Intelligent wine brewing equipment and control method

Abstract

This application provides an intelligent brewing equipment and control method. It extracts key technological features characterizing the dynamic evolution of the brewing process from operational status data related to fermentation during the brewing process. Based on the time-varying trends of these key technological features, it generates a brewing state evolution trajectory and identifies the state deviation between the current brewing stage and the target process stage. The operational status data is uniformly mapped at the technological scale to determine the degree of synergy between the current brewing process execution state and the target brewing process. The influence of the current brewing process control on the stability of brewing quality is determined based on the state deviation and the degree of synergy. Based on the influence, a set of control parameters for the brewing process is adaptively generated, thereby enabling coordinated control of the actuators in the current brewing process. Using the scheme of this application, staged intelligent control of the brewing process can be achieved based on the coordinated control between the actuators in the brewing process.

Description

Technical Field

[0001] This application relates to the field of intelligent control technology, and more specifically, to an intelligent brewing equipment and control method. Background Technology

[0002] Brewing process control is a complex process of controlling fermentation. It usually involves the coordinated adjustment of various operating parameters such as temperature, time, material state, and environmental conditions. Its goal is to ensure the stable progress of the brewing process and ultimately obtain a wine product of consistent quality.

[0003] In existing technologies, the control methods for brewing processes mostly adopt control strategies based on empirical rules or fixed process curves. That is, according to the preset fermentation stage division, the process parameters of the corresponding stages are manually set or simply adjusted in a closed loop. In practical applications, this type of control method usually only focuses on the instantaneous changes of a single or a few key parameters, lacking a systematic characterization of the overall dynamic evolution characteristics of the brewing process. It is difficult to reflect the continuous changes in the fermentation process over time, resulting in control decisions relying more on human experience or static threshold judgments. This makes it difficult to adapt to the nonlinear and uncertain characteristics of the brewing process under conditions such as raw material differences, environmental fluctuations, and changes in equipment operating status. At the same time, existing technologies usually use single parameters or fixed thresholds to control brewing equipment, which is difficult to adapt to the stage-by-stage changes in the fermentation process. Therefore, how to achieve stage-by-stage intelligent control of the brewing process based on the linkage control between the actuators in the brewing process has become a challenge for the industry. Summary of the Invention

[0004] This application provides an intelligent brewing equipment and control method, which can realize the staged intelligent control of the brewing process based on the linkage control between the actuators in the brewing process.

[0005] In a first aspect, this application provides an adaptive control method for a brewing process, applied to intelligent brewing equipment, the method comprising the following steps: Acquire operational status data related to the fermentation state during the brewing process; Key process features characterizing the dynamic evolution of the brewing process are extracted from the operational status data. Based on the time variation trend of the key process features, a brewing state evolution trajectory is generated, and the state deviation between the current brewing stage and the target process stage is identified based on the brewing state evolution trajectory. The operational status data is mapped to a unified process scale to determine the degree of compatibility between the current brewing process execution status and the target brewing process. The impact of the current brewing process control on the stability of brewing quality is determined based on the state deviation and the degree of cooperative fit. Based on the aforementioned influence degree, an adaptive set of control parameters for the brewing process is generated, thereby enabling coordinated control of the actuators in the current brewing process.

[0006] In conjunction with the first aspect, in one possible implementation, extracting key process features characterizing the dynamic evolution of the brewing process from the operational status data specifically includes: The operational status data is preprocessed according to time series to obtain standardized multi-parameter time series data; From the standardized multi-parameter time-series data, several initial process characteristics reflecting fermentation kinetics are determined; Key process features characterizing the dynamic evolution of the brewing process were selected based on all initial process features.

[0007] In conjunction with the first aspect, in one possible implementation, generating the brewing state evolution trajectory based on the time-varying trend of the key process characteristics specifically includes: The key process features are acquired within a continuous time window to form a multidimensional feature time series. The multidimensional feature time series is subjected to dimensionality reduction processing to obtain the low-dimensional state vector corresponding to each time step; Connect all low-dimensional state vectors in chronological order to generate the state evolution trajectory of brewing.

[0008] In conjunction with the first aspect, in one possible implementation, identifying the state deviation between the current brewing stage and the target process stage based on the brewing state evolution trajectory specifically includes: Obtain the reference state trajectory of the target process stage in the state space corresponding to the current brewing stage; Align and compare the brewing state evolution trajectory with the reference state trajectory; The deviation between the current brewing stage and the target process stage is determined based on the comparison results.

[0009] In conjunction with the first aspect, in one possible implementation, performing a unified process-scale mapping on the operational status data to determine the degree of compatibility between the current brewing process execution status and the target brewing process specifically includes: The operational status data is mapped onto a unified process evaluation scale to obtain a set of dimensionless process execution indicators. From the target brewing process specifications, the range of target process parameters corresponding to the process execution indicators is extracted; Based on the process execution indicators and the target process parameter range, the degree of synergy and compatibility between the current brewing process execution status and the target brewing process is determined.

