Intelligent control method and system for wall breaking machine

Abstract

The invention provides an intelligent control method and system for a wall breaking machine, and the method comprises the steps: correcting the addition amount if there is a deviation between auxiliary material addition amount data in a current time window and a preset standard, extracting a final auxiliary material metering value from the corrected data, and determining an execution scheme of time-sharing precise management; according to data feedback of the mixing uniformity degree, high-temperature stirring influence parameters possibly occurring in the follow-up manufacturing process are obtained, predictive analysis is carried out on the parameters, and whether the follow-up auxiliary material adding opportunity or the metering value needs to be adjusted or not is judged; and according to the adjusted execution scheme, obtaining a complete data record of a final beverage making process, and carrying out comprehensive evaluation on a nutrition structure and a taste uniformity index in the record to obtain a quality optimization result of the target beverage.

Description

Technical Field

[0001] This invention relates to the field of blender control technology, and in particular to an intelligent control method and system for blenders. Background Technology

[0002] As a core component of modern kitchen equipment, the intelligent control technology of blenders is crucial for enhancing user experience and beverage quality. With consumers' increasing demand for healthy eating and personalized tastes, the function of blenders has expanded from simply grinding ingredients to intelligent control of the entire production process. This technological advancement not only relates to the efficient operation of the equipment but also directly impacts the nutritional value and taste of beverages, becoming a key direction for innovation in the home appliance industry.

[0003] However, the intelligent control methods of existing high-speed blenders have significant limitations in practical applications. Many devices can only achieve simple timed stirring or single ingredient addition, lacking precise management of complex production processes. This is especially true in the preparation of compound beverages, where it is difficult to accurately control the addition of ingredients based on their different characteristics. This can lead to nutritional components interfering with each other due to improper timing of addition, and the taste being reduced due to a lack of scientific combination. Summary of the Invention

[0004] In order to solve the above-mentioned technical problems, the present invention provides an intelligent control method and system for a blender.

[0005] The technical solution of this invention is implemented as follows:

[0006] A method for intelligent control of a high-speed blender, comprising:

[0007] By using a pre-established database of ingredient properties, we can obtain data on the physical changes and chemical reactions of various ingredients involved in the production process of the target beverage. Based on the changes in the properties of each ingredient at different time points, we can determine the specific range of requirements for the timing of adding auxiliary materials.

[0008] Based on the above-determined range of timing requirements for adding auxiliary materials, the production process is dynamically monitored in real time. The relevant parameters of the current state of the ingredients and the influence of high-temperature stirring are extracted from the monitoring data to obtain the optimal time window for adding auxiliary materials.

[0009] To meet the metering requirements for adding auxiliary ingredients within the optimal time window, the system obtains auxiliary ingredient ratio data that matches the target beverage type by using preset standards for beverage nutritional structure and uniform taste, and determines the precise amount of each auxiliary ingredient to be added within the current time window.

[0010] If the amount of auxiliary materials added in the current time window deviates from the preset standard, the amount added is corrected, and the final auxiliary material measurement value is extracted from the corrected data to determine the execution plan for time-based precise management.

[0011] Furthermore, the determination of the specific range of requirements for the timing of adding auxiliary ingredients based on the characteristic changes of each ingredient at different time points includes:

[0012] By using a pre-set ingredient characteristic database, data on the physical changes and chemical reactions of various ingredients in the target beverage preparation process are obtained. The characteristic parameters of each ingredient are extracted using a structured query language to obtain an initial data set.

[0013] For the initial dataset, analyze the physical changes and chemical reaction trends of each ingredient at different time points to determine the characteristic change curves;

[0014] If the slope of the characteristic change curve is within the preset threshold range, then the time node is marked as a critical state point, and a set of critical state points is obtained.

[0015] Based on the set of key state points, obtain the physical changes and chemical reactions of each ingredient at the key state points, determine the candidate time range for adding auxiliary materials, and obtain the set of candidate time ranges.

[0016] By analyzing the interaction between the changes in the characteristics of auxiliary materials and ingredients through a set of candidate time ranges, the required range for the timing of adding auxiliary materials is calculated, and the time range for adding auxiliary materials is determined.

[0017] Furthermore, the optimal time window for obtaining the excipient addition includes:

[0018] The current food status parameters are obtained from real-time monitoring data. Using preset filtering rules, the temperature, viscosity and chemical reaction rate during the high-temperature stirring process are extracted to obtain the food status dataset.

[0019] Based on the food state dataset, the influence trend of high-temperature stirring on each state parameter is calculated to obtain the state change trend.

[0020] If the slope of the state change trend exceeds the preset threshold, the sliding window method is used to analyze the matching degree between the current time point of the food state and the addition of auxiliary materials, and obtain a matching degree score set.

[0021] By using a matching score set, the optimal time window for adding excipients is predicted, and the optimal time range for addition is determined.

[0022] Furthermore, determining the precise amount of each excipient to be added within the current time window includes:

[0023] By using a pre-set beverage type database, the nutritional structure and taste uniformity standards of the target beverage type are obtained, and an initial dataset of auxiliary ingredient ratios is generated.

[0024] Process condition data are obtained within the optimal time window, and temperature parameters and stirring rate are extracted to obtain a process environment dataset.

[0025] If the temperature parameters and stirring rate in the process environment dataset deviate from the preset standard threshold beyond the limit, the initial dataset of auxiliary material proportions will be adjusted to obtain the optimized dataset of auxiliary material proportions.

[0026] Based on the optimized auxiliary material ratio dataset and the process conditions within the time window, a weighted average method is used to calculate the addition amount of each auxiliary material, thus obtaining a set of precise addition amounts.

[0027] Furthermore, the implementation plan for determining precise time-sharing management includes:

[0028] If the amount of excipients added in the current time window deviates from the preset standard, the deviation value is calculated to obtain the excipient addition deviation dataset; the deviation value is extracted from the excipient addition deviation dataset, and the amount of excipients added is adjusted using a weighted calculation method to obtain the corrected excipient measurement dataset;

[0029] Based on the revised auxiliary material metering dataset and combined with the process conditions within the time window, control parameters for time-sharing precise management are generated, resulting in a time-sharing execution scheme dataset.

[0030] If the matching degree between the control parameters in the time-sharing execution scheme dataset and the real-time process conditions is lower than the preset threshold, then process feedback data is obtained from real-time monitoring through data extraction methods to obtain the process verification dataset.

[0031] Furthermore, this method also includes:

[0032] Based on the time-sharing precision management plan, real-time stirring speed and temperature change data in the production process are obtained. The matching degree of these data with the timing of adding auxiliary materials is analyzed to obtain a judgment result on whether the current process is suitable for performing the addition operation.

[0033] If the analysis results indicate that the current process is suitable for adding auxiliary materials, an addition instruction is sent to the execution unit, and relevant data on the degree of mixing uniformity are extracted from the instruction execution feedback to determine whether the auxiliary materials have been evenly distributed in the beverage.

[0034] Based on the data feedback on the degree of mixing uniformity, we obtain the parameters that may be affected by high-temperature stirring in the subsequent production process, and conduct predictive analysis on these parameters to determine whether it is necessary to adjust the timing or measurement value of subsequent auxiliary materials.

[0035] If the predictive analysis determines that the timing or measurement value of subsequent auxiliary materials needs to be adjusted, the control strategy of the production process is updated, new time windows and addition amount data are extracted from the updated strategy, and the adjusted execution plan is determined.

[0036] Based on the adjusted implementation plan, complete data records of the final beverage production process are obtained. The nutritional structure and taste uniformity indicators in the records are comprehensively evaluated to obtain the quality optimization results of the target beverage.

[0037] Furthermore, the determination result of whether the current process is suitable for performing the add operation includes:

[0038] Real-time stirring speed and temperature change data are obtained from dynamic monitoring, and time series analysis is used to extract data features to obtain a time series feature set of stirring speed and temperature changes;

[0039] Based on the time series feature set, the matching degree between stirring speed and temperature changes and the timing of additive addition is analyzed to obtain a matching degree score set;

[0040] If the score in the matching score set is lower than the preset threshold, real-time process parameter data is obtained from dynamic monitoring, and process constraints are extracted through data processing methods to obtain a process constraint dataset.

