresponding to the current fermentation stage of the beer.

[0021] In this embodiment, the second target parameter is a parameter to be predicted corresponding to the current fermentation stage of the beer, which may include yeast specific growth rate, sugar metabolism rate, etc. In this embodiment, the second target parameter corresponding to the yeast free reproduction stage is the yeast specific growth rate; the second target parameter corresponding to the main fermentation stage is the sugar metabolism rate; the second target parameter corresponding to the heating stage is the diacetyl conversion rate; the second target parameter corresponding to the diacetyl reduction stage is the diacetyl reduction rate; and the second target parameter corresponding to the cooling stage is the yeast settling rate. After determining the current fermentation stage of the beer based on the fermentation time, the second target parameter corresponding to that fermentation stage is determined. The value of the second target parameter can directly affect the quality and grade of beer fermentation.

[0022] S104: Determine the temperature range corresponding to the current fermentation stage of the beer, and determine the temperature influence factor value corresponding to this fermentation stage based on the temperature range.

[0023] In this embodiment, the temperature range corresponding to the current fermentation stage of the beer is determined.

[0024] The temperature influence factor is a parameter used to quantify the impact of actual temperature deviation from the standard range on fermentation quality. The temperature range for the current fermentation stage is obtained, and the corresponding temperature influence factor value for that stage is determined based on this range.

[0025] S105: Determine the parameter value of the second target parameter corresponding to the current fermentation sub-time period based on the temperature influence factor value corresponding to the fermentation stage and the parameter value of the first target parameter corresponding to the current fermentation sub-time period. Predict the parameter value of the second target parameter in the next fermentation sub-time period based on the parameter value of the second target parameter corresponding to the current fermentation sub-time period.

[0026] In this embodiment, after determining the temperature influence factor value corresponding to the fermentation stage, the parameter value of the second target parameter corresponding to the current fermentation sub-time period is determined based on the preset parameter association model for the fermentation stage, the temperature influence factor value for the fermentation stage, and the parameter value of the first target parameter corresponding to the current fermentation sub-time period. Based on the parameter value of the second target parameter corresponding to the current fermentation sub-time period, and combined with the time continuity pattern, the changing trend or parameter value of the second target parameter in the next fermentation sub-time period is predicted.

[0027] As can be seen from the above, the embodiments of this application determine the fermentation stage by the fermentation time of the beer, match the corresponding temperature range for the fermentation stage, determine the corresponding temperature influence factor value based on the temperature range, and determine the second target parameter value for the current fermentation sub-time period by using the temperature influence factor value corresponding to the fermentation stage and the parameter value of the first target parameter corresponding to the current fermentation sub-time period. Furthermore, the second target parameter value for the next fermentation sub-time period is predicted using the second target parameter value for the current fermentation sub-time period. This allows for dynamic adjustment of the temperature influence factor value based on the temperature range corresponding to the fermentation stage, thereby achieving the adjustment of the second target parameter. Moreover, the prediction of the future second target parameter value based on the current second target parameter value avoids the prediction result of the second target parameter for the next fermentation sub-time period being affected by errors in obtaining the first target parameter, thus improving the controllability of the beer fermentation process and improving the quality of the beer.

[0028] In one embodiment of this application, after predicting the parameter value of the second target parameter in the next fermentation sub-time period based on the parameter value of the second target parameter corresponding to the current fermentation sub-time period, the method further includes: For this fermentation stage, the prediction curve of the second target parameter is obtained. The prediction curve of the second target parameter is generated based on the predicted parameter values ​​of the second target parameter in each target fermentation sub-time period and the predicted parameter values ​​of the second target parameter in the next fermentation sub-time period. Each target fermentation sub-time period includes the current fermentation sub-time period and all sub-time periods before the current fermentation sub-time period. If the target deviation between the predicted curve and the actual curve is outside the preset range, the parameter value of the first target parameter corresponding to the fermentation stage is adjusted, and the parameter value of the second target parameter in the next fermentation sub-period is re-predicted based on the adjusted parameter value of the first target parameter, until the target deviation between the predicted curve and the actual curve of the second target parameter in the fermentation stage is within the preset range.

[0029] In this embodiment, based on the parameter value of the first target parameter within the current fermentation sub-time period, the parameter value of the second target parameter for that fermentation sub-time period is determined. Based on the parameter value of the second target parameter within that fermentation sub-time period, the parameter value of the second target parameter for the next fermentation sub-time period is predicted. The prediction curve of the second target parameter is then confirmed based on the parameter value of the second target parameter in the current fermentation sub-time period and the corresponding fermentation sub-time period.

[0030] Based on the predicted and actual curves of the second target parameter, determine whether the parameter value of the second target parameter needs adjustment. If the target deviation between the predicted and actual curves is outside the preset range, it is determined that the parameter value of the second target parameter needs adjustment. The adjusted parameter value of the second target parameter is determined by adjusting the parameter value of the first target parameter corresponding to that fermentation stage. The predicted curve of the second target parameter is then adjusted based on the adjusted parameter value until the target deviation between the predicted and actual curves is within the preset range.

[0031] If the target deviation between the predicted curve and the actual curve is within the preset range, then the second target parameter is determined to be unnecessary to adjust.

[0032] This embodiment can determine whether the target parameters corresponding to a fermentation stage need to be adjusted by the target deviation between the predicted curve and the actual curve, thus avoiding fermentation abnormalities caused by unreasonable target parameters and improving the stability of the fermentation process. By predicting the parameter value of the second target parameter in the next fermentation sub-period based on the parameter value of the second target parameter in the previous fermentation sub-period, the second target parameter can be adjusted in a timely manner to avoid losses in the fermentation process and improve the quality of beer fermentation.

[0033] For example, see Figure 2 , Figure 2 This diagram illustrates the concentration of the first target parameter at each fermentation stage. Taking the second target parameter in the main fermentation stage as an example, the main fermentation stage typically lasts 1-3 days after fermentation begins. In this example, the time period corresponding to the main fermentation stage is set from 36h to 72h. Fermentation sub-time periods can be set to 2 hours, with sugar concentration predicted every 2 hours, dividing the main fermentation stage into 18 fermentation sub-time periods. Using the sugar concentration value corresponding to 36h (e.g., 20g / L) as the initial sugar concentration value of the main fermentation stage, a linear prediction method is used. Based on historical data (the change in sugar concentration value in the previous fermentation stage), the average rate of decrease in sugar concentration in each fermentation sub-time period is determined (e.g., the average rate of decrease in sugar concentration every two hours is 1g / L). Based on this average rate of decrease, the predicted sugar concentration values ​​corresponding to each fermentation sub-time period within 36h-72h are then predicted.

[0034] Based on the predicted sugar concentration values ​​for each sub-fermentation time period, a predicted sugar concentration curve for that time period is plotted using linear fitting. This predicted curve is compared with the actual curve for the main fermentation stage, and the target deviation between the predicted and actual curves for that fermentation sub-time period is calculated to be 2 g / L. This target deviation is the average of the deviations for each fermentation sub-time period. A preset deviation range of 0-1 g / L is set. If the target deviation between the predicted and actual curves for the main fermentation stage is outside this preset range, the first target parameter needs to be adjusted. For example, the yeast concentration can be adjusted from 10 g / L to 12 g / L. Based on the adjusted first target parameter value, the adjusted predicted sugar concentration value for the main fermentation stage is re-determined, and the predicted curve is re-plotted based on the predicted sugar concentration values ​​for each sub-fermentation time period. At this point, the target deviation between the adjusted predicted and actual curves is reduced to 0.8 g / L, within the preset range of 0-1 g / L. Therefore, the adjusted second target parameter value is reasonable and effective, and fermentation can be carried out based on this second target parameter. The actual curve in this example can be plotted based on sugar concentration values ​​from historical data.

