Yeast production data processing method and device based on cloud computing

Abstract

The invention discloses a data processing method and device for yeast production based on cloud computing, and the method comprises the steps: obtaining temperature data, humidity data, time data and PH data of a historical fermentation environment, and carrying out the feature enhancement operation to obtain historical environment data; performing logistic growth model fitting operation according to a pre-acquired historical yeast population number and the historical environment data to obtain production data; performing cloud storage according to the production data to obtain a multi-node data backup; calculating the maximum yeast population quantity according to the production data to obtain a yeast production prediction result; and performing fermentation environment optimization calculation operation according to the historical environment data to obtain environment adjustment data so as to realize yeast production control optimization. The method can increase the yeast yield.

Description

Technical Field

[0001] The present invention relates to the technical field of cloud computing, and particularly to a data processing method and device for yeast production based on cloud computing. Background Art

[0002] Currently, in the era of big data, cloud computing, as a new generation of information technology, is leading a new round of global industrial transformation and upgrading. Cloud computing is a new generation of information technology based on virtualization, with computing, network, and storage resources as the core, aiming to achieve large-scale computing capabilities, innovative service models, develop new types of businesses and applications, and build a new generation of information infrastructure. Cloud computing technology provides secure, reliable, elastic, and scalable data processing and storage services, and is becoming the core of the new round of informatization innovation and development, and an indispensable part of future industrial production. The application of cloud computing technology is not only the evolution of new technologies, but also the start of a new round of industrial production revolution. Data processing is the collection, storage, retrieval, processing, transformation, and transmission of data.

[0003] Yeast is a eukaryote belonging to the fungal kingdom and is the second single-celled organism after animals among known organisms. With the in-depth study of yeast, the advantages of yeast are increasingly recognized by humans and rationally utilized. Now yeast is an important industrial microorganism, and many industrial fungal products are produced using yeast. The biosynthesis of yeast is very complex, and the chemical changes involved in industrial yeast production reach hundreds. Yeast can use hexose to be reduced to ketose without heating through phosphorolysis, which is necessary for the synthesis of nucleic acids, high-level carbohydrates, and lipids. At the same time, acetone is used as a precursor for the synthesis of some metabolites. Yeast has high activity in the metabolism of organic compounds. For example, it can be used to produce compounds such as pyruvic acid, lactic acid, malic acid, glycolic acid, and succinic acid. Yeast has a wide range of uses in industry, mainly as a leavening agent, nutrient, and hops. However, during the production process of yeast, due to the harsh growth conditions of yeast, the environmental requirements for humidity, temperature, and pH value are very high.

[0004] In the prior art, there is a manual monitoring link in the traditional industrial production method, and there is a problem that the influence of production environment factors makes the manual monitoring inaccurate, and there are errors in the monitoring results, resulting in low yeast yield. Summary of the Invention

[0005] The present invention provides a data processing method and device for yeast production based on cloud computing to achieve an increase in yeast yield.

[0006] In a first aspect, to solve the above technical problems, the present invention provides a data processing method for yeast production based on cloud computing, including:

[0007] Obtain the temperature data, humidity data, time data, and PH data of the historical fermentation environment, perform feature enhancement operations, and obtain historical environment data;

[0008] According to the pre-obtained historical yeast population quantity and the historical environment data, perform a logistic growth model fitting operation to obtain production data;

[0009] According to the production data, perform cloud storage to obtain multi-node data backups;

[0010] According to the production data, perform a calculation of the maximum yeast population quantity to obtain a yeast production prediction result;

[0011] According to the historical environment data, perform a fermentation environment optimization calculation operation to obtain environment adjustment data to achieve optimization of yeast production control.

[0012] In an alternative embodiment, according to the pre-obtained historical yeast population quantity and the historical environment data, perform a logistic growth model fitting operation to obtain production data, including:

[0013] According to the historical yeast population quantity and the historical environment data, perform normalization processing to obtain normalized data;

[0014] According to the normalized data, perform a least squares fitting operation to obtain model parameter data;

[0015] According to a video sensor, perform a calculation of the yeast population quantity to obtain the current yeast population quantity;

[0016] According to the model parameter data, the current yeast population quantity, and a preset maximum yeast production value, perform a yeast growth rate calculation operation to obtain the yeast growth rate;

[0017] According to a preset initial yeast population quantity and model parameter data, perform a yeast production prediction operation to obtain yeast production prediction data;

[0018] According to the yeast growth rate and the yeast production prediction data, perform a data packaging operation to obtain production data.

[0019] In an alternative embodiment, according to the production data, perform a calculation of the maximum yeast population quantity to obtain the maximum yeast population quantity, including

[0020] According to the production environment, perform an ideal situation calculation to obtain the maximum ideal yeast production value;

[0021] The calculation formula of the cloud server is as follows:

[0022]

[0023] Among them, P max represents the maximum yeast population that can be achieved in the current production environment; C represents the maximum value of the ideal yeast yield; P0 represents the preset initial yeast population; r represents the yeast growth rate; t0 represents the time length from the start of fermentation to a certain moment; e represents the base of the natural logarithm.