[0041] Based on the process constraint dataset, the matching score set is adjusted, and the weighted average method is used to generate the optimized matching score set.

[0042] Optimization scores are extracted from the optimization score set, and it is determined whether the optimization scores meet the execution conditions for adding excipients, thus obtaining the feasibility judgment result of the addition operation.

[0043] Furthermore, determining whether the excipients have been evenly distributed in the beverage includes:

[0044] By obtaining feedback data of the addition instruction from the execution unit, and processing the information related to the uniform mixing in the feedback data, a preliminary assessment result of the excipient distribution is obtained.

[0045] Based on the preliminary assessment results, a data filtering method was used to remove noise from the feedback data, resulting in purified and uniformly mixed data.

[0046] If the purified and uniformly mixed data does not reach the preset uniformity threshold, the distribution status will be further detected by data analysis tools to determine the specific areas of uneven distribution.

[0047] For areas with unevenly distributed information, generate local adjustment instructions, send targeted hybrid operations to the execution unit, and obtain the adjusted feedback data;

[0048] New uniformity information is extracted from the adjusted feedback data, the new uniformity is scored, and it is determined whether the uniform distribution condition is met.

[0049] If the score is still lower than the preset threshold, a secondary adjustment instruction is generated based on the score result, and the mixed operation parameters are updated through the execution unit to obtain the final distribution state data;

[0050] Based on the final distribution data, a threshold comparison method is used to verify the distribution of excipients in the beverage to determine whether the distribution of excipients has reached the expected uniform state.

[0051] Furthermore, the determination of whether to adjust the timing or measurement value of subsequent excipient addition includes:

[0052] High-temperature stirring parameters are extracted from the feedback data on the degree of mixing uniformity, and the parameter variation trend is predicted by time series analysis to obtain the parameter fluctuation range;

[0053] Based on the parameter fluctuation range, a preset threshold comparison method is used. If the fluctuation range exceeds the threshold, an adjustment instruction for the timing of adding excipients is generated to determine the adjusted addition time.

[0054] By adjusting the addition time point, real-time parameter monitoring data is obtained, and stirring influencing factors are extracted from the monitoring data to obtain the distribution status of influencing factors;

[0055] Based on the distribution of influencing factors, a model is built to examine the relationship between the metering value of auxiliary materials and the mixing effect, and suggestions for optimizing the metering value are obtained.

[0056] An intelligent control system for a high-speed blender includes:

[0057] The ingredient characteristic analysis and proportion calculation module is used to obtain physical changes and chemical reaction data of various ingredients involved in the production process of the target beverage through a pre-established ingredient characteristic database. Based on the characteristic changes of each ingredient at different time points, it determines the specific range of requirements for the timing of adding auxiliary materials. Based on the auxiliary material addition measurement requirements within the optimal time window, it obtains auxiliary material proportion data matching the target beverage type through preset beverage nutritional structure and taste uniformity standards, and determines the precise addition amount of each auxiliary material within the current time window.

[0058] The timing monitoring and measurement correction module dynamically monitors the production process in real time based on the determined range of timing requirements for adding auxiliary materials. It extracts relevant parameters of the current state of ingredients and the impact of high-temperature stirring from the monitoring data to obtain the optimal time window for adding auxiliary materials. If there is a deviation between the amount of auxiliary materials added in the current time window and the preset standard, the amount of addition is corrected. The final measurement value of auxiliary materials is extracted from the corrected data to determine the execution plan for precise time-sharing management.

[0059] The process matching and execution control module, based on the time-sharing precise management scheme, acquires real-time stirring speed and temperature change data in the dynamic production process. It analyzes the matching degree of these data with the timing of adding auxiliary materials to obtain a judgment result on whether the current process is suitable for adding auxiliary materials. If the judgment result indicates that the current process is suitable for adding auxiliary materials, it sends an addition command to the execution unit and extracts relevant data on the degree of mixing uniformity from the command execution feedback to determine whether the auxiliary materials have been evenly distributed in the beverage.

[0060] The impact prediction and strategy update module obtains the parameters that may be affected by high-temperature stirring in the subsequent production process based on the data feedback on the degree of mixing uniformity. It performs predictive analysis on these parameters to determine whether the timing or measurement value of subsequent auxiliary materials needs to be adjusted. On the other hand, if the predictive analysis determines that the timing or measurement value of subsequent auxiliary materials needs to be adjusted, it updates the control strategy of the production process, extracts new time windows and addition amount data from the updated strategy, and determines the adjusted execution plan.

[0061] The quality assessment module is used to obtain complete data records of the final beverage production process based on the adjusted execution plan, and to comprehensively evaluate the nutritional structure and taste uniformity indicators in the records to obtain the quality optimization results of the target beverage.

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

[0063] 1. This invention accurately obtains data on the physical changes and chemical reactions of various ingredients at different time points, thereby determining the specific range of requirements for the timing of adding auxiliary ingredients for each ingredient. Based on the nutritional structure and taste uniformity standards of beverages, it matches precise auxiliary ingredient ratios for different beverage types, solving the problem that existing equipment is difficult to achieve precise addition control in the production of compound beverages.

[0064] 2. By monitoring the production process in real time, extracting relevant parameters of the state of ingredients and the effect of stirring, determining the optimal time window for adding auxiliary materials, and correcting when the amount added deviates from the preset standard, ensuring the accuracy and timeliness of the addition of auxiliary materials, and avoiding the mutual interference of nutrients due to improper timing of addition;

[0065] 3. By analyzing the matching degree between stirring speed and temperature change data and the timing of adding auxiliary materials, it is determined whether the process is suitable for adding auxiliary materials. Based on the feedback of the degree of mixing uniformity and the prediction analysis of the impact parameters of subsequent high-temperature stirring, the timing or measurement value of addition is adjusted in a timely manner, thereby ensuring the uniformity of the beverage's taste and the scientific combination, and improving the overall quality of the beverage. Attached Figure Description

[0066] Figure 1 This is a flowchart of an intelligent control method for a blender, as described in Example 1.

[0067] Figure 2 This is a framework diagram of an intelligent control system for a blender, as shown in Example 2. Detailed Implementation

[0068] In order to make the purposes, features, and advantages of the present invention more obvious and easy to understand, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described below are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0069] Example 1

[0070] like Figure 1 As shown, this embodiment provides an intelligent control method for a blender, including:

[0071] By using a pre-established database of ingredient properties, we can obtain data on the physical changes and chemical reactions of various ingredients involved in the production process of the target beverage. Based on the changes in the properties of each ingredient at different time points, we can determine the specific range of requirements for the timing of adding auxiliary materials.

[0072] Based on the above-determined range of timing requirements for adding auxiliary materials, the production process is dynamically monitored in real time. The relevant parameters of the current state of the ingredients and the influence of high-temperature stirring are extracted from the monitoring data to obtain the optimal time window for adding auxiliary materials.

[0073] To meet the metering requirements for adding auxiliary ingredients within the optimal time window, the system obtains auxiliary ingredient ratio data that matches the target beverage type by using preset standards for beverage nutritional structure and uniform taste, and determines the precise amount of each auxiliary ingredient to be added within the current time window.

[0074] If the amount of auxiliary materials added in the current time window deviates from the preset standard, the amount added is corrected, and the final auxiliary material measurement value is extracted from the corrected data to determine the execution plan for time-based precise management.

[0075] Furthermore, the determination of the specific range of requirements for the timing of adding auxiliary ingredients based on the characteristic changes of each ingredient at different time points includes:

[0076] By using a pre-set ingredient characteristic database, data on the physical changes and chemical reactions of various ingredients in the target beverage preparation process are obtained. The characteristic parameters of each ingredient are extracted using a structured query language to obtain an initial data set.

[0077] For the initial dataset, analyze the physical changes and chemical reaction trends of each ingredient at different time points to determine the characteristic change curves;

[0078] If the slope of the characteristic change curve is within the preset threshold range, then the time node is marked as a critical state point, and a set of critical state points is obtained.