[0035] In one embodiment of this application, adjusting the parameter value of the first target parameter corresponding to the fermentation stage includes: Obtain the deviation between the parameter value of each first target parameter and the corresponding actual value within each fermentation sub-time period; The first target parameter that generates the target deviation is determined based on the deviation between the parameter value of each first target parameter and the corresponding actual value within each target fermentation sub-time period; The parameter value of the first target parameter that causes the target deviation is adjusted in the current fermentation sub-time period.

[0036] In this embodiment, when the predicted curve and the actual curve are detected to deviate from the target within a preset range during the fermentation stage, the fermentation sub-time period corresponding to the time when the target deviation exceeds the preset range is determined by time stamping. Based on the deviation between the parameter value of the first target parameter corresponding to the fermentation sub-time period when the target deviation exceeds the preset range and the corresponding actual value, the first target parameter whose deviation exceeds the preset deviation range is determined as the first target parameter causing the target deviation. The first target parameter causing the target deviation is adjusted so that the second target parameter determined based on the adjusted parameter value is closer to a reasonable range.

[0037] In one possible implementation, the specific method for adjusting the parameter value of the first target parameter that causes the target deviation in this embodiment can be as follows: The specific fermentation sub-cycle corresponding to the deviation exceeding the preset range is determined by time stamping. Then, based on the deviation between the parameter value of the first target parameter and its actual value within that sub-cycle, the parameter causing the target deviation is identified. Multi-factor coordinated adjustment is employed, comprehensively considering the influence of environmental factors such as temperature, pH, dissolved oxygen, and alcohol inhibition on the parameter. The adjustment direction and magnitude are determined by calculating the parameter sensitivity coefficient. The identified first target parameter is adjusted, and the prediction model is re-run to calculate the second target parameter value. If the second target parameter value still does not enter a reasonable range, the parameter value in the first target parameter is iteratively adjusted based on the degree of deviation and the sensitivity analysis results until the second target parameter value reaches the preset reasonable range.

[0038] This embodiment can accurately locate the fermentation sub-time period that causes the target deviation and the parameter value corresponding to the first target parameter of the fermentation sub-time period, and adjust the second target parameter so that the second target parameter is within the reasonable range of the fermentation stage. This avoids blindly adjusting the parameter value of the target parameter of the fermentation stage, improves the accuracy of parameter adjustment, and quickly corrects the target deviation between the predicted curve and the actual curve, so that the fermentation process can quickly return to normal.

[0039] In one embodiment of this application, determining the first target parameter that generates the target deviation based on the deviation between the parameter value of each first target parameter and the corresponding actual value within each target fermentation sub-time period includes: For each target fermentation sub-time period, the contribution of each deviation to the target deviation is determined based on the deviation between the parameter value of each first target parameter and the corresponding actual value within that target fermentation sub-time period. The contribution percentage of each parameter is determined by the absolute value of the sum of the absolute values ​​of each contribution and the deviations. The first target parameter corresponding to the contribution percentage that exceeds the preset threshold is determined as the first target parameter that generates the target deviation.

[0040] In this embodiment, for each fermentation sub-time period, the deviation between the parameter value of each first target parameter and the corresponding actual value within that fermentation sub-time period is determined. Based on each deviation and the fermentation mechanism model (e.g., kinetic equation), the contribution of the deviation to the target deviation of the current fermentation sub-time period is determined.

[0041] The sum of the absolute values ​​of each contribution is determined based on the contribution degree. For each first target parameter, the contribution percentage of that target parameter in the fermentation sub-period is determined based on the sum of the absolute values ​​of the contribution degree of that first target parameter and the contribution degree of the first target parameter.

[0042] Set a preset threshold for the contribution percentage (for example, the preset threshold can be 40%), and determine the first target parameter whose contribution percentage is higher than the preset threshold as the first target parameter that generates the target deviation.

[0043] This embodiment determines the first target parameter that affects the second target parameter by quantifying the contribution ratio of each first target parameter deviation to the target deviation, ensuring that the parameter values ​​of the second target parameter in each fermentation stage are always within a reasonable parameter range, thereby improving the stability of the fermentation process.

[0044] In one embodiment of this application, determining the parameter value of the second target parameter corresponding to the current fermentation sub-time period based on the temperature influence factor value corresponding to the fermentation stage and the parameter value of the first target parameter corresponding to the current fermentation sub-time period includes: For the yeast free reproduction stage, the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period are obtained. The parameter values ​​include the sugar concentration influence factor value, dissolved oxygen limitation factor value, pH influence factor value, alcohol inhibition factor value, and density limitation factor value corresponding to the current fermentation sub-time period. Based on the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period and the temperature influence factor value corresponding to the yeast free reproduction stage, the yeast specific growth rate in the current fermentation sub-time period is determined. For the main fermentation stage, the parameter values ​​of the second target parameters corresponding to the current fermentation sub-time period are obtained. The parameter values ​​include the yeast concentration value, sugar concentration influencing factor value, pH influencing factor value, and alcohol inhibition factor value corresponding to the current fermentation sub-time period. The sugar metabolism rate of the main fermentation stage is determined based on the parameter values ​​of the first target parameters corresponding to the current fermentation sub-time period and the temperature influencing factor value of the main fermentation stage. For the heating phase, the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period are obtained. The parameter values ​​include the sugar metabolism rate, sugar concentration influence factor value, pH influence factor value, dissolved oxygen influence factor value, yeast concentration value, and fermentation stage factor value corresponding to the current fermentation sub-time period. The concentration of acetolactate in the current fermentation sub-time period is determined based on the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period and the temperature influence factor value of the heating phase. The parameter values ​​of the first target parameters corresponding to the conversion of acetolactate to diacetyl during the heating stage are obtained. The parameter values ​​include the concentration of acetolactate, temperature conversion factor, pH conversion factor, dissolved oxygen conversion factor, and diacetyl concentration in the current fermentation sub-time period. The conversion rate of diacetyl is determined based on the parameter values. For the diacetyl reduction stage, the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period are obtained. The parameter values ​​include the temperature reduction factor value, yeast activity, pH reduction factor value, dissolved oxygen reduction factor value, and diacetyl concentration factor value of the current fermentation sub-time period. The reduction rate of diacetyl is determined based on the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period. For the cooling phase, the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period are obtained. The parameter values ​​include the dissolved oxygen concentration and diacetyl concentration of the current fermentation sub-time period. The sedimentation rate of the yeast is determined based on the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period.

[0045] In this embodiment, see Figure 3 , Figure 3 The flowchart for determining the second target parameter of the yeast free-range reproduction stage is as follows: For the yeast free-range reproduction stage, the second target parameter of the yeast free-range reproduction stage is determined, including: S301: Obtain the parameter value corresponding to the first target parameter of the yeast free reproduction stage; S302: Determine the influence factor value corresponding to each parameter value based on the parameter value corresponding to the first target parameter; S303: Determine the temperature influence factor value based on the temperature during the yeast free reproduction stage; S304: Determine the second target parameter value for this fermentation stage based on the influence factor values ​​corresponding to each parameter and the temperature influence factor value.