[0024] In an alternative embodiment, according to the historical environment data, perform fermentation environment optimization calculation operations to obtain environment adjustment data to achieve optimization of yeast production control, including:

[0025] According to the historical environment data, perform feature extraction operations to obtain the initial values, maximum values, and minimum values of the historical temperature, historical humidity, historical pH value, and historical fermentation time;

[0026] According to the initial values, maximum values, and minimum values of the historical temperature, historical humidity, historical pH value, and historical fermentation time, perform parameter adjustment calculation operations to obtain the adjustment target values of the temperature, humidity, pH value, and fermentation time;

[0027] According to the adjustment target values of the temperature, humidity, pH value, and fermentation time, generate control instructions to achieve optimization of yeast production control.

[0028] In an alternative embodiment, according to the normalized data, perform least squares fitting operations to obtain model parameter data, including:

[0029] The objective function of the least squares fitting operation is as follows:

[0030]

[0031] Among them, y represents the normalized historical yeast population, x represents the normalized historical environment data; a and b are model parameter data determined through fitting operations; a represents the growth coefficient; b represents the inhibition constant; t represents the t moment; the model parameter data consists of a and b; e represents the base of the natural logarithm.

[0032] In an alternative embodiment, according to the model parameter data, the current yeast population, and the preset maximum yeast yield, perform yeast growth rate calculation operations to obtain the yeast growth rate, including:

[0033] The yeast growth rate calculation formula is as follows:

[0034]

[0035] Among them, r represents the yeast growth rate; a represents the growth coefficient, P(t) represents the yeast population at the t moment; C represents the preset maximum yeast yield.

[0036] In an alternative embodiment, a yeast production prediction operation is performed according to a preset initial yeast population quantity and model parameter data to obtain yeast production prediction data, including:

[0037] The yeast production prediction calculation formula is as follows:

[0038]

[0039] Wherein, P(t) represents the predicted yeast population quantity at time t; P0 represents the preset initial yeast population quantity; a represents the growth coefficient; b represents the inhibition constant; and e represents the base of the natural logarithm.

[0040] In an alternative embodiment, according to the initial values, maximum values, and minimum values of the historical temperature, historical humidity, historical pH value, and historical fermentation time, a parameter adjustment calculation operation is performed to obtain the adjusted target values of the temperature, humidity, pH value, and fermentation time, including:

[0041] According to the maximum values and minimum values of the historical temperature, historical humidity, historical pH value, and historical fermentation time, a variation range calculation is performed to obtain the variation ranges of the temperature, humidity, pH value, and fermentation time;

[0042] According to the variation ranges, initial values, and preset weights of the temperature, humidity, pH value, and fermentation time, a target parameter calculation is performed to obtain the adjusted target values of the temperature, humidity, pH value, and fermentation time;

[0043] The variation range calculation formula is as follows:

[0044] TR = T max - T min

[0045] HR = H max - H min

[0046] pHR = pH max - pH min

[0047] TimeR = Time max - Time min

[0048] Wherein, TR represents the variation range of the temperature; T max represents the maximum temperature value in the historical data; T min represents the minimum temperature value in the historical data; HR is the variation range of the humidity; H max represents the maximum humidity value in the historical data; H minRepresents the minimum humidity in historical data; pHR is the change range of pH value; pH max Represents the maximum pH in historical data; pH min Represents the minimum pH in historical data; TimeR is the change range of fermentation time; Time max Represents the maximum fermentation time in historical data; Time min Represents the minimum fermentation time in historical data;

[0049] The parameter adjustment calculation formula is as follows:

[0050] T Target = T + α·TR

[0051] H Target = HT + β·HR

[0052] pH Target = pHT + γ·pHR

[0053] TimeV Target = TimeV + ∈·TimeR

[0054] Wherein, T Target Represents the target temperature, T represents the initial temperature, and α represents the weight of temperature; H Target Represents the target humidity, HT represents the initial humidity, and β represents the weight of humidity; pH Target Represents the pH value, pHT represents the initial pH value, and γ represents the weight of pH value; TimeV Target Represents the target fermentation time, TimeV represents the initial fermentation time, and ∈ represents the weight of fermentation time.

[0055] In a second aspect, the present invention provides a data processing device for yeast production based on cloud computing, including:

[0056] An environmental data acquisition module, configured to acquire temperature data, humidity data, time data, and PH data of a historical fermentation environment, perform a feature enhancement operation, and obtain historical environment data;

[0057] A production data calculation module, configured to perform a logistic growth model fitting operation according to the historical environment data to obtain production data;

[0058] A data storage module, configured to perform cloud storage according to the production data to obtain multi-node data backup;

[0059] A production prediction module, configured to calculate the maximum yeast population according to the production data to obtain a yeast production prediction result;

[0060] A control optimization module, configured to perform fermentation environment optimization calculation operations based on the historical environment data to obtain environment adjustment data for optimizing yeast production control.

[0061] In a third aspect, the present invention further provides an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the data processing method for yeast production based on cloud computing described in any one of the above.