[0079] Based on the set of key state points, obtain the physical changes and chemical reactions of each ingredient at the key state points, determine the candidate time range for adding auxiliary materials, and obtain the set of candidate time ranges.

[0080] By analyzing the interaction between the changes in the characteristics of auxiliary materials and ingredients through the candidate time range set, the required range for the timing of adding auxiliary materials is calculated, and the time range for adding auxiliary materials is determined.

[0081] By determining the time range for adding auxiliary materials, process optimization parameters are obtained, and the time node allocation of the production process is adjusted to obtain the optimized production process.

[0082] Based on the optimized production process, the ingredient characteristic parameters and auxiliary material addition rules in the database are updated to generate a new set of process data.

[0083] Specifically, as shown in the example below, by using a pre-established ingredient characteristic database, the physical and chemical characteristic data of the ingredients (such as coffee beans, water, and syrup) involved in the target beverage (such as Americano) are first extracted from the database, including the content of volatile aromatic substances in coffee beans (initial value is 0.85 mg / g), the effect of water temperature on the extraction rate (the extraction rate is 18% at 95℃), and the viscosity of syrup (0.12 Pa·s at 25℃).

[0084] The database uses Structured Query Language (SQL) to retrieve data using the query "SELECT * FROM ingredients WHERE drink_id = 'espresso'" and stores the returned results in JSON format.

[0085] Next, a kinetic model was used to analyze the changes in characteristics of each ingredient at specific time points in the production process (e.g., extraction 0-30 seconds, syrup addition 30-45 seconds). (k is the reaction rate constant; for coffee extraction, k = 0.02 s) -1 The change in the concentration of aromatic compounds in coffee over time was calculated, and it was found that the concentration dropped to 0.72 mg / g after 20 seconds, affecting the flavor release.

[0086] The required range for when to add syrup is determined by the relationship between viscosity and temperature. (E is the activation energy, R is the gas constant) Calculations show that the viscosity of the syrup at 40-50℃ is 0.08-0.10 Pa·s, which is suitable for uniform mixing;

[0087] Further combining the decision tree algorithm, the input features include time (t), temperature (T), and concentration (C), and the output is the optimal time window for adding excipients (e.g., adding syrup at t=35 seconds and T=45℃). The accuracy of the model is verified by the mean squared error (MSE=0.015).

[0088] If the database lacks data on a certain ingredient (such as a new type of syrup), its characteristics can be inferred from similar ingredients (such as honey with a viscosity of 0.15 Pa·s) through transfer learning, and temporary data can be generated to supplement the analysis.

[0089] Finally, the system outputs the addition timing range in JSON format (e.g., {"syrup_add_time":35~40s", "temp":40-50℃"}), and interfaces with the beverage making equipment API to automatically adjust process parameters and ensure consistent flavor.

[0090] Furthermore, the optimal time window for obtaining the excipient addition includes:

[0091] The current food status parameters are obtained from real-time monitoring data. Using preset filtering rules, the temperature, viscosity and chemical reaction rate during the high-temperature stirring process are extracted to obtain the food status dataset.

[0092] Based on the food state dataset, the influence trend of high-temperature stirring on each state parameter is calculated to obtain the state change trend.

[0093] If the slope of the state change trend exceeds the preset threshold, the sliding window method is used to analyze the matching degree between the current time point of the food state and the addition of auxiliary materials, and obtain a matching degree score set.

[0094] By using a matching score set, the optimal time window for adding excipients is predicted, and the optimal time range for addition is determined.

[0095] Based on the optimal addition time range, obtain the process parameters, adjust the duration and intensity of high-temperature stirring, and obtain the optimized process parameters;

[0096] By optimizing the process parameters, updating the control rules for real-time monitoring, and generating dynamically adjusted production process data;

[0097] Based on the dynamically adjusted production process data, the preset ingredient status database is updated to obtain a new process control dataset.

[0098] Specifically, as shown in the example below, dynamic data in the production process of a target beverage (such as a latte) can be obtained through real-time monitoring equipment sensors, including coffee extraction time (t), stirring temperature (T), stirring rate (ω), and the degree of milk emulsification (E).

[0099] The sensor collects data every 0.5 seconds to generate a time series dataset. For example, at t=10 seconds, T=85℃, ω=300rpm, E=0.65 (the degree of emulsification is measured by light scattering, in the range of 0-1).

[0100] First, the collected data is preprocessed by using a Kalman filter to smooth the noise. The filter parameters are Q = 0.01 and R = 0.1, resulting in the smoothed temperature sequence T. smoothed =84.8℃;

[0101] Next, the effect of high-temperature stirring on the state of the ingredients was analyzed using a heat conduction model. (k = 0.6 W / m·K is the thermal conductivity of milk) The temperature gradient during stirring was calculated, and it was found that when ω = 300 rpm, the rate of temperature drop of the milk surface dT / dt = -0.15℃ / s, which affects the emulsion stability.

[0102] To determine the optimal time window for adding milk, a Support Vector Machine (SVM) algorithm was used. The input features included time (t) and smoothed temperature (T). smoothed The parameters are: emulsification degree (E), stirring rate (ω), kernel function is radial basis function (RBF), parameters C = 1.0, γ = 0.1, and the output is the predicted addition time t. add ;

[0103] The training dataset contains 500 historical production data sets, and the test set accuracy is 92%. The prediction t... add =15.5 seconds, T=82-84℃;

[0104] Further analysis of the effect of stirring rate on the degree of emulsification was conducted using the regression model E(ω)=aω b (a=0.02, b=0.45) Calculation shows that when ω=280-320rpm, E=0.62-0.68, which is suitable for forming fine foam;

[0105] If sensor data is missing (e.g., stirring rate), the current state is estimated from historical data (mean ω = 310 rpm, standard deviation σ = 15 rpm) using Bayesian inference, generating a temporary value ω. est =305 rpm;

[0106] Finally, the system generates a JSON output in the format {"milk_add_time": "15~16 seconds", "temp": "82-84℃", "stir_rate": "280-320rpm"}, and transmits the parameters to the mixing equipment in real time via API to automatically adjust the process.

[0107] The entire process is completed via cloud computing, ensuring data processing latency of less than 50 milliseconds.

[0108] Furthermore, determining the precise amount of each excipient to be added within the current time window includes:

[0109] By using a pre-set beverage type database, the nutritional structure and taste uniformity standards of the target beverage type are obtained, and an initial dataset of auxiliary ingredient ratios is generated.

[0110] Process condition data are obtained within the optimal time window, and temperature parameters and stirring rate are extracted to obtain a process environment dataset.

[0111] If the temperature parameters and stirring rate in the process environment dataset deviate from the preset standard threshold beyond the limit, the initial dataset of auxiliary material proportions will be adjusted to obtain the optimized dataset of auxiliary material proportions.

[0112] Based on the optimized excipient ratio dataset and combined with the process conditions within the time window, the weighted average method is used to calculate the addition amount of each excipient, thus obtaining a set of precise addition amounts.

[0113] By precisely setting the dosage, updating the control rules for real-time monitoring, and generating a dynamically adjusted dataset of auxiliary material addition instructions;

[0114] Based on the dynamically adjusted auxiliary ingredient addition instruction dataset, feedback data of the beverage production process is obtained to determine the matching degree of taste uniformity and nutritional structure, and process verification dataset is obtained.

[0115] If the matching degree in the process verification dataset is lower than the preset standard threshold, the auxiliary material addition instruction dataset is optimized to obtain the final auxiliary material addition control parameters.

[0116] Specifically, as shown in the example below, for the toppings of a target beverage (such as matcha latte), the system can automatically obtain the topping ratio data that matches the beverage type based on the preset nutritional structure and taste uniformity standards, and calculate the precise amount of each topping to be added within the optimal time window.

[0117] Taking matcha latte as an example, the beverage recipe is first extracted from the database, with a total volume of 300 ml, of which matcha powder accounts for 2.5% (7.5 g), syrup accounts for 5% (15 g), milk accounts for 92.5% (277.5 ml), and the target taste uniformity (U) needs to reach 0.9 or higher (measured by refractive index, range 0-1).