[0010] In conjunction with the first aspect, in one possible implementation, determining the degree of influence of the current brewing process control on the stability of brewing quality based on the state deviation and the degree of cooperative fit specifically includes: The state deviation is converted into a risk assessment value that characterizes the risk of process operation deviation. The cooperative fit is converted into a fit evaluation value that characterizes the deviation of process parameter execution. The risk assessment value and the adaptation assessment value are fused to obtain the degree of influence of the current brewing process control on the stability of brewing quality.

[0011] In conjunction with the first aspect, in one possible implementation, the adaptive generation of a set of control parameters for the brewing process based on the aforementioned influence level, and the subsequent coordinated control of the actuators in the current brewing process, specifically includes: The overall intensity level of regulatory intervention is determined based on the aforementioned degree of influence. Based on the overall control intensity level and the current brewing stage, a set of control parameters containing specific set values ​​is generated; Based on the set of control parameters, coordinated control commands are sent to each actuator in the current brewing process to complete the linkage control.

[0012] Secondly, this application provides an intelligent brewing equipment, including an adaptive control unit, the adaptive control unit comprising: The acquisition module is used to acquire operational status data related to the fermentation state during the brewing process; The processing module is used to extract key process features that characterize the dynamic evolution of the brewing process from the operating status data, generate the state evolution trajectory of the brewing process based on the time change trend of the key process features, and identify the state deviation between the current brewing stage and the target process stage based on the state evolution trajectory of the brewing process. The processing module is also used to perform a unified process scale mapping on the operating status data, thereby determining the degree of coordination and compatibility between the current brewing process execution status and the target brewing process. The processing module is also used to determine the degree of influence of the current brewing process control on the stability of brewing quality based on the state deviation and the degree of cooperative fit. The execution module is used to adaptively generate a set of control parameters for the brewing process based on the influence degree, and then perform linkage control on the execution mechanism of the current brewing process.

[0013] Thirdly, this application provides a computer device, the computer device including a memory and a processor, the memory for storing a computer program, and the processor for calling and running the computer program from the memory, so that the computer device executes the above-described adaptive control method for the brewing process.

[0014] Fourthly, this application provides a computer-readable storage medium storing instructions or code that, when executed on a computer, cause the computer to implement the aforementioned adaptive control method for the brewing process.

[0015] The technical solution provided in this application has the following beneficial effects: This application's solution, firstly, identifies the state deviation between the current brewing stage and the target process stage based on the brewing state evolution trajectory. This clearly depicts the stage evolution relationship of the brewing process in the time dimension, enabling the linkage control of the actuators to respond based on the actual stage position, rather than fixed time or single parameter thresholds. This achieves stage-based identification and precise entry into the brewing process, providing a prerequisite for intelligent stage control. Secondly, it performs a unified process-scale mapping on the operating state data, thereby determining the synergy and adaptability between the current brewing process execution state and the target brewing process. This transforms multi-source data into the same process evaluation space, allowing each process parameter to be analyzed collaboratively at the same level. This avoids the problem of single parameter compliance leading to overall process imbalance, enabling linkage control to be adjusted based on parameter group synergy. This supports the collaborative actions of multiple actuators at different brewing stages, realizing the transformation of stage-based control from single-point adjustment to overall linkage. Then, based on the state deviation and the synergy and adaptability, it determines the current... The impact of brewing process control on brewing quality stability can distinguish the actual risk level of deviations at different stages, avoiding over-regulation in low-risk stages or insufficient regulation in high-risk stages. This allows for dynamic adjustment of control intervention levels based on differences in quality sensitivity at different brewing stages, giving the coordinated control of actuators stage-specific differences and target orientation, thereby improving the rationality and stability of staged intelligent control. Finally, based on the aforementioned impact level, an adaptive set of control parameters for the brewing process is generated, enabling coordinated control of the actuators in the current brewing process. This allows for dynamic adjustment of the control amplitude, response sequence, and linkage relationship of each actuator at different brewing stages, avoiding the problem of isolated parameter adjustments in traditional control. This process forms a closed-loop linkage between stage identification, quality impact assessment, and actuator control, enabling the brewing process to automatically switch control strategies according to stage changes, thus achieving staged intelligent control. In summary, this scheme can achieve staged intelligent control of the brewing process based on the coordinated control between actuators. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is an exemplary flowchart of an adaptive control method for a brewing process according to some embodiments of this application; Figure 2 This is an exemplary flowchart illustrating the determination of state deviation according to some embodiments of this application; Figure 3 This is an exemplary flowchart illustrating the determination of cooperative adaptation degree according to some embodiments of this application; Figure 4 This is a schematic diagram of the structure of an adaptive control unit according to some embodiments of this application; Figure 5 This is a schematic diagram of the structure of a computer device for implementing an adaptive control method for a brewing process, according to some embodiments of this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] refer to Figure 1 The figure is an exemplary flowchart of an adaptive control method for a brewing process according to some embodiments of this application. The adaptive control method for the brewing process mainly includes the following steps: In step 101, operational status data related to the fermentation state during the brewing process are obtained.