[0062] Compared with the prior art, the present invention has the following beneficial effects:

[0063] (1) Based on cloud computing technology, the present invention obtains temperature data, humidity data, time data, and PH data of the historical fermentation environment, performs feature enhancement operations to obtain historical environment data; based on the historical environment data, performs logistic growth model fitting operations to obtain production data; based on the production data, performs cloud storage to obtain multi-node data backup; based on the production data, performs maximum yeast population quantity calculation to obtain yeast production prediction results; it realizes safe, reliable, elastic, and scalable data processing and storage services;

[0064] (2) The present invention uses historical environment data to perform logistic growth model fitting operations and obtains model parameters based on the logistic growth model, thereby predicting yeast production; it avoids the inaccurate and untimely monitoring in traditional yeast production, and finally can obtain more accurate and rapid yeast production prediction and control;

[0065] (3) Based on the historical environment data, the present invention performs fermentation environment optimization calculation operations to obtain environment adjustment data for optimizing yeast production control; it performs optimization control based on historical data for specific environment problems, thereby achieving an increase in yeast production; finally, through intelligent environment control optimization, the maximization of yeast production is realized, which is of great significance for the reform of the yeast production industry and realizes the intelligent improvement of traditional industries. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 is a flowchart of the data processing method for yeast production based on cloud computing provided by an embodiment of the present invention;

[0067] Figure 2 is a flowchart of the logistic growth model fitting operation provided by an embodiment of the present invention;

[0068] Figure 3 is a structural diagram of the data processing device for yeast production based on cloud computing provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0069] Next, in combination with the accompanying drawings in the embodiments of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0070] Referring to Figure 1 , the embodiments of the present invention provide a data processing method for yeast production based on cloud computing, including the following steps:

[0071] S11. Obtain the temperature data, humidity data, time data, and PH data of the historical fermentation environment, perform a feature enhancement operation, and obtain historical environment data;

[0072] S12. According to the pre-obtained historical yeast population quantity and the historical environment data, perform a logistic growth model fitting operation to obtain production data;

[0073] S13. According to the production data, perform cloud storage to obtain multi-node data backups;

[0074] S14. According to the production data, perform a calculation of the maximum yeast population quantity to obtain a yeast production prediction result;

[0075] S15. According to the historical environment data, perform a fermentation environment optimization calculation operation to obtain environment adjustment data to achieve optimization of yeast production control.

[0076] In step S11, obtaining the temperature data, humidity data, time data, and PH data of the historical fermentation environment, performing a feature enhancement operation, and obtaining historical environment data includes:

[0077] Obtain the temperature data, humidity data, time data, and PH data of the historical fermentation environment;

[0078] According to the temperature data, humidity data, time data, and PH data of the historical fermentation environment, perform a data integrity check operation to obtain complete data;

[0079] According to the complete data, perform an outlier detection and processing operation to obtain complete normal data;

[0080] According to the complete normal data, perform a data cleaning operation to obtain high-quality data;

[0081] According to the high-quality data, perform a data preprocessing operation to obtain historical environment data.

[0082] It should be noted that in step S11, a series of data processing operations are performed to enhance features for a more accurate understanding and prediction of the growth environment of yeast during the fermentation process. First, data on the temperature, humidity, time (fermentation time), and pH value of the historical fermentation environment are collected, which are key factors affecting yeast growth. The data integrity check operation is to ensure a continuous and non-missing dataset, which is crucial for subsequent analysis. Exemplarily, if temperature data is missing within a certain period, the interpolation method is selected in the present invention to fill in these blanks to ensure data integrity. Of course, depending on the application scenario and different customer requirements, operations such as deletion can also be taken to construct data integrity, and the present invention does not limit this. The outlier detection and processing operation is to identify and process those data points that do not conform to the expected range or pattern, and these outliers are caused by measurement errors or equipment failures. Exemplarily, a sudden change in humidity data is shown as 0%, which obviously does not conform to the actual situation of the fermentation process, and it needs to be identified and corrected or deleted. The present invention uses the average value of the features before and after calculation for substitution. Of course, depending on the application scenario and different customer requirements, operations such as deletion can also be taken to modify data outliers, and the present invention does not limit this. The data cleaning operation is to remove or correct inconsistent or inaccurate data to ensure the quality of the dataset. Exemplarily, duplicate records are removed, incorrect data entries are corrected, or different data formats are standardized. The data preprocessing operation is to further process high-quality data to make it suitable for modeling and analysis. Exemplarily, it includes normalizing data to eliminate the influence of different dimensions, encoding categorical variables, or feature selection to retain the features most useful for the model.

[0083] Refer to Figure 2 , in step S12, according to the pre-acquired historical yeast population quantity and the historical environment data, a logistic growth model fitting operation is performed to obtain production data, including:

[0084] S121, according to the historical yeast population quantity and the historical environment data, perform a normalization process to obtain normalized data;

[0085] S122, according to the normalized data, perform a least squares fitting operation to obtain model parameter data;

[0086] S123, according to the video sensor, calculate the yeast population quantity to obtain the current yeast population quantity;

[0087] S124, according to the model parameter data, the current yeast population quantity, and the preset maximum yeast production, perform a yeast growth rate calculation operation to obtain the yeast growth rate;

[0088] S125. Perform yeast production prediction operations based on the preset initial yeast population quantity and model parameter data to obtain yeast production prediction data;

[0089] S126. Perform data packaging operations based on the yeast growth rate and the yeast production prediction data to obtain production data.

[0090] In S121, perform normalization processing based on the historical yeast population quantity and the historical environmental data to obtain normalized data. The normalized data includes the normalized historical environmental data and the normalized historical yeast population quantity.

[0091] Specifically, process the historical environmental data through the Logistic function mapping calculation formula:

[0092]

[0093] Among them, x represents the normalized historical environmental data; x0 represents the initial environmental value in the historical environmental data.

