Production control system of compound additive

Abstract

The invention provides a production control method and system for a compound additive, and relates to the technical field of data processing, and the method comprises the steps: data collection: collecting the ratio data, production process parameters and quality parameters of each component of the compound additive, integrating the parameters into a complete production data set, and inputting the complete production data set into a data preprocessing module for subsequent processing; data preprocessing: preprocessing the collected data, and generating a processed data set; data analysis: analyzing the data in the data set, and identifying the key influence relationship between the quality parameters of the finished product and the proportion of each component of the compound additive; dynamic feedback: dynamically adjusting the ratio of each component according to data monitored in real time in the production process; the problem that in the prior art, quality parameters of the same product fluctuate in the production process, and then the final taste consistency is affected is solved.

Description

Technical Field

[0001] The present application relates to the technical field of data processing, and in particular to a production control system for compound additives. Background Art

[0002] In the field of food processing, in order to improve the quality of processed meat products (such as sausages, fish tofu, hot pot meatballs such as tempura) and frozen prepared products, compound food additives are usually used to improve the key quality parameters of the products such as elasticity, crispness, and antifreeze. These compound additives are generally mixed in a specific proportion by a variety of food additives (such as konjac gum, seaweed powder, alginate, etc.). However, the inventors found in the process of realizing the embodiments of the present application that the production and use of existing compound additives are difficult to ensure the consistency of the finished product: due to the changes in various parameters in the processing loop of different batches of processed meat products, the quality parameters of the same product (such as elasticity, brittleness, etc.) may fluctuate during the production process, thereby affecting the final consistency of taste.

[0003] Therefore, it is difficult for existing compound additive control systems to identify and adjust the proportion of ingredients that cause quality deviations in real time during the production process, resulting in the problem of being unable to achieve high-precision and high-consistency quality control. Summary of the invention

[0004] The purpose of this application is to provide a production control system for compound additives to solve the problem of fluctuations in quality parameters (such as elasticity, brittleness, etc.) of the same product during the production process in the prior art, thereby affecting the final taste consistency; In view of the above problems, the present application provides a production control method and system for compound additives, because the inventors found that there are many factors that affect the consistency of product taste, such as changes in the processing environment temperature, different batches of processing raw materials, and changes in various parameters during processing, which can all lead to the problem that the final quality of products from different batches using the same ratio is uneven. This problem is a long-term problem and may require several batches of processing before the problem gradually emerges. However, due to too many factors affecting product quality, it is very difficult to make the quality of products from different batches close to the same by adjusting the processing parameters. Therefore, the inventors solve the above problems by designing a production control method and system for compound additives, and the specific solution is as follows.

[0005] A production control method for a compound additive comprises: Data collection: Collect the ratio data, production process parameters and quality parameters of each component of the compound additive, integrate them into a complete production data set, and input them into the data preprocessing module for subsequent processing; Use unified timestamps to integrate collected data and ensure that all data accurately correspond to the same time node; Data preprocessing: Preprocess the collected data and generate a processed data set; Data Analysis: Analyze the data in the dataset to identify the key influencing relationships between the quality parameters of the finished product and the proportions of the various ingredients in the compound additives; Dynamic feedback; During the production process, the ratio of each ingredient is dynamically adjusted according to real-time monitoring data.

[0006] Wherein, the data preprocessing further includes: Convert data from different sources in the production data set into a unified format; Integrate various data in the production data set, and synchronize the composition ratio, process parameters, quality parameters and environmental data into a table format with the same timestamp record; Identify and remove abnormal data in the original data file data; Normalize the data in the original data file; Mark the data in batches according to production batches and finished product parameters; Merge the processed data in time and batch sequence to generate processed data sets and store them in a data warehouse or database; The data analysis includes: Collecting the component ratio information and finished product quality parameter information in the pretreatment results and grouping them by batches; A multiple regression model was established for each component ratio and finished product quality parameters, and the regression coefficients of each component were analyzed to obtain the direct influence of each component on the quality parameters; Wherein, the data analysis further includes: Based on the regression model, small adjustments are made up and down to the proportion of each ingredient, and the changes in the quality parameters of the finished product caused by these adjustments are calculated; Set the composition ratio to change within a certain range, observe the corresponding impact on the quality parameters, and calculate the sensitivity coefficient; Based on the results of regression analysis and sensitivity analysis, predict the impact of ingredient adjustments on finished product quality.

