Fermentation management method and system for yoghourt preparation

Abstract

The invention relates to the technical field of yogurt fermentation, and discloses a fermentation management method and system for yogurt preparation, and the system comprises an acquisition module, a factor construction module, a classification module, a fermentation optimization module and a storage module. The acquisition module acquires fermentation parameters in the historical fermentation data; the factor construction module constructs a fermentation feature set and an evolution factor set based on the fermentation parameters; the classification module calculates the fermentation deviation degree by comparing the fermentation characteristics of the current yoghourt with historical data, and performs classification according to a set standard; when the classification is the second class, the fermentation optimization module outputs an optimization suggestion; and the storage module stores the constructed fermentation characteristics, evolution factors and classification data. According to the invention, the fermentation process can be automatically monitored based on historical data, the fermentation parameters of yoghourt are adjusted in real time, and the stability and consistency of product quality are ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of yogurt fermentation, in particular to a fermentation management method and system for yogurt preparation. BACKGROUND

[0002] The quality and flavor of yogurt largely depend on the precise control during its fermentation process. Traditional yogurt production usually relies on manual operation and experience-based judgment, although the quality of the final product can be influenced by adjusting fermentation conditions such as temperature, pH value and bacterial population activity, this method cannot provide precise real-time adjustment and is easily affected by external environmental changes and operational errors. Therefore, how to achieve precise control and optimization of the yogurt fermentation process to ensure the consistency and high quality of each batch of yogurt has become a technical problem in the current food industry.

[0003] In the prior art, some fermentation control is performed by manual intervention and rule-based monitoring systems, but there is a lack of intelligent real-time analysis and feedback mechanism. These systems often cannot effectively respond to complex changes in the fermentation environment, and lack systematic data analysis and prediction mechanisms, resulting in poor stability of the yogurt fermentation process and large fluctuations in the quality of the final product.

[0004] Therefore, how to realize real-time monitoring and optimization of the yogurt fermentation process based on a data-driven method to improve the stability and production efficiency of the fermentation process is a technical problem to be solved. SUMMARY

[0005] In view of this, the present application proposes a fermentation management method and system for yogurt preparation to solve the above problems.

[0006] In one aspect, the present application proposes a fermentation management system for yogurt preparation, comprising: The acquisition module is configured to obtain fermentation parameters of several batches of yogurt fermentation in historical fermentation data; The factor construction module is configured to construct a fermentation feature set according to the fermentation parameters, and construct a fermentation evolution factor set according to the fermentation feature set; The classification module is configured to obtain the fermentation feature set and the fermentation evolution factor of the current yogurt fermentation, and compare them with the fermentation feature set and the fermentation evolution factor set of the historical fermentation data, calculate the fermentation deviation degree, and match the fermentation deviation degree with the set classification standard to determine the classification; the classification includes a first class and a second class with increasing fermentation deviation degrees; The fermentation optimization module is configured to analyze a matching relationship between a moving direction of the fermentation feature set of the current yogurt and a moving direction of the fermentation evolution factor when classified as the second type; and output an optimization suggestion according to the relationship between the moving direction of the fermentation feature set and the moving direction of the fermentation evolution factor. The storage module is configured to store the constructed fermentation feature set, the fermentation evolution factor and the classification.

[0007] Further, it further comprises: The analysis module is configured to compare the fermentation feature set of the current yogurt and the fermentation evolution factor with historical fermentation data, obtain a historical fermentation sample, and output an adjustment amplitude of the current yogurt and a fermentation process deviation risk based on a historical fermentation evolution factor moving direction and a classification of the historical fermentation sample.

[0008] Further, the fermentation parameters include temperature, pH value, bacterial activity and fermentation time; According to the temperature, pH value and bacterial activity, curve data of the temperature, pH value and bacterial activity changing with time in the fermentation process is established.

[0009] Further, the fermentation feature set constructed by the factor construction module comprises: a temperature difference value between the temperature and a set fermentation temperature, a fitting residual value between the pH value and a target acidity value, an activity difference value between the bacterial activity and a target activity level, and a correlation analysis value of the temperature and the pH value; The fermentation evolution factor set constructed by the factor construction module comprises: a temperature change rate, a pH value change rate, a time period from the start to the stable stage of the fermentation stage, and a slope value of the temperature and pH value change curve in the time period; a growth rate of the bacterial activity in the initial growth stage and a fluctuation amplitude in the bacterial stability stage; The temperature change rate is the change amount of the temperature per unit time, and the pH value change rate is the change amount of the pH value per unit time.

[0010] Further, the classification module specifically comprises: calculating a similarity degree based on the fermentation feature set and the fermentation evolution factor set, and calculating a difference degree of the current yogurt and the historical fermentation data; generating a fermentation deviation vector according to the similarity degree calculation result, and obtaining a fermentation deviation degree by normalization weighting of each parameter value in the deviation vector.

[0011] Further, the fermentation deviation degree is matched with a set classification standard threshold value, and is respectively assigned to the first type or the second type.