[0020] In practice, acquiring operational status data related to the fermentation state during the brewing process can be achieved in the following ways: A multi-source sensor array deployed within the fermentation vessel can synchronously and in real-time collect key parameters directly characterizing the core physicochemical state of fermentation. These parameters include at least fermentation temperature, tank pressure, dissolved oxygen concentration, and raw material conversion rate. For example, wall-mounted or insertion-type temperature sensors can be used to measure the fermentation temperature at different depths of the fermentation mash; a pressure transmitter installed on the tank top can be used to monitor the tank pressure; an immersion-type dissolved oxygen probe can be used to detect the dissolved oxygen concentration; and an online refractometer or near-infrared spectrometer can be used to continuously measure the sugar content or specific parameters in the mash. The product concentration is calculated, and the raw material conversion rate is calculated based on its rate of change over time. All sensors synchronously collect data with a uniform sampling period. The raw electrical signals are standardized by the transmitter and converted from analog to digital before being transmitted to the control station via fieldbus. The data acquisition software in the control station performs time-stamp alignment, removes gross errors, and packages the collected key parameter data streams to form timestamped structured state data, i.e., operational state data related to the fermentation state during the brewing process. This data constitutes a complete initial operating condition description for the current fermentation moment. Other methods can also be used to acquire this data in other embodiments, which are not specifically limited here.

[0021] It should be noted that the operational status data in this application refers to the basic dataset characterizing the internal physicochemical state and processes of brewing fermentation equipment.

[0022] In step 102, key process features characterizing the dynamic evolution of the brewing process are extracted from the operating status data. A brewing state evolution trajectory is generated based on the time change trend of the key process features. The state deviation between the current brewing stage and the target process stage is identified based on the brewing state evolution trajectory.

[0023] In some embodiments, extracting key process features characterizing the dynamic evolution of the brewing process from the operational status data can be achieved through the following steps: The operational status data is preprocessed according to time series to obtain standardized multi-parameter time series data; From the standardized multi-parameter time-series data, several initial process characteristics reflecting fermentation kinetics are determined; Key process features characterizing the dynamic evolution of the brewing process were selected based on all initial process features.

[0024] In specific implementation, the time-series preprocessing of the operational status data to obtain standardized multi-parameter time-series data can be achieved in the following way: First, the operational status data, including fermentation temperature, tank pressure, dissolved oxygen concentration, and raw material conversion rate, is subjected to missing value imputation and outlier removal. Specifically, linear interpolation of adjacent time point data can be used to handle missing values, and the Laida criterion based on a sliding window is used to identify and remove outliers that significantly deviate from the normal fluctuation range. Then, the processed data sequence is smoothed and filtered to suppress random noise, which can be achieved using a first-order moving average filter with a window length of 5 sampling points. Next, data from different sensors with a unified timestamp but different dimensions are normalized. The Z-score normalization method can be used to transform the data sequence of each parameter into a standard normal distribution with a mean of 0 and a standard deviation of 1. Finally, the data of the key parameters processed above are aligned and reorganized according to time points to form a structured data table in which each row corresponds to a sampling time and each column corresponds to a standardized parameter value. This data table serves as the standardized multi-parameter time-series data.

[0025] In specific implementation, determining multiple initial process features reflecting fermentation kinetics from the standardized multi-parameter time-series data can be achieved in the following way: Based on the standardized multi-parameter time-series data, a set of indicators reflecting the intensity of microbial metabolic activity and environmental interaction can be directly extracted or derived through time-domain calculations. For example: calculating the average rate of change of fermentation temperature over a sliding time window, such as the past hour, as a temperature trend feature; calculating the cumulative increase in tank pressure over the same time period as a gas production intensity feature; calculating the instantaneous decrease slope of dissolved oxygen concentration over time as an oxygen consumption rate feature; calculating the second difference of feed conversion rate, i.e., acceleration, as a metabolic acceleration feature; and simultaneously calculating the moving correlation coefficient between temperature and dissolved oxygen concentration as an environmental coupling feature. The five features obtained above through difference, numerical integration, linear fitting, and statistical correlation analysis are used together as multiple initial process features reflecting the current fermentation kinetics.

[0026] In specific implementation, the key process features characterizing the dynamic evolution of the brewing process can be selected based on all initial process features in the following way: multiple initial process features, namely temperature trend, gas production intensity, oxygen consumption rate, metabolic acceleration, and environmental coupling features, can be input into a predefined process knowledge filter. This filter embeds rules based on the principles of brewing technology. For example, in the primary fermentation stage, the rules assign higher weights to gas production intensity and metabolic acceleration features because they are direct indicators reflecting sugar conversion and yeast activity. In the secondary fermentation stage, the rules assign higher weights to temperature trend and environmental coupling features to monitor fermentation stability and environmental stability. Based on the currently identified brewing stage, which can be initially determined by fermentation time or cumulative conversion rate, the filter applies the corresponding weight rules to perform weighted scoring on all initial process features and selects the top N features with the highest scores, such as three features, as key process features characterizing the dynamic evolution of the brewing process. Other methods can also be used to determine these features in other embodiments, which are not limited here.

[0027] It should be noted that the multi-parameter time series data in this application refers to time series data with a unified statistical scale and regular structure; the initial process features in this application refer to intermediate indicators that preliminarily quantify and characterize the microbial metabolic activity and physicochemical changes of fermentation equipment from different dimensions; and the key process features in this application refer to the most representative and information-rich subset of features, which is used to highly condense the core dynamic essence of the current brewing stage.