[0007] Wherein, the dynamic feedback module comprises: Obtain various quality parameters of the finished product, Analyze the changes in various quality parameters of finished products; Automatically fine-tune the proportion of ingredients according to the changes in various quality parameters so that the quality of the finished product remains consistent; Wherein, the method further comprises: History recording and optimization are used to record the parameter changes and adjustment effects of each adjustment process, so as to optimize the adjustment strategy in subsequent production.

[0008] A production control system for compound additives, comprising: Data acquisition module: used to collect the ratio data, production process parameters and quality parameters of each component of the compound additive, integrate them into a complete production data set, and input them into the data preprocessing module for subsequent processing; Data preprocessing module: used to preprocess the data collected by the data acquisition module and then transmit it to the data analysis module; Data analysis module: used to analyze and process the data transmitted by the pre-processing module, and identify the key influencing relationship between the quality parameters of the finished product and the proportions of each component of the compound additive; The dynamic feedback module is used to dynamically adjust the ratio of each ingredient according to real-time monitoring data during the production process.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages: Through real-time data collection and closed-loop feedback control systems, this solution can dynamically adjust the compounding ratio during the production process to ensure that the quality parameters of the finished product remain stable and consistent, reduce differences between production batches, and thus improve the taste and quality consistency of the product.

[0010] This solution establishes a feedback control mechanism based on real-time data, which enables the system to respond quickly to deviation parameters and adjust the compounding ratio in time to avoid batch inconsistency problems caused by delayed adjustment, thus achieving rapid response and real-time control.

[0011] Through the generation and implementation of intelligent adjustment plans, this solution reduces material consumption and unnecessary rework, optimizes resource utilization and production costs by optimizing the compounding ratio while ensuring the quality of the finished product.

[0012] The closed-loop feedback mechanism and data storage function of this solution provide detailed data support for subsequent data model optimization. Through the long-term accumulation and analysis of collected data, the prediction accuracy and adjustment efficiency of the system can be further improved, and the production control model can be continuously optimized.

[0013] In summary, this solution greatly improves the quality consistency and production efficiency of finished products through an intelligent, closed-loop feedback controlled compound additive production control system, achieving real-time, accurate, and cost-effective control of compound additives.

[0014] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0016] Figure 1 A schematic diagram of a production control method for a compound additive in this application; Figure 2 This is a schematic diagram of the structure of a production control system for a compound additive in this application; Explanation of reference numerals: data acquisition module 11 , data preprocessing module 12 , data analysis module 13 , dynamic feedback module 14 , history recording and optimization module 15 . DETAILED DESCRIPTION

[0017] This application provides a production control system for compound additives to solve the technical problem in the prior art that it is difficult to capture the dynamic changes in employee performance and the complex relationships within the team, resulting in poor efficiency in enterprise management due to the usual reliance on static data or simple statistical methods for employee performance ranking and team performance analysis. By obtaining team performance data, intercepting positive and negative performance segments, and combining employee expected goals with enterprise training data, a competitive and balanced optimization layer is established, and enterprise development training data is merged with employee basic training data. Combined with the initial segmentation of employee performance and the global optimization strategy, team planning and training plans are dynamically updated, thereby improving the overall management efficiency of the enterprise.

[0018] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0019] For examples, please see the attached Figure 1 The present application provides a production control system for a compound additive, wherein the production control method for the compound additive comprises: S100 data collection, this step includes: S110 collects the ratio data, production process parameters and quality parameters of each component of the compound additive, integrates them into a complete production data set, and inputs them into the data preprocessing module for subsequent processing; S120 uses a unified timestamp to integrate collected data, ensuring that all data accurately corresponds to the same time node; Specifically; It can obtain the ratio data of each component of its compound additives by manual input or directly from its production system, and then record the ratio data into the ratio database according to the user, ingredient name, quantity and unit to ensure the accuracy of the ratio; It can also collect production process parameters while collecting data. It can install sensors at key process nodes on the production line, such as installing temperature, humidity and pressure sensors on the mixer.