[0046] Specifically, the parameter value of the first target parameter corresponding to the current fermentation sub-time period is obtained. Based on the yeast growth kinetics model, the yeast specific growth rate in the current fermentation sub-time period is determined according to the parameter value of the first target parameter corresponding to the current fermentation sub-time period and the temperature influence factor value corresponding to the yeast free reproduction stage.

[0047] The yeast growth kinetic model is as follows:

[0048] in, Yeast specific growth rate, The maximum specific growth rate of yeast. S Sugar concentration, K s The sugar half-saturation constant, O Dissolved oxygen concentration, K o It is the oxygen half-saturation constant. f ( T ) represents the temperature influence factor value during the yeast's free reproduction phase, f( pH The value represents the pH influence factor during the free-floating stage of yeast. f ( EtOH () represents the alcohol inhibitory factor value during the yeast's free-floating stage. f ( DO () represents the dissolved oxygen limiting factor value during the free-floating stage of yeast. f ( Density () represents the density limiting factor value during the free reproduction phase of yeast.

[0049] During the free-floating stage of yeast, sugar concentration, dissolved oxygen concentration, pH concentration, and alcohol concentration can be obtained from laboratory data. The corresponding influencing factor values ​​(pH influencing factor value and alcohol inhibition factor value) can be calculated from the obtained data. The dissolved oxygen limiting factor value is obtained from the dissolved oxygen concentration and the oxygen half-saturation constant, and the density limiting factor value is calculated from the yeast concentration, the maximum yeast concentration, and the density parameter.

[0050] For example, 20 hours after the start of fermentation, the current time can be set to 20 hours. At this time, the fermentation stage is the yeast free reproduction stage, and the target temperature for this stage is 9°C. During this fermentation stage, the yeast is more adapted to the environment and begins to multiply rapidly.

[0051] In this embodiment, the yeast growth kinetics model uses a multiplicative approach to combine various influencing factors, ensuring that the overall growth rate is zero when any factor is zero. This aligns with biological principles and provides accurate fault diagnosis capabilities. When a factor approaches zero, the root cause of the problem is immediately identified, providing operators with a clear direction for improvement. It can also identify key parameters and quickly locate limiting factors through sensitivity analysis. Furthermore, it ensures mathematical rigor and logical consistency, correctly handles extreme cases, and avoids biologically impossible results.

[0052] This embodiment also determines the optimal temperature range for different stages of fermentation based on the temperature control strategy and dynamically adjusts the temperature influencing factor values ​​to achieve precise temperature control. The model introduces a dissolved oxygen limiting factor to simulate the inhibitory effect of an oxygen-deficient environment on yeast growth. The alcohol inhibition factor value can represent the inhibitory effect of alcohol concentration on yeast growth. A density limiting factor is introduced to simulate the growth limitation when the yeast density reaches the current environmental carrying capacity.

[0053] See Figure 4 , Figure 4 The flowchart for determining the second target parameter of the main fermentation stage is as follows: For the main fermentation stage, the second target parameter of the main fermentation stage is determined, including: S311: Obtain the parameter value corresponding to the first target parameter in the main fermentation stage; S312: Determine the influence factor value corresponding to each parameter value based on the parameter value corresponding to the first target parameter; S313: Determine the temperature influence factor value based on the temperature during the main fermentation stage; S314: Determine the second target parameter value for the main fermentation stage based on the influence factor values ​​corresponding to each parameter and the temperature influence factor value.

[0054] Specifically, the parameter value of the first target parameter corresponding to the current fermentation sub-time period is obtained. Based on the sugar metabolism kinetic model, the sugar metabolism rate of the main fermentation stage is determined according to the parameter value of the first target parameter corresponding to the current fermentation sub-time period and the temperature influence factor value of the main fermentation stage.

[0055] The kinetic model of glucose metabolism is as follows:

[0056] in, dS / dt For the rate of glucose metabolism, k Based on the rate of basal glucose metabolism, Y The yeast concentration factor value during the primary fermentation stage. f s ( S The sugar concentration influencing factor value during the main fermentation stage. f t ( T The temperature influence factor value during the main fermentation stage. f p ( pH pH influencing factors during the main fermentation stage. f a ( EtOH The alcohol inhibition factor value during the main fermentation stage.

[0057] The sugar concentration, yeast concentration, pH value, and alcohol concentration in the main fermentation stage can be obtained from laboratory data. The corresponding influencing factor values ​​(sugar concentration influencing factor value, yeast concentration influencing factor value, pH influencing factor value, and alcohol inhibition factor value) can be calculated from the corresponding data.

[0058] The glucose metabolism kinetic model in this embodiment sets a baseline glucose metabolism rate to avoid unreasonable predictions under extreme conditions and maintain the stability of the model. The model introduces a yeast concentration factor to improve its applicability under different inoculation conditions. The glucose metabolism rate is determined based on the yeast concentration factor value, wherein the glucose metabolism rate is directly proportional to the yeast concentration factor value. In this embodiment, high concentrations of alcohol reduce the glucose metabolism rate through the alcohol inhibition factor value.

[0059] See Figure 5 , Figure 5 A flowchart illustrating the process for determining the second target parameter during the heating phase is provided. For the heating phase, the second target parameter is determined, including: S321: Obtain the parameter value corresponding to the first target parameter in the heating stage; S322: Determine the influence factor value corresponding to each parameter value based on the parameter value corresponding to the first target parameter; S323: Determine the temperature influence factor value based on the temperature during the heating stage; S324: Determine the second target parameter value for the heating stage based on the influence factor values ​​corresponding to each parameter and the temperature influence factor value.

[0060] Specifically, the parameter value of the first target parameter corresponding to the current fermentation sub-time period is obtained. Based on the acetolactate production model, the concentration of acetolactate in the current fermentation sub-time period is determined according to the parameter value of the first target parameter corresponding to the current fermentation sub-time period and the temperature influence factor value during the heating phase. The acetolactate production rate is proportional to the sugar metabolism rate and can reflect the influence of sugar metabolism on the production of diacetyl precursors.

[0061] The heating phase includes the diacetyl cycle phase, which includes the acetolactate production phase and the diacetyl conversion phase.

[0062] During the acetolactate production stage, the acetolactate production model is as follows:

[0063] in, d [AL] / dt The rate of acetolactate production. dS / dt This represents the rate of glucose metabolism during the acetolactate production phase. k p This represents the basic production rate during the acetolactate production phase. f g This represents the growth factor value during the acetolactate production phase. f s The value of the sugar concentration influencing factor during the acetolactate production stage. f t The temperature-dependent factor value during the acetolactate production stage. f p This represents the pH influence factor value during the acetolactate production stage. f o This refers to the dissolved oxygen factor value during the acetolactate production phase. fstage This represents the fermentation stage factor value during the acetolactate production stage. f y This represents the yeast concentration factor value during the acetolactate production stage.

[0064] In this embodiment, the dissolved oxygen concentration, pH value, yeast concentration, and sugar concentration can be obtained from laboratory data. The corresponding influencing factor values ​​for each data point (dissolved oxygen factor value, pH influencing factor value, yeast concentration factor value, and sugar concentration influencing factor value) can be calculated from the obtained data. The fermentation stage factor values, the basal production rate, and the growth factor values ​​during the acetolactate production stage can be calculated based on the fermentation stage, actual environmental parameters, and fermentation time.