[0012] Further, the fermentation optimization module, upon receiving the second type, performs the following operations: Obtain the moving direction of temperature, pH value and bacterial activity in the fermentation characteristic set in the current yogurt; Meanwhile, extract the moving direction of temperature change rate, pH value change rate, bacterial activity growth rate and fluctuation amplitude in the fermentation evolution factor set; If the moving direction of temperature, pH value and bacterial activity in the fermentation characteristic set is the same as the moving direction of any parameter in the fermentation evolution factor set, it is judged that the fermentation adjustment is consistent with the performance response, and at this time the fine adjustment of temperature and pH value is carried out; If the moving direction of any parameter in the fermentation characteristic set is opposite to the direction of two or more parameters in the fermentation evolution factor set, it is judged that the ratio disturbance is mismatched, the bacterial activity is re-evaluated, and the temperature adjustment is suspended; If the moving amplitude of the bacterial activity is greater than 1.5 times the average of the moving amplitude of the bacterial activity in the historical fermentation characteristic set, an abnormal fermentation stability prompt is output, and the fermentation time is adjusted or the temperature control setting is optimized.

[0013] Further, the analysis module performs the following operations based on the matching results of the fermentation characteristic set and the fermentation evolution factor set in the storage module: Select the top five historical samples with the smallest Euclidean distance from the current yogurt fermentation characteristic set as the historical fermentation samples; Extract the corresponding fermentation evolution factor set in the historical fermentation sample, including temperature change rate, pH value change rate and bacterial activity growth rate; According to the moving direction of the fermentation evolution factor set and the corresponding ratio parameter adjustment record, the response path trajectory is constructed; Based on the change trend of the fermentation evolution factor set of the current yogurt under different ratio parameter adjustment conditions, a structure response prediction sequence is formed, and the prediction result is output to the fermentation optimization module.

[0014] Further, the analysis module further includes a risk unit, which is configured to: According to the combination change history of the fermentation characteristic set and the fermentation evolution factor set in the historical fermentation sample, calculate the adjustment amplitude of the current yogurt under the current structure condition; According to whether the bacterial activity change rate and the temperature change rate are higher than the corresponding 95% confidence interval of the sample in the storage module, calculate the structure deviation trend risk signal; When the bacterial activity change rate and the temperature change rate are both in the abnormal interval, output a high risk signal, if only one parameter is high, output a medium risk signal, and when both are in the normal interval, output a low risk signal.

[0015] Compared with the prior art, the present application has the beneficial effects that: The system cooperates with the factor construction module through the acquisition module, extracts not only basic parameters such as temperature, pH value, and microbial activity, but also constructs a fermentation characteristic set and a fermentation evolution factor set reflecting the evolution trend, and quantifies the state structure of the entire fermentation process in the form of curve slope, change rate, and correlation factor, thereby breaking away from the limitation of judging the fermentation state by single-point data in the traditional way and realizing structured modeling and trend mapping of the entire process. The system introduces the quantitative logic of “fermentation deviation degree” in the classification module, calculates the similarity between the current characteristic set and the historical data, constructs a normalized deviation vector, divides each batch of yogurt fermentation state into “class I” (normal) and “class II” (deviation), enables the system to identify the slight deviation state early, and is no longer limited to the result judgment after the final product is out of control, thereby effectively improving the fault tolerance and control sensitivity of the fermentation process. The present application proposes to analyze the matching relationship between the current fermentation parameters and the evolution factor “moving direction” under the “class II” state. This mechanism is equivalent to introducing a verification mechanism of “fermentation control-system response”: if the directions are consistent, it means that the adjustment is effective, and the system gives a fine control suggestion; if the directions conflict, it means that the adjustment is ineffective or even disturbs the system, thereby avoiding the vicious cycle of “adjustment-no response-readjustment-out of control” in the traditional control.

[0016] On the other hand, the present application proposes a fermentation management system for yogurt preparation, comprising: S2: constructing a fermentation characteristic set according to the fermentation parameters, and constructing a fermentation evolution factor set according to the fermentation characteristic set; S3: acquiring the fermentation characteristic set and the fermentation evolution factor of the current yogurt fermentation, comparing them with the fermentation characteristic set and the fermentation evolution factor set of the historical fermentation data, calculating the fermentation deviation degree, matching the fermentation deviation degree with the set classification standard, and determining the classification; the classification includes class I and class II in which the fermentation deviation degree increases successively; S4: when the classification is class II, analyzing the matching relationship between the moving direction of the fermentation characteristic set of the current yogurt and the moving direction of the fermentation evolution factor; according to the relationship between the moving direction of the fermentation characteristic set and the moving direction of the fermentation evolution factor, and outputting an optimization suggestion; S5: storing the constructed fermentation characteristic set, fermentation evolution factor, and classification.