[0020] Collect and monitor various parameters in real time through the PLC (Programmable Logic Controller) system and send the data to the central database; For product quality parameter collection, the hardness, elasticity, chewiness, cohesiveness, resilience and other quality parameters of the products produced by the same batch of compound additives can be collected, and the collected quality parameter data can be uploaded to the system and compared with the preset quality standards. If quality deviation is detected (such as hardness deviating too much from the standard hardness), it is considered that adjustment is needed; Integrate the ratio data of each component of compound additives, production process parameters and product quality parameters, and synchronize the data through a unified timestamp to ensure data consistency and timeliness; Specifically, it can be achieved through: The central control system of the production line generates a unique timestamp for each piece of data to ensure that all data is aligned at the same time node.

[0021] Each parameter data is stored in order by timestamp to facilitate subsequent analysis; The system integrates the timestamp-matched data into a complete data table, including ratio, process, and quality parameters.

[0022] Check the integrated data to ensure that there are no omissions or deviations. If there are abnormal timestamps, the system will automatically prompt and realign them. The integrated data sets are stored by batch number and transferred to the data preprocessing module for further data cleaning and conversion to ensure an accurate and complete data basis for subsequent analysis; The specific operations are as follows: The integrated data set is backed up to the master database through the system and archived by batch number; The system automatically backs up regularly to ensure data security and facilitate subsequent query and traceability; The stored complete data set is then transferred to the preprocessing module, and the system automatically performs the preprocessing steps.

[0023] The main purpose of step S100 of this application is to complete the data collection and integration work in the production process of compound additives, from the collection of ratios, processes, and quality parameters to unified timestamp integration, and finally form a complete data set, laying a solid foundation for subsequent data preprocessing and analysis.

[0024] S200 data preprocessing: preprocess the collected data and generate processed data sets. It mainly forms a structured and unified format processed data set by standardizing the collected data, removing abnormal data, normalizing, batch marking, etc., to provide high-quality input data for subsequent analysis; Wherein, the S200 data preprocessing further includes: S210 converts data from different sources in the production data set into a unified format, including field name, data type, unit, etc.; and checks whether the format of each field meets the unified standard. If there is data that does not meet the standard, it will be automatically converted or manually corrected; S220 integrates various types of data in the production data set, and synchronizes ingredient ratios, process parameters, quality parameters and environmental data into a table format with the same timestamp record.

[0025] Specifically: Use timestamps to align data from different sources to ensure that records at the same time point are integrated into one row of data. For example, parameters such as temperature, humidity, hardness, and elasticity are all recorded at the same time point; multiple records with the same timestamp are merged into a single row, and further merged by batch, and recorded in a table format; S230 identifies and removes abnormal data in the original data file data; That is, determine the reasonable range of each parameter; Use anomaly detection algorithms (such as the 3σ criterion) or set upper and lower thresholds to mark and remove abnormal data that exceeds the range; If abnormal data is found, the system will automatically remove it and record the cause of the abnormality; S240 normalizes the data in the original data file.

[0026] Specifically, to facilitate data analysis and model training, the data is normalized so that data of different dimensions are normalized to the same numerical range; Select a normalization method based on the data type. Common normalization methods include minimum-maximum normalization and Z-score normalization; After normalizing each data item, store the normalized result for subsequent analysis; S250 marks the data in batches according to production batches and finished product parameters; That is, a unique batch number is generated based on factors such as production time and formula changes; Tag each piece of data by batch number and classify the data into the corresponding batch; S260 merges the processed data according to time and batch sequence to generate a processed data set and stores it in a data warehouse or database; That is, sort the data by time and batch to ensure the continuity and integrity of the data set; The merged data is stored in a structured database in batches and chronological order; Store the merged data set in the data warehouse and set up automatic backup to ensure data security and stability; The raw data is converted, integrated, anomaly eliminated, normalized, batch labeled and stored through the data preprocessing process in step S200 to form a structured and queryable data set, providing high-quality input data for subsequent data analysis. This series of steps ensures that the data is accurate, consistent in format and traceable for subsequent analysis.