[0118] The sensor collects state data within the current time window (15-16 seconds), including the liquid volume in the container (V = 200 ml), the solubility of matcha powder (S = 0.85, range 0-1, measured based on light transmission method), and the viscosity of syrup (η = 0.05 Pa·s).

[0119] To ensure accurate proportions, a linear programming algorithm is used to optimize the amount of excipients added. The objective function is:

[0120] min(|V total -300|+|U-0.9|), the constraints include 7.5g≤matcha powder≤8g, 14g≤syrup≤16g, and milk to make up the remaining volume;

[0121] The calculated amounts are: 7.8 grams of matcha powder, 15.2 grams of syrup, and 276.8 ml of milk.

[0122] Next, the solubility characteristics of the excipients were analyzed using a diffusion model. (k=1.2×10^-9m 2 The dissolution rate of matcha powder at the current viscosity is calculated using the diffusion coefficient (s is the diffusion coefficient). This indicates that S = 0.88 can be achieved at 15.5 seconds, which meets the requirement for uniform taste;

[0123] If sensor data is missing (e.g., viscosity), η can be estimated from historical data (mean η = 0.048 Pa·s, standard deviation σ = 0.002 Pa·s) using Gaussian process regression. est = 0.049 Pa·s;

[0124] Finally, the JSON output {"matcha": "7.8 g", "syrup": "15.2 g", "milk": "276.8 ml"} is generated and transmitted to the automatic metering device via API to adjust the amount added in real time with a latency of less than 40 milliseconds.

[0125] Furthermore, the implementation plan for determining precise time-sharing management includes:

[0126] If the amount of auxiliary materials added in the current time window deviates from the preset standard, the deviation value is calculated and the auxiliary material addition deviation dataset is obtained.

[0127] The deviation analysis algorithm uses linear regression. The input variable x represents the amount of excipients added, y represents the preset standard value, and the output deviation value d is the difference between x and y.

[0128] Calculation formula: d = xy. Assuming the preset standard value y = 15 grams and the actual amount added x = 14.5 grams, then the deviation value d = 14.5 - 15 = -0.5 grams.

[0129] The deviation values ​​are extracted from the excipient addition deviation dataset, and the excipient addition amount is adjusted using a weighted calculation method to obtain the corrected excipient metering dataset.

[0130] In the weighted calculation method, the weight w is determined based on the stability of the process conditions within the time window, and the corrected measurement value m is output.

[0131] Calculation formula: m=x+w·d, assuming weight w=0.8 and deviation value d=-0.5 grams, then the corrected measurement value m=14.5+0.8·(-0.5)=14.1 grams.

[0132] Based on the revised auxiliary material metering dataset and combined with the process conditions within the time window, control parameters for time-sharing precise management are generated, resulting in a time-sharing execution scheme dataset.

[0133] The decision tree algorithm takes process conditions as input features and outputs control parameters p.

[0134] Input characteristics: Process conditions within the time window, such as temperature, stirring rate, etc.

[0135] Output: Control parameter p;

[0136] Example: Suppose that the decision tree model outputs control parameters p = {temperature = 85℃, stirring rate = 300rpm} based on the current process conditions.

[0137] If the matching degree between the control parameters in the time-sharing execution scheme dataset and the real-time process conditions is lower than the preset threshold, process feedback data is obtained from real-time monitoring through data extraction methods to obtain the process verification dataset.

[0138] The data extraction method is based on time series analysis, and the output is validation data v;

[0139] Validation data is extracted from the process validation dataset, and the time-sharing execution scheme dataset is adjusted using a weighted average method to obtain the optimized time-sharing execution scheme.

[0140] The weighted average method takes validation data v as input and outputs optimized parameters o.

[0141] Calculation formula: o=p+w′·(vp), where w′ is the adjustment weight; assuming the adjustment weight w′=7, then the optimized control parameters o={temperature=85+0.7·(84-85)=84.3℃, stirring rate=300+0.7·(290-300)=293rpm}.

[0142] Based on the optimized time-sharing execution scheme, the dynamically adjusted auxiliary material addition instruction dataset is obtained by updating the real-time monitoring instructions through control parameters.

[0143] The instruction dataset takes the optimization parameter o as input and outputs the instruction set i; the instruction dataset contains the precise addition amount and addition time for each excipient;

[0144] Example: Dynamically adjusted instruction dataset i = {matcha powder = 7.8 g, syrup = 15.2 g, milk = 276.8 ml, temperature = 84.3℃, stirring speed = 293 rpm}.

[0145] Extract the instruction set from the dynamically adjusted auxiliary material addition instruction dataset, determine the matching degree between the instruction set and the preset standard, and obtain the final auxiliary material addition control parameters;

[0146] The judgment is based on the threshold comparison method, and the output control parameter c is given; assuming the preset standard y = {matcha powder = 7.5g, syrup = 15g, milk = 277.5ml, temperature = 85℃, stirring speed = 300rpm}, the threshold is 0.5g and 1rpm;

[0147] Matching degree judgment: |7.8-7.5|=0.3<0.5, |15.2-15|=0.2<0.5, |276.8-277.5|=0.7<0.5, |84.3-85|=0.7<1, |293-300|=7>1;

[0148] Final control parameters: c = {matcha powder = 7.8g, syrup = 15.2g, milk = 276.8ml, temperature = 84.3℃, stirring speed = 293rpm}.

[0149] Specifically, as shown in the example below, the measurement deviation of the additives for the target beverage (such as cappuccino) can be corrected in real time to ensure that the final amount added meets the preset standard and generate a precise time-sharing management plan.

[0150] Taking cappuccino as an example, the preset total volume is 250 ml, the recipe requires coffee liquid to account for 20% (50 ml), milk foam to account for 30% (75 ml), milk to account for 50% (125 ml), and the target consistency coefficient (C) is 0.75 (based on ultrasonic measurement, range 0-1).

[0151] The sensor detected the actual added amounts as 48 ml of coffee liquid, 70 ml of milk foam, and 130 ml of milk within the current time window (10-11 seconds), with deviations of -2 ml, -5 ml, and +5 ml, respectively.

[0152] First, a deviation correction algorithm is used, with the objective function being min(∑|V actual -V target |), with the constraints being 48 ml ≤ coffee liquid ≤ 52 ml, 70 ml ≤ milk foam ≤ 80 ml, and milk replenished to 250 ml;

[0153] The calculated correction amounts are: coffee liquid increased by 2.1 ml to 50.1 ml, milk foam increased by 4.8 ml to 74.8 ml, and milk decreased by 4.9 ml to 125.1 ml;

[0154] Next, the change in milk foam consistency was analyzed using the fluid dynamics model C = α·Vf oam The current consistency C = 0.73 is calculated using / (V_total·μ)(α = 0.8 is a constant, μ = 0.01 Pa·s is the milk viscosity), which is slightly lower than the target of 0.75.

[0155] To optimize consistency, the milk foam generation time was adjusted and increased by 0.2 seconds (from 10.5 seconds to 10.7 seconds), so that the C content reached 0.76.

[0156] If sensor data is missing (e.g., milk foam volume), Kalman filtering can be used to extract it from historical data (mean V). foam =73 ml, standard deviation σ = 2 ml) Estimate V foam _est = 72.5 ml;

[0157] Finally, the JSON output {"coffee":50.1 ml", "foam":74.8 ml", "milk":125.1 ml"} is generated and transmitted to the automatic allocation device via API for real-time time-sharing management with a latency of less than 30 milliseconds.

[0158] Furthermore, this method also includes:

[0159] Based on the time-sharing precision management plan, real-time stirring speed and temperature change data in the production process are obtained. The matching degree of these data with the timing of adding auxiliary materials is analyzed to obtain a judgment result on whether the current process is suitable for performing the addition operation.

[0160] If the analysis results indicate that the current process is suitable for adding auxiliary materials, an addition instruction is sent to the execution unit, and relevant data on the degree of mixing uniformity are extracted from the instruction execution feedback to determine whether the auxiliary materials have been evenly distributed in the beverage.

[0161] Based on the data feedback on the degree of mixing uniformity, we obtain the parameters that may be affected by high-temperature stirring in the subsequent production process, and conduct predictive analysis on these parameters to determine whether it is necessary to adjust the timing or measurement value of subsequent auxiliary materials.