[0065] The parameters for the first target parameter corresponding to the conversion of acetolactate to diacetyl during the heating stage are obtained. These parameters include the concentration of acetolactate, temperature conversion factor, pH conversion factor, dissolved oxygen conversion factor, and diacetyl concentration at the current fermentation sub-time. Based on the diacetyl conversion model, the conversion rate of diacetyl is determined according to these parameter values. This stage is easily affected by the concentration of acetolactate, temperature, pH, and dissolved oxygen; the higher the concentration of acetolactate, the faster the conversion rate.

[0066] In the diacetyl conversion stage, the diacetyl conversion model is as follows:

[0067] in, d [Diacetyl] / dt This represents the diacetyl conversion rate during the diacetyl conversion stage. k c This represents the baseline conversion rate for the diacetyl conversion stage. f tc This represents the temperature conversion factor value during the diacetyl conversion stage. f pc This represents the pH conversion factor value during the diacetyl conversion stage. f oc This represents the dissolved oxygen conversion factor value during the diacetyl conversion stage. f cc The concentration factor value of diacetyl during the diacetyl conversion stage, [ AL [ ] represents the concentration of acetolactate during the diacetyl conversion stage.

[0068] In this embodiment, the concentrations of acetolactate, diacetyl, dissolved oxygen, and pH can be obtained from laboratory data. The corresponding influencing factor values ​​(dissolved oxygen conversion factor and pH conversion factor) for each data can be calculated from the data. The basic conversion rate in this embodiment can be obtained from fermentation temperature, pH, and dissolved oxygen concentration.

[0069] See Figure 6 , Figure 6To determine the flowchart for the second target parameter in the diacetyl reduction stage, the second target parameter for the diacetyl reduction stage is determined, including: S331: Obtain the parameter value corresponding to the first target parameter in the diacetyl reduction stage; S332: Determine the influence factor value corresponding to each parameter value based on the parameter value corresponding to the first target parameter; S333: Determine the temperature influence factor value based on the temperature during the diacetyl reduction stage; S334: Determine the second target parameter value for the diacetyl reduction stage based on the influence factor values ​​corresponding to each parameter and the temperature influence factor value.

[0070] Obtain the parameter value of the first target parameter corresponding to the current fermentation sub-time period, and determine the diacetyl reduction rate based on the diacetyl reduction model and the parameter value of the first target parameter corresponding to the current fermentation sub-time period.

[0071] The diacetyl reduction model is as follows:

[0072] in, d [ ] / dt denoted as the diacetyl reduction rate, kr as the baseline reduction rate of the diacetyl reduction phase, [Diacetyl] as the diacetyl concentration during the diacetyl reduction phase, Yactivity as the yeast activity during the diacetyl reduction phase, ftr as the temperature reduction factor during the diacetyl reduction phase, fpr as the pH reduction factor during the diacetyl reduction phase, for as the dissolved oxygen reduction factor during the diacetyl reduction phase, and fcr as the concentration factor during the diacetyl reduction phase.

[0073] In this embodiment, the temperature, pH, dissolved oxygen concentration, diacetyl concentration, and yeast activity can be obtained from laboratory data. The corresponding influencing factors (temperature reduction factor, pH reduction factor, dissolved oxygen reduction factor, and concentration factor during the acetyl reduction stage) can be calculated from the data. The basic reduction rate can be calculated from the temperature, pH, and dissolved oxygen during the diacetyl reduction stage.

[0074] The acetolactate production model, diacetyl conversion model, and diacetyl reduction model in this embodiment constitute a diacetyl cycle kinetic model. This embodiment can accurately describe the diacetyl change characteristics at different times through the diacetyl cycle kinetic model, thereby improving the model's prediction accuracy.

[0075] See Figure 7 , Figure 7A flowchart illustrating the process for determining the second target parameter during the cooling phase is provided. For the cooling phase, the second target parameter is determined, including: S341: Obtain the parameter value corresponding to the first target parameter in the cooling stage; S342: Determine the influence factor value corresponding to each parameter value based on the parameter value corresponding to the first target parameter; S343: Determine the temperature influence factor value based on the temperature during the cooling phase; S344: Determine the second target parameter value for the cooling stage based on the influence factor values ​​corresponding to each parameter and the temperature influence factor value.

[0076] Specifically, the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period are obtained. The parameter values ​​include the dissolved oxygen concentration and diacetyl concentration values ​​of the current fermentation sub-time period. The sedimentation rate of the yeast is determined based on the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period.

[0077] In one embodiment of this application, before determining the temperature influence factor value corresponding to the fermentation stage based on the temperature range, the method further includes: Based on each fermentation stage, determine the first temperature range corresponding to each fermentation stage; Determine the mapping relationship between the second temperature range and the temperature influence factor value; the second temperature range and the temperature influence factor value are in one-to-one correspondence. Among them, the temperature influence factor value corresponding to this fermentation stage is determined according to the temperature range, including: Based on the current fermentation stage of the beer, determine the second temperature range to which the first temperature range corresponding to this fermentation stage belongs, and determine the temperature factor value corresponding to the second temperature range as the temperature influence factor value corresponding to this fermentation stage.

[0078] This embodiment is based on the beer fermentation process standard, sets the correspondence between the fermentation time of beer and the fermentation stage, and determines the corresponding first temperature range according to each fermentation stage.

[0079] The second temperature range is determined according to the preset temperature control strategy. The second temperature range includes multiple sub-ranges, and each sub-range corresponds to a temperature influence factor value.

[0080] The mapping relationship between each sub-interval in the second temperature range and the temperature influence factor value is determined. There is a one-to-one correspondence between each sub-interval and the temperature influence factor value in the second temperature range.

[0081] By comparing the first temperature range corresponding to the current fermentation stage of the beer with each sub-range within the second temperature range, the second temperature range to which the first temperature range belongs is determined, and the temperature influence factor value corresponding to the second temperature range to which the first temperature range belongs is determined as the temperature influence factor value corresponding to this fermentation stage.

[0082] In this embodiment, the first temperature range corresponding to each fermentation stage is as follows: the first temperature range corresponding to the yeast free reproduction period is 9℃, the first temperature range corresponding to the main fermentation period is 12℃, the first temperature range corresponding to the heating stage is 12~13℃, the first temperature range corresponding to the diacetyl reduction period is 13℃, and the first temperature range corresponding to the cooling stage is 13~4℃.

[0083] The temperature control strategy (second temperature range) is as follows: f(T) = { 0.3, T<10℃ 0.6, 10℃ ≤ T < 12℃ 0.8, 12℃ ≤ T < 15℃ 1.0, 15℃ ≤ T ≤ 20℃ 0.8, 20℃<T ≤ 25℃ 0.5,T> 25℃ }

[0084] The second temperature range is divided into several sub-ranges. The first sub-range is 0-10℃, with a temperature influence factor of 0.3. The second sub-range is 10-12℃, with a temperature influence factor of 0.6. The third sub-range is 12-15℃, with a temperature influence factor of 0.8. The fourth sub-range is 15-20℃, with a temperature influence factor of 1.0. The fifth sub-range is 20-25℃, with a temperature influence factor of 0.8. The sixth sub-range is above 25℃, with a temperature influence factor of 0.5.

[0085] For example, if the current fermentation stage is the yeast free reproduction stage, then the first temperature range is 9℃, and the sub-range to which the first temperature range belongs is the first sub-range, that is, 0-10℃; at this time, the corresponding temperature influence factor value is 0.3.