[0027] The S300 data analysis includes: S310 collects the component ratio information and finished product quality parameter information in the pretreatment result and groups them by batch; That is, extract the proportion data of each component (such as the proportion of konjac flour, carrageenan content) and the quality parameters of the finished product (such as elasticity, hardness, etc.) from the pretreatment results; Group the data by production batches so that each batch of data contains the ratio and corresponding quality parameters. This step facilitates the subsequent analysis of the relationship between ingredients and quality within and between batches; S320 establishes a multiple regression model for each component ratio and finished product quality parameters, and analyzes the regression coefficient of each component to obtain the direct influence of each component on the quality parameters; Specifically, it can use multiple linear regression, nonlinear regression, or machine learning regression methods. Use batch data sets to train regression models, taking component ratios as input variables and finished product quality parameters as output variables, and establish a quantitative relationship model between quality parameters and the ratios of each component; Analyze the regression coefficient of each ingredient to quantify the direct impact of each ingredient on the quality parameter. A high regression coefficient indicates that the ingredient has a significant impact on the quality of the finished product; Based on the regression model, S330 makes small adjustments up and down to the proportion of each component and calculates the changes in the quality parameters of the finished product caused by these adjustments to further verify the impact of the components; Specifically, a small adjustment range (e.g., ±5%) is set according to the production requirements of the component ratio, and the ratio within this range is input into the model for prediction; Use regression models to calculate the changes in finished product quality parameters caused by proportional adjustments and record the trend of changes; Compare the results of each component adjustment and confirm whether the regression coefficient accurately reflects the degree of influence of the component on the quality parameter; S340 sets the variation of the component ratio within a certain range and observes the corresponding impact on the quality parameter to calculate the sensitivity coefficient, so that it can be calculated by adjusting the component ratio within a larger range and observing the sensitivity of the component to the quality parameter of the finished product; Specifically; Vary the composition ratio by ±10-20% to assess composition sensitivity over a wide range Calculate the impact of the adjustment ratio on the quality parameters of the finished product; Ingredients with higher sensitivity coefficients have a more significant impact on quality parameters and are suitable for key monitoring and optimization in the subsequent adjustment process; S350 predicts the impact of ingredient adjustments on finished product quality based on regression analysis and sensitivity analysis results; Specifically, the target quality parameter values ​​of the finished product (such as setting the elasticity target to 9.00 and the hardness target to 7.00) can be determined as the target for adjusting the component ratio.

[0028] Using regression models and sensitivity coefficients, determine the specific proportion of ingredient adjustments to achieve the set quality parameters for the finished product; Before the system is officially used, it can conduct a small batch trial production on the predicted ratio to verify whether the quality of the finished product meets expectations. If not, the model parameters can be adjusted further. This application first groups the pre-processed ingredient ratio and finished product quality parameter data through data analysis step S300, and then analyzes the regression coefficient of the ingredient based on the multivariate regression model to identify the key influencing factors. After that, through small and large ratio adjustments, the sensitivity of the ingredient is evaluated, the sensitivity coefficient is calculated, and finally the influence of the ingredient ratio on the quality parameters is predicted, providing a scientific basis for the production process and ensuring the consistency of the finished product quality.

[0029] S400 dynamic feedback; During the production process, the ratio of each ingredient is dynamically adjusted according to real-time monitoring data.