[0094] Specifically, the historical yeast population quantity includes the population quantity and the environmental carrying capacity (maximum population quantity). Calculate the ratio of the population quantity to the environmental carrying capacity (maximum population quantity), and use the ratio as the normalized historical yeast population quantity.

[0095] It should be noted that in step S121, the Logistic function is used to map the historical environmental data into the interval [0, 1] for normalization processing. Normalization is a data preprocessing technique that transforms data with different ranges and dimensions to the same scale, which is very important in machine learning and statistical analysis because it can prevent certain features from occupying too much weight in the model due to large dimensions. Exemplarily, there is a set of temperature data ranging from 20°C to 40°C. The Logistic function can be used to map these temperature values into the interval [0, 1]. In this way, 20°C will be mapped to 0.05, and 40°C will be mapped to 0.95. This mapping not only helps to fairly compare different environmental factors in the model but also reveals the non-linear relationship of the data. Normalized data allows for more accurate simulation of the growth dynamics of the yeast population in the logistic growth model fitting. By using normalized data, the model can be trained more effectively, and the maximum population quantity of yeast under different environmental conditions can be predicted. In addition, normalized data can also be used for fermentation environment optimization calculations to help determine the optimal environmental parameter settings to maximize yeast production.

[0096] In S122, perform least squares fitting operations based on the normalized data to obtain model parameter data, including:

[0097] The objective function of the least squares fitting operation is as follows:

[0098]

[0099] Among them, y represents the normalized historical yeast population quantity, x represents the normalized historical environmental data; a and b are model parameter data determined through the fitting operation, a represents the growth coefficient; b represents the inhibition constant; e represents the base of the natural logarithm.

[0100] It should be noted that in step S122, the least squares method is used to fit the normalized data to determine the parameters of the logistic growth model. This step is crucial for establishing a mathematical model that accurately describes the growth dynamics of the yeast population. Among them, y represents the normalized historical yeast population quantity, that is, the ratio of the population quantity to the environmental carrying capacity (maximum population quantity). The parameter a represents the growth coefficient, which determines the maximum growth rate of the yeast population, while the parameter b represents the inhibition constant, which is related to the environmental carrying capacity and affects the speed at which the yeast population reaches its maximum value. The model parameter data consists of a and b, which are obtained through least squares fitting to minimize the sum of the squares of the errors between the model predicted values and the actual observed values. In this process, historical environmental data, including temperature, humidity, pH value, etc., have been normalized and prepared for model fitting in the previous steps. Through the least squares method, the optimal values of a and b can be found, enabling the logistic model to describe the growth trend of the yeast population. The parameters a and b of this model are crucial for understanding and predicting the key factors in the yeast production process. They can not only help predict the maximum quantity of the yeast population under specific environmental conditions but also guide how to optimize yeast production by adjusting fermentation conditions. Exemplarily, when it is determined that the value of a is low, it means that the growth rate of the yeast population is slow, and the temperature or pH value can be selected to be adjusted to increase this rate. Similarly, when it is determined that the value of b is high, it indicates that the inhibition effect of the environment on the yeast population is strong, and measures can be taken to reduce this inhibition or provide more resources to support the growth of the yeast.

[0101] In step S123, based on the video sensor, the yeast population quantity is calculated to obtain the current yeast population quantity.

[0102] It should be noted that the video sensor captures images regularly during the fermentation process, and these images contain visual information of yeast cells. The acquired images need to be preprocessed. Exemplarily, the present invention uses denoising, contrast enhancement, etc. to improve the accuracy of subsequent analysis. Through image analysis algorithms, exemplarily, the present invention uses edge detection and threshold segmentation to automatically identify and distinguish yeast cells from other elements in the fermentation process. When it is determined to be a yeast cell, the algorithm calculates the number of yeast cells in the image, thereby obtaining the current yeast population number. Integrating the calculated yeast population number with time data forms a yeast growth curve.

[0103] It should be noted that in step S123, the video sensor technology is used to monitor and calculate the yeast population number in real time, and this step is crucial for obtaining the current yeast population number. The video sensor can capture images or video data during the fermentation process. Through image processing and analysis techniques, the morphology and quantity information of yeast cells can be extracted. The video sensor technology is a non-invasive monitoring means that does not interfere with the fermentation process, and the automated image analysis reduces the need for manual counting, improving efficiency and accuracy. Step S123, through the video sensor technology, can not only accurately calculate the current yeast population number, but also provide a real-time, non-invasive, and automated monitoring means, thus providing strong support for the optimization and control of yeast production.

[0104] In step S124, according to the model parameter data, the current yeast population number, and the preset maximum yeast production value, a yeast growth rate calculation operation is performed to obtain the yeast growth rate, including:

[0105] The yeast growth rate calculation formula is as follows:

[0106]

[0107] Among them, r represents the yeast growth rate; a represents the growth coefficient, P(t) represents the yeast population number at time t; C represents the preset maximum yeast production value.

[0108] In step S125, according to the preset initial yeast population number and model parameter data, a yeast production prediction operation is performed to obtain yeast production prediction data, including:

[0109] The yeast production prediction calculation formula is as follows:

[0110]

[0111] Among them, P(t) represents the predicted yeast population number at time t; P0 represents the preset initial yeast population number; a represents the growth coefficient; b represents the inhibition constant; e represents the base of the natural logarithm.