[0086] In one embodiment of this application, before adjusting the parameter value of the first target parameter that generates the target deviation in the current fermentation sub-time period, the method further includes: For each first target parameter value in this fermentation stage, the adjustment range corresponding to the parameter value of the first target parameter is determined by the relative change factor method; This includes adjusting the parameter value of the first target parameter that causes the target deviation in the current fermentation sub-time period, including: Within the adjustment range, adjust the current parameter value of the first target parameter that causes the target deviation.

[0087] This embodiment can determine the adjustment range corresponding to the parameter value of each first target parameter (e.g., yeast inoculation amount, pH influence factor value, dissolved oxygen concentration) using the relative change factor method, based on the characteristics of each target parameter. Specifically, for each first target parameter to be adjusted, based on its parameter value and a preset safety range, the relative maximum allowable upward or downward adjustment limit of the first target parameter is determined. The adjustment range corresponding to the parameter value of the first target parameter is then determined based on this relative maximum allowable upward or downward adjustment limit.

[0088] The adjusted value of the first target parameter is set to P, and the minimum value of this first target parameter is P. min The maximum value of the first objective parameter is P. max At this point, the lower limit change factor of the first target parameter is: , The lower limit of the first target parameter is defined by a change factor that represents the allowable reduction ratio; the upper limit of the first target parameter is defined by: , This is the lower limit change factor for the second target parameter, representing the allowable increase in adjustment. The adjustment range for the first target parameter is: P 下限 To P 上限 , where P 下限 =P×(1- ), P 上限 =P×(1+ ).

[0089] Based on the determined adjustment range of each first target parameter, the parameter value of the first target parameter that causes the target deviation is adjusted in the current fermentation sub-time period.

[0090] In one embodiment of this application, for each fermentation stage, the degree of influence of each first target parameter on the second target parameter is determined by analyzing the sensitivity of each first target parameter within that fermentation stage.

[0091] For each first target parameter, during the fermentation stage, the parameter value of the first target parameter is adjusted according to the adjustment range corresponding to the first target parameter, so as to observe the degree of influence of the first target parameter on the second target parameter during the fermentation process.

[0092] This embodiment can employ the principle of local sensitivity analysis, changing only the value of one primary target parameter at a time while keeping the values ​​of other primary target parameters unchanged during the fermentation stage, thus ensuring the accuracy and reliability of the analysis results.

[0093] The specific method for using local sensitivity analysis is as follows: After determining the actual significance of the first target parameter and establishing a reasonable adjustment range using the relative change factor method, the parameter value of the first target parameter is adjusted within the range of 80% to 120% of the baseline value, where the baseline value is the theoretical value of the first target parameter. For example, for the initial sugar concentration value, if its baseline value is 12°P, the variation range can be from 9.6°P to 14.4°P.

[0094] Based on the parameter adjustment range of the first target parameter, the parameter value of the first target parameter is adjusted, and the simulation process of the fermentation stage is determined based on the adjusted parameter value. The parameter value of the second target parameter after adjustment for the fermentation stage is recorded.

[0095] Determine the parameter values ​​of the second target parameters corresponding to the adjusted first target parameter values ​​for each fermentation stage. Based on the parameter values ​​of each second target parameter, determine which first target parameter value has the greatest influence on the second target parameter value, and thus determine the first target parameter with the highest sensitivity.

[0096] In one possible embodiment, the parameter value of each first target parameter is adjusted by an amplitude (e.g., ±10%) to obtain an adjusted parameter value. The second target parameter value is recalculated using the adjusted parameter value to determine the amplitude of change in the second target parameter value. The influence of all adjusted first target parameter values ​​is numerically compared and sorted from largest to smallest. The parameter corresponding to the parameter value with the largest influence is determined as the parameter with the highest sensitivity.

[0097] For example, taking the main fermentation stage of beer fermentation as an example, we determined which parameter had the greatest impact on alcohol concentration during this stage. Specifically, adjusting the sugar concentration from 12.0 g / L to 13.2 g / L resulted in a change in alcohol concentration from 4.0% to 4.4%, thus determining the effect of sugar concentration on alcohol concentration as 10%. Adjusting the temperature from 12.0°C to 13.2°C resulted in a change in alcohol concentration from 4.0% to 4.2%, thus determining the effect of temperature on alcohol concentration as 5%. Adjusting the pH value from 5.2 to 5.72 resulted in a change in alcohol concentration from 4.0% to 4.1%, thus determining the effect of pH value on alcohol concentration as 2.5%. Comparing these effects, we determined that sugar concentration had the highest impact on alcohol concentration (10%) during this fermentation stage, thus identifying sugar concentration as the parameter with the highest sensitivity.

[0098] This embodiment can calculate multiple sensitivity indicators to quantify the influence of parameters on the output. These sensitivity indicators include: relative rate of change (the ratio of output change to input change), sensitivity coefficient (output rate of change divided by input rate of change), and correlation coefficient (the degree of linear correlation between the parameter and the output). These sensitivity indicators can reflect the sensitivity of the first target parameter from different perspectives.

[0099] In one possible embodiment, the relative rate of change can be determined as follows: The first target parameter is adjusted by an amplitude (the adjustment range can be ±10%) to obtain the adjusted parameter. The adjusted parameter value is then determined based on the adjusted parameter. The adjusted parameter value is used to redetermine the adjusted second target parameter value. The difference between the adjusted parameter value and the original parameter value (the parameter value corresponding to the first target parameter before adjustment) is obtained, and this difference is divided by the original parameter value to obtain the input rate of change. The difference between the adjusted second target parameter value and the original second target parameter value (the second target parameter value before adjustment) is obtained, and this difference is divided by the original second target parameter value to obtain the output rate of change. The relative rate of change is determined based on the ratio of the output rate of change to the input rate of change. For example, sugar concentration is used as the first target parameter value, and alcohol concentration is used as the second target parameter value. When the sugar concentration is adjusted from 12.0 g / L to 13.2 g / L (a change of 10%), the alcohol concentration changes from 4.0% to 4.4% (a change of 10%), with a relative change rate of 1.0, indicating that a 10% change in sugar concentration also results in a 10% change in alcohol concentration.

[0100] In this embodiment, the sensitivity coefficient can be determined as follows: The input change rate and output change rate are obtained using the method described above for calculating relative change rates. The sensitivity coefficient is obtained by dividing the output change rate by the input change rate. For example, when the temperature is adjusted from 12.0°C to 13.0°C (a change of 8.3%), the diacetyl concentration changes from 0.1 mg / L to 0.08 mg / L (a change of -20%), and the sensitivity coefficient is -2.4, indicating that for every 8.3% change in temperature, the diacetyl concentration changes by 20%, showing a negative correlation.

[0101] It should be noted that in this embodiment, the relative rate of change and the sensitivity coefficient are mathematically equivalent. Both are defined as the ratio of the output rate of change to the input rate of change, only the expression is different.

[0102] In this embodiment, the correlation coefficient can be determined by collecting output value data points corresponding to multiple different parameter values ​​in the first target parameter. Statistical methods (e.g., the Pearson correlation coefficient method) can be used to calculate the degree of linear correlation between the parameter value and the output value. In this embodiment, the correlation coefficient ranges from -1 to 1, where 1 represents a perfect positive correlation, -1 represents a perfect negative correlation, and 0 represents no linear correlation. For example, during the yeast free-range reproduction stage, by analyzing the yeast concentration [10.0, 12.0, 15.0, 18.0, 20.0] (unit: million cells / mL) and the corresponding alcohol concentration [3.2, 3.8, 4.5, 5.1, 5.6] (unit: %), a correlation coefficient of 0.98 can be determined, indicating a high positive correlation between yeast concentration and alcohol concentration during the yeast free-range reproduction stage.