[0017] It should be noted that the fermentation management method for yogurt preparation of the present application and the system thereof have the same beneficial effects, which will not be described here. BRIEF DESCRIPTION OF DRAWINGS

[0018] Various other advantages and benefits will become apparent to those of ordinary skill in the art, upon reading the following detailed description of the preferred embodiments. The accompanying drawings are included to provide a description of preferred embodiments, and are not meant to limit the present application. Furthermore, the same reference numerals are intended to identify the same components throughout the various figures. In the drawings: Figure 1 A functional block diagram of a fermentation management system for yogurt preparation according to an embodiment of the present application.

[0019] Figure 2 A flowchart of a fermentation management method for yogurt preparation according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] Exemplary embodiments of the present application will be described herein below with reference to the accompanying drawings. Although exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the present application to those skilled in the art. It should be noted that the embodiments and features of the present application can be combined with each other, if not in conflict. The present application will be described in detail with reference to the accompanying drawings and embodiments.

[0021] Referring to Figure 1 As shown in the drawings, an embodiment of the present application provides a fermentation management system for yogurt preparation, comprising: A collection module configured to obtain fermentation parameters of several batches of yogurt fermentation in historical fermentation data; A factor construction module configured to construct a fermentation feature set according to the fermentation parameters, and construct a fermentation evolution factor set according to the fermentation feature set; A classification module configured to obtain fermentation features and fermentation evolution factors of current yogurt fermentation, and compare them with fermentation features and fermentation evolution factor sets of historical fermentation data, calculate fermentation deviation degree, match the fermentation deviation degree with a set classification standard, and determine the classification; the classification includes a first class and a second class with increasing fermentation deviation degree; A fermentation optimization module configured to analyze the matching relationship between the moving direction of the fermentation feature set and the moving direction of the fermentation evolution factor when the classification is the second class; output an optimization suggestion according to the relationship between the moving direction of the fermentation feature set and the moving direction of the fermentation evolution factor; A storage module configured to store the constructed fermentation feature set, fermentation evolution factor and classification.

[0022] It can be understood that by collecting historical fermentation data and constructing a set of fermentation characteristics and a set of evolution factors, the fermentation process of each batch of yogurt can be comprehensively tracked. This makes the control of the fermentation process more accurate, reduces the limitations of traditional reliance on human experience, and ensures the quality and consistency of the product.

[0023] By comparing the fermentation data of the current yogurt with historical samples in real time, the system can automatically calculate the degree of fermentation deviation and classify according to the set standard. This classification mechanism can identify deviations in the fermentation process in a timely manner, especially in cases of large deviations, and can quickly respond to avoid affecting the quality of the final product.

[0024] When the fermentation deviation reaches the second category, the system will analyze the matching relationship between the set of fermentation characteristics and the fermentation evolution factors, and provide personalized optimization suggestions. By fine-tuning various parameters in the fermentation process, the system can optimize key factors such as temperature, pH value, and microbial activity, thereby improving the stability and quality of yogurt fermentation.

[0025] All fermentation characteristics, evolution factors, and classification results are stored in a database. This not only facilitates the review of historical data, but also supports future fermentation trend analysis and prediction, thereby achieving long-term optimization of the production process.

[0026] Through intelligent data analysis and optimization suggestions, the system greatly reduces manual intervention and errors, making the production process more efficient and stable. In addition, the system can adjust fermentation parameters in a timely manner to ensure the quality of each batch of yogurt is more consistent, avoiding quality fluctuations caused by improper human operation.

[0027] This system not only applies to the production and management of yogurt, but also can be flexibly applied to the production process control of other fermented products, with strong adaptability and expandability, and can meet different production needs In some embodiments of the present application, further comprising: The analysis module is configured to compare the set of fermentation characteristics and the fermentation evolution factors of the current yogurt with historical fermentation data, obtain historical fermentation samples, and based on the historical fermentation evolution factor movement direction and classification of the historical fermentation samples, output the adjustment amplitude of the current yogurt and the fermentation process deviation risk.

[0028] It should be noted that the implementation steps of the analysis module are as follows: the system first collects the fermentation characteristic set and the fermentation evolution factor set of the current yogurt batch, which includes important fermentation parameters such as temperature, pH value, and microbial activity, as well as the curve data of the change over time. The fermentation characteristic set of the current yogurt is compared with the fermentation characteristic set in the historical database to find similar historical fermentation samples to the current yogurt fermentation process. The purpose of this step is to find the historical batch closest to the current yogurt fermentation conditions by calculating the similarity between the current data and the historical data. From the found historical fermentation samples, the corresponding fermentation evolution factors are extracted, including temperature change rate, pH value change rate, and microbial activity growth rate. These factors will be used to compare the change trend of the parameters in the current yogurt fermentation process. Based on the moving direction of the fermentation evolution factors of the historical samples and the change trend of the fermentation evolution factors of the current yogurt, the degree of deviation of the current yogurt fermentation process is analyzed. If the change direction of the current fermentation characteristics is consistent with that of the historical samples, it means that the fermentation process is stable, otherwise, if the change direction is inconsistent, it means that the fermentation process may be abnormal. The system outputs the adjustment amplitude of the current yogurt (i.e. the specific value that needs to be adjusted) and the fermentation process deviation risk (evaluates the degree of deviation of the fermentation process from the historical samples, so as to determine the potential risk).