[0112] It should be noted that in step S125, the yeast production prediction operation is carried out by using the preset initial yeast population quantity P0 and the model parameters a and b obtained by least squares fitting. The core of this step lies in applying the logistic growth model to predict the yeast population quantity P(t) at a specific time t. This formula can provide a dynamic prediction model for estimating the yeast population quantity at any time point during the fermentation process. Through this model, the growth trend of the yeast population can be predicted, including its growth rate and the final possible population quantity. This is crucial for the monitoring and control of the fermentation process because it allows timely adjustments to be made during the fermentation process to optimize yeast production. Exemplarily, when it is predicted that the yeast population quantity will reach an unsatisfactory level at a certain time point, the fermentation conditions, such as temperature, pH value, or nutrient supply, can be adjusted according to this prediction to promote better growth of the yeast. In addition, this prediction model can also help estimate the maximum potential of yeast production, thereby providing a scientific basis for production planning and resource allocation.

[0113] In step S126, according to the yeast growth rate and the yeast production prediction data, a data packaging operation is carried out to obtain production data.

[0114] It should be noted that in step S126, the data packaging operation is carried out by combining the yeast growth rate and the yeast production prediction data. This step is to integrate key production information for more comprehensive analysis and utilization of these data. The data packaging operation includes the following aspects: combining the yeast growth rate with the predicted yeast production data to form a comprehensive data set; in order to facilitate storage and transmission, the integrated data needs to be converted into a unified format. Exemplarily, the present invention adopts the XML format. Of course, according to different application scenarios and user requirements, other formats such as JSON format can also be selected. The present invention does not make any limitations in this regard; during the packaging process, the data is verified to ensure its accuracy and integrity. The data packaging operation in step S126 is an important link in the yeast production process. It not only improves the availability and security of the data, but also provides a basis for production monitoring, quality control, production optimization, and decision support.

[0115] In S13, according to the production data, cloud storage is carried out to obtain multi-node data backup.

[0116] It should be noted that in step S13, storing the production data in the cloud is a crucial step to ensure the security, accessibility, and reliability of the data. The cloud storage operation includes the following aspects: uploading the packaged production data to the cloud server; in the cloud, the data will be distributed and stored on multiple nodes, and this distributed storage can improve the reliability and fault tolerance of the data; backing up the data at different geographical locations or servers to prevent data loss caused by the failure of a single node; performing encryption processing before or after the data is uploaded to the cloud to ensure the security of the data during transmission and storage; setting appropriate access permissions to ensure that only authorized users can access specific data; tracking the modification of the data and retaining the historical versions of the data so that it can be restored to a previous version when needed. Through the multi-node data backup obtained by cloud storage, even if a certain node fails, the data can still be restored from other nodes, ensuring the continuity of the business. And users can access the cloud data through the network from any location, improving the flexibility of work. The cloud service provider provides professional security measures, including firewalls, intrusion detection systems, etc., to protect data security. The cloud storage operation in step S13 not only provides a secure and reliable storage solution for the production data, but also enhances the durability and accessibility of the data through multi-node data backup, providing a solid data foundation for the continuous optimization and monitoring of yeast production.

[0117] In S14, according to the production data, calculate the maximum yeast population quantity to obtain the maximum yeast population quantity, including:

[0118] According to the production environment, perform an ideal situation calculation to obtain the maximum value of the ideal yeast yield;

[0119] The calculation formula of the cloud server is as follows:

[0120]

[0121] Among them, P max represents the maximum yeast population quantity that can be achieved in the current production environment; C represents the maximum value of the ideal yeast yield, which is the maximum yeast population quantity that the environment can support; P0 represents the preset initial yeast population quantity, that is, the yeast quantity at the beginning of the fermentation process; r represents the yeast growth rate, reflecting the speed of yeast population growth; t0 represents the time length from the start of fermentation to a certain moment; e represents the base of the natural logarithm.

[0122] It should be noted that in step S14, by analyzing the production data and combining with the computing power of the cloud server, the maximum population number in the yeast production process is predicted. This step involves the calculation of the maximum yeast production value under ideal conditions, and the use of the logistic growth model to predict the maximum number that the yeast population may reach in the current production environment. In this process, first, the maximum ideal yeast production value C is set according to the production environment, which is the maximum yeast population number that the environment can support under the most suitable conditions. Then, the preset initial yeast population number P0 is used, which is the number of yeast at the start of the fermentation process. Through the cloud server, the calculation formula of the logistic growth model is applied, where P max represents the maximum yeast population number that can be reached in the current production environment. The parameter r represents the yeast growth rate, which reflects the speed of yeast population growth. The base e of the natural logarithm is a mathematical constant, approximately equal to 2.71828. Through this formula, the yeast production prediction result can be obtained, that is, the maximum possible number of the yeast population at a specific time point. This prediction result is crucial for the optimization of yeast production, because it can help understand the growth potential of the yeast population under the current production conditions, and how to adjust the production parameters to maximize the yield. Exemplarily, when it is determined that the predicted maximum yeast population number is lower than expected, the present invention selects to adjust the temperature, pH value or nutrient supply during the fermentation process to increase the yeast growth rate r. In addition, this prediction result can also be used for production planning and resource allocation to ensure the efficiency of the production process. The ultimate goal of the operation in step S14 is to increase the yeast yield and production efficiency.