[0103] The sensitivity analysis results of each primary target parameter can be displayed in various chart formats, providing users with intuitive and visual analysis results.

[0104] This embodiment provides the following chart types to display the sensitivity analysis results, achieving visualization. The sensitivity index bar chart visually displays the sensitivity coefficient of each first target parameter to the second target parameter, facilitating rapid identification of key parameters. The parameter change impact curve details the influence trend of a single first target parameter change on the second target parameter, aiding in understanding the relationship between the two. The sensitivity heatmap uses color coding to display the sensitivity relationship between the first and second target parameters; darker colors indicate stronger sensitivity. The parameter importance radar chart uses polar coordinates to map the sensitivity coefficients of multiple first target parameters onto the axes of the radar chart, forming polygonal shapes. By comparing the polygon area and shape of each first target parameter, the degree of influence of the corresponding first target parameter on the second target parameter can be intuitively determined.

[0105] In this embodiment, for each fermentation stage, the first target parameters in that stage are combined to form different parameter pairs. Each parameter pair includes the parameter values ​​of two first target parameters. Each parameter pair is combined to generate a two-dimensional variation grid. For example, the first target parameter A is varied by 8 points within the range of 0.8 to 1.2, and the first target parameter B is varied by 8 points within the range of 0.8 to 1.2, forming 64 parameter combinations of 8×8. The parameter value of the corresponding second target parameter is determined based on each combination.

[0106] This embodiment uses analysis of variance to calculate the interaction strength between the first objective parameters in each combination. The significance, synergistic effect and antagonistic effect of the interaction are quantified by statistics and probability values. The synergistic effect represents the enhancement effect on the output when the two first objective parameters increase at the same time, and the antagonistic effect represents the mutual cancellation effect of the two first objective parameters.

[0107] In one embodiment of this application, for each fermentation stage, the changing trend of the parameter value of the second target parameter in the current fermentation sub-time period can be determined based on the changing trend of the parameter value of the first target parameter in the current fermentation sub-time period. The changing trend of the parameter value of the second target parameter in the next fermentation sub-time period is predicted based on the changing trend of the parameter value of the second target parameter in the next fermentation sub-time period. Whether the changing trend of the parameter value of the second target parameter in the next fermentation sub-time period is an abnormal changing trend is determined based on whether it falls within a preset changing trend range. If the changing trend of the parameter value of the second target parameter in the next fermentation sub-time period is within the preset changing trend range, it is determined that the changing trend is normal; if the changing trend of the parameter value of the second target parameter in the next fermentation sub-time period is outside the preset changing trend range, it is determined that the changing trend is abnormal. This embodiment can also predict whether there are abnormal mutation points in the fermentation stage based on the changing trend of the parameter value of the first target parameter in the fermentation stage. If the changing trend of the parameter value of the first target parameter in the fermentation stage is within a preset range, it is determined that there are no abnormal mutation points in the fermentation stage; if the changing trend of the parameter value of the first target parameter in the fermentation stage is outside the preset range, it is determined that there are abnormal mutation points in the fermentation stage.

[0108] This embodiment can determine and predict the changing trend of the second target parameter based on the changing trend of the first target parameter. It can judge whether the changing trend of the second target parameter is abnormal before the actual abnormality occurs. It can detect potential problems in the fermentation process in advance and adjust the first target parameter, avoiding the need to deal with the second target parameter after it becomes abnormal and affects the fermentation, thereby reducing losses and ensuring the stability of the fermentation process.

[0109] Corresponding to the multi-parameter prediction method for beer fermentation in the above embodiment, Figure 8 This is a structural block diagram of a multi-parameter prediction system for beer fermentation provided in one embodiment of this application. For ease of explanation, only the parts relevant to the embodiment of this application are shown. References Figure 8 The beer fermentation multi-parameter prediction system 80 includes: a fermentation stage determination module 81, a target parameter value determination module 82, a second target parameter determination module 82, a temperature influence factor value determination module 84, and a parameter prediction module 85.

[0110] Among them, the fermentation stage determination module 81 is used to obtain the fermentation time of the beer and determine the current fermentation stage of the beer based on the fermentation time. There is a corresponding relationship between the fermentation stage of the beer and the fermentation time of the beer. The fermentation stages of the beer include: yeast free reproduction stage, main fermentation stage, heating stage, diacetyl reduction stage and cooling stage. Each fermentation stage of the beer contains multiple fermentation sub-time periods. The target parameter value determination module 82 is used to obtain the parameter value of the first target parameter corresponding to the current fermentation sub-time period of beer. There is a mapping relationship between the current fermentation sub-time period of beer and the parameter value of the first target parameter. The second target parameter determination module 82 is used to determine the second target parameter corresponding to the current fermentation stage of the beer; The temperature influence factor value determination module 84 is used to determine the temperature range corresponding to the current fermentation stage of the beer, and to determine the temperature influence factor value corresponding to the fermentation stage based on the temperature range. The parameter prediction module 85 is used to determine the parameter value of the second target parameter corresponding to the current fermentation sub-time period based on the temperature influence factor value corresponding to the fermentation stage and the parameter value of the first target parameter corresponding to the current fermentation sub-time period, and to predict the parameter value of the second target parameter in the next fermentation sub-time period based on the parameter value of the second target parameter corresponding to the current fermentation sub-time period.

[0111] In one embodiment of this application, the beer fermentation multi-parameter prediction system 80 further includes a parameter adjustment module. When predicting the parameter value of the second target parameter in the next fermentation sub-time period based on the parameter value of the second target parameter corresponding to the current fermentation sub-time period, the parameter adjustment module is specifically used for: For this fermentation stage, the prediction curve of the second target parameter is obtained. The prediction curve of the second target parameter is generated based on the predicted parameter values ​​of the second target parameter in each target fermentation sub-time period and the predicted parameter values ​​of the second target parameter in the next fermentation sub-time period. Each target fermentation sub-time period includes the current fermentation sub-time period and all sub-time periods before the current fermentation sub-time period. If the target deviation between the predicted curve and the actual curve is outside the preset range, the parameter value of the first target parameter corresponding to the fermentation stage is adjusted, and the parameter value of the second target parameter in the next fermentation sub-period is re-predicted based on the adjusted parameter value of the first target parameter, until the target deviation between the predicted curve and the actual curve of the second target parameter in the fermentation stage is within the preset range.

[0112] In one embodiment of this application, for each fermentation stage, when the parameter adjustment module adjusts the parameter value of the first target parameter corresponding to that fermentation stage, it is specifically used for: Obtain the deviation between the parameter value of each first target parameter and the corresponding actual value within the time period of each target fermentation sub-process; The first target parameter that generates the target deviation is determined based on the deviation between the parameter value of each first target parameter and the corresponding actual value within each target fermentation sub-time period; The parameter value of the first target parameter that causes the target deviation is adjusted in the current fermentation sub-time period.

[0113] In one embodiment of this application, when the parameter adjustment module determines the first target parameter that generates the target deviation based on the deviation between the parameter value of each first target parameter and the corresponding actual value within each target fermentation time period, it is specifically used for: For each target fermentation sub-time period, the contribution of each deviation to the target deviation is determined based on the deviation between the parameter value of each first target parameter and the corresponding actual value within that target fermentation sub-time period. The contribution percentage of each parameter is determined by the absolute value of the sum of the absolute values ​​of each contribution and the deviations. The first target parameter is determined as the first target parameter that generates the target deviation, based on the proportion of contribution exceeding the preset threshold.