[0029] The analysis module will output the adjustment amplitude for the current fermentation process and evaluate the deviation risk of the fermentation process. If the system judges that the current yogurt fermentation process deviates from the normal range, it may issue a warning and give corresponding adjustment suggestions, such as adjusting the fermentation temperature, extending the fermentation time, etc., to ensure the smooth progress of the yogurt fermentation process and improve the consistency of the product.

[0030] In some embodiments of the present application, the fermentation parameters include: temperature, pH value, microbial activity, and fermentation time; According to the temperature, pH value, and microbial activity, the curve data of the change of the temperature, pH value, and microbial activity over time in the fermentation process is established.

[0031] The fermentation characteristic set constructed by the factor construction module includes: temperature difference value between temperature and set fermentation temperature, fitting residual value between pH value and target acidity value, activity difference value between microbial activity and target activity level; correlation analysis value of temperature and pH value; The fermentation evolution factor set constructed by the factor construction module includes: In the fermentation stage, the time period from the start to the stable stage of the temperature change rate and the pH value change rate, and the slope value of the temperature and pH value change curve in this time period; the growth rate of microbial activity in the initial growth stage and the fluctuation amplitude in the microbial stability stage; The temperature change rate is the change amount of temperature per unit time, and the pH value change rate is the change amount of pH value per unit time.

[0032] It should be noted that real-time temperature data during the fermentation of yogurt is obtained, and a target fermentation temperature is set. The temperature difference value = current fermentation temperature - set fermentation temperature. The influence of temperature fluctuation on the fermentation process is obtained by this calculation. Real-time pH value data is collected, and a target acidity value is obtained. The relationship between the pH value in the historical fermentation data and the target acidity value is fitted by the least squares method to obtain a fitting curve. The residual error value is the difference between the actual measured pH value and the fitting curve value. The residual error value = measured pH value - predicted value of the fitting curve, and the larger the residual error value, the greater the acidity fluctuation and the greater the influence on the fermentation process. The activity of the microbial population during the fermentation process is monitored in real time and compared with the set target activity level. The activity difference value = current microbial population activity - target activity level. The difference value can be used to determine whether the microbial population activity meets the expected requirements, and if the difference value is too large, it indicates that the fermentation process is abnormal. Temperature and pH value data during the fermentation process are collected. The linear relationship between temperature and pH value is calculated using the Pearson Correlation Coefficient.

[0033] The stable stage refers to the stage after the start of fermentation, during which the activity of the microbial population gradually increases. During this stage, temperature and pH value usually undergo relatively intense changes, and the activity of the microbial population rapidly increases. During the fermentation process, various parameters such as temperature, pH value, and microbial population activity usually exhibit relatively obvious fluctuations.

[0034] The initial growth stage is a later stage in the fermentation process, during which the fermentation environment tends to be stable. The activity of the microbial population gradually reaches equilibrium, the change range of temperature and pH value decreases, the fluctuation of fermentation parameters tends to be stable, and the change rate is relatively low. At this time, the main fermentation process of yogurt has been completed, and all fermentation parameters have stabilized within the set range, ensuring stable product quality.

[0035] In some embodiments of the present application, the classification module specifically includes: Based on the fermentation feature set and the fermentation evolution factor set, the similarity is calculated to calculate the difference degree of the current yogurt and the historical fermentation data; According to the similarity calculation result, a fermentation deviation vector is generated, and each parameter value in the deviation vector is obtained by normalization weighting to obtain the fermentation deviation degree.

[0036] It is necessary to extract the relevant fermentation feature set and fermentation evolution factor set from the current yogurt fermentation process and historical fermentation data. The similarity between these sets is calculated to quantify the difference between the current fermentation sample and the historical sample. Common calculation methods include Euclidean distance, cosine similarity or Mahalanobis distance, which can reflect the similarity and difference between samples. According to the similarity calculation result of the previous step, the fermentation deviation vector is generated. This vector represents the deviation of the current yogurt fermentation sample from the historical sample. Each deviation value represents the difference between the current sample and the historical sample in different fermentation parameters (such as temperature, pH value, microbial activity, etc.). By calculating the difference value of each parameter and normalizing, it ensures that different unit and scale feature values can be compared. Normalize each fermentation feature and evolution factor, that is, standardize their values to a relatively unified range. By normalizing, the dimensional differences between different feature values can be eliminated. Then, by weighting each index, the weight reflects the relative importance of each fermentation feature to the final fermentation quality. The weighted fermentation deviation vector provides a more comprehensive deviation evaluation. Finally, based on the generated deviation vector, the overall fermentation deviation degree of the current yogurt sample is calculated by weighted average or summation. The higher this value, the greater the deviation of the current fermentation process from the historical fermentation sample, which may indicate problems in the fermentation process. The calculated deviation degree is matched with the set classification standard. According to the size of the deviation degree, the current yogurt sample will be classified into the first class or the second class. The first class represents a smaller deviation, and the second class represents a larger deviation. When the deviation degree exceeds the upper limit of the second class, it is considered that there are major problems in the fermentation process, which needs to be further optimized.