[0162] If the predictive analysis determines that the timing or measurement value of subsequent auxiliary materials needs to be adjusted, the control strategy of the production process is updated, new time windows and addition amount data are extracted from the updated strategy, and the adjusted execution plan is determined.

[0163] Based on the adjusted implementation plan, complete data records of the final beverage production process are obtained. The nutritional structure and taste uniformity indicators in the records are comprehensively evaluated to obtain the quality optimization results of the target beverage.

[0164] Furthermore, the determination result of whether the current process is suitable for performing the add operation includes:

[0165] Real-time stirring speed and temperature change data are obtained from dynamic monitoring, and time series analysis is used to extract data features to obtain a time series feature set of stirring speed and temperature changes;

[0166] The time series analysis method is based on a sliding window and outputs a feature vector f = [T1,T2,...,T5,ω1,ω2,...,ω5].

[0167] Based on the time series feature set, the matching degree between stirring speed and temperature changes and the timing of additive addition is analyzed to obtain a matching degree score set;

[0168] The support vector machine algorithm takes a feature vector f as input and outputs a matching score s, for example, s = 0.85;

[0169] If the score in the matching score set is lower than the preset threshold, real-time process parameter data is obtained from dynamic monitoring, and process constraints are extracted through data processing methods to obtain a process constraint dataset; the preset threshold is set to 0.9, and since s = 0.85 < 0.9, further processing is required;

[0170] The data processing method is based on feature filtering, and the output constraint condition c; for example, c = {temperature range = [80, 90]℃, stirring rate range = [280, 320]rpm}

[0171] Based on the process constraint dataset, the matching score set is adjusted, and the weighted average method is used to generate the optimized matching score set.

[0172] The weighted average method takes the constraint condition c and the matching score s as input and outputs the optimization score o.

[0173] Input constraint c and matching score s, output optimization score o. Assuming weight w = 0.7, then o = 0.7·s + 0.3·mean(c). Example optimization score: o = 0.7·0.85 + 0.3i0.88 = 0.86;

[0174] Optimization scores are extracted from the optimization score set, and it is determined whether the optimization scores meet the execution conditions for adding excipients, thus obtaining the feasibility judgment result of the addition operation.

[0175] The determination is based on a threshold comparison method, and the feasibility flag r is output.

[0176] If the feasibility flag indicates that it is suitable to add the operation, then the auxiliary material addition instruction is generated according to the optimization score set, and the control parameters monitored in real time are updated through instruction distribution to obtain a dynamic addition instruction set;

[0177] The instruction set takes the optimization score o as input and outputs the instruction set i; for example, the feasibility flag r = 1 (indicating that it is suitable to add the operation), and the instruction set i = {addition time = 15s, temperature = 85℃, stirring speed = 300rpm}.

[0178] The instruction set is extracted from the dynamically added instruction set, and the matching degree between the instruction set and the real-time stirring speed and temperature changes is verified by the time series analysis method to obtain the final auxiliary material addition control parameters.

[0179] The timing analysis method takes instruction set i and real-time data as input and outputs control parameter p.

[0180] Specifically, as shown in the example below, during the process of making a latte, dynamic data of the process is obtained through real-time monitoring equipment to ensure that the matching degree between the stirring speed and temperature changes and the timing of adding ingredients is optimal, thereby determining whether it is appropriate to perform the addition operation.

[0181] First, the built-in sensor collects stirring speed data within a time window (15-20 seconds). Assuming the current stirring speed is 300 rpm, while the preset standard is 350 rpm, the deviation is -50 rpm. At the same time, temperature data is collected. The current temperature is 65.5 degrees Celsius, the target temperature is 70.0 degrees Celsius, and the deviation is -4.5 degrees Celsius.

[0182] Next, a matching degree analysis algorithm is used to calculate the comprehensive matching degree score of stirring speed and temperature, as shown in the formula: Where V actual V represents the actual stirring speed. target For the target speed, T actual T represents the actual temperature. target Assuming the target temperature, after substituting the data, we calculate M = 0.6 × (300 / 350) + 0.4 × (65.5 / 70.0) = 0.514 + 0.374 = 0.888, with a matching score of 0.888, which is lower than the preset threshold of 0.9.

[0183] Further analysis reveals that if the matching degree is below the threshold, the current process is considered unsuitable for immediately performing the auxiliary material addition operation.

[0184] To optimize the matching degree, the power of the stirring motor is automatically adjusted, increasing the output by 10%, which raises the stirring speed to 330 rpm. At the same time, the temperature is raised to 69.0 degrees Celsius within 5 seconds. The matching degree score is recalculated as M = 0.6 × (330 / 350) + 0.4 × (69.0 / 70.0) = 0.566 + 0.394 = 0.960, which is higher than the threshold of 0.9.

[0185] At this point, it is determined that the current process is suitable for performing the addition operation, and an instruction is generated and transmitted to the addition device through the internal interface. The preset amount of syrup, 15.0 ml, is added within the next time window (21-25 seconds) to ensure a balanced taste in the beverage.

[0186] Furthermore, determining whether the excipients have been evenly distributed in the beverage includes:

[0187] By obtaining feedback data of the addition instruction from the execution unit, and processing the information related to the uniform mixing in the feedback data, a preliminary assessment result of the excipient distribution is obtained.

[0188] Based on the preliminary assessment results, a data filtering method was used to remove noise from the feedback data, resulting in purified and uniformly mixed data.

[0189] If the purified and uniformly mixed data does not reach the preset uniformity threshold, the distribution status will be further detected by data analysis tools to determine the specific areas of uneven distribution.

[0190] For areas with unevenly distributed information, generate local adjustment instructions, send targeted hybrid operations to the execution unit, and obtain the adjusted feedback data;

[0191] New uniformity information is extracted from the adjusted feedback data, the new uniformity is scored, and it is determined whether the uniform distribution condition is met.

[0192] If the score is still lower than the preset threshold, a secondary adjustment instruction is generated based on the score result, and the mixed operation parameters are updated through the execution unit to obtain the final distribution state data;

[0193] Based on the final distribution data, a threshold comparison method is used to verify the distribution of excipients in the beverage to determine whether the distribution of excipients has reached the expected uniform state.

[0194] Specifically, as shown in the example below, during the cappuccino beverage preparation process, after analyzing and determining that the current process is suitable for adding auxiliary ingredients, an instruction is sent to the auxiliary ingredient addition execution unit through the internal communication protocol. The instruction includes adding 20.0 ml of milk foam and adding it within a time window of 25 to 30 seconds.

[0195] After receiving the instruction, the execution unit starts the precision metering pump, completes the addition of milk foam in 28 seconds, and collects data in real time during the mixing process through the built-in sensor, specifically the stirring speed and the frequency of liquid surface fluctuation.

[0196] The sensor recorded the current stirring speed as 400 rpm and the liquid surface ripple frequency as 5.2 Hz;

[0197] The uniformity analysis algorithm is used to evaluate the distribution of milk foam. The algorithm formula is as follows:

[0198] Where S actual S represents the actual stirring speed. reference With a reference speed of 450 rpm, F actual F is the actual fluctuation frequency. reference The ideal fluctuation frequency is 6.0 Hz;

[0199] Substituting the data, we get U = 0.7 × (400 / 450) + 0.3 × (5.2 / 6.0) = 0.622 + 0.260 = 0.882, and the uniformity score is 0.882.

[0200] The preset uniformity threshold is 0.85. The current score is higher than the threshold, indicating that the milk foam has been initially evenly distributed.

[0201] To further confirm, data was collected again within 5 seconds after addition. The stirring speed was stabilized at 410 rpm and the fluctuation frequency increased to 5.8 Hz. The uniformity score was recalculated as U = 0.7 × (410 / 450) + 0.3 × (5.8 / 6.0) = 0.637 + 0.290 = 0.927. The score improved to 0.927, confirming that the milk foam was completely and evenly distributed.

[0202] The uniformity analysis results are stored in the log database, and feedback instructions are generated to notify the main control unit that the current process can proceed to the next stage, such as adjusting the beverage temperature to 55.0 degrees Celsius to ensure consistent taste.