[0030] The S400 dynamic feedback includes: S410 obtains various quality parameters of finished products to ensure the timeliness and accuracy of data and provide a basis for subsequent adjustments; It can detect various quality parameters of the finished product through TPA test parameters of the texture analyzer, and obtain various quality parameters of the finished product through manual or systematic methods. It can obtain various quality parameters of this batch of finished products through sampling inspection; S420 analyzes the changes in various quality parameters of the finished products; That is, according to the quality requirements of the product, set the target range of each quality parameter; Compare current quality parameters with target range in real time and calculate deviation value; Determine whether any quality parameters are outside the target range. If the deviation exceeds the preset limit, the ingredients need to be adjusted; if the parameter is within the range, continue monitoring; S430 automatically fine-tunes the proportion of ingredients according to the changes in various quality parameters so that the quality of the finished product remains consistent; That is, according to the deviation of quality parameters, the proportion of each component is automatically adjusted to restore the quality of the finished product to the target range; Specifically; According to the deviation value and sensitivity analysis results, set the adjustment range of each component. For example, if the sensitivity analysis shows that konjac flour has a greater impact on elasticity, the proportion of konjac flour should be adjusted first; According to the regression model and sensitivity coefficient, determine the specific proportion of adjustment. Assuming that the elasticity parameter is lower than the target, increase the proportion of konjac flour by 1-2% to compensate for the lack of elasticity; The system sends the adjusted ratio to the batching equipment of the production line through the control module to achieve automatic fine-tuning of the proportion of each ingredient; When the next batch of finished products passes the test, verify whether the adjustment has achieved the expected effect. If the adjustment is successful, continue production at the new ratio; if it does not reach the target range, further fine-tune; Wherein, the method further comprises: S500 history recording and optimization is used to record the parameter changes and adjustment effects of each adjustment process, so as to optimize the adjustment strategy in subsequent production.

[0031] That is, the system records the proportion of ingredients for each fine-tuning, the quality parameter values ​​before and after the adjustment, and the final effect, so as to track the adjustment history; The data of each adjustment is stored in the database to form a historical record of adjustments and quality parameter changes, providing data support for subsequent further optimization; Based on historical data, regularly analyze the adjustment effects, identify effective component ratio adjustment patterns, and optimize the settings of regression models and sensitivity coefficients.

[0032] Embodiment 2 Based on the same inventive concept as the production control method of a compound additive in the above embodiment, Figure 2 As shown, the present application provides a production control system for compound additives, wherein the system comprises: Data acquisition module 11: used to collect the ratio data, production process parameters and quality parameters of each component of the compound additive, integrate them into a complete production data set, and input them into the data preprocessing module for subsequent processing; Data preprocessing module 12: used to preprocess the data collected by the data acquisition module and then transmit it to the data analysis module; Data analysis module 13: used to analyze and process the data transmitted by the pre-processing module, and identify the key influencing relationship between the quality parameters of the finished product and the proportions of each component of the compound additive; A dynamic feedback module 14 is used to dynamically adjust the ratio of each component according to real-time monitoring data during the production process; The history recording and optimization module 15 is used to record the parameter changes and adjustment effects of each adjustment process so as to optimize the adjustment strategy in subsequent production.

[0033] Wherein, the data acquisition module 11 includes: Component ratio acquisition unit: used to obtain the ratio data of each component of the compound additive by manual input or directly from its production system; Production process parameter collection unit: used to record key process parameters in the production process, such as mixing time, temperature, humidity, pressurization time, etc.; The quality parameter acquisition unit collects quality parameters through online monitoring equipment or manual testing equipment and integrates the data into the system. Some quality parameters may require intermittent measurement using professional testing equipment.

[0034] Data Integration Unit: Synchronizes and integrates the data on ingredient ratios, production process parameters, and quality parameters to form a complete set of production data sets, and ensures the temporal consistency and integrity of the data, providing a basis for subsequent data analysis and dynamic adjustments.

[0035] In the data acquisition module 11, each unit collects data of different types in production. Finally, the data integration unit compiles this information into a complete data set and inputs it into the system. It also uses a unified timestamp to integrate the collected data to ensure that each data accurately corresponds to the same time node, thereby providing high-quality data support for data preprocessing and analysis.

[0036] Wherein, the data preprocessing module 12 includes: Data cleaning unit: used to detect and process missing values, outliers, and erroneous data in the original data to ensure the accuracy and completeness of the data, that is, to clean the data through rule setting (such as range detection, threshold setting) and statistical methods (such as replacing missing values ​​with mean and median, deleting outliers, etc.).