[0037] In some embodiments of the present application, the fermentation deviation degree is matched with the set classification standard threshold, and the first class or the second class is respectively assigned.

[0038] In some embodiments of the present application, when the fermentation optimization module receives the second class, it performs the following operations: Obtain the moving direction of temperature, pH value and microbial activity in the fermentation feature set in the current yogurt; At the same time, extract the moving direction of temperature change rate, pH value change rate, microbial activity growth rate and fluctuation amplitude in the fermentation evolution factor set; If the moving direction of temperature, pH value and microbial activity in the fermentation feature set is the same as the moving direction of any parameter in the fermentation evolution factor set, it is judged that the fermentation adjustment and performance response are consistent, and at this time, fine adjustment of temperature and pH value is performed; If the moving direction of any parameter in the fermentation feature set is opposite to the direction of two or more parameters in the fermentation evolution factor set, it is judged that the ratio disturbance is mismatched, the microbial activity is re-evaluated, and the temperature adjustment is suspended; If the moving range of the microbial activity is greater than 1.5 times the average of the moving range of the microbial activity in the historical fermentation feature set, an abnormal fermentation stability prompt is output, and the fermentation duration is adjusted or the temperature control setting is optimized.

[0039] Specifically, the parameter change direction in the fermentation feature set of the current yogurt is obtained: from the feature data obtained during the fermentation process of the current yogurt, the change trend of the fermentation parameters such as temperature, pH value and microbial activity in the fermentation feature set is analyzed and recorded. The change direction of each parameter (such as increase, decrease or remain stable) reflects the state of the fermentation process.

[0040] Extract the parameter change direction in the fermentation evolution factor set: extract relevant data such as temperature change rate, pH value change rate, microbial activity growth rate and fluctuation range from the fermentation evolution factor set, and analyze the change trend of these indicators. The change rate and fluctuation range will reveal the rapidity and volatility of the changes in temperature, pH value and microbial activity during the fermentation process.

[0041] Determine whether the change direction of temperature, pH value and microbial activity is consistent with the change direction of the fermentation evolution factor: if the change direction of temperature, pH value and microbial activity in the fermentation feature set is consistent with the change direction of any parameter in the fermentation evolution factor set, it indicates that the adjustment of the fermentation process is consistent with the performance response. At this time, fine adjustment of temperature and pH value is carried out to optimize the fermentation process and make it stable.

[0042] Determine whether there is a matching disturbance mismatch: if the change direction of any parameter in the fermentation feature set is opposite to the direction of two or more parameters in the fermentation evolution factor set, it indicates that there may be a disturbance mismatch in the fermentation process. At this time, the microbial activity needs to be re-evaluated and the temperature adjustment is suspended to avoid further interference with the fermentation process.

[0043] Determine whether the microbial activity is greater than the average of 1.5 times the fluctuation range of the historical sample: if the fluctuation range of the microbial activity of the current yogurt exceeds 1.5 times the average of the fluctuation range of the microbial activity in the historical fermentation feature set, it indicates that instability may occur in the fermentation process, and an abnormal fermentation stability prompt is output. Fermentation duration adjustment or optimization of temperature control setting is carried out according to the prompt to restore the stability of the fermentation process.

[0044] In some embodiments of the present application, the analysis module performs the following operations based on the matching results of the fermentation feature set and the fermentation evolution factor set in the storage module: Select the top five historical samples with the smallest Euclidean distance from the current yogurt fermentation feature set as the historical fermentation samples; Extract the corresponding fermentation evolution factor set in the historical fermentation sample, including temperature change rate, pH value change rate and microbial activity growth rate; According to the moving direction of the fermentation evolution factor set and the corresponding matching parameter adjustment record, a response path trajectory is constructed; Based on the change trend of the fermentation evolution factor set of the current yogurt under different matching parameter adjustment conditions, a structure response prediction sequence is formed, and the prediction result is output to the fermentation optimization module.

[0045] It should be noted that the historical fermentation samples are selected: the analysis module compares the current yogurt fermentation characteristic set with the fermentation characteristic set of the historical fermentation data in the storage module, selects the top five historical samples that best match the current yogurt fermentation sample fermentation characteristic set by calculating the Euclidean distance. These historical samples have the most similar characteristics to the current yogurt fermentation sample, which can help predict the current fermentation state.

[0046] Extract the fermentation evolution factor set in the historical fermentation sample: from the selected historical fermentation sample, extract the corresponding fermentation evolution factor set. Specifically, it includes temperature change rate, pH value change rate and microbial activity growth rate and other data. These factors help understand the fermentation process characteristics of historical fermentation samples and provide reference for the current yogurt fermentation process.