[0114] In one embodiment of this application, during the yeast free reproduction stage, the second target parameter is the yeast specific growth rate; during the main fermentation stage, the second target parameter is the sugar metabolism rate; during the heating stage, the second target parameter is the diacetyl conversion rate; during the diacetyl reduction stage, the second target parameter is the diacetyl reduction rate; and during the cooling stage, the second target parameter is the yeast sedimentation rate. When the parameter prediction module 85 determines the parameter value of the second target parameter for the current fermentation sub-time period based on the temperature influence factor value corresponding to the fermentation stage and the parameter value of the target parameter corresponding to the current fermentation sub-time period, it is specifically used for: For the yeast free reproduction stage, the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period are obtained. The parameter values ​​include the sugar concentration influence factor value, dissolved oxygen limitation factor value, pH influence factor value, alcohol inhibition factor value, and density limitation factor value corresponding to the current fermentation sub-time period. Based on the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period and the temperature influence factor value corresponding to the yeast free reproduction stage, the yeast specific growth rate in the current fermentation sub-time period is determined. For the main fermentation stage, the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period are obtained. The parameter values ​​include the yeast concentration value, sugar concentration influence factor value, pH influence factor value, and alcohol inhibition factor value corresponding to the current fermentation sub-time period. The sugar metabolism rate of the main fermentation stage is determined based on the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period and the temperature influence factor value of the main fermentation stage. For the heating phase, the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period are obtained. The parameter values ​​include the sugar metabolism rate, sugar concentration influence factor value, pH influence factor value, dissolved oxygen influence factor value, yeast concentration value, and fermentation stage factor value corresponding to the current fermentation sub-time period. The concentration of acetolactate in the current fermentation sub-time period is determined based on the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period and the temperature influence factor value of the heating phase. The parameter values ​​of the first target parameters corresponding to the conversion of acetolactate to diacetyl during the heating stage are obtained. The parameter values ​​include the concentration of acetolactate, temperature conversion factor, pH conversion factor, dissolved oxygen conversion factor, and diacetyl concentration in the current fermentation sub-time period. The conversion rate of diacetyl is determined based on the parameter values. For the diacetyl reduction stage, the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period are obtained. The parameter values ​​include the temperature reduction factor value, yeast activity, pH reduction factor value, dissolved oxygen reduction factor value, and diacetyl concentration factor value of the current fermentation sub-time period. The reduction rate of diacetyl is determined based on the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period. For the cooling phase, the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period are obtained. The parameter values ​​include the dissolved oxygen concentration and diacetyl concentration of the current fermentation sub-time period. The sedimentation rate of the yeast is determined based on the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period.

[0115] In one embodiment of this application, when the temperature influence factor value determination module 84 determines the temperature influence factor value corresponding to the fermentation stage based on the temperature range, it is specifically used for: Based on each fermentation stage, determine the first temperature range corresponding to each fermentation stage; Determine the mapping relationship between the second temperature range and the temperature influence factor; the second temperature range and the temperature influence factor are in one-to-one correspondence. Based on the current fermentation stage of the beer, determine the second temperature range to which the first temperature range corresponding to this fermentation stage belongs, and determine the temperature factor value corresponding to the second temperature range as the temperature influence factor value corresponding to this fermentation stage.

[0116] In one embodiment of this application, before adjusting the parameter value of the first target parameter that generates the target deviation in the current fermentation sub-time period, the parameter adjustment module is specifically used for: For each first target parameter value in this fermentation stage, the adjustment range corresponding to the parameter value of the first target parameter is determined by the relative change factor method; When adjusting the parameter value of the first target parameter that causes the target deviation in the current fermentation sub-time period, the parameter adjustment module is specifically used for: Within the adjustment range, the parameter value of the first target parameter that causes the target deviation is adjusted in the current fermentation sub-time period.

[0117] See Figure 9 , Figure 9 This is a schematic block diagram of an electronic device provided according to an embodiment of this application. Figure 9 The electronic device 900 in this embodiment may include one or more processors 901, one or more input devices 902, one or more output devices 903, and one or more memories 904. The processors 901, input devices 902, output devices 903, and memories 904 communicate with each other via a communication bus 905. The memory 904 stores computer programs, including program instructions. The processor 901 executes the program instructions stored in the memory 904. The processor 901 is configured to invoke the program instructions to perform the functions of each module / unit in the above system embodiments, for example... Figure 8 The module shown includes modules 81 for determining the fermentation stage, 82 for determining the target parameter value, 83 for determining the second target parameter, 84 for determining the temperature influence factor value, and 85 for parameter prediction.

[0118] It should be understood that, in the embodiments of this application, the processor 901 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0119] Input device 902 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint orientation information), a microphone, etc., and output device 903 may include a display (LCD, etc.), a speaker, etc.

[0120] The memory 904 may include read-only memory and random access memory, and provides instructions and data to the processor 901. A portion of the memory 904 may also include non-volatile random access memory. For example, the memory 904 may also store information such as the various fermentation sub-time periods of beer, the parameter values ​​of the first target parameter of each fermentation stage, and the parameter values ​​of the second target parameter.

[0121] In specific implementations, the processor 901, input device 902, and output device 903 described in the embodiments of this application can execute the implementation method described in the beer fermentation multi-parameter prediction method provided in the embodiments of this application, or they can execute the implementation method of the electronic device described in the embodiments of this application, which will not be repeated here.

[0122] In another embodiment of this application, a computer-readable storage medium is provided. This computer-readable storage medium stores a computer program, which includes program instructions. When executed by a processor, the program instructions implement all or part of the processes in the methods described above. Alternatively, the computer program can instruct related hardware to implement these processes. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or system capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0123] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., provided on the electronic device. Furthermore, the computer-readable storage medium can include both internal and external storage units of the electronic device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0124] Those skilled in the art will recognize that the modules / units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0125] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the electronic devices and units described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0126] In the embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules, units, or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces or modules / units, or it may be an electrical, mechanical, or other form of connection.

[0127] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of the embodiments of this application, depending on actual needs.

[0128] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The integrated modules / units described above can be implemented in hardware or in the form of software functional modules / units.

[0129] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for predicting multiple parameters of beer fermentation, characterized in that, include: The fermentation time of the beer is obtained, and based on the fermentation time, the current fermentation stage of the beer is determined. There is a corresponding relationship between the fermentation stage of the beer and the fermentation time of the beer. The fermentation stage of the beer includes: yeast free reproduction stage, main fermentation stage, heating stage, diacetyl reduction stage and cooling stage. Each fermentation stage of the beer contains multiple fermentation sub-time periods. Obtain the parameter value of the first target parameter corresponding to the current fermentation sub-time period of the beer, wherein there is a mapping relationship between the current fermentation sub-time period of the beer and the parameter value of the first target parameter; Determine the second target parameter corresponding to the current fermentation stage of the beer; Determine the temperature range corresponding to the current fermentation stage of the beer, and determine the temperature influence factor value corresponding to the fermentation stage based on the temperature range; The parameter value of the second target parameter corresponding to the current fermentation sub-time period is determined based on the temperature influence factor value corresponding to the fermentation stage and the parameter value of the first target parameter corresponding to the current fermentation sub-time period. The parameter value of the second target parameter in the next fermentation sub-time period is predicted based on the parameter value of the second target parameter corresponding to the current fermentation sub-time period.