[0203] Furthermore, the determination of whether to adjust the timing or measurement value of subsequent excipient addition includes:

[0204] High-temperature stirring parameters are extracted from the feedback data on the degree of mixing uniformity, and the parameter variation trend is predicted by time series analysis to obtain the parameter fluctuation range;

[0205] Based on the parameter fluctuation range, a preset threshold comparison method is used. If the fluctuation range exceeds the threshold, an adjustment instruction for the timing of adding excipients is generated to determine the adjusted addition time.

[0206] By adjusting the addition time point, real-time parameter monitoring data is obtained, and stirring influencing factors are extracted from the monitoring data to obtain the distribution status of influencing factors;

[0207] Based on the distribution of influencing factors, a model is built to examine the relationship between the metering value of auxiliary materials and the mixing effect, and suggestions for optimizing the metering value are obtained.

[0208] Based on the metering value optimization suggestions, process flow optimization instructions are generated, updated auxiliary material metering values ​​are sent to the execution unit, and new feedback data is obtained.

[0209] Extract the uniformity information from the new feedback data. If the uniformity does not reach the preset threshold, clean up the noise using data filtering methods to determine the final uniformity state.

[0210] Based on the final uniform state, process parameter adjustment records are generated and stored in the database for reference in subsequent process optimization.

[0211] Specifically, as shown in the following example, during the beverage preparation process, based on data feedback on the degree of mixing uniformity, the system can automatically initiate predictive analysis of parameters that may be affected by high-temperature stirring in subsequent processes, in order to optimize the timing and measurement values ​​of additives.

[0212] First, the built-in sensors continuously monitor the current beverage temperature and viscosity, assuming the current temperature is 65.5 degrees Celsius and the viscosity index is 3.8 (unitless, based on internal standards), and combine historical data to predict the impact of high-temperature stirring (set to 75.0 degrees Celsius) on these parameters;

[0213] Call the prediction model, the formula is: Where T current T represents the current temperature. target To achieve a target high temperature of 75.0 degrees Celsius, V current V represents the current viscosity. reference The reference viscosity is 4.5;

[0214] Substituting the data, we get P = 0.6 × (65.5 / 75.0) + 0.4 × (3.8 / 4.5) = 0.524 + 0.338 = 0.862, and the predicted impact score is 0.862.

[0215] The preset impact threshold is 0.9. If the score is lower than the threshold, it indicates that high-temperature stirring may lead to excessively low viscosity, and the timing of adding auxiliary materials needs to be adjusted in advance.

[0216] Subsequently, the system automatically analyzes the time window of the subsequent process. Assuming that the original plan was to add 15.0 ml of syrup at the 40th second, it is now adjusted to add it at the 35th second based on the prediction results, and the measurement value is finely adjusted to 16.5 ml to balance the viscosity.

[0217] After adjustment, the expected viscosity is recalculated using an internal algorithm, as shown in the formula below.

[0218] V expected =V current +0.2×(A new -A original ), where A new The newly added amount is 16.5 ml, A original The original added amount was 15.0 ml, and V was calculated. expected=3.8 + 0.2 × (16.5 - 15.0) = 3.8 + 0.3 = 4.1, which is close to the reference value of 4.5 and meets expectations;

[0219] Next, the adjustment plan is stored in the process database, and an update instruction is sent to the execution unit to ensure that the subsequent process runs according to the new parameters. If the predicted temperature exceeds 75.0 degrees Celsius, the cooling program is started in advance to lock the target temperature at 72.0 degrees Celsius to avoid overheating and affecting the taste.

[0220] Furthermore, determining the adjusted execution plan includes:

[0221] Based on the results of predictive analysis, the timing of addition and the need for adjustment of measurement values ​​are determined. If the prediction results show a deviation, the corresponding adjustment standard is obtained from the preset threshold database to determine the initial direction of strategy adjustment.

[0222] Based on the initial strategy adjustment direction, update the control strategy in the production process, obtain the adjusted time window and addition amount data, and obtain the optimized process configuration information;

[0223] Based on the optimized process configuration information, preset mapping rules are used to transform the time window and added quantity data into specific execution plans, and determine the final process execution instructions;

[0224] By executing the final process instructions, real-time monitoring data is obtained, key indicators related to the timing of addition are extracted from the monitoring data, and it is determined whether the indicators meet the preset range requirements.

[0225] If the key indicators do not meet the preset range requirements, data cleaning tools are used to preprocess the monitoring data, filter out outliers, and obtain corrected indicator data.

[0226] Based on the revised indicator data, the relationship between the amount of additives and the process effect is modeled and analyzed using a linear regression algorithm to determine the optimized value of the amount of additives.

[0227] By adjusting the added amount optimization value, the relevant parameters in the execution plan are updated, new process instructions are sent down, and the updated running status data is obtained.

[0228] Specifically, as shown in the example below, during the beverage preparation process, based on the predictive analysis results of the mixing uniformity, it is determined that the timing and measurement value of the auxiliary materials need to be adjusted. The control strategy of the preparation process is automatically updated, and new time windows and addition amount data are extracted to generate an optimized execution plan.

[0229] First, the acidity and fluidity of the beverage are monitored by sensors. Assuming the current acidity is 4.2 (pH value) and the fluidity index is 2.5 (based on internal standards, no unit), the impact of subsequent low-temperature stirring (set to 10.0 degrees Celsius) on these parameters is analyzed in conjunction with historical data.

[0230] Call the evaluation model, the formula is: pH current The current acidity is 4.2, and the pH is... reference For reference acidity 4.0, F current With current liquidity of 2.5, F reference For reference liquidity 3.0;

[0231] Substituting the data, we get Q = 0.5 × (4.2 / 4.0) + 0.5 × (2.5 / 3.0) = 0.525 + 0.416 = 0.941;

[0232] The threshold is set at 0.95. If the score is lower than the threshold, it indicates that low-temperature stirring may lead to insufficient fluidity, and the auxiliary material addition strategy needs to be adjusted.

[0233] Analyzing the subsequent process time window, the original plan was to add 10.0 ml of lemon extract at the 50th second, but based on the calculation results, it has now been adjusted to add it at the 45th second, and the volume has been increased to 11.2 ml to improve fluidity;

[0234] After adjustment, the new liquidity is predicted using an algorithm, with the formula F. expected =F current +0.15×(A new -A original ), where A new The newly added amount is 11.2 ml, A original The original added amount was 10.0 ml, and F was calculated. expected =2.5 + 0.15 × (11.2 - 10.0) = 2.5 + 0.18 = 2.68, which is close to the reference value of 3.0;

[0235] Furthermore, the quality optimization results obtained for the target beverage include:

[0236] Complete data records of the beverage preparation process are obtained. Preliminary information on nutritional structure and taste uniformity in the records is extracted. The data is then layered using a pre-set classification tool to obtain a structured set of process data.

[0237] Based on the structured process data set, index analysis is performed on the distribution of nutritional structure and taste uniformity. By comparing each index with a preset threshold range, it is determined whether there is any deviation and preliminary index analysis results are obtained.

[0238] Based on the preliminary indicator analysis results, if it is found that the indicators of nutritional structure or uniform taste deviate from the preset range, the corresponding adjustment rules are extracted from the preset database, and combined with the current process data, the targeted direction of indicator correction is determined.

[0239] Based on the direction of indicator correction and combined with the key control points in the production process, the parameters in the execution plan are dynamically adjusted. A data mapping tool is used to convert the adjusted parameters into specific process data to obtain the updated plan configuration.

[0240] By updating the scheme configuration, real-time beverage production process data is obtained, and secondary extraction is performed on the nutritional structure and taste uniformity indicators to determine whether they meet the preset quality assessment standards and obtain secondary analysis results.

[0241] Based on the results of the secondary analysis, if the nutritional structure or taste uniformity index still does not meet the preset standard, a linear regression model is used to model the relationship between process data and quality assessment results to determine the final optimization adjustment parameters.

[0242] By optimizing and adjusting the parameters, updating the relevant configurations in the execution plan, issuing the adjusted process instructions, obtaining the updated running status data, determining whether the beverage quality meets the requirements of the target beverage, and obtaining the final evaluation result.