[0047] Construct a response path trajectory: according to the change trend of each parameter in the extracted fermentation evolution factor set, combined with the matching parameter adjustment record recorded in the historical sample, a response path trajectory is constructed. This trajectory represents the change path of the historical fermentation sample under different conditions.

[0048] Generate a structure response prediction sequence: based on the change trend of the fermentation characteristic set of the current yogurt and the fermentation evolution factor set under different matching parameter adjustment conditions, a structure response prediction sequence is formed. This sequence can predict the future change trend of the yogurt fermentation process under the current conditions. Output the prediction result: output the generated structure response prediction sequence to the fermentation optimization module. The optimization module can adjust the yogurt fermentation conditions such as temperature, pH value and microbial activity in time according to the prediction result, so as to optimize the fermentation process and improve the consistency and quality of the final product.

[0049] Specific implementation steps: obtain the comparison result of the current yogurt fermentation characteristic set and the historical fermentation data. Select the top five historical samples with the smallest Euclidean distance. Extract the fermentation evolution factor set (temperature change rate, pH value change rate, microbial activity growth rate) of the historical sample. According to the change direction, a response path trajectory is constructed. Based on the change trend of the fermentation evolution factor set, a response prediction sequence is formed. The prediction result is output to the fermentation optimization module for optimization and adjustment.

[0050] In some embodiments of the present application, the analysis module further comprises a risk unit, which is configured to: According to the historical changes in the combination of the set of fermentation characteristics and the set of fermentation evolution factors in historical fermentation samples, the adjustment amplitude of the current yogurt under the current structural conditions is calculated; According to whether the rate of change of microbial activity and the rate of change of temperature are higher than the 95% confidence interval corresponding to the sample in the storage module, a structural deviation trend risk signal is calculated; When the rate of change of microbial activity and the rate of change of temperature are both in the abnormal interval, a high-risk signal is output, if only one parameter is high, a medium-risk signal is output, and if both are in the normal interval, a low-risk signal is output.

[0051] It should be noted that the adjustment amplitude of the current yogurt is calculated: the risk unit analyzes and calculates the adjustment amplitude of the current yogurt under its current structural conditions according to the historical changes in the combination of the set of fermentation characteristics and the set of fermentation evolution factors in historical fermentation samples. This adjustment amplitude helps to identify the differences between the current fermentation state and the historical state, and then judge whether further optimization and adjustment is needed.

[0052] Calculate the structural deviation trend risk signal: the risk unit evaluates the stability of the current yogurt fermentation process by judging whether the rate of change of microbial activity and the rate of change of temperature are higher than the 95% confidence interval corresponding to the sample in the storage module. If these rate changes exceed the normal fluctuation range, it indicates that the fermentation process may be abnormal, thus generating a structural deviation trend risk signal.

[0053] Output risk signal: high-risk signal: when the rate of change of microbial activity and the rate of change of temperature are both in the abnormal interval, a high-risk signal is output, indicating that the fermentation process may have serious problems and immediate measures should be taken to adjust. Medium-risk signal: if only one of the rate of change of microbial activity or the rate of change of temperature is high, a medium-risk signal is output, indicating that attention should be paid and appropriate adjustment should be made. Low-risk signal: if the rate of change of microbial activity and the rate of change of temperature are both within the normal interval, a low-risk signal is output, indicating that the fermentation process is stable and no urgent adjustment is needed.

[0054] Specific implementation steps: based on the set of fermentation characteristics and the set of evolution factors of historical samples, the adjustment amplitude of the current yogurt is calculated. Compare whether the rate of change of microbial activity and the rate of change of temperature are higher than the 95% confidence interval to judge the structural deviation risk. According to the risk judgment, the corresponding risk signal (high risk, medium risk or low risk) is output, which provides the basis for subsequent fermentation adjustment.

[0055] By monitoring the rate of change of microbial activity and temperature, the risk unit can evaluate the stability of the current yogurt fermentation process in real time, and output appropriate risk signals according to the analysis results, helping to adjust the fermentation conditions in time to ensure the efficiency and stability of the yogurt preparation process.

[0056] ReferenceFigure 2 As shown, the embodiment of the present application provides a fermentation management method for yogurt preparation, comprising: S1: in historical fermentation data, obtaining fermentation parameters of several batches of yogurt fermentation; S2: constructing a fermentation feature set according to the fermentation parameters, and constructing a fermentation evolution factor set according to the fermentation feature set; S3: obtaining the fermentation feature set and the fermentation evolution factor at the current yogurt fermentation, and comparing them with the fermentation feature set and the fermentation evolution factor set of the historical fermentation data, calculating the fermentation deviation degree, and matching the fermentation deviation degree with the set classification standard to determine the classification; the classification includes a first class and a second class with gradually increasing fermentation deviation degrees; S4: when the classification is the second class, analyzing the matching relationship between the moving direction of the fermentation feature set of the current yogurt and the moving direction of the fermentation evolution factor; according to the relationship between the moving direction of the fermentation feature set and the moving direction of the fermentation evolution factor, and outputting the optimization suggestion; S5: storing the constructed fermentation feature set, fermentation evolution factor and classification.