[0037] Data conversion unit: used to convert data from different sources in the production data set into a unified format, including field name, data type, unit, etc.; and check whether the format of each field meets the unified standard. If there is data that does not meet the standard, it will be automatically converted or manually corrected; Integrate various data in the production data set, and synchronize the composition ratio, process parameters, quality parameters and environmental data into a table format with the same timestamp record; Identify and remove abnormal data in the original data file data. If abnormal data is found, the system will automatically remove it and record the cause of the abnormality; Data normalization unit; used to normalize or standardize data to eliminate the impact between different dimensions and magnitudes, making data analysis more effective; After normalizing each data item, store the normalized result for subsequent analysis; Feature extraction unit; used to extract features that have a significant impact on the quality of the finished product from the original data to reduce data dimensions and computational complexity, that is, to identify and retain key features through statistical methods, correlation analysis or data mining technology, and remove features that have little impact on the results or are redundant.

[0038] Data synthesis unit; used to generate new data features or comprehensive indicators based on data integration, so as to facilitate the subsequent analysis module to deeply explore data relationships, that is, to generate new composite indicators through mathematical operations (such as addition, subtraction, multiplication, division, weighted average, etc.) or logical operations (such as conditional judgment) on existing data, such as generating a score representing the comprehensive quality, to ensure that the new features after data synthesis can effectively represent the quality characteristics of the finished product, so as to enhance the depth and breadth of data analysis.

[0039] Data grouping unit: Generate unique batch numbers based on production time, formula changes, etc. Tag each piece of data by batch number and classify the data into the corresponding batch; It is used to group data and generate unique batch numbers according to different production batches, production time and ratio schemes, add tags to each data according to the batch number, classify the data into corresponding batches, and merge the processed data according to time and batch sequence to generate processed data sets, and store them in a data warehouse or database to facilitate subsequent data analysis modules to perform classification and comparative analysis, that is, divide the data set by labels or conditions, such as grouping by time, production batch or specific parameter range, so that subsequent analysis modules can perform targeted processing, so that the data grouping standards are consistent with the analysis objectives, ensure comparability between data groups, and do not lose useful detail information.

[0040] After the preprocessing module, the raw data collected in the data acquisition module can be converted into high-quality, standardized analysis data, thereby greatly improving the analysis efficiency and accuracy of the data analysis module; Wherein, the data analysis module 13 includes: Statistical analysis unit: used to collect the component ratio information and finished product quality parameter information in the pre-processing results, and group them by batches so that the data of each batch contains the ratio and corresponding quality parameters; Correlation analysis unit: Through quantitative correlation analysis methods, the significant influencing factors of the compound additive ratio on the quality of the finished product are identified, so that the distribution characteristics and basic relationships of the data can be understood through basic statistical description and analysis. Specifically, the distribution of each parameter can be evaluated by calculating statistical indicators such as mean, variance, standard deviation, maximum value, minimum value, etc.; the correlation analysis between the ratio of ingredients and quality parameters (such as Pearson correlation coefficient, Spearman correlation coefficient, etc.) will also be carried out, and the correlation coefficient between the ratio of ingredients and the quality parameters of the finished product will be calculated to determine which ingredients have a greater impact on the quality parameters, so as to judge the preliminary impact of each ingredient; Regression analysis unit: constructs a regression model between ingredient ratios and finished product quality parameters in order to predict the quality of finished products under different ratios, i.e., uses multiple linear regression, nonlinear regression, or machine learning regression methods (such as decision tree regression, support vector regression, etc.) to establish a quantitative relationship model between quality parameters and each ingredient ratio; Use the batch dataset to train a regression model with ingredient ratios as input variables and finished product quality parameters as output variables; Analyze the regression coefficient of each ingredient to quantify the direct impact of each ingredient on the quality parameter. A high regression coefficient indicates that the ingredient has a significant impact on the quality of the finished product; Factor analysis unit: used to simplify data dimensions and identify a few key factors that represent the main relationship between ingredient ratios and quality parameters. That is, multiple components and parameters are aggregated into a few factors through factor analysis methods (such as principal component analysis PCA, factor analysis FA, etc.) to explain the main sources of variation in quality parameters. The factor analysis results can help understand the interaction of different ingredients in compound additives, reduce model complexity and enhance interpretability.