2. The method for predicting multiple parameters of beer fermentation as described in claim 1, characterized in that, After predicting the parameter value of the second target parameter in the next fermentation sub-time period based on the parameter value of the second target parameter corresponding to the current fermentation sub-time period, the method further includes: For this fermentation stage, a prediction curve for the second target parameter is obtained. The prediction curve for the second target parameter is generated based on the predicted parameter values ​​of the second target parameter in each target fermentation sub-time period and the predicted parameter values ​​of the second target parameter in the next fermentation sub-time period. Each target fermentation sub-time period includes the current fermentation sub-time period and each sub-time period before the current fermentation sub-time period. If the target deviation between the predicted curve and the actual curve is outside the preset range, the parameter value of the first target parameter corresponding to the fermentation stage is adjusted, and the parameter value of the second target parameter in the next fermentation sub-time period is re-predicted based on the adjusted parameter value of the first target parameter, until the target deviation between the predicted curve and the actual curve of the second target parameter in the fermentation stage is within the preset range.

3. The method for predicting multiple parameters of beer fermentation as described in claim 2, characterized in that, The adjustment of the parameter value of the first target parameter corresponding to this fermentation stage includes: Obtain the deviation between the parameter value of each first target parameter and the corresponding actual value within the time period of each target fermentation unit; The first target parameter that generates the target deviation is determined based on the deviation between the parameter value of each first target parameter and the corresponding actual value within each target fermentation sub-time period; The parameter value of the first target parameter that generates the target deviation is adjusted in the current fermentation sub-time period.

4. The method for predicting multiple parameters of beer fermentation as described in claim 3, characterized in that, The step of determining the first target parameter that generates the target deviation based on the deviation between the parameter value of each first target parameter and the corresponding actual value within each target fermentation sub-time period includes: For each target fermentation sub-time period, the contribution of each deviation to the target deviation is determined based on the deviation between the parameter value of each first target parameter and the corresponding actual value within that target fermentation sub-time period. The contribution percentage of the corresponding first target parameter is determined based on the absolute value of the sum of the absolute values ​​of each contribution and the deviations. The first target parameter corresponding to the contribution percentage that exceeds the preset threshold is determined as the first target parameter that generates the target deviation.

5. The method for predicting multiple parameters of beer fermentation as described in claim 1, characterized in that, During the yeast free reproduction stage, the second target parameter is the yeast specific growth rate; during the main fermentation stage, the second target parameter is the sugar metabolism rate; during the heating stage, the second target parameter is the diacetyl conversion rate; during the diacetyl reduction stage, the second target parameter is the diacetyl reduction rate; and during the cooling stage, the second target parameter is the yeast sedimentation rate. Determining the value of the second target parameter corresponding to the current fermentation sub-time period based on the temperature influence factor value corresponding to the fermentation stage and the value of the first target parameter corresponding to the current fermentation sub-time period includes: During the yeast free reproduction stage, the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period are obtained. The parameter values ​​include the sugar concentration influence factor value, dissolved oxygen limitation factor value, pH influence factor value, alcohol inhibition factor value, and density limitation factor value corresponding to the current fermentation sub-time period. Based on the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period and the temperature influence factor value corresponding to the yeast free reproduction stage, the yeast specific growth rate in the current fermentation sub-time period is determined. For the main fermentation stage, the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period are obtained. The parameter values ​​include the yeast concentration value, sugar concentration influencing factor value, pH influencing factor value, and alcohol inhibition factor value corresponding to the current fermentation sub-time period. The sugar metabolism rate of the main fermentation stage is determined based on the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period and the temperature influencing factor value of the main fermentation stage. For the heating phase, the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period are obtained. The parameter values ​​include the sugar metabolism rate, sugar concentration influence factor value, pH influence factor value, dissolved oxygen influence factor value, yeast concentration value, and fermentation stage factor value corresponding to the current fermentation sub-time period. The concentration of acetolactate in the current fermentation sub-time period is determined based on the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period and the temperature influence factor value of the heating phase. The parameter values ​​of the first target parameters corresponding to the conversion of acetolactate to diacetyl during the heating stage are obtained. The parameter values ​​include the concentration of acetolactate, temperature conversion factor, pH conversion factor, dissolved oxygen conversion factor, and diacetyl concentration in the current fermentation sub-time period. The conversion rate of diacetyl is determined based on the parameter values. For the diacetyl reduction stage, the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period are obtained. The parameter values ​​include the temperature reduction factor value, yeast activity, pH reduction factor value, dissolved oxygen reduction factor value, and diacetyl concentration factor value of the current fermentation sub-time period. The reduction rate of the diacetyl is determined based on the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period. For the cooling phase, the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period are obtained. The parameter values ​​include the dissolved oxygen concentration and diacetyl concentration values ​​of the current fermentation sub-time period. The sedimentation rate of the yeast is determined based on the parameter values ​​of the first target parameter corresponding to the current fermentation sub-time period.

6. The method for predicting multiple parameters of beer fermentation as described in claim 1, characterized in that, Before determining the temperature influence factor value corresponding to the fermentation stage based on the temperature range, the method further includes: Based on each fermentation stage, determine the first temperature range corresponding to each fermentation stage; Determine the mapping relationship between the second temperature range and the temperature influence factor value, wherein the second temperature range and the temperature influence factor value are in one-to-one correspondence. Wherein, determining the temperature influence factor value corresponding to the fermentation stage based on the temperature range includes: Based on the current fermentation stage of the beer, determine the second temperature range to which the first temperature range corresponding to the fermentation stage belongs, and determine the temperature factor value corresponding to the second temperature range as the temperature influence factor value corresponding to the fermentation stage.

7. The method for predicting multiple parameters of beer fermentation as described in claim 3, characterized in that, Before adjusting the parameter value of the first target parameter that generates the target deviation in the current fermentation sub-time period, the method further includes: For each first target parameter value in this fermentation stage, the adjustment range corresponding to the parameter value of the first target parameter is determined by the relative change factor method; The adjustment of the parameter value of the first target parameter that generates the target deviation in the current fermentation sub-time period includes: Within the adjustment range, the current parameter value of the first target parameter that generates the target deviation is adjusted.

8. A multi-parameter prediction system for beer fermentation, characterized in that, include: The fermentation stage determination module is used to obtain the fermentation time of the beer and determine the current fermentation stage of the beer based on the fermentation time. There is a corresponding relationship between the fermentation stage of the beer and the fermentation time of the beer. The fermentation stage of the beer includes: yeast free reproduction stage, main fermentation stage, heating stage, diacetyl reduction stage and cooling stage. Each fermentation stage of the beer contains multiple fermentation sub-time periods. The target parameter value determination module is used to obtain the parameter value of the first target parameter corresponding to the current fermentation sub-time period of beer, wherein there is a mapping relationship between the current fermentation sub-time period of beer and the parameter value of the first target parameter; The second target parameter determination module is used to determine the second target parameter corresponding to the current fermentation stage of the beer; The temperature influence factor value determination module is used to determine the temperature range corresponding to the current fermentation stage of the beer, and to determine the temperature influence factor value corresponding to the fermentation stage based on the temperature range. The parameter prediction module is used to determine the parameter value of the second target parameter corresponding to the current fermentation sub-time period based on the temperature influence factor value corresponding to the fermentation stage and the parameter value of the first target parameter corresponding to the current fermentation sub-time period, and to predict the parameter value of the second target parameter in the next fermentation sub-time period based on the parameter value of the second target parameter corresponding to the current fermentation sub-time period.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images