[0028] In some embodiments, generating the brewing state evolution trajectory based on the time variation trend of the key process features can be achieved by the following steps: The key process features are acquired within a continuous time window to form a multidimensional feature time series. The multidimensional feature time series is subjected to dimensionality reduction processing to obtain the low-dimensional state vector corresponding to each time step; Connect all low-dimensional state vectors in chronological order to generate the state evolution trajectory of brewing.

[0029] In specific implementation, the acquisition of time-series data of the key process features within a continuous time window to form a multidimensional feature time series can be achieved in the following way: the key process features corresponding to each sampling moment in the most recent complete process cycle or a preset duration, such as the past 24 hours, can be read from the process history database in chronological order. These key process features include the values ​​of N features such as temperature trend, gas production intensity, and oxygen consumption rate. These values ​​are then organized according to the sampling moment to form a two-dimensional data matrix, where each row represents a sampling time point and each column represents the value of a key process feature at that time point. This matrix constitutes a multidimensional feature time series used to describe the co-evolution law of key process features over time.

[0030] In specific implementation, the dimensionality reduction of the multidimensional feature time series to obtain the low-dimensional state vector corresponding to each time step can be achieved in the following way: Principal component analysis can be used to process the matrix corresponding to the multidimensional feature time series. Specifically, firstly, the covariance matrix of all key process features in the matrix can be calculated, and then the eigenvalues ​​and eigenvectors of the covariance matrix can be solved. Next, the eigenvectors corresponding to the two or three largest eigenvalues ​​are selected as the principal component directions to retain the main variance of the original data. Finally, each row in the original multidimensional feature time series, i.e., the multidimensional feature value at each time step, is projected onto the selected principal component direction, thereby converting the high-dimensional feature data at each sampling time step into a low-dimensional state vector containing only two or three components. This vector serves as a concise mathematical table of the brewing process state at that time step, thus obtaining the low-dimensional state vector corresponding to each time step.

[0031] In specific implementation, the state evolution trajectory of brewing can be generated by connecting all low-dimensional state vectors in chronological order as follows: the low-dimensional state vectors calculated at each sampling moment can be arranged in chronological order according to their corresponding timestamps; in the low-dimensional state space, such as a two-dimensional plane with the first principal component as the horizontal axis and the second principal component as the vertical axis, each state vector is represented as a point, and these points are connected sequentially with line segments in chronological order; the path formed by this series of points and line segments connected in chronological order constitutes the state evolution trajectory that intuitively shows the continuous migration and change of the brewing process state in the feature space over time; this trajectory can be stored as an ordered list of state vectors or a trajectory matrix to identify the state deviation; other methods can also be used in other embodiments, which are not limited here.

[0032] It should be noted that the multidimensional feature time series in this application refers to a two-dimensional data table formed by synchronously aligning and structuring the values ​​of multiple key process features that change over time, used to simultaneously record and present the complete history of the coordinated evolution of multiple core state indicators over time; the low-dimensional state vector in this application refers to a low-dimensional mathematical representation obtained by condensing the multidimensional feature information at a certain moment, used to characterize the comprehensive state of the brewing process at the corresponding moment; the state evolution trajectory in this application refers to integrating discrete moment state points into a continuous, visualized overall process image, which is used to intuitively and quantitatively display the complete migration path and development trend of the brewing process state in the feature space.

[0033] In some embodiments, reference Figure 2 As shown, this figure is an exemplary flowchart for determining the state deviation amount in some embodiments of this application. Identifying the state deviation amount between the current brewing stage and the target process stage based on the brewing state evolution trajectory can be achieved using the following steps: Obtain the reference state trajectory of the target process stage in the state space corresponding to the current brewing stage; Align and compare the brewing state evolution trajectory with the reference state trajectory; The deviation between the current brewing stage and the target process stage is determined based on the comparison results.

[0034] In specific implementation, obtaining the reference state trajectory in the state space corresponding to the current brewing stage can be achieved in the following way: First, based on the current brewing stage, such as the middle of primary fermentation, a standard process template bound to the name of the stage is retrieved from a preset process knowledge base; the template stores a standard state vector sequence generated by cluster analysis or time-series averaging in the same low-dimensional state space, such as principal component space, based on a large amount of historical successful batch data, and this sequence constitutes the reference state trajectory; specifically, the trajectory exists in the same data structure as the real-time state evolution trajectory, such as an ordered list of state vectors, where each state vector represents the standard state coordinates that the process should reach at the corresponding moment of the ideal process stage.

[0035] In specific implementation, aligning and comparing the brewing state evolution trajectory with the reference state trajectory can be achieved in the following way: a dynamic time warping algorithm can be used to handle the nonlinear scaling problem of the two trajectories on the time axis. For example, the real-time acquired brewing state evolution trajectory, i.e., the current segment, and the retrieved reference state trajectory can be used as inputs to calculate the Euclidean distance between any two state vectors on the two trajectories and construct a distance matrix. Then, a path with the minimum cumulative distance from the starting point to the ending point is found in this matrix. This path is the optimal alignment path, which determines which state vector on the reference trajectory best matches each state vector on the real-time trajectory. After alignment, a set of one-to-one corresponding state vector pairs can be obtained based on this optimal path for subsequent difference calculation.