[0041] Sensitivity analysis unit: used to analyze the sensitivity of changes in the proportion of each component to the quality parameters of the finished product, so as to identify the component with the most significant impact on the quality, that is, by gradually changing the proportion of a single component, observing the change in the quality of the finished product, and determining the sensitivity of the quality parameters to each component; usually, local sensitivity analysis, global sensitivity analysis or simulation test methods can be used to help identify key proportion components through sensitivity analysis, and then predict the impact of component adjustment on the quality of the finished product based on the results of regression analysis and sensitivity analysis, so as to assist in determining the specific proportion of component adjustment so that the finished product can reach the set quality parameters; Through the collaborative work of these units, the data analysis module can deeply analyze the relationship between the quality of the finished product and the proportion of compound additives, providing a scientific basis and data support for the dynamic regulation and optimization of the production process.

[0042] Wherein, the dynamic feedback module 14 includes: Real-time data monitoring unit: obtain various quality parameters of finished products; Data processing and analysis unit: Analyze the changes in various quality parameters of finished products, that is, set the target range of various quality parameters according to the quality requirements of the products; Compare current quality parameters with target range in real time and calculate deviation value; Determine whether any quality parameters are outside the target range. If the deviation exceeds the preset limit, the ingredients need to be adjusted; if the parameter is within the range, continue monitoring; Decision-making unit: used to generate specific ratio adjustment plans based on the changes in various quality parameters in the analysis results; that is, combining the prediction model of the data analysis module and the current production status, the unit calculates the ideal adjustment range of the ingredient ratio. The control algorithm (such as PID control, fuzzy control or decision-making algorithm based on machine learning) can be used to generate the optimal ratio adjustment plan and fine-tune the various components of the compound additive.

[0043] Execution control unit: converts the adjustment plan into actual operation instructions of the production equipment to automatically complete the ratio adjustment. That is, the system sends the adjusted ratio to the batching equipment of the production line through the control module to achieve automatic fine-tuning of the proportion of each component; Feedback monitoring unit: tracks the effect of adjustments and provides feedback data to verify the effect of decisions. That is, after the execution control unit completes the ratio adjustment, the unit checks the changes in product quality after the adjustment. By comparing with the target parameters, the feedback monitoring unit evaluates the effect of the adjustment to confirm whether the expected quality is achieved. The feedback results can be used as a reference for the next adjustment to form a closed-loop control. At the same time, the adjustment data can be automatically recorded to provide a basis for subsequent optimization; The abnormality handling unit is used to automatically trigger an alarm and start an emergency plan when the unit detects parameters that are beyond the normal range. For example, when it is monitored that a certain ingredient ratio is out of control or the quality parameters fluctuate greatly, the ratio adjustment is automatically suspended and an abnormal prompt is issued.

[0044] Through the cooperation of these units, the dynamic feedback module can respond and adjust the ratio in real time during the production process, thus ensuring the quality of the finished product and the stability of production. This closed-loop control mechanism helps to maintain the high quality and consistency of products in a complex and changing production environment.

[0045] Among them, the history record and optimization module includes: Historical data recording unit: records the changes of all parameters in the production process, including detailed data such as ingredient ratio adjustment, production parameters, environmental parameters and production results. That is, after each adjustment operation is completed, the unit automatically collects and stores the key parameter values ​​before and after the adjustment, such as the ratio of each ingredient, the time of adjustment, the reason for adjustment, the adjustment range, etc.; Effect feedback recording unit: records the changes in quality indicators after each adjustment, which is used to evaluate the effect of the adjustment. That is, in the production process after the adjustment, the unit continuously monitors the quality parameters of the finished product (such as hardness, elasticity, etc.) and records the specific values ​​before and after the adjustment. The unit compares the adjustment effect with the expected target in order to analyze the adjustment effect.

[0046] Data archiving and retrieval unit: Systematically store the recorded historical adjustment data for subsequent review and analysis, such as archiving by adjustment batch, time, ingredient ratio, etc. The system supports keyword retrieval, which makes it easy for operators to find similar production situations and adjustment strategies.