[0123] In S15, according to the historical environment data, an operation of optimizing the fermentation environment calculation is performed to obtain environment adjustment data to achieve the optimization of yeast production control, including:

[0124] According to the historical environment data, a feature extraction operation is performed to obtain the initial values, maximum values and minimum values of the historical temperature, historical humidity, historical pH value and historical fermentation time;

[0125] According to the initial values, maximum values and minimum values of the historical temperature, historical humidity, historical pH value and historical fermentation time, a parameter adjustment calculation operation is performed to obtain the adjustment target values of the temperature, humidity, pH value and fermentation time;

[0126] According to the adjustment target values of the temperature, humidity, pH value and fermentation time, a control instruction is generated to achieve the optimization of yeast production control.

[0127] Among them, according to the initial values, maximum values and minimum values of the historical temperature, historical humidity, historical pH value and historical fermentation time, a parameter adjustment calculation operation is performed to obtain the adjustment target values of the temperature, humidity, pH value and fermentation time, including:

[0128] Calculate the variation ranges of temperature, humidity, pH value, and fermentation time based on the maximum and minimum values of the historical temperature, historical humidity, historical pH value, and historical fermentation time.

[0129] Calculate the adjustment target values of temperature, humidity, pH value, and fermentation time based on the variation ranges, initial values, and preset weights of temperature, humidity, pH value, and fermentation time.

[0130] The formula for calculating the variation range is as follows:

[0131] TR = T max - T min

[0132] HR = H max - H min

[0133] pHR = pH max - pH min

[0134] TimeR = Time max - Time min

[0135] Wherein, TR represents the variation range of temperature; T max represents the maximum value of temperature in the historical data; T min represents the minimum value of temperature in the historical data; HR is the variation range of humidity; H max represents the maximum value of humidity in the historical data; H min represents the minimum value of humidity in the historical data; pHR is the variation range of pH value; pH max represents the maximum value of pH in the historical data; pH min represents the minimum value of pH in the historical data; TimeR is the variation range of fermentation time; Time max represents the maximum value of fermentation time in the historical data; Time min represents the minimum value of fermentation time in the historical data;

[0136] The formula for parameter adjustment is as follows:

[0137] T Target = T + α·TR

[0138] H Target = HT + β·HR

[0139] pH Target = pHT + γ·pHR

[0140] TimeV Target = TimeV + ∈·TimeR

[0141] Among them, T Target represents the target temperature, T represents the initial temperature, and α represents the weight of temperature; H Target represents the target humidity, HT represents the initial humidity, and β represents the weight of humidity; pH Target represents the pH value, pHT represents the initial pH value, and γ represents the weight of the pH value; TimeV Target represents the target fermentation time, TimeV represents the initial fermentation time, and ∈ represents the weight of the fermentation time.

[0142] It should be noted that in step S15, the fermentation environment for yeast production is optimized by in-depth analysis of historical environmental data. This step extracts the key features from the historical data, including the initial values, maximum values, and minimum values of temperature, humidity, pH value, and fermentation time. These features provide a comprehensive overview of the yeast growth environment, including their historical variation ranges. First, the variation ranges of these environmental parameters are calculated, such as the temperature variation range (TR), humidity variation range (HR), pH value variation range (pHR), and fermentation time variation range (TimeR). These variation ranges are obtained through simple subtraction operations, that is, the maximum value of each parameter minus the minimum value. Exemplarily, the maximum value of temperature in the historical data is 40 °C, and the minimum value is 20 °C, then the temperature variation range is 20 °C. Next, these variation ranges, along with the initial values and preset weights, are used to calculate the target parameters. The weights (α, β, γ, ε) are preset according to the historical data and production goals, and are used to adjust the influence of each environmental parameter on yeast production. Through the parameter adjustment calculation formula, the adjusted target values of temperature (T_Target), humidity (H_Target), pH value (pH_Target), and fermentation time (TimeV_Target) can be obtained. The subsequent use of these adjusted target values is to generate control instructions to achieve the optimization of yeast production control. By precisely adjusting the temperature, humidity, pH value, and fermentation time during the fermentation process, the most suitable growth environment can be provided for yeast, thereby improving the yield and quality of yeast. Further, the weights of temperature, humidity, pH value, and fermentation time are set and adjusted based on the yeast production prediction results. Exemplarily, when it is determined that yeast grows better at a lower pH value, the fermentation process can be adjusted by increasing the weight γ of the pH value to make it more inclined to a lower pH value. The operations in step S15 not only improve the understanding of the yeast growth environment, but also achieve the maximization of yeast production through intelligent environmental control optimization.

[0143] It should be noted that in the implementation of the fermentation environment optimization control method, advanced control algorithms are adopted to precisely adjust the key parameters in the fermentation process, including temperature and pH value, to ensure the optimal conditions for yeast production. Exemplarily, for temperature control, the present invention uses the proportional-integral-derivative (PID) algorithm, which is an algorithm widely used in industrial control and can adjust the control signal according to the error between the set temperature and the actual temperature. The formula of the PID algorithm is where u(t) is the control signal, e(t) is the error, and K p is the proportionality coefficient, K i is the integral coefficient, and K d is the derivative coefficient. By continuously adjusting these coefficients, the PID controller can stabilize the temperature in the fermenter near the optimal growth temperature of yeast. Exemplarily, for pH value adjustment, the present invention adopts an analog feedback control algorithm. This algorithm calculates the amount of acid or base to be added according to the difference between the target pH value and the actual pH value. For example, when pH error = pH target - pH actual , then the amount of acid or base to be added can be calculated by the formula Q = k × pH error , where k is a coefficient determined according to factors such as the concentration of acid and base and the volume of the fermentation broth. In this way, the pH value in the fermentation process can be precisely adjusted to maintain the optimal acidity and alkalinity required for yeast growth. The implementation of these control methods makes the optimization control of the fermentation environment more automated and intelligent. By precisely controlling the temperature and pH value in the fermentation process, the production efficiency and product quality of yeast can be significantly improved. This method not only improves the stability of the production process but also reduces the need for manual intervention, thereby reducing production costs and improving the sustainability of the production process. In this way, it can be ensured that the yeast production process is carried out under the optimal conditions, thereby maximizing the yeast yield.