[0036] In specific implementation, the state deviation between the current brewing stage and the target process stage can be determined based on the comparison results in the following way: Based on the optimal alignment path obtained from the comparison results, the Euclidean distance between each pair of matching state vectors can be calculated to obtain a distance sequence; then, statistical features are extracted from this distance sequence, such as calculating its average value as the overall average deviation and its maximum value as the maximum instantaneous deviation; finally, these two statistical values, namely the average deviation and the maximum deviation, are combined into a two-dimensional vector, which serves as the state deviation that quantifies the overall and local differences between the real-time process and the target process, i.e., the state deviation between the current brewing stage and the target process stage; other methods can also be used to determine this in other embodiments, which are not limited here.

[0037] It should be noted that the reference state trajectory in this application refers to a predefined standard state change path that should be followed in the brewing stage under ideal process conditions; the comparison result in this application refers to the direct point-to-point mapping relationship between the actual brewing process and the ideal process in the state space; and the state deviation in this application refers to the degree and nature of the deviation of the real-time brewing process state from its ideal process reference.

[0038] In step 103, the operating status data is mapped to a unified process scale to determine the degree of compatibility between the current brewing process execution status and the target brewing process.

[0039] In some embodiments, reference Figure 3 As shown, this figure is an exemplary flowchart for determining the degree of collaborative adaptation in some embodiments of this application. In this embodiment, the process scale is uniformly mapped to the running status data, and the degree of collaborative adaptation between the current brewing process execution status and the target brewing process can be determined by the following steps: First, in step 1031, the operating status data is mapped to a unified process evaluation scale to obtain a set of dimensionless process execution indicators. Secondly, in step 1032, the target process parameter range corresponding to the process execution index is extracted from the target brewing process specification; Finally, in step 1033, based on the process execution indicators and the target process parameter range, the degree of synergistic adaptation between the current brewing process execution status and the target brewing process is determined.

[0040] In practice, mapping the operational status data to a unified process evaluation scale to obtain a set of dimensionless process performance indicators can be achieved in the following way: For each key parameter in the operational status data, namely fermentation temperature, tank pressure, dissolved oxygen concentration, and raw material conversion rate, a predefined scoring function is called to convert its physical measurement value with specific dimensions and values ​​into a unified, dimensionless evaluation score; for example, for fermentation temperature, the scoring function can be defined as: within the allowable temperature range of the current brewing stage, such as primary fermentation, mapping the actual temperature value to a score between 0 and 100. The closer the temperature is to the optimal process temperature, the higher the score; if it exceeds the allowable range, the score is 0. Similarly, scoring functions based on process knowledge, such as the pressure safety range, optimal dissolved oxygen window, and expected conversion rate curve, are defined for tank pressure, dissolved oxygen concentration, and raw material conversion rate. By executing these four scoring functions in parallel, the four operating status parameters are converted into four dimensionless process execution indicators with values ​​ranging from 0 to 100. This quantifies the quality of process execution for each individual parameter in the operating status data on a unified percentage scale. Other methods can also be used in other embodiments, which are not limited here.

[0041] In practice, the extraction of the target process parameter range corresponding to the process execution indicators from the target brewing process specification can be achieved in the following way: Based on a process knowledge base pre-set from historical data or expert experience, a target brewing process specification entry that perfectly matches the current brewing stage can be retrieved. This entry clearly defines the target process parameter range necessary for calculating the four scoring functions of the process execution indicators, including: the lower and upper limits of each parameter (temperature, pressure, dissolved oxygen, conversion rate), the optimal value or optimal range of the process, and the type of scoring function, such as linear scoring or trapezoidal membership scoring. These values ​​and rules stored in this entry are extracted as direct parameter bases for calculating the scoring functions of the process execution indicators and as a benchmark for suitability assessment.

[0042] In specific implementation, the degree of synergy between the current brewing process execution state and the target brewing process can be determined based on the process execution indicators and the target process parameter range. This can be achieved in the following way: First, the calculated process execution indicators, namely temperature score, pressure score, dissolved oxygen score, and conversion rate score, are weighted and integrated. The weight allocation can be based on the importance coefficient of each parameter defined in the target process specification at the current stage. For example, in the main fermentation stage, the raw material conversion rate and temperature have higher weights, while pressure has a lower weight. Then, the weighted average of all process execution indicators is calculated to obtain a comprehensive score between 0 and 100. Finally, this comprehensive score is used as the quantified degree of synergy between the current brewing process execution state and the target brewing process. The closer the value is to 100, the higher the degree of synergy between the current process execution state and the target brewing process; the closer it is to 0, the worse the synergy. Other methods can also be used in other embodiments, which are not limited here.