[0243] For example, after the beverage is made, the complete process data record generated by the adjusted execution plan is automatically obtained, and the nutritional structure and taste uniformity of the beverage are comprehensively evaluated to optimize the final quality.

[0244] First, extract detailed logs of the production process from the database, including raw material ratio data and mixing time records for each stage. For example, the total production time is 120 seconds, with 5.0 grams of protein added, 8.0 grams of sugar added, and 60% of the time spent mixing evenly.

[0245] Subsequently, the nutritional assessment model was invoked, and the formula was used. Where P actual The actual protein content is 5.0 grams, P target The target protein content is 4.8 grams, S actual The actual sugar content is 8.0 grams, S target With a target sugar content of 7.5 grams, the calculated N = 0.4 × (5.0 / 4.8) + 0.6 × (8.0 / 7.5) = 0.416 + 0.64 = 1.056, indicating that the nutritional structure is slightly higher than the target value, which is within the optimization range (1.0-1.1).

[0246] Next, the uniformity of taste was analyzed. Concentration distribution data for different areas of the beverage were collected using sensors. Assuming the concentration in the central area was 3.2 (internal standard value) and the concentration in the edge area was 3.0, the uniformity was calculated. A value close to the ideal value of 1.0 indicates a better texture distribution;

[0247] If the uniformity is below 0.9, a suggested solution to extend the stirring time by 5 seconds will be automatically generated and stored in the database;

[0248] Finally, the nutritional scores and evenness data were integrated to derive the overall quality index Q. total =0.5×N+0.5×U=0.5×1.056+0.5×0.9375=0.9965, which is close to the ideal value of 1.0. This confirms that the beverage quality has reached the optimization target, and the results are recorded in the log for subsequent analysis and improvement.

[0249] Example 2

[0250] like Figure 2 As shown, this embodiment provides an intelligent control system for a blender, including:

[0251] The ingredient characteristic analysis and proportion calculation module is used to obtain physical changes and chemical reaction data of various ingredients involved in the production process of the target beverage through a pre-established ingredient characteristic database. Based on the characteristic changes of each ingredient at different time points, it determines the specific range of requirements for the timing of adding auxiliary materials. Based on the auxiliary material addition measurement requirements within the optimal time window, it obtains auxiliary material proportion data matching the target beverage type through preset beverage nutritional structure and taste uniformity standards, and determines the precise addition amount of each auxiliary material within the current time window.

[0252] The timing monitoring and measurement correction module dynamically monitors the production process in real time based on the determined range of timing requirements for adding auxiliary materials. It extracts relevant parameters of the current state of ingredients and the impact of high-temperature stirring from the monitoring data to obtain the optimal time window for adding auxiliary materials. If there is a deviation between the amount of auxiliary materials added in the current time window and the preset standard, the amount of addition is corrected. The final measurement value of auxiliary materials is extracted from the corrected data to determine the execution plan for precise time-sharing management.

[0253] The process matching and execution control module, based on the time-sharing precise management scheme, acquires real-time stirring speed and temperature change data in the dynamic production process. It analyzes the matching degree of these data with the timing of adding auxiliary materials to obtain a judgment result on whether the current process is suitable for adding auxiliary materials. If the judgment result indicates that the current process is suitable for adding auxiliary materials, it sends an addition command to the execution unit and extracts relevant data on the degree of mixing uniformity from the command execution feedback to determine whether the auxiliary materials have been evenly distributed in the beverage.

[0254] The impact prediction and strategy update module obtains the parameters that may be affected by high-temperature stirring in the subsequent production process based on the data feedback on the degree of mixing uniformity. It performs predictive analysis on these parameters to determine whether the timing or measurement value of subsequent auxiliary materials needs to be adjusted. On the other hand, if the predictive analysis determines that the timing or measurement value of subsequent auxiliary materials needs to be adjusted, it updates the control strategy of the production process, extracts new time windows and addition amount data from the updated strategy, and determines the adjusted execution plan.

[0255] The quality assessment module is used to obtain complete data records of the final beverage production process based on the adjusted execution plan, and to comprehensively evaluate the nutritional structure and taste uniformity indicators in the records to obtain the quality optimization results of the target beverage.

[0256] This embodiment of the intelligent control system for the blender achieves refined management and quality optimization in beverage production through multiple collaborative modules. The ingredient characteristic analysis and proportion calculation module utilizes an ingredient characteristic database to accurately determine the characteristic changes of each ingredient at different time points, thus clarifying the specific timing and precise proportions for adding auxiliary ingredients. The timing monitoring and measurement correction module monitors the production process in real time, dynamically adjusting the amount of auxiliary ingredients added based on the current state of the ingredients and the impact of high-temperature stirring, ensuring the accuracy of the added amount. The process matching and execution control module analyzes real-time stirring speed and temperature change data to determine whether the current process is suitable for adding ingredients, and ensures that the auxiliary ingredients are evenly distributed in the beverage through execution control. The impact prediction and strategy update module predicts potential impact parameters in subsequent processes based on data feedback on the degree of mixing uniformity, dynamically adjusting the timing and measurement values ​​of adding auxiliary ingredients to optimize the production process. Finally, the quality assessment module comprehensively evaluates the complete data record of the beverage production process to ensure that the nutritional structure and taste uniformity of the beverage reach their optimal state, achieving optimized beverage quality.

[0257] The specific embodiments of the invention have been described in detail above, but these are merely examples. The invention is not limited to the specific embodiments described above. Those skilled in the art should understand that the embodiments and descriptions in the specification are only illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent control method for a high-speed blender, characterized in that, The method includes: By using a pre-established database of ingredient properties, we can obtain data on the physical changes and chemical reactions of various ingredients involved in the production process of the target beverage. Based on the changes in the properties of each ingredient at different time points, we can determine the specific range of requirements for the timing of adding auxiliary materials. Based on the above-determined range of timing requirements for adding auxiliary materials, the production process is dynamically monitored in real time. The relevant parameters of the current state of the ingredients and the influence of high-temperature stirring are extracted from the monitoring data to obtain the optimal time window for adding auxiliary materials. To meet the metering requirements for adding auxiliary ingredients within the optimal time window, the system obtains auxiliary ingredient ratio data that matches the target beverage type by using preset standards for beverage nutritional structure and uniform taste, and determines the precise amount of each auxiliary ingredient to be added within the current time window. If the amount of auxiliary materials added in the current time window deviates from the preset standard, the amount added is corrected, and the final auxiliary material measurement value is extracted from the corrected data to determine the execution plan for time-based precise management.

2. The intelligent control method for a blender according to claim 1, characterized in that, The specific range of requirements for determining the timing of adding auxiliary ingredients based on the characteristic changes of each ingredient at different time points includes: By using a pre-set ingredient characteristic database, data on the physical changes and chemical reactions of various ingredients in the target beverage preparation process are obtained. The characteristic parameters of each ingredient are extracted using a structured query language to obtain an initial data set. For the initial dataset, analyze the physical changes and chemical reaction trends of each ingredient at different time points to determine the characteristic change curves; If the slope of the characteristic change curve is within the preset threshold range, then the time node is marked as a critical state point, and a set of critical state points is obtained. Based on the set of key state points, obtain the physical changes and chemical reactions of each ingredient at the key state points, determine the candidate time range for adding auxiliary materials, and obtain the set of candidate time ranges. By analyzing the interaction between the changes in the characteristics of auxiliary materials and ingredients through a set of candidate time ranges, the required range for the timing of adding auxiliary materials is calculated, and the time range for adding auxiliary materials is determined.

3. The intelligent control method for a blender according to claim 1, characterized in that, The optimal time window for adding excipients includes: The current food status parameters are obtained from real-time monitoring data. Using preset filtering rules, the temperature, viscosity and chemical reaction rate during the high-temperature stirring process are extracted to obtain the food status dataset. Based on the food state dataset, the influence trend of high-temperature stirring on each state parameter is calculated to obtain the state change trend. If the slope of the state change trend exceeds the preset threshold, the sliding window method is used to analyze the matching degree between the current time point of the food state and the addition of auxiliary materials, and obtain a matching degree score set. By using a matching score set, the optimal time window for adding excipients is predicted, and the optimal time range for addition is determined.