[0144] In summary, the present invention provides a data processing method for yeast production based on cloud computing, including: obtaining temperature data, humidity data, time data, and PH data of the historical fermentation environment, performing feature enhancement operations to obtain historical environment data; according to the historical environment data, performing a logistic growth model fitting operation to obtain production data; according to the production data, performing cloud storage to obtain multi-node data backup; according to the production data, calculating the maximum yeast population quantity to obtain a yeast production prediction result; according to the historical environment data, performing a fermentation environment optimization calculation operation to obtain environment adjustment data to achieve the optimization of yeast production control. The present invention fits the historical environment data, accurately predicts the growth trend and yield of yeast, and performs optimization control based on historical data for specific environmental problems, thereby achieving the improvement of yeast yield.

[0145] Reference Figure 3 , an embodiment of the present invention provides a data processing device for yeast production based on cloud computing, including:

[0146] An environmental data acquisition module, configured to acquire temperature data, humidity data, time data, and PH data of a historical fermentation environment, perform feature enhancement operations, and obtain historical environmental data;

[0147] A production data calculation module, configured to perform a logistic growth model fitting operation according to the historical environmental data to obtain production data;

[0148] A data storage module, configured to perform cloud storage according to the production data to obtain multi-node data backup;

[0149] A production prediction module, configured to calculate the maximum yeast population according to the production data to obtain a yeast production prediction result;

[0150] A control optimization module, configured to perform a fermentation environment optimization calculation operation according to the historical environmental data to obtain environmental adjustment data to achieve yeast production control optimization.

[0151] It should be noted that the data processing device for yeast production based on cloud computing provided by the embodiment of the present invention is used to execute all the process steps of the data processing method for yeast production based on cloud computing in the above embodiment. The working principles and beneficial effects of the two correspond one by one, so they will not be elaborated here.

[0152] The embodiment of the present invention also provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned embodiments of the data processing method for yeast production based on cloud computing are implemented, such as Figure 1 the steps S11 shown. Alternatively, when the processor executes the computer program, the functions of each module / unit in the above-mentioned device embodiments are implemented.

[0153] Exemplarily, the computer program can be divided into one or more modules / units. The one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0154] The electronic device may be a computing device such as a desktop computer, notebook, palm computer, and smart tablet. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above components are only examples of the electronic device and do not constitute a limitation on the electronic device. It may include more or fewer components than the above, or combine some components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, etc.

[0155] The so-called processor may be a central processing unit (CPU), or may also 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 the processor may also be any conventional processor, etc. The processor is the control center of the electronic device, connecting various parts of the entire electronic device through various interfaces and lines.

[0156] The memory can be used to store the computer program and / or module. The processor realizes various functions of the electronic device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory may mainly include a program storage area and a data storage area. Among them, the program storage area may store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area may store data created according to the use of the mobile phone (such as audio data, phone book, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one magnetic disk storage device, flash device, or other volatile solid-state storage devices.

[0157] Among them, if the modules / units integrated in the electronic device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-described embodiment methods of the present invention, it can also be completed by a computer program instructing relevant hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0158] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the attached drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that they have a communication connection, which can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement it without creative effort.

[0159] The above-described specific embodiments have further elaborated on the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above is only the specific embodiments of the present invention and is not used to limit the protection scope of the present invention. It is particularly pointed out that for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A data processing method for yeast production based on cloud computing, characterized in that: Executed by a computer, including: Obtain temperature data, humidity data, time data and pH data of the historical fermentation environment, perform feature enhancement operations, and obtain historical environmental data; Performing a logistic growth model fitting operation according to the previously acquired historical yeast population quantity and the historical environmental data to obtain production data; According to the production data, cloud storage is performed to obtain multi-node data backup; Calculating the maximum yeast population according to the production data to obtain a yeast production prediction result; According to the historical environmental data, fermentation environment optimization calculation operation is performed to obtain environmental adjustment data to achieve yeast production control optimization.

2. The data processing method for yeast production based on cloud computing according to claim 1, characterized in that: According to the previously acquired historical yeast population and the historical environmental data, a logistic growth model fitting operation is performed to obtain production data, including: Performing normalization processing according to the historical yeast population quantity and the historical environmental data to obtain normalized data; Performing a least squares fitting operation according to the normalized data to obtain model parameter data; According to the video sensor, the yeast population is calculated to obtain the current yeast population; According to the model parameter data, the current yeast population and the preset maximum yeast yield, a yeast growth rate calculation operation is performed to obtain a yeast growth rate; According to the preset initial yeast population quantity and model parameter data, a yeast production prediction operation is performed to obtain yeast production prediction data; According to the yeast growth rate and the yeast production prediction data, a data packaging operation is performed to obtain production data.