[0043] It should be noted that the process execution indicators in this application refer to the degree of performance of each individual parameter in the quantified operational status data relative to the process requirements on the same benchmark; the target process parameter range in this application refers to the set of values ​​and rules extracted from the target brewing process specification to define the allowable fluctuation range and ideal value of each parameter, which is used to provide a conversion benchmark and evaluation scale for mapping operational status data to process execution indicators; the synergistic fit degree in this application refers to a comprehensive quantitative evaluation value that reflects the overall matching and compliance degree between the current multi-parameter synergistic execution status of the brewing process and the target brewing process requirements.

[0044] In step 104, the influence of the current brewing process control on the stability of brewing quality is determined based on the state deviation and the degree of cooperative fit.

[0045] In some embodiments, determining the impact of the current brewing process control on the stability of brewing quality based on the state deviation and the degree of cooperative fit can be achieved through the following steps: The state deviation is converted into a risk assessment value that characterizes the risk of process operation deviation. The cooperative fit is converted into a fit evaluation value that characterizes the deviation of process parameter execution. The risk assessment value and the adaptation assessment value are fused to obtain the degree of influence of the current brewing process control on the stability of brewing quality.

[0046] In specific implementation, the conversion of the state deviation into a risk assessment value characterizing the risk of process deviation can be achieved in the following way: the state deviation, including a two-dimensional vector of average deviation and maximum deviation, can be input into a preset risk mapping function; this risk mapping function can comprehensively evaluate the two deviation components based on the risk tolerance thresholds for each stage defined in the process knowledge base; for example, the function can be designed as follows: first, the average deviation and maximum deviation are compared with the corresponding stage thresholds respectively. If either value exceeds its warning threshold, a high-risk level is triggered; if both are between the attention threshold and the warning threshold, it is a medium-risk level; if both are below the attention threshold, it is a low-risk level; then, according to the determined risk level, i.e., high, medium, and low, it is mapped to a specific numerical risk assessment value, for example: high risk is mapped to 80-100, medium risk to 40-79, and low risk to 0-39. The higher the value, the greater the potential risk that the current state deviation poses to the stability of brewing quality.

[0047] In specific implementation, the conversion of the collaborative fit degree into a fit evaluation value characterizing the deviation of process parameter execution can be achieved in the following way: The collaborative fit degree, i.e., the comprehensive score between 0 and 100, can be input into a linear converter; the converter performs a subtraction operation, subtracting the current value of the collaborative fit degree from the constant 100, and using the difference as the fit evaluation value characterizing the deviation of process parameter execution; through this operation, the collaborative fit degree, which originally indicated that the larger the value, the better, is converted into a fit evaluation value that is also between 0 and 100, but the larger the value, the greater the deviation of process parameter execution. That is, the more serious the deviation of the current multi-parameter collaborative execution state from the target process requirements, the greater its negative impact on quality stability, thus semantically consistent with the risk assessment value.

[0048] In specific implementation, the risk assessment value and the adaptation assessment value are fused to obtain the influence of the current brewing process control on the stability of brewing quality. This can be achieved in the following way: a fusion calculation module can be called, which reads two preset weight coefficients for the current brewing stage from the process knowledge base: risk weight and adaptation weight, the sum of which is 1. The module can use a weighted geometric average algorithm for fusion. For example, firstly, the result of the power operation with the risk assessment value as the base and the risk weight as the exponent, and the result of the power operation with the adaptation assessment value as the base and the adaptation weight as the exponent are calculated respectively. Then, the two power operation results are multiplied together, and the product is used as the influence of the current brewing process control on the stability of brewing quality. This influence is a dimensionless scalar with a value between 0 and 100. The higher the value, the greater the threat of the overall state of the current brewing process to the stability of the final brewing quality, that is, the greater the overall negative impact, and the more immediate or strong regulatory intervention is needed for strong correction. Other methods can also be used in other embodiments, which are not limited here.

[0049] It should be noted that the risk assessment value in this application refers to a scalar value used to quantify the potential threat posed by deviations to the stable operation of the brewing process, which can reflect the level of deviation risk; the adaptation assessment value in this application refers to a scalar value used to quantify the overall degree of deviation between the current static execution of multiple parameters and the process requirements, which can reflect the magnitude of the execution deviation; and the impact degree in this application refers to a scalar index used to comprehensively characterize the overall impact of the current control status of the entire brewing process on the stability of the final brewed product quality.

[0050] In step 105, a set of control parameters for the brewing process is adaptively generated based on the influence degree, and then the actuators of the current brewing process are linked for control.

[0051] In some embodiments, the following steps can be used to adaptively generate a set of control parameters for the brewing process based on the influence degree, and then to perform coordinated control of the actuators in the current brewing process: The overall intensity level of regulatory intervention is determined based on the aforementioned degree of influence. Based on the overall control intensity level and the current brewing stage, a set of control parameters containing specific set values ​​is generated; Based on the set of control parameters, coordinated control commands are sent to each actuator in the current brewing process to complete the linkage control.

[0052] In specific implementation, the overall control intensity level of intervention based on the influence degree can be determined in the following way: The influence degree, i.e., a scalar between 0 and 100, can be input into a level classifier. The classifier has three preset intensity level thresholds. For example, when the influence degree is below 30, it is classified as a mild control level; when the influence degree is between 30 and 70, it is classified as a moderate control level; and when the influence degree is above 70, it is classified as a strong control level. The classifier compares the current influence degree value with the fixed threshold and directly outputs the corresponding mild, moderate, or strong overall control intensity level according to its range. This level determines the overall magnitude and urgency of subsequent control actions.