4. The intelligent control method for a blender according to claim 1, characterized in that, The determination of the precise addition amount of each excipient within the current time window includes: By using a pre-set beverage type database, the nutritional structure and taste uniformity standards of the target beverage type are obtained, and an initial dataset of auxiliary ingredient ratios is generated. Process condition data are obtained within the optimal time window, and temperature parameters and stirring rate are extracted to obtain a process environment dataset. If the temperature parameters and stirring rate in the process environment dataset deviate from the preset standard threshold beyond the limit, the initial dataset of auxiliary material proportions will be adjusted to obtain the optimized dataset of auxiliary material proportions. Based on the optimized auxiliary material ratio dataset and the process conditions within the time window, a weighted average method is used to calculate the addition amount of each auxiliary material, thus obtaining a set of precise addition amounts.

5. The intelligent control method for a blender according to claim 1, characterized in that, The implementation plan for precise time-sharing management includes: If the amount of auxiliary materials added in the current time window deviates from the preset standard, the deviation value is calculated and the auxiliary material addition deviation dataset is obtained. The deviation values ​​are extracted from the excipient addition deviation dataset, and the excipient addition amount is adjusted using a weighted calculation method to obtain the corrected excipient metering dataset. Based on the revised auxiliary material metering dataset and combined with the process conditions within the time window, a time-sharing execution scheme dataset is obtained by generating control parameters for precise time-sharing management. If the matching degree between the control parameters in the time-sharing execution scheme dataset and the real-time process conditions is lower than the preset threshold, then process feedback data is obtained from real-time monitoring through data extraction methods to obtain the process verification dataset.

6. The intelligent control method for a blender according to claim 1, characterized in that, Also includes: Based on the time-sharing precision management plan, real-time stirring speed and temperature change data in the production process are obtained. The matching degree of these data with the timing of adding auxiliary materials is analyzed to obtain a judgment result on whether the current process is suitable for performing the addition operation. If the analysis results indicate that the current process is suitable for adding auxiliary materials, an addition instruction is sent to the execution unit, and relevant data on the degree of mixing uniformity are extracted from the instruction execution feedback to determine whether the auxiliary materials have been evenly distributed in the beverage. Based on the data feedback on the degree of mixing uniformity, we obtain the parameters that may be affected by high-temperature stirring in the subsequent production process, and conduct predictive analysis on these parameters to determine whether it is necessary to adjust the timing or measurement value of subsequent auxiliary materials. If the predictive analysis determines that the timing or measurement value of subsequent auxiliary materials needs to be adjusted, the control strategy of the production process is updated, new time windows and addition amount data are extracted from the updated strategy, and the adjusted execution plan is determined. Based on the adjusted implementation plan, complete data records of the final beverage production process are obtained. The nutritional structure and taste uniformity indicators in the records are comprehensively evaluated to obtain the quality optimization results of the target beverage.

7. The intelligent control method for a blender according to claim 6, characterized in that, The determination result of whether the current process is suitable for performing the add operation includes: Real-time stirring speed and temperature change data are obtained from dynamic monitoring, and time series analysis is used to extract data features to obtain a time series feature set of stirring speed and temperature changes; Based on the time series feature set, the matching degree between stirring speed and temperature changes and the timing of additive addition is analyzed to obtain a matching degree score set; If the score in the matching score set is lower than the preset threshold, real-time process parameter data is obtained from dynamic monitoring, and process constraints are extracted through data processing methods to obtain a process constraint dataset. Based on the process constraint dataset, the matching score set is adjusted, and the weighted average method is used to generate the optimized matching score set. Optimization scores are extracted from the optimization score set, and it is determined whether the optimization scores meet the execution conditions for adding excipients, thus obtaining the feasibility judgment result of the addition operation.

8. The intelligent control method for a blender according to claim 6, characterized in that, Determining whether the excipients have been evenly distributed in the beverage includes: By obtaining feedback data of the addition instruction from the execution unit, and processing the information related to the uniform mixing in the feedback data, a preliminary assessment result of the excipient distribution is obtained. Based on the preliminary assessment results, a data filtering method was used to remove noise from the feedback data, resulting in purified and uniformly mixed data. If the purified and uniformly mixed data does not reach the preset uniformity threshold, the distribution status will be further detected by data analysis tools to determine the specific areas of uneven distribution. For areas with unevenly distributed information, generate local adjustment instructions, send targeted hybrid operations to the execution unit, and obtain the adjusted feedback data; New uniformity information is extracted from the adjusted feedback data, the new uniformity is scored, and it is determined whether the uniform distribution condition is met. If the score is still lower than the preset threshold, a secondary adjustment instruction is generated based on the score result, and the mixed operation parameters are updated through the execution unit to obtain the final distribution state data; Based on the final distribution data, a threshold comparison method is used to verify the distribution of excipients in the beverage to determine whether the distribution of excipients has reached the expected uniform state.

9. The intelligent control method for a blender according to claim 6, characterized in that, The determination of whether the timing or measurement value of subsequent excipient addition needs to be adjusted includes: High-temperature stirring parameters are extracted from the feedback data on the degree of mixing uniformity, and the parameter variation trend is predicted by time series analysis to obtain the parameter fluctuation range; Based on the parameter fluctuation range, a preset threshold comparison method is used. If the fluctuation range exceeds the threshold, an adjustment instruction for the timing of adding excipients is generated to determine the adjusted addition time. By adjusting the addition time point, real-time parameter monitoring data is obtained, and stirring influencing factors are extracted from the monitoring data to obtain the distribution status of influencing factors; Based on the distribution of influencing factors, a model is built to examine the relationship between the metering value of auxiliary materials and the mixing effect, and suggestions for optimizing the metering value are obtained.

10. An intelligent control system for a high-speed blender, used to implement the above-mentioned intelligent control method for a high-speed blender, characterized in that, The system includes: The ingredient characteristic analysis and proportion calculation module is used to obtain physical changes and chemical reaction data of various ingredients involved in the production process of the target beverage through a pre-established ingredient characteristic database. Based on the characteristic changes of each ingredient at different time points, it determines the specific range of requirements for the timing of adding auxiliary materials. Based on the auxiliary material addition measurement requirements within the optimal time window, it obtains auxiliary material proportion data matching the target beverage type through preset beverage nutritional structure and taste uniformity standards, and determines the precise addition amount of each auxiliary material within the current time window. The timing monitoring and measurement correction module dynamically monitors the production process in real time based on the determined range of timing requirements for adding auxiliary materials. It extracts relevant parameters of the current state of ingredients and the impact of high-temperature stirring from the monitoring data to obtain the optimal time window for adding auxiliary materials. If there is a deviation between the amount of auxiliary materials added in the current time window and the preset standard, the amount of addition is corrected. The final measurement value of auxiliary materials is extracted from the corrected data to determine the execution plan for precise time-sharing management. The process matching and execution control module, based on the time-sharing precise management scheme, acquires real-time stirring speed and temperature change data in the dynamic production process. It analyzes the matching degree of these data with the timing of adding auxiliary materials to obtain a judgment result on whether the current process is suitable for adding auxiliary materials. If the judgment result indicates that the current process is suitable for adding auxiliary materials, it sends an addition command to the execution unit and extracts relevant data on the degree of mixing uniformity from the command execution feedback to determine whether the auxiliary materials have been evenly distributed in the beverage. The impact prediction and strategy update module obtains the parameters that may be affected by high-temperature stirring in the subsequent production process based on the data feedback on the degree of mixing uniformity. It performs predictive analysis on these parameters to determine whether the timing or measurement value of subsequent auxiliary materials needs to be adjusted. On the other hand, if the predictive analysis determines that the timing or measurement value of subsequent auxiliary materials needs to be adjusted, it updates the control strategy of the production process, extracts new time windows and addition amount data from the updated strategy, and determines the adjusted execution plan. The quality assessment module is used to obtain complete data records of the final beverage production process based on the adjusted execution plan, and to comprehensively evaluate the nutritional structure and taste uniformity indicators in the records to obtain the quality optimization results of the target beverage.

Images