[0047] Data Analysis Unit: By analyzing historical adjustment data, we can identify key factors and trends that affect quality and provide a basis for optimization strategies.

[0048] Based on the archived data, this unit can cooperate with the data analysis module to use the archived data as new data for further analysis through the data analysis module, so that it can continuously update the results of its regression analysis and sensitivity analysis. The unit regularly compares the latest production results with the historical optimal results, adjusts the algorithm model parameters, updates the optimization strategy library, and enhances the system's automatic adjustment capabilities to further increase the accuracy of the adjustment.

[0049] Through the cooperation of these units, a complete closed-loop system is formed, which enables the history recording and optimization modules to continuously accumulate data and optimize adjustment strategies during the production process, thereby improving the stability of the production process and the consistency of the finished product.

[0050] Any of the above methods or steps can be stored as computer instructions or programs in various types of computer memories, and the computer instructions or programs can be recognized by various types of computer processors to implement any of the above methods or steps; Secondly, the above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0051] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A production control method for a compound additive, characterized in that: include: Data collection: Collect the ratio data, production process parameters and quality parameters of each component of the compound additive, integrate them into a complete production data set, and input them into the data preprocessing module for subsequent processing; Data preprocessing: preprocess the collected data and generate processed data sets; Data analysis: Analyze the data in the data set to identify the key influencing relationships between the quality parameters of the finished product and the proportions of the various ingredients in the compound additives; Dynamic feedback: dynamically adjust the ratio of each ingredient according to real-time monitoring data during the production process.

2. A production control system for compound additives as claimed in claim 1, characterized in that: The data preprocessing further includes: Convert data from different sources in the production data set into a unified format; Integrate various data in the production data set, and synchronize the composition ratio, process parameters, quality parameters and environmental data into a table format with the same timestamp record; Identify and remove abnormal data in the original data file data; Normalize the data in the original data file; Mark the data in batches according to production batches and finished product parameters; The processed data is merged according to time and batch sequences to generate processed data sets and stored in the data warehouse or database.

3. A production control system for compound additives as claimed in claim 1, characterized in that: The data analysis includes: Collecting the component ratio information and finished product quality parameter information in the pretreatment results and grouping them by batches; A multiple regression model was established for each component ratio and finished product quality parameters, and the regression coefficient of each component was analyzed to obtain the direct influence of each component on the quality parameters.

4. A production control system for compound additives as claimed in claim 1, characterized in that: The data analysis further includes: Based on the regression model, small adjustments are made up and down to the proportion of each ingredient, and the changes in the quality parameters of the finished product caused by these adjustments are calculated; Set the composition ratio to change within a certain range, observe the corresponding impact on the quality parameters, and calculate the sensitivity coefficient; Based on the results of regression analysis and sensitivity analysis, predict the impact of ingredient adjustments on finished product quality.

5. The production control system of a compound additive according to claim 1, characterized in that: The dynamic feedback module comprises: Obtain various quality parameters of the finished product, Analyze the changes in various quality parameters of finished products; Automatically fine-tune the proportion of ingredients according to changes in various quality parameters so that the quality of the finished product remains consistent.

6. A production control system for compound additives as claimed in claim 1, characterized in that: The method further comprises: History recording and optimization are used to record the parameter changes and adjustment effects of each adjustment process, so as to optimize the adjustment strategy in subsequent production.

7. A production control system for compound additives, the system being used to execute the method according to any one of claims 1 to 6, characterized in that: include: Data acquisition module: used to collect the ratio data, production process parameters and quality parameters of each component of the compound additive, integrate them into a complete production data set, and input them into the data preprocessing module for subsequent processing; Data preprocessing module: used to preprocess the data collected by the data acquisition module and then transmit it to the data analysis module; Data analysis module: used to analyze and process the data transmitted by the pre-processing module, and identify the key influencing relationship between the quality parameters of the finished product and the proportions of each component of the compound additive; The dynamic feedback module is used to dynamically adjust the ratio of each ingredient according to real-time monitoring data during the production process.

Images