[0053] In specific implementation, the generation of a set of control parameters containing specific set values ​​based on matching the overall control intensity level with the current brewing stage can be achieved in the following way: using the overall control intensity level and the current brewing stage as a composite query key, a preset control strategy library is queried; each record in this control strategy library clearly defines the specific set values ​​to be issued to each actuator at a predetermined stage and for a predetermined control level, such as: the opening percentage of the cooling valve, the speed of the stirring motor, the instantaneous flow rate of the feed pump, etc.; after retrieving a matching record, all set values ​​in the record are extracted and encapsulated into a structured data set, which is the control parameter set that needs to be issued now; this control parameter set enables the abstract control intensity level to be instantiated into a series of executable equipment control commands.

[0054] In specific implementation, based on the set of control parameters, coordinated control commands are sent to each actuator in the current brewing process to complete the linkage control. This can be achieved in the following way: the control command distribution center parses each set value in the set of control parameters and converts it into a standard industrial control signal that can be recognized by the corresponding actuator, such as a proportional regulating valve, a variable frequency motor, or a metering pump, such as a 4-20mA analog signal or a Modbus TCP command; then, through the industrial control network, these control commands are sent synchronously or in a preset sequence to the temperature control unit, stirring drive unit, and material addition unit of the fermentation tank; after receiving the commands, each unit adjusts its physical output in real time, thereby achieving coordinated and linked adjustment of fermentation temperature, stirring intensity, and material replenishment rate, and finally completing the adaptive control closed loop of the current brewing process; other methods can also be used in other embodiments, which are not limited here.

[0055] Furthermore, in another aspect of this application, in some embodiments, this application provides an intelligent brewing equipment, which includes an adaptive control unit, with reference to... Figure 4The figure is a schematic diagram of the structure of an adaptive control unit according to some embodiments of this application. The adaptive control unit 400 includes: an acquisition module 401, a processing module 402, and an execution module 403, which are described below: The acquisition module 401 in this application is mainly used to acquire operating status data related to the fermentation state during the brewing process; Processing module 402 in this application is mainly used to extract key process features that characterize the dynamic evolution of the brewing process from the running status data, generate the state evolution trajectory of brewing based on the time change trend of the key process features, and identify the state deviation between the current brewing stage and the target process stage based on the state evolution trajectory of brewing. The processing module 402 described in this application is also used to perform a unified process scale mapping on the operating status data, thereby determining the degree of coordination and adaptation between the current brewing process execution status and the target brewing process. The processing module 402 described in this application is also used to determine the degree of influence of the current brewing process control on the stability of brewing quality based on the state deviation and the degree of cooperative fit. The execution module 403 in this application is mainly used to adaptively generate a set of control parameters for the brewing process based on the influence degree, and then to perform linkage control on the execution mechanism of the current brewing process.

[0056] The foregoing has detailed examples of intelligent brewing equipment and control methods provided in the embodiments of this application. It is understood that, in order to achieve the aforementioned functions, the corresponding apparatus includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0057] In some embodiments, this application also provides a computer device, the computer device including a memory and a processor, the memory for storing a computer program, and the processor for calling and running the computer program from the memory, causing the computer device to execute the above-described adaptive control method for the brewing process.

[0058] In some embodiments, reference Figure 5The dashed lines in the figure indicate that the unit or module is optional. This figure is a schematic diagram of the structure of a computer device implementing the adaptive control method for the brewing process of this application. The adaptive control method for the brewing process in the above embodiments can be achieved through… Figure 5 The computer device 500 shown is used to implement this, and the computer device 500 includes at least one processor 501, a memory 502 and at least one communication unit 505. The computer device 500 may be a terminal device, a server or a chip.

[0059] The processor 501 can be a general-purpose processor or a special-purpose processor. For example, the processor 501 can be a central processing unit (CPU). The CPU can be used to control the computer device 500, execute software programs, and process data from the software programs. The computer device 500 may also include a communication unit 505 for inputting (receiving) and outputting (transmitting) signals.

[0060] For example, computer device 500 may be a chip, communication unit 505 may be the input and / or output circuit of the chip, or communication unit 505 may be the communication interface of the chip, and the chip may be a component of terminal device, network device or other device.

[0061] For example, computer device 500 may be a terminal device or a server, and communication unit 505 may be a transceiver of the terminal device or the server, or communication unit 505 may be a transceiver circuit of the terminal device or the server.

[0062] The computer device 500 may include one or more memories 502 storing a program 504. The program 504 can be executed by a processor 501 to generate instructions 503, causing the processor 501 to perform the methods described in the above method embodiments according to the instructions 503. Optionally, the memory 502 may also store data (such as a target audit model). Optionally, the processor 501 may also read data stored in the memory 502, which may be stored at the same storage address as the program 504, or the data may be stored at a different storage address than the program 504.

[0063] The processor 501 and memory 502 can be configured separately or integrated together, for example, integrated on the system-on-chip (SOC) of the terminal device.