3. The data processing method for yeast production based on cloud computing according to claim 1, characterized in that: According to the production data, the maximum yeast population quantity is calculated to obtain the maximum yeast population quantity, including According to the production environment, the ideal situation is calculated to obtain the maximum ideal yeast yield; The cloud server calculation formula is as follows: Among them, P max It represents the maximum yeast population that can be achieved under the current production environment; C represents the maximum ideal yeast yield; P0 represents the preset initial yeast population; r represents the yeast growth rate; t0 represents the length of time from the start of fermentation to a certain moment; e represents the base of the natural logarithm.

4. The data processing method for yeast production based on cloud computing according to claim 1, characterized in that: According to the historical environmental data, a fermentation environment optimization calculation operation is performed to obtain environmental adjustment data to achieve yeast production control optimization, including: Performing feature extraction operations based on the historical environmental data to obtain initial values, maximum values, and minimum values ​​of historical temperature, historical humidity, historical pH value, and historical fermentation time; According to the initial value, maximum value and minimum value of the historical temperature, historical humidity, historical pH value and historical fermentation time, a parameter adjustment calculation operation is performed to obtain adjustment target values ​​of temperature, humidity, pH value and fermentation time; According to the adjustment target values ​​of the temperature, humidity, pH value and fermentation time, control instructions are generated to achieve yeast production control optimization.

5. The data processing method for yeast production based on cloud computing according to claim 2, characterized in that: According to the normalized data, a least squares fitting operation is performed to obtain model parameter data, including: The objective function of the least squares fitting operation is as follows: Among them, y represents the normalized historical yeast population, x represents the normalized historical environmental data; a and b are model parameter data determined by fitting operations; a represents the growth coefficient; b represents the inhibition constant; the model parameter data consists of a and b; e represents the base of the natural logarithm.

6. The data processing method for yeast production based on cloud computing according to claim 2, characterized in that: According to the model parameter data, the current yeast population and the preset maximum yeast yield, a yeast growth rate calculation operation is performed to obtain the yeast growth rate, including: The yeast growth rate calculation formula is as follows: Among them, r represents the yeast growth rate; a represents the growth coefficient, P(t) represents the yeast population at time t; and C represents the preset maximum yeast yield.

7. The data processing method for yeast production based on cloud computing according to claim 2, characterized in that: According to the preset initial yeast population quantity and model parameter data, yeast production prediction operation is performed to obtain yeast production prediction data, including: The yeast production prediction calculation formula is as follows: Among them, P(t) represents the predicted yeast population at time t; P0 represents the preset initial yeast population; a represents the growth coefficient; b represents the inhibition constant; and e represents the base of the natural logarithm.

8. The data processing method for yeast production based on cloud computing according to claim 4, characterized in that: According to the initial value, maximum value and minimum value of the historical temperature, historical humidity, historical pH value and historical fermentation time, a parameter adjustment calculation operation is performed to obtain adjustment target values ​​of temperature, humidity, pH value and fermentation time, including: According to the maximum and minimum values ​​of the historical temperature, historical humidity, historical pH value and historical fermentation time, a variation range is calculated to obtain the variation range of temperature, humidity, pH value and fermentation time; According to the variation range, initial value and preset weight of temperature, humidity, pH value and fermentation time, target parameter calculation is performed to obtain the adjustment target values ​​of temperature, humidity, pH value and fermentation time; The formula for calculating the variation range is as follows: TR=T max -T min HR=H max -H min pH=pH max -pH min TimeR=Time max -Time min Where TR represents the temperature range; T max Indicates the maximum temperature in historical data; T min Indicates the minimum temperature in historical data; HR is the range of humidity; H max Indicates the maximum humidity in historical data; H min Indicates the minimum humidity value in historical data; pHR is the range of pH value; pH max Indicates the maximum pH value in historical data; pH min Indicates the minimum pH value in historical data; TimeR is the range of fermentation time; Time max Indicates the maximum fermentation time in historical data; Time min Indicates the minimum fermentation time in historical data; The parameter adjustment calculation formula is as follows: T Target =T+α·TR H Target =HT+β·HR pH Target =pHT+γ·pHR TimeV Target =TimeV+∈·TimeR Among them, T Target represents the target temperature, T represents the initial temperature, α represents the weight of the temperature; H Target represents the target humidity, HT represents the initial humidity, β represents the weight of humidity; pH Target represents pH value, pHT represents initial pH value, γ represents weight of pH value; TimeV Target represents the target fermentation time, TimeV represents the initial fermentation time, and ∈ represents the weight of the fermentation time.

9. A data processing device for yeast production based on cloud computing, characterized in that: include: The environmental data acquisition module is used to obtain the temperature data, humidity data, time data and pH data of the historical fermentation environment, perform feature enhancement operations, and obtain historical environmental data; A production data calculation module, used to perform a logistic growth model fitting operation based on the historical yeast population number and the historical environmental data obtained in advance to obtain production data; A data storage module, used to perform cloud storage based on the production data to obtain multi-node data backup; A production prediction module, used to calculate the maximum yeast population according to the production data to obtain a yeast production prediction result; The control optimization module is used to perform fermentation environment optimization calculation operations according to the historical environmental data to obtain environmental adjustment data to achieve yeast production control optimization.

10. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the data processing method for yeast production based on cloud computing according to any one of claims 1 to 8 is implemented.

Images