[0057] It can be understood that the present application obtains the fermentation parameters of the current yogurt fermentation in real time, such as temperature, pH value, and microbial activity, and compares them with the fermentation characteristic set and evolution factor set in the historical fermentation data to calculate the deviation degree of the current fermentation process. By matching with the set classification standard, the quality deviation of the fermentation process can be judged, so that abnormalities can be discovered and corrected in time. Such a control method avoids the limitations of traditional manual experience and can accurately adjust the fermentation parameters to ensure the stability and consistency of the fermentation process. By calculating the fermentation deviation degree and classifying it into the first category (small deviation, normal) and the second category (larger deviation, needs optimization), when classified as the second category, the change direction of the current yogurt fermentation characteristic set and the fermentation evolution factor set is further analyzed. By analyzing the matching relationship of these change directions, it can accurately identify whether there is a mismatch and give specific optimization suggestions, such as adjusting the temperature, pH value, and microbial activity, to ensure that the fermentation process is carried out under the best conditions. In the fermentation process, when the fermentation process deviates from the normal range and is in the second category, the fermentation optimization module will output specific optimization suggestions to guide the operator to make adjustments. These suggestions are based on the deep analysis of real-time data and historical data, which not only saves the time of manual judgment, but also ensures that each adjustment is more scientific and accurate, thereby improving the production efficiency and product quality of yogurt. The present application continuously accumulates historical fermentation data to build a fermentation characteristic set and a fermentation evolution factor set, providing rich data support. Based on these historical data, more accurate models and prediction mechanisms can be established to achieve continuous optimization. The optimization of each fermentation process not only helps the production of the current batch, but also provides a reference for the production of subsequent batches, enhancing the adaptive ability. Through the matching and analysis of the fermentation characteristic set and the evolution factor, abnormalities in the fermentation process can be identified in time before the fermentation deviation occurs. For example, when the change amplitude of microbial activity is greater than the standard deviation of historical samples, a fermentation stability abnormality prompt will be immediately output, and it is recommended to adjust the fermentation time or optimize the temperature control setting. This early warning mechanism effectively avoids quality fluctuations or failures that may occur in the yogurt production process. Through real-time data analysis and feedback control, fermentation management can ensure that each batch of yogurt reaches the same high-quality standard under the same production conditions, reducing human errors in the production process and improving production efficiency. In addition, it can also adjust the production process in real time to adapt to changes in the environment or raw materials, further improving the flexibility and controllability of production. The present embodiment can automatically calculate and adjust the optimal value of the key fermentation parameters in the optimization of the fermentation process, thereby minimizing resource waste. For example, optimizing microbial activity and pH value can reduce fermentation time, avoid excessive or insufficient fermentation process, and save energy and raw materials, improving the utilization rate of the production line.

[0058] It should be pointed out finally that the above embodiments are only used to illustrate the technical solutions of the present application but not to limit it. Although the present application has been described in detail with reference to the above embodiments, it should be understood by those skilled in the art that the specific embodiments of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application, and any modification or equivalent replacement should be covered in the protection scope of the claims of the present application.

Claims

1. A fermentation management system for yogurt preparation, characterized by, The method comprises the following steps: a collection module configured to obtain fermentation parameters of several batches of yogurt fermentation in historical fermentation data; a factor construction module configured to construct a fermentation feature set according to the fermentation parameters, and construct a fermentation evolution factor set according to the fermentation feature set; a classification module configured to obtain the fermentation feature set and the fermentation evolution factor of the current yogurt fermentation, compare them with the fermentation feature set and the fermentation evolution factor set of the historical fermentation data, calculate the fermentation deviation degree, match the fermentation deviation degree with the set classification standard, and determine the classification; the classification includes a first class and a second class with increasing fermentation deviation degrees; a fermentation optimization module configured to analyze the matching relationship between the moving direction of the fermentation feature set and the moving direction of the fermentation evolution factor when the classification is the second class; according to the relationship between the moving direction of the fermentation feature set and the moving direction of the fermentation evolution factor, and output the optimization suggestion; a storage module configured to store the constructed fermentation feature set, fermentation evolution factor and classification.

2. The fermentation management system for yogurt preparation of claim 1, wherein, Further comprising: an analysis module configured to compare the fermentation feature set and the fermentation evolution factor of the current yogurt with the historical fermentation data, obtain the historical fermentation sample, and output the adjustment amplitude of the current yogurt and the fermentation process deviation risk based on the historical fermentation evolution factor moving direction and classification of the historical fermentation sample.

3. The fermentation management system for yogurt preparation of claim 2, wherein, The fermentation parameters include temperature, pH value, microbial activity and fermentation time; According to the temperature, pH value and microbial activity, the curve data of temperature, pH value and microbial activity changing with time in the fermentation process are established.

4. The fermentation management system for yogurt preparation of claim 3, wherein, The fermentation feature set constructed by the factor construction module includes: temperature difference value between temperature and set fermentation temperature, fitting residual value between pH value and target acidity value, activity difference value between microbial activity and target activity level; correlation analysis value of temperature and pH value; The fermentation evolution factor set constructed by the factor construction module includes: temperature change rate, pH value change rate, time period from the start to the stable stage, and the slope value of the temperature and pH value change curve in the time period in the fermentation stage; growth rate of microbial activity in the initial growth stage and fluctuation amplitude in the microbial stability stage; Wherein, the temperature change rate is the change amount of temperature per unit time, and the pH value change rate is the change amount of pH value per unit time.

5. The fermentation management system for yogurt preparation of claim 4, wherein, The classification module specifically includes: calculate the difference degree of the current yogurt and the historical fermentation data based on the fermentation feature set and the fermentation evolution factor set; generate a fermentation deviation vector based on the similarity calculation result, and each parameter value in the deviation vector is obtained by normalization weighting to obtain the fermentation deviation degree.

6. The fermentation management system for yogurt preparation of claim 5, wherein, Match the fermentation deviation degree with the set classification standard threshold, and assign the first class or the second class respectively.

7. The fermentation management system for yogurt preparation of claim 6, wherein, When the fermentation optimization module receives the second class, the following operations are performed: obtain the moving direction of temperature, pH value and microbial activity in the fermentation feature set in the current yogurt; At the same time, extract the moving direction of temperature change rate, pH value change rate, growth rate of microbial activity and fluctuation amplitude in the fermentation evolution factor set; If the moving direction of the temperature, pH value and microbial activity in the fermentation characteristic set is the same as the moving direction of any parameter in the fermentation evolution factor set, it is determined that the fermentation adjustment is consistent with the performance response, and fine adjustment of the temperature and pH value is performed at this time; If the moving direction of any parameter in the fermentation characteristic set is opposite to the direction of two or more parameters in the fermentation evolution factor set, it is determined that the matching of the ratio disturbance is not matched, the microbial activity is re-evaluated, and the temperature adjustment is temporarily suspended; If the moving amplitude of the microbial activity is greater than 1.5 times the average of the moving amplitude of the microbial activity in the historical fermentation characteristic set, an abnormal fermentation stability prompt is output, and the fermentation time is adjusted or the temperature control setting is optimized.

8. The fermentation management system for yogurt preparation of claim 7, wherein, The analysis module performs the following operations based on the matching results of the fermentation characteristic set and the fermentation evolution factor set in the storage module: Select the first five groups of historical samples with the smallest Euclidean distance from the current yogurt fermentation characteristic set as the historical fermentation samples; Extract the corresponding fermentation evolution factor set in the historical fermentation sample, including the temperature change rate, the pH value change rate and the microbial activity growth rate; According to the moving direction of the fermentation evolution factor set and the corresponding ratio parameter adjustment record, a response path trajectory is constructed; Based on the change trend of the fermentation evolution factor set of the current yogurt under different ratio parameter adjustment conditions, a structure response prediction sequence is formed, and the prediction result is output to the fermentation optimization module.

9. The fermentation management system for yogurt preparation of claim 8, wherein, The analysis module further includes a risk unit, which is configured to: According to the combination change history of the fermentation characteristic set and the fermentation evolution factor set in the historical fermentation sample, the adjustment amplitude of the current yogurt under the current structure condition is calculated; According to whether the microbial activity change rate and the temperature change rate are higher than the corresponding 95% confidence interval of the sample in the storage module, a structure deviation trend risk signal is calculated; When the microbial activity change rate and the temperature change rate are both in the abnormal interval, a high risk signal is output, if only one parameter is high, a medium risk signal is output, and if both are in the normal interval, a low risk signal is output.

10. A fermentation management method for yogurt preparation, applied in the fermentation management system for yogurt preparation according to any one of claims 1-9, characterized in that, The method comprises: S1: In the historical fermentation data, the fermentation parameters of several batches of yogurt fermentation are obtained; S2: The fermentation characteristic set is constructed according to the fermentation parameters, and the fermentation evolution factor set is constructed according to the fermentation characteristic set; S3: The fermentation characteristic set and the fermentation evolution factor of the current yogurt fermentation are obtained, and are compared with the fermentation characteristic set and the fermentation evolution factor set of the historical fermentation data, the fermentation deviation degree is calculated, the fermentation deviation degree is matched with the set classification standard, and the classification is determined; The classification includes the first class and the second class with increasing fermentation deviation degree; S4: When the classification is the second class, the matching relationship between the moving direction of the fermentation characteristic set of the current yogurt and the moving direction of the fermentation evolution factor is analyzed; According to the relationship between the moving direction of the fermentation characteristic set and the moving direction of the fermentation evolution factor, an optimization suggestion is output; S5: The constructed fermentation characteristic set, fermentation evolution factor and classification are stored.

Images