[0064] It should be understood that each step of the above method embodiment can be completed by hardware logic circuits or software instructions in the processor 501. The processor 501 can be a CPU, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, such as discrete gates, transistor logic devices, or discrete hardware components.

[0065] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0066] For example, in some embodiments, this application also provides a computer-readable storage medium storing instructions or code that, when executed on a computer, cause the computer to implement the above-described adaptive control method for the brewing process.

[0067] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0068] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. An adaptive control method for a brewing process, applied to intelligent brewing equipment, characterized in that, The method includes the following steps: Acquire operational status data related to the fermentation state during the brewing process; Key process features characterizing the dynamic evolution of the brewing process are extracted from the operational status data. Based on the time variation trend of the key process features, a brewing state evolution trajectory is generated, and the state deviation between the current brewing stage and the target process stage is identified based on the brewing state evolution trajectory. The operational status data is mapped to a unified process scale to determine the degree of compatibility between the current brewing process execution status and the target brewing process. The impact of the current brewing process control on the stability of brewing quality is determined based on the state deviation and the degree of cooperative fit. Based on the aforementioned influence degree, an adaptive set of control parameters for the brewing process is generated, thereby enabling coordinated control of the actuators in the current brewing process.

2. The method as described in claim 1, characterized in that, Extracting key process features characterizing the dynamic evolution of the brewing process from the operational status data specifically includes: The operational status data is preprocessed according to time series to obtain standardized multi-parameter time series data; From the standardized multi-parameter time-series data, several initial process characteristics reflecting fermentation kinetics are determined; Key process features characterizing the dynamic evolution of the brewing process were selected based on all initial process features.

3. The method as described in claim 1, characterized in that, The generation of the brewing state evolution trajectory based on the time variation trend of the key process characteristics specifically includes: The key process features are acquired within a continuous time window to form a multidimensional feature time series. The multidimensional feature time series is subjected to dimensionality reduction processing to obtain the low-dimensional state vector corresponding to each time step; Connect all low-dimensional state vectors in chronological order to generate the state evolution trajectory of brewing.

4. The method as described in claim 1, characterized in that, The identification of the state deviation between the current brewing stage and the target process stage based on the brewing state evolution trajectory specifically includes: Obtain the reference state trajectory of the target process stage in the state space corresponding to the current brewing stage; Align and compare the brewing state evolution trajectory with the reference state trajectory; The deviation between the current brewing stage and the target process stage is determined based on the comparison results.

5. The method as described in claim 1, characterized in that, The process of mapping the operational status data to a unified process scale to determine the compatibility between the current brewing process execution status and the target brewing process specifically includes: The operational status data is mapped onto a unified process evaluation scale to obtain a set of dimensionless process execution indicators. From the target brewing process specifications, the range of target process parameters corresponding to the process execution indicators is extracted; Based on the process execution indicators and the target process parameter range, the degree of synergy and compatibility between the current brewing process execution status and the target brewing process is determined.

6. The method as described in claim 1, characterized in that, The determination of the impact of the current brewing process control on the stability of brewing quality based on the state deviation and the cooperative fit specifically includes: The state deviation is converted into a risk assessment value that characterizes the risk of process operation deviation. The cooperative fit is converted into a fit evaluation value that characterizes the deviation of process parameter execution. The risk assessment value and the adaptation assessment value are fused to obtain the degree of influence of the current brewing process control on the stability of brewing quality.

7. The method as described in claim 1, characterized in that, Based on the aforementioned influence degree, an adaptive set of control parameters for the brewing process is generated, and then the actuators of the current brewing process are linked for coordinated control, specifically including: The overall intensity level of regulatory intervention is determined based on the aforementioned degree of influence. Based on the overall control intensity level and the current brewing stage, a set of control parameters containing specific set values ​​is generated; Based on the set of control parameters, coordinated control commands are sent to each actuator in the current brewing process to complete the linkage control.

8. An intelligent brewing equipment, comprising an adaptive control unit, characterized in that, The adaptive control unit includes: The acquisition module is used to acquire operational status data related to the fermentation state during the brewing process; The processing module is used to extract key process features that characterize the dynamic evolution of the brewing process from the operating status data, generate the state evolution trajectory of the brewing process based on the time change trend of the key process features, and identify the state deviation between the current brewing stage and the target process stage based on the state evolution trajectory of the brewing process. The processing module is also used to perform a unified process scale mapping on the operating status data, thereby determining the degree of coordination and compatibility between the current brewing process execution status and the target brewing process. The processing module is also used to determine the degree of influence of the current brewing process control on the stability of brewing quality based on the state deviation and the degree of cooperative fit. The execution module is used to adaptively generate a set of control parameters for the brewing process based on the influence degree, and then perform linkage control on the execution mechanism of the current brewing process.

9. A computer device, characterized in that, The computer device includes a memory and a processor, the memory for storing a computer program, and the processor for calling and running the computer program from the memory, causing the computer device to perform the adaptive control method for the brewing process according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions or code that, when executed on a computer, cause the computer to implement the adaptive control method for the brewing process as described in any one of claims 1 to 